759 files changed, 42725 insertions, 22681 deletions

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index d4bcfd8f95bf..8b644113715e 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -51,12 +51,16 @@ static int vlan_group_prealloc_vid(struct vlan_group *vg,
 				   __be16 vlan_proto, u16 vlan_id)
 {
 	struct net_device **array;
-	unsigned int pidx, vidx;
+	unsigned int vidx;
 	unsigned int size;
+	int pidx;
 
 	ASSERT_RTNL();
 
 	pidx  = vlan_proto_idx(vlan_proto);
+	if (pidx < 0)
+		return -EINVAL;
+
 	vidx  = vlan_id / VLAN_GROUP_ARRAY_PART_LEN;
 	array = vg->vlan_devices_arrays[pidx][vidx];
 	if (array != NULL)
@@ -280,8 +284,7 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id)
 	return 0;
 
 out_free_newdev:
-	if (new_dev->reg_state == NETREG_UNINITIALIZED)
-		free_netdev(new_dev);
+	free_netdev(new_dev);
 	return err;
 }
 
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index bb7ec1a3915d..953405362795 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -36,7 +36,7 @@ struct vlan_info {
 	struct rcu_head		rcu;
 };
 
-static inline unsigned int vlan_proto_idx(__be16 proto)
+static inline int vlan_proto_idx(__be16 proto)
 {
 	switch (proto) {
 	case htons(ETH_P_8021Q):
@@ -44,8 +44,8 @@ static inline unsigned int vlan_proto_idx(__be16 proto)
 	case htons(ETH_P_8021AD):
 		return VLAN_PROTO_8021AD;
 	default:
-		BUG();
-		return 0;
+		WARN(1, "invalid VLAN protocol: 0x%04x\n", ntohs(proto));
+		return -EINVAL;
 	}
 }
 
@@ -64,17 +64,24 @@ static inline struct net_device *vlan_group_get_device(struct vlan_group *vg,
 						       __be16 vlan_proto,
 						       u16 vlan_id)
 {
-	return __vlan_group_get_device(vg, vlan_proto_idx(vlan_proto), vlan_id);
+	int pidx = vlan_proto_idx(vlan_proto);
+
+	if (pidx < 0)
+		return NULL;
+
+	return __vlan_group_get_device(vg, pidx, vlan_id);
 }
 
 static inline void vlan_group_set_device(struct vlan_group *vg,
 					 __be16 vlan_proto, u16 vlan_id,
 					 struct net_device *dev)
 {
+	int pidx = vlan_proto_idx(vlan_proto);
 	struct net_device **array;
-	if (!vg)
+
+	if (!vg || pidx < 0)
 		return;
-	array = vg->vlan_devices_arrays[vlan_proto_idx(vlan_proto)]
+	array = vg->vlan_devices_arrays[pidx]
 				       [vlan_id / VLAN_GROUP_ARRAY_PART_LEN];
 	array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev;
 }
diff --git a/net/9p/client.c b/net/9p/client.c
index 09f1ec589b80..4f62f299da0c 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -412,8 +412,9 @@ static void p9_tag_cleanup(struct p9_client *c)
 
 /**
  * p9_client_cb - call back from transport to client
- * c: client state
- * req: request received
+ * @c: client state
+ * @req: request received
+ * @status: request status, one of REQ_STATUS_*
  *
  */
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
@@ -555,6 +556,7 @@ out_err:
  * p9_check_zc_errors - check 9p packet for error return and process it
  * @c: current client instance
  * @req: request to parse and check for error conditions
+ * @uidata: external buffer containing error
  * @in_hdrlen: Size of response protocol buffer.
  *
  * returns error code if one is discovered, otherwise returns 0
@@ -901,6 +903,7 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 	fid->clnt = clnt;
 	fid->rdir = NULL;
 	fid->fid = 0;
+	refcount_set(&fid->count, 1);
 
 	idr_preload(GFP_KERNEL);
 	spin_lock_irq(&clnt->lock);
@@ -908,7 +911,6 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 			    GFP_NOWAIT);
 	spin_unlock_irq(&clnt->lock);
 	idr_preload_end();
-
 	if (!ret)
 		return fid;
 
@@ -1187,7 +1189,6 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
 
 	p9_debug(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %ud wname[0] %s\n",
 		 oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL);
-
 	req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid,
 								nwname, wnames);
 	if (IS_ERR(req)) {
@@ -1219,7 +1220,7 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
 	if (nwname)
 		memmove(&fid->qid, &wqids[nwqids - 1], sizeof(struct p9_qid));
 	else
-		fid->qid = oldfid->qid;
+		memmove(&fid->qid, &oldfid->qid, sizeof(struct p9_qid));
 
 	kfree(wqids);
 	return fid;
@@ -1272,6 +1273,7 @@ int p9_client_open(struct p9_fid *fid, int mode)
 		p9_is_proto_dotl(clnt) ? "RLOPEN" : "ROPEN",  qid.type,
 		(unsigned long long)qid.path, qid.version, iounit);
 
+	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
 	fid->mode = mode;
 	fid->iounit = iounit;
 
@@ -1317,6 +1319,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
 			(unsigned long long)qid->path,
 			qid->version, iounit);
 
+	memmove(&ofid->qid, qid, sizeof(struct p9_qid));
 	ofid->mode = mode;
 	ofid->iounit = iounit;
 
@@ -1362,6 +1365,7 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 				(unsigned long long)qid.path,
 				qid.version, iounit);
 
+	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
 	fid->mode = mode;
 	fid->iounit = iounit;
 
@@ -1458,12 +1462,14 @@ int p9_client_clunk(struct p9_fid *fid)
 	struct p9_req_t *req;
 	int retries = 0;
 
-	if (!fid) {
-		pr_warn("%s (%d): Trying to clunk with NULL fid\n",
+	if (!fid || IS_ERR(fid)) {
+		pr_warn("%s (%d): Trying to clunk with invalid fid\n",
 			__func__, task_pid_nr(current));
 		dump_stack();
 		return 0;
 	}
+	if (!refcount_dec_and_test(&fid->count))
+		return 0;
 
 again:
 	p9_debug(P9_DEBUG_9P, ">>> TCLUNK fid %d (try %d)\n", fid->fid,
diff --git a/net/9p/trans_common.c b/net/9p/trans_common.c
index 3dff68f05fb9..6ea5ea548cd4 100644
--- a/net/9p/trans_common.c
+++ b/net/9p/trans_common.c
@@ -17,7 +17,9 @@
 #include "trans_common.h"
 
 /**
- *  p9_release_pages - Release pages after the transaction.
+ * p9_release_pages - Release pages after the transaction.
+ * @pages: array of pages to be put
+ * @nr_pages: size of array
  */
 void p9_release_pages(struct page **pages, int nr_pages)
 {
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index c0762a302162..fa158397bb63 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -45,7 +45,7 @@ static struct p9_trans_module p9_fd_trans;
  * @rfd: file descriptor for reading (trans=fd)
  * @wfd: file descriptor for writing (trans=fd)
  * @port: port to connect to (trans=tcp)
- *
+ * @privport: port is privileged
  */
 
 struct p9_fd_opts {
@@ -95,6 +95,8 @@ struct p9_poll_wait {
  * @err: error state
  * @req_list: accounting for requests which have been sent
  * @unsent_req_list: accounting for requests that haven't been sent
+ * @rreq: read request
+ * @wreq: write request
  * @req: current request being processed (if any)
  * @tmp_buf: temporary buffer to read in header
  * @rc: temporary fcall for reading current frame
@@ -1023,7 +1025,7 @@ p9_fd_create_unix(struct p9_client *client, const char *addr, char *args)
 
 	csocket = NULL;
 
-	if (addr == NULL)
+	if (!addr || !strlen(addr))
 		return -EINVAL;
 
 	if (strlen(addr) >= UNIX_PATH_MAX) {
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 2885ff9c76f0..af0a8a6cd3fd 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -99,6 +99,7 @@ struct p9_rdma_req;
 /**
  * struct p9_rdma_context - Keeps track of in-process WR
  *
+ * @cqe: completion queue entry
  * @busa: Bus address to unmap when the WR completes
  * @req: Keeps track of requests (send)
  * @rc: Keepts track of replies (receive)
@@ -115,6 +116,7 @@ struct p9_rdma_context {
 /**
  * struct p9_rdma_opts - Collection of mount options
  * @port: port of connection
+ * @privport: Whether a privileged port may be used
  * @sq_depth: The requested depth of the SQ. This really doesn't need
  * to be any deeper than the number of threads used in the client
  * @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index a3cd90a74012..93f2f8654882 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -50,7 +50,11 @@ static atomic_t vp_pinned = ATOMIC_INIT(0);
  * @client: client instance
  * @vdev: virtio dev associated with this channel
  * @vq: virtio queue associated with this channel
+ * @ring_bufs_avail: flag to indicate there is some available in the ring buf
+ * @vc_wq: wait queue for waiting for thing to be added to ring buf
+ * @p9_max_pages: maximum number of pinned pages
  * @sg: scatter gather list which is used to pack a request (protected?)
+ * @chan_list: linked list of channels
  *
  * We keep all per-channel information in a structure.
  * This structure is allocated within the devices dev->mem space.
@@ -74,8 +78,8 @@ struct virtio_chan {
 	unsigned long p9_max_pages;
 	/* Scatterlist: can be too big for stack. */
 	struct scatterlist sg[VIRTQUEUE_NUM];
-	/*
-	 * tag name to identify a mount null terminated
+	/**
+	 * @tag: name to identify a mount null terminated
 	 */
 	char *tag;
 
@@ -204,6 +208,7 @@ static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req)
  * this takes a list of pages.
  * @sg: scatter/gather list to pack into
  * @start: which segment of the sg_list to start at
+ * @limit: maximum number of pages in sg list.
  * @pdata: a list of pages to add into sg.
  * @nr_pages: number of pages to pack into the scatter/gather list
  * @offs: amount of data in the beginning of first page _not_ to pack
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index bc8807d9281f..f4fea28e05da 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -451,13 +451,13 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev,
 		char str[16];
 
 		BUILD_BUG_ON(XEN_9PFS_NUM_RINGS > 9);
-		sprintf(str, "ring-ref%u", i);
+		sprintf(str, "ring-ref%d", i);
 		ret = xenbus_printf(xbt, dev->nodename, str, "%d",
 				    priv->rings[i].ref);
 		if (ret)
 			goto error_xenbus;
 
-		sprintf(str, "event-channel-%u", i);
+		sprintf(str, "event-channel-%d", i);
 		ret = xenbus_printf(xbt, dev->nodename, str, "%u",
 				    priv->rings[i].evtchn);
 		if (ret)
diff --git a/net/Kconfig b/net/Kconfig
index 3831206977a1..f4c32d982af6 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -386,8 +386,6 @@ source "net/mac80211/Kconfig"
 
 endif # WIRELESS
 
-source "net/wimax/Kconfig"
-
 source "net/rfkill/Kconfig"
 source "net/9p/Kconfig"
 source "net/caif/Kconfig"
@@ -434,7 +432,6 @@ config NET_SOCK_MSG
 config NET_DEVLINK
 	bool
 	default n
-	imply NET_DROP_MONITOR
 
 config PAGE_POOL
 	bool
diff --git a/net/Makefile b/net/Makefile
index 5744bf1997fd..d96b0aa8f39f 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -66,7 +66,6 @@ obj-$(CONFIG_MAC802154)		+= mac802154/
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_SYSCTL)		+= sysctl_net.o
 endif
-obj-$(CONFIG_WIMAX)		+= wimax/
 obj-$(CONFIG_DNS_RESOLVER)	+= dns_resolver/
 obj-$(CONFIG_CEPH_LIB)		+= ceph/
 obj-$(CONFIG_BATMAN_ADV)	+= batman-adv/
diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c
index 45f584171de7..be18af481d7d 100644
--- a/net/appletalk/aarp.c
+++ b/net/appletalk/aarp.c
@@ -44,15 +44,15 @@ int sysctl_aarp_resolve_time = AARP_RESOLVE_TIME;
 /* Lists of aarp entries */
 /**
  *	struct aarp_entry - AARP entry
- *	@last_sent - Last time we xmitted the aarp request
- *	@packet_queue - Queue of frames wait for resolution
- *	@status - Used for proxy AARP
- *	expires_at - Entry expiry time
- *	target_addr - DDP Address
- *	dev - Device to use
- *	hwaddr - Physical i/f address of target/router
- *	xmit_count - When this hits 10 we give up
- *	next - Next entry in chain
+ *	@last_sent: Last time we xmitted the aarp request
+ *	@packet_queue: Queue of frames wait for resolution
+ *	@status: Used for proxy AARP
+ *	@expires_at: Entry expiry time
+ *	@target_addr: DDP Address
+ *	@dev:  Device to use
+ *	@hwaddr:  Physical i/f address of target/router
+ *	@xmit_count:  When this hits 10 we give up
+ *	@next: Next entry in chain
  */
 struct aarp_entry {
 	/* These first two are only used for unresolved entries */
diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c
index 1d48708c5a2e..ca1a0d07a087 100644
--- a/net/appletalk/ddp.c
+++ b/net/appletalk/ddp.c
@@ -1407,9 +1407,10 @@ drop:
 
 /**
  *	atalk_rcv - Receive a packet (in skb) from device dev
- *	@skb - packet received
- *	@dev - network device where the packet comes from
- *	@pt - packet type
+ *	@skb: packet received
+ *	@dev: network device where the packet comes from
+ *	@pt: packet type
+ *	@orig_dev: the original receive net device
  *
  *	Receive a packet (in skb) from device dev. This has come from the SNAP
  *	decoder, and on entry skb->transport_header is the DDP header, skb->len
diff --git a/net/atm/lec.c b/net/atm/lec.c
index b570ef919c28..7226c784dbe0 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -954,9 +954,8 @@ static void *lec_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct lec_state *state = seq->private;
 
-	v = lec_get_idx(state, 1);
-	*pos += !!PTR_ERR(v);
-	return v;
+	++*pos;
+	return lec_get_idx(state, 1);
 }
 
 static int lec_seq_show(struct seq_file *seq, void *v)
@@ -1070,7 +1069,7 @@ module_exit(lane_module_cleanup);
 /*
  * LANE2: 3.1.3, LE_RESOLVE.request
  * Non force allocates memory and fills in *tlvs, fills in *sizeoftlvs.
- * If sizeoftlvs == NULL the default TLVs associated with with this
+ * If sizeoftlvs == NULL the default TLVs associated with this
  * lec will be used.
  * If dst_mac == NULL, targetless LE_ARP will be sent
  */
diff --git a/net/atm/raw.c b/net/atm/raw.c
index b3ba44aab0ee..2b5f78a7ec3e 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -54,6 +54,8 @@ static int atm_send_aal0(struct atm_vcc *vcc, struct sk_buff *skb)
 		kfree_skb(skb);
 		return -EADDRNOTAVAIL;
 	}
+	if (vcc->dev->ops->send_bh)
+		return vcc->dev->ops->send_bh(vcc, skb);
 	return vcc->dev->ops->send(vcc, skb);
 }
 
@@ -71,7 +73,10 @@ int atm_init_aal34(struct atm_vcc *vcc)
 	vcc->push = atm_push_raw;
 	vcc->pop = atm_pop_raw;
 	vcc->push_oam = NULL;
-	vcc->send = vcc->dev->ops->send;
+	if (vcc->dev->ops->send_bh)
+		vcc->send = vcc->dev->ops->send_bh;
+	else
+		vcc->send = vcc->dev->ops->send;
 	return 0;
 }
 
@@ -80,7 +85,10 @@ int atm_init_aal5(struct atm_vcc *vcc)
 	vcc->push = atm_push_raw;
 	vcc->pop = atm_pop_raw;
 	vcc->push_oam = NULL;
-	vcc->send = vcc->dev->ops->send;
+	if (vcc->dev->ops->send_bh)
+		vcc->send = vcc->dev->ops->send_bh;
+	else
+		vcc->send = vcc->dev->ops->send;
 	return 0;
 }
 EXPORT_SYMBOL(atm_init_aal5);
diff --git a/net/atm/signaling.c b/net/atm/signaling.c
index fbd0c5e7b299..5de06ab8ed75 100644
--- a/net/atm/signaling.c
+++ b/net/atm/signaling.c
@@ -52,7 +52,7 @@ static void modify_qos(struct atm_vcc *vcc, struct atmsvc_msg *msg)
 			msg->type = as_okay;
 	}
 	/*
-	 * Should probably just turn around the old skb. But the, the buffer
+	 * Should probably just turn around the old skb. But then, the buffer
 	 * space accounting needs to follow the change too. Maybe later.
 	 */
 	while (!(skb = alloc_skb(sizeof(struct atmsvc_msg), GFP_KERNEL)))
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index c762758a4649..993afd5ff7bb 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -76,37 +76,14 @@ config BATMAN_ADV_MCAST
 	  reduce the air overhead while improving the reliability of
 	  multicast messages.
 
-config BATMAN_ADV_DEBUGFS
-	bool "batman-adv debugfs entries"
-	depends on BATMAN_ADV
-	depends on DEBUG_FS
-	help
-	  Enable this to export routing related debug tables via debugfs.
-	  The information for each soft-interface and used hard-interface can be
-	  found under batman_adv/
-
-	  If unsure, say N.
-
 config BATMAN_ADV_DEBUG
 	bool "B.A.T.M.A.N. debugging"
 	depends on BATMAN_ADV
 	help
 	  This is an option for use by developers; most people should
 	  say N here. This enables compilation of support for
-	  outputting debugging information to the debugfs log or tracing
-	  buffer. The output is controlled via the batadv netdev specific
-	  log_level setting.
-
-config BATMAN_ADV_SYSFS
-	bool "batman-adv sysfs entries"
-	depends on BATMAN_ADV
-	help
-	  Say Y here if you want to enable batman-adv device configuration and
-	  status interface through sysfs attributes. It is replaced by the
-	  batadv generic netlink family but still used by various userspace
-	  tools and scripts.
-
-	  If unsure, say Y.
+	  outputting debugging information to the tracing buffer. The output is
+	  controlled via the batadv netdev specific log_level setting.
 
 config BATMAN_ADV_TRACING
 	bool "B.A.T.M.A.N. tracing support"
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index daa49af7ff40..8010c34b987c 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -11,14 +11,12 @@ batman-adv-$(CONFIG_BATMAN_ADV_BATMAN_V) += bat_v_elp.o
 batman-adv-$(CONFIG_BATMAN_ADV_BATMAN_V) += bat_v_ogm.o
 batman-adv-y += bitarray.o
 batman-adv-$(CONFIG_BATMAN_ADV_BLA) += bridge_loop_avoidance.o
-batman-adv-$(CONFIG_BATMAN_ADV_DEBUGFS) += debugfs.o
 batman-adv-$(CONFIG_BATMAN_ADV_DAT) += distributed-arp-table.o
 batman-adv-y += fragmentation.o
 batman-adv-y += gateway_client.o
 batman-adv-y += gateway_common.o
 batman-adv-y += hard-interface.o
 batman-adv-y += hash.o
-batman-adv-$(CONFIG_BATMAN_ADV_DEBUGFS) += icmp_socket.o
 batman-adv-$(CONFIG_BATMAN_ADV_DEBUG) += log.o
 batman-adv-y += main.o
 batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
@@ -28,7 +26,6 @@ batman-adv-y += originator.o
 batman-adv-y += routing.o
 batman-adv-y += send.o
 batman-adv-y += soft-interface.o
-batman-adv-$(CONFIG_BATMAN_ADV_SYSFS) += sysfs.o
 batman-adv-$(CONFIG_BATMAN_ADV_TRACING) += trace.o
 batman-adv-y += tp_meter.o
 batman-adv-y += translation-table.o
diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c
index 382fbe51fd34..c5f404f6892f 100644
--- a/net/batman-adv/bat_algo.c
+++ b/net/batman-adv/bat_algo.c
@@ -11,7 +11,6 @@
 #include <linux/moduleparam.h>
 #include <linux/netlink.h>
 #include <linux/printk.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/stddef.h>
 #include <linux/string.h>
@@ -34,7 +33,13 @@ void batadv_algo_init(void)
 	INIT_HLIST_HEAD(&batadv_algo_list);
 }
 
-static struct batadv_algo_ops *batadv_algo_get(char *name)
+/**
+ * batadv_algo_get() - Search for algorithm with specific name
+ * @name: algorithm name to find
+ *
+ * Return: Pointer to batadv_algo_ops on success, NULL otherwise
+ */
+struct batadv_algo_ops *batadv_algo_get(const char *name)
 {
 	struct batadv_algo_ops *bat_algo_ops = NULL, *bat_algo_ops_tmp;
 
@@ -97,7 +102,7 @@ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops)
  *
  * Return: 0 on success or negative error number in case of failure
  */
-int batadv_algo_select(struct batadv_priv *bat_priv, char *name)
+int batadv_algo_select(struct batadv_priv *bat_priv, const char *name)
 {
 	struct batadv_algo_ops *bat_algo_ops;
 
@@ -110,29 +115,6 @@ int batadv_algo_select(struct batadv_priv *bat_priv, char *name)
 	return 0;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-
-/**
- * batadv_algo_seq_print_text() - Print the supported algorithms in a seq file
- * @seq: seq file to print on
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_algo_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct batadv_algo_ops *bat_algo_ops;
-
-	seq_puts(seq, "Available routing algorithms:\n");
-
-	hlist_for_each_entry(bat_algo_ops, &batadv_algo_list, list) {
-		seq_printf(seq, " * %s\n", bat_algo_ops->name);
-	}
-
-	return 0;
-}
-#endif
-
 static int batadv_param_set_ra(const char *val, const struct kernel_param *kp)
 {
 	struct batadv_algo_ops *bat_algo_ops;
diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h
index 686a60bc9492..43b045ac8ac7 100644
--- a/net/batman-adv/bat_algo.h
+++ b/net/batman-adv/bat_algo.h
@@ -10,7 +10,6 @@
 #include "main.h"
 
 #include <linux/netlink.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
 
@@ -18,9 +17,9 @@ extern char batadv_routing_algo[];
 extern struct list_head batadv_hardif_list;
 
 void batadv_algo_init(void);
+struct batadv_algo_ops *batadv_algo_get(const char *name);
 int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops);
-int batadv_algo_select(struct batadv_priv *bat_priv, char *name);
-int batadv_algo_seq_print_text(struct seq_file *seq, void *offset);
+int batadv_algo_select(struct batadv_priv *bat_priv, const char *name);
 int batadv_algo_dump(struct sk_buff *msg, struct netlink_callback *cb);
 
 #endif /* _NET_BATMAN_ADV_BAT_ALGO_H_ */
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index a4faf5f904d9..168621c9a081 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -27,11 +27,11 @@
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/pkt_sched.h>
+#include <linux/prandom.h>
 #include <linux/printk.h>
 #include <linux/random.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -1779,106 +1779,6 @@ free_skb:
 	return ret;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_iv_ogm_orig_print_neigh() - print neighbors for the originator table
- * @orig_node: the orig_node for which the neighbors are printed
- * @if_outgoing: outgoing interface for these entries
- * @seq: debugfs table seq_file struct
- *
- * Must be called while holding an rcu lock.
- */
-static void
-batadv_iv_ogm_orig_print_neigh(struct batadv_orig_node *orig_node,
-			       struct batadv_hard_iface *if_outgoing,
-			       struct seq_file *seq)
-{
-	struct batadv_neigh_node *neigh_node;
-	struct batadv_neigh_ifinfo *n_ifinfo;
-
-	hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) {
-		n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing);
-		if (!n_ifinfo)
-			continue;
-
-		seq_printf(seq, " %pM (%3i)",
-			   neigh_node->addr,
-			   n_ifinfo->bat_iv.tq_avg);
-
-		batadv_neigh_ifinfo_put(n_ifinfo);
-	}
-}
-
-/**
- * batadv_iv_ogm_orig_print() - print the originator table
- * @bat_priv: the bat priv with all the soft interface information
- * @seq: debugfs table seq_file struct
- * @if_outgoing: the outgoing interface for which this should be printed
- */
-static void batadv_iv_ogm_orig_print(struct batadv_priv *bat_priv,
-				     struct seq_file *seq,
-				     struct batadv_hard_iface *if_outgoing)
-{
-	struct batadv_neigh_node *neigh_node;
-	struct batadv_hashtable *hash = bat_priv->orig_hash;
-	int last_seen_msecs, last_seen_secs;
-	struct batadv_orig_node *orig_node;
-	struct batadv_neigh_ifinfo *n_ifinfo;
-	unsigned long last_seen_jiffies;
-	struct hlist_head *head;
-	int batman_count = 0;
-	u32 i;
-
-	seq_puts(seq,
-		 "  Originator      last-seen (#/255)           Nexthop [outgoingIF]:   Potential nexthops ...\n");
-
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
-			neigh_node = batadv_orig_router_get(orig_node,
-							    if_outgoing);
-			if (!neigh_node)
-				continue;
-
-			n_ifinfo = batadv_neigh_ifinfo_get(neigh_node,
-							   if_outgoing);
-			if (!n_ifinfo)
-				goto next;
-
-			if (n_ifinfo->bat_iv.tq_avg == 0)
-				goto next;
-
-			last_seen_jiffies = jiffies - orig_node->last_seen;
-			last_seen_msecs = jiffies_to_msecs(last_seen_jiffies);
-			last_seen_secs = last_seen_msecs / 1000;
-			last_seen_msecs = last_seen_msecs % 1000;
-
-			seq_printf(seq, "%pM %4i.%03is   (%3i) %pM [%10s]:",
-				   orig_node->orig, last_seen_secs,
-				   last_seen_msecs, n_ifinfo->bat_iv.tq_avg,
-				   neigh_node->addr,
-				   neigh_node->if_incoming->net_dev->name);
-
-			batadv_iv_ogm_orig_print_neigh(orig_node, if_outgoing,
-						       seq);
-			seq_putc(seq, '\n');
-			batman_count++;
-
-next:
-			batadv_neigh_node_put(neigh_node);
-			if (n_ifinfo)
-				batadv_neigh_ifinfo_put(n_ifinfo);
-		}
-		rcu_read_unlock();
-	}
-
-	if (batman_count == 0)
-		seq_puts(seq, "No batman nodes in range ...\n");
-}
-#endif
-
 /**
  * batadv_iv_ogm_neigh_get_tq_avg() - Get the TQ average for a neighbour on a
  *  given outgoing interface.
@@ -2108,59 +2008,6 @@ batadv_iv_ogm_orig_dump(struct sk_buff *msg, struct netlink_callback *cb,
 	cb->args[2] = sub;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_iv_hardif_neigh_print() - print a single hop neighbour node
- * @seq: neighbour table seq_file struct
- * @hardif_neigh: hardif neighbour information
- */
-static void
-batadv_iv_hardif_neigh_print(struct seq_file *seq,
-			     struct batadv_hardif_neigh_node *hardif_neigh)
-{
-	int last_secs, last_msecs;
-
-	last_secs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen) / 1000;
-	last_msecs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen) % 1000;
-
-	seq_printf(seq, "   %10s   %pM %4i.%03is\n",
-		   hardif_neigh->if_incoming->net_dev->name,
-		   hardif_neigh->addr, last_secs, last_msecs);
-}
-
-/**
- * batadv_iv_ogm_neigh_print() - print the single hop neighbour list
- * @bat_priv: the bat priv with all the soft interface information
- * @seq: neighbour table seq_file struct
- */
-static void batadv_iv_neigh_print(struct batadv_priv *bat_priv,
-				  struct seq_file *seq)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_hardif_neigh_node *hardif_neigh;
-	struct batadv_hard_iface *hard_iface;
-	int batman_count = 0;
-
-	seq_puts(seq, "           IF        Neighbor      last-seen\n");
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface != net_dev)
-			continue;
-
-		hlist_for_each_entry_rcu(hardif_neigh,
-					 &hard_iface->neigh_list, list) {
-			batadv_iv_hardif_neigh_print(seq, hardif_neigh);
-			batman_count++;
-		}
-	}
-	rcu_read_unlock();
-
-	if (batman_count == 0)
-		seq_puts(seq, "No batman nodes in range ...\n");
-}
-#endif
-
 /**
  * batadv_iv_ogm_neigh_diff() - calculate tq difference of two neighbors
  * @neigh1: the first neighbor object of the comparison
@@ -2556,72 +2403,6 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/* fails if orig_node has no router */
-static int batadv_iv_gw_write_buffer_text(struct batadv_priv *bat_priv,
-					  struct seq_file *seq,
-					  const struct batadv_gw_node *gw_node)
-{
-	struct batadv_gw_node *curr_gw;
-	struct batadv_neigh_node *router;
-	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
-	int ret = -1;
-
-	router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT);
-	if (!router)
-		goto out;
-
-	router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT);
-	if (!router_ifinfo)
-		goto out;
-
-	curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
-
-	seq_printf(seq, "%s %pM (%3i) %pM [%10s]: %u.%u/%u.%u MBit\n",
-		   (curr_gw == gw_node ? "=>" : "  "),
-		   gw_node->orig_node->orig,
-		   router_ifinfo->bat_iv.tq_avg, router->addr,
-		   router->if_incoming->net_dev->name,
-		   gw_node->bandwidth_down / 10,
-		   gw_node->bandwidth_down % 10,
-		   gw_node->bandwidth_up / 10,
-		   gw_node->bandwidth_up % 10);
-	ret = seq_has_overflowed(seq) ? -1 : 0;
-
-	if (curr_gw)
-		batadv_gw_node_put(curr_gw);
-out:
-	if (router_ifinfo)
-		batadv_neigh_ifinfo_put(router_ifinfo);
-	if (router)
-		batadv_neigh_node_put(router);
-	return ret;
-}
-
-static void batadv_iv_gw_print(struct batadv_priv *bat_priv,
-			       struct seq_file *seq)
-{
-	struct batadv_gw_node *gw_node;
-	int gw_count = 0;
-
-	seq_puts(seq,
-		 "      Gateway      (#/255)           Nexthop [outgoingIF]: advertised uplink bandwidth\n");
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.gateway_list, list) {
-		/* fails if orig_node has no router */
-		if (batadv_iv_gw_write_buffer_text(bat_priv, seq, gw_node) < 0)
-			continue;
-
-		gw_count++;
-	}
-	rcu_read_unlock();
-
-	if (gw_count == 0)
-		seq_puts(seq, "No gateways in range ...\n");
-}
-#endif
-
 /**
  * batadv_iv_gw_dump_entry() - Dump a gateway into a message
  * @msg: Netlink message to dump into
@@ -2746,24 +2527,15 @@ static struct batadv_algo_ops batadv_batman_iv __read_mostly = {
 	.neigh = {
 		.cmp = batadv_iv_ogm_neigh_cmp,
 		.is_similar_or_better = batadv_iv_ogm_neigh_is_sob,
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-		.print = batadv_iv_neigh_print,
-#endif
 		.dump = batadv_iv_ogm_neigh_dump,
 	},
 	.orig = {
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-		.print = batadv_iv_ogm_orig_print,
-#endif
 		.dump = batadv_iv_ogm_orig_dump,
 	},
 	.gw = {
 		.init_sel_class = batadv_iv_init_sel_class,
 		.get_best_gw_node = batadv_iv_gw_get_best_gw_node,
 		.is_eligible = batadv_iv_gw_is_eligible,
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-		.print = batadv_iv_gw_print,
-#endif
 		.dump = batadv_iv_gw_dump,
 	},
 };
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index 0ecaf1bb0068..e4455babe4c2 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -13,14 +13,13 @@
 #include <linux/if_ether.h>
 #include <linux/init.h>
 #include <linux/jiffies.h>
-#include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/list.h>
+#include <linux/minmax.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
 #include <linux/stddef.h>
@@ -119,92 +118,6 @@ batadv_v_hardif_neigh_init(struct batadv_hardif_neigh_node *hardif_neigh)
 		  batadv_v_elp_throughput_metric_update);
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_v_orig_print_neigh() - print neighbors for the originator table
- * @orig_node: the orig_node for which the neighbors are printed
- * @if_outgoing: outgoing interface for these entries
- * @seq: debugfs table seq_file struct
- *
- * Must be called while holding an rcu lock.
- */
-static void
-batadv_v_orig_print_neigh(struct batadv_orig_node *orig_node,
-			  struct batadv_hard_iface *if_outgoing,
-			  struct seq_file *seq)
-{
-	struct batadv_neigh_node *neigh_node;
-	struct batadv_neigh_ifinfo *n_ifinfo;
-
-	hlist_for_each_entry_rcu(neigh_node, &orig_node->neigh_list, list) {
-		n_ifinfo = batadv_neigh_ifinfo_get(neigh_node, if_outgoing);
-		if (!n_ifinfo)
-			continue;
-
-		seq_printf(seq, " %pM (%9u.%1u)",
-			   neigh_node->addr,
-			   n_ifinfo->bat_v.throughput / 10,
-			   n_ifinfo->bat_v.throughput % 10);
-
-		batadv_neigh_ifinfo_put(n_ifinfo);
-	}
-}
-
-/**
- * batadv_v_hardif_neigh_print() - print a single ELP neighbour node
- * @seq: neighbour table seq_file struct
- * @hardif_neigh: hardif neighbour information
- */
-static void
-batadv_v_hardif_neigh_print(struct seq_file *seq,
-			    struct batadv_hardif_neigh_node *hardif_neigh)
-{
-	int last_secs, last_msecs;
-	u32 throughput;
-
-	last_secs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen) / 1000;
-	last_msecs = jiffies_to_msecs(jiffies - hardif_neigh->last_seen) % 1000;
-	throughput = ewma_throughput_read(&hardif_neigh->bat_v.throughput);
-
-	seq_printf(seq, "%pM %4i.%03is (%9u.%1u) [%10s]\n",
-		   hardif_neigh->addr, last_secs, last_msecs, throughput / 10,
-		   throughput % 10, hardif_neigh->if_incoming->net_dev->name);
-}
-
-/**
- * batadv_v_neigh_print() - print the single hop neighbour list
- * @bat_priv: the bat priv with all the soft interface information
- * @seq: neighbour table seq_file struct
- */
-static void batadv_v_neigh_print(struct batadv_priv *bat_priv,
-				 struct seq_file *seq)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_hardif_neigh_node *hardif_neigh;
-	struct batadv_hard_iface *hard_iface;
-	int batman_count = 0;
-
-	seq_puts(seq,
-		 "  Neighbor        last-seen ( throughput) [        IF]\n");
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface != net_dev)
-			continue;
-
-		hlist_for_each_entry_rcu(hardif_neigh,
-					 &hard_iface->neigh_list, list) {
-			batadv_v_hardif_neigh_print(seq, hardif_neigh);
-			batman_count++;
-		}
-	}
-	rcu_read_unlock();
-
-	if (batman_count == 0)
-		seq_puts(seq, "No batman nodes in range ...\n");
-}
-#endif
-
 /**
  * batadv_v_neigh_dump_neigh() - Dump a neighbour into a message
  * @msg: Netlink message to dump into
@@ -337,75 +250,6 @@ batadv_v_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb,
 	cb->args[1] = idx;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_v_orig_print() - print the originator table
- * @bat_priv: the bat priv with all the soft interface information
- * @seq: debugfs table seq_file struct
- * @if_outgoing: the outgoing interface for which this should be printed
- */
-static void batadv_v_orig_print(struct batadv_priv *bat_priv,
-				struct seq_file *seq,
-				struct batadv_hard_iface *if_outgoing)
-{
-	struct batadv_neigh_node *neigh_node;
-	struct batadv_hashtable *hash = bat_priv->orig_hash;
-	int last_seen_msecs, last_seen_secs;
-	struct batadv_orig_node *orig_node;
-	struct batadv_neigh_ifinfo *n_ifinfo;
-	unsigned long last_seen_jiffies;
-	struct hlist_head *head;
-	int batman_count = 0;
-	u32 i;
-
-	seq_puts(seq,
-		 "  Originator      last-seen ( throughput)           Nexthop [outgoingIF]:   Potential nexthops ...\n");
-
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
-			neigh_node = batadv_orig_router_get(orig_node,
-							    if_outgoing);
-			if (!neigh_node)
-				continue;
-
-			n_ifinfo = batadv_neigh_ifinfo_get(neigh_node,
-							   if_outgoing);
-			if (!n_ifinfo)
-				goto next;
-
-			last_seen_jiffies = jiffies - orig_node->last_seen;
-			last_seen_msecs = jiffies_to_msecs(last_seen_jiffies);
-			last_seen_secs = last_seen_msecs / 1000;
-			last_seen_msecs = last_seen_msecs % 1000;
-
-			seq_printf(seq, "%pM %4i.%03is (%9u.%1u) %pM [%10s]:",
-				   orig_node->orig, last_seen_secs,
-				   last_seen_msecs,
-				   n_ifinfo->bat_v.throughput / 10,
-				   n_ifinfo->bat_v.throughput % 10,
-				   neigh_node->addr,
-				   neigh_node->if_incoming->net_dev->name);
-
-			batadv_v_orig_print_neigh(orig_node, if_outgoing, seq);
-			seq_putc(seq, '\n');
-			batman_count++;
-
-next:
-			batadv_neigh_node_put(neigh_node);
-			if (n_ifinfo)
-				batadv_neigh_ifinfo_put(n_ifinfo);
-		}
-		rcu_read_unlock();
-	}
-
-	if (batman_count == 0)
-		seq_puts(seq, "No batman nodes in range ...\n");
-}
-#endif
-
 /**
  * batadv_v_orig_dump_subentry() - Dump an originator subentry into a message
  * @msg: Netlink message to dump into
@@ -685,13 +529,6 @@ static ssize_t batadv_v_store_sel_class(struct batadv_priv *bat_priv,
 	return count;
 }
 
-static ssize_t batadv_v_show_sel_class(struct batadv_priv *bat_priv, char *buff)
-{
-	u32 class = atomic_read(&bat_priv->gw.sel_class);
-
-	return sprintf(buff, "%u.%u MBit\n", class / 10, class % 10);
-}
-
 /**
  * batadv_v_gw_throughput_get() - retrieve the GW-bandwidth for a given GW
  * @gw_node: the GW to retrieve the metric for
@@ -829,78 +666,6 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/* fails if orig_node has no router */
-static int batadv_v_gw_write_buffer_text(struct batadv_priv *bat_priv,
-					 struct seq_file *seq,
-					 const struct batadv_gw_node *gw_node)
-{
-	struct batadv_gw_node *curr_gw;
-	struct batadv_neigh_node *router;
-	struct batadv_neigh_ifinfo *router_ifinfo = NULL;
-	int ret = -1;
-
-	router = batadv_orig_router_get(gw_node->orig_node, BATADV_IF_DEFAULT);
-	if (!router)
-		goto out;
-
-	router_ifinfo = batadv_neigh_ifinfo_get(router, BATADV_IF_DEFAULT);
-	if (!router_ifinfo)
-		goto out;
-
-	curr_gw = batadv_gw_get_selected_gw_node(bat_priv);
-
-	seq_printf(seq, "%s %pM (%9u.%1u) %pM [%10s]: %u.%u/%u.%u MBit\n",
-		   (curr_gw == gw_node ? "=>" : "  "),
-		   gw_node->orig_node->orig,
-		   router_ifinfo->bat_v.throughput / 10,
-		   router_ifinfo->bat_v.throughput % 10, router->addr,
-		   router->if_incoming->net_dev->name,
-		   gw_node->bandwidth_down / 10,
-		   gw_node->bandwidth_down % 10,
-		   gw_node->bandwidth_up / 10,
-		   gw_node->bandwidth_up % 10);
-	ret = seq_has_overflowed(seq) ? -1 : 0;
-
-	if (curr_gw)
-		batadv_gw_node_put(curr_gw);
-out:
-	if (router_ifinfo)
-		batadv_neigh_ifinfo_put(router_ifinfo);
-	if (router)
-		batadv_neigh_node_put(router);
-	return ret;
-}
-
-/**
- * batadv_v_gw_print() - print the gateway list
- * @bat_priv: the bat priv with all the soft interface information
- * @seq: gateway table seq_file struct
- */
-static void batadv_v_gw_print(struct batadv_priv *bat_priv,
-			      struct seq_file *seq)
-{
-	struct batadv_gw_node *gw_node;
-	int gw_count = 0;
-
-	seq_puts(seq,
-		 "      Gateway        ( throughput)           Nexthop [outgoingIF]: advertised uplink bandwidth\n");
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(gw_node, &bat_priv->gw.gateway_list, list) {
-		/* fails if orig_node has no router */
-		if (batadv_v_gw_write_buffer_text(bat_priv, seq, gw_node) < 0)
-			continue;
-
-		gw_count++;
-	}
-	rcu_read_unlock();
-
-	if (gw_count == 0)
-		seq_puts(seq, "No gateways in range ...\n");
-}
-#endif
-
 /**
  * batadv_v_gw_dump_entry() - Dump a gateway into a message
  * @msg: Netlink message to dump into
@@ -1046,26 +811,16 @@ static struct batadv_algo_ops batadv_batman_v __read_mostly = {
 		.hardif_init = batadv_v_hardif_neigh_init,
 		.cmp = batadv_v_neigh_cmp,
 		.is_similar_or_better = batadv_v_neigh_is_sob,
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-		.print = batadv_v_neigh_print,
-#endif
 		.dump = batadv_v_neigh_dump,
 	},
 	.orig = {
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-		.print = batadv_v_orig_print,
-#endif
 		.dump = batadv_v_orig_dump,
 	},
 	.gw = {
 		.init_sel_class = batadv_v_init_sel_class,
 		.store_sel_class = batadv_v_store_sel_class,
-		.show_sel_class = batadv_v_show_sel_class,
 		.get_best_gw_node = batadv_v_gw_get_best_gw_node,
 		.is_eligible = batadv_v_gw_is_eligible,
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-		.print = batadv_v_gw_print,
-#endif
 		.dump = batadv_v_gw_dump,
 	},
 };
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index d35aca0e969a..0512ea6cd818 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -18,8 +18,10 @@
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
+#include <linux/minmax.h>
 #include <linux/netdevice.h>
 #include <linux/nl80211.h>
+#include <linux/prandom.h>
 #include <linux/random.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index 717fe657561d..798d659855d0 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -18,8 +18,10 @@
 #include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
+#include <linux/minmax.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
+#include <linux/prandom.h>
 #include <linux/random.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index c350ab63cd54..d2de12e527ba 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -28,7 +28,6 @@
 #include <linux/preempt.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -1863,7 +1862,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 	ret = queue_work(batadv_event_workqueue, &backbone_gw->report_work);
 
-	/* backbone_gw is unreferenced in the report work function function
+	/* backbone_gw is unreferenced in the report work function
 	 * if queue_work() call was successful
 	 */
 	if (!ret)
@@ -2115,69 +2114,6 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_bla_claim_table_seq_print_text() - print the claim table in a seq file
- * @seq: seq file to print on
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hashtable *hash = bat_priv->bla.claim_hash;
-	struct batadv_bla_backbone_gw *backbone_gw;
-	struct batadv_bla_claim *claim;
-	struct batadv_hard_iface *primary_if;
-	struct hlist_head *head;
-	u16 backbone_crc;
-	u32 i;
-	bool is_own;
-	u8 *primary_addr;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		goto out;
-
-	primary_addr = primary_if->net_dev->dev_addr;
-	seq_printf(seq,
-		   "Claims announced for the mesh %s (orig %pM, group id %#.4x)\n",
-		   net_dev->name, primary_addr,
-		   ntohs(bat_priv->bla.claim_dest.group));
-	seq_puts(seq,
-		 "   Client               VID      Originator        [o] (CRC   )\n");
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(claim, head, hash_entry) {
-			backbone_gw = batadv_bla_claim_get_backbone_gw(claim);
-
-			is_own = batadv_compare_eth(backbone_gw->orig,
-						    primary_addr);
-
-			spin_lock_bh(&backbone_gw->crc_lock);
-			backbone_crc = backbone_gw->crc;
-			spin_unlock_bh(&backbone_gw->crc_lock);
-			seq_printf(seq, " * %pM on %5d by %pM [%c] (%#.4x)\n",
-				   claim->addr, batadv_print_vid(claim->vid),
-				   backbone_gw->orig,
-				   (is_own ? 'x' : ' '),
-				   backbone_crc);
-
-			batadv_backbone_gw_put(backbone_gw);
-		}
-		rcu_read_unlock();
-	}
-out:
-	if (primary_if)
-		batadv_hardif_put(primary_if);
-	return 0;
-}
-#endif
-
 /**
  * batadv_bla_claim_dump_entry() - dump one entry of the claim table
  * to a netlink socket
@@ -2348,72 +2284,6 @@ out:
 	return ret;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_bla_backbone_table_seq_print_text() - print the backbone table in a
- *  seq file
- * @seq: seq file to print on
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hashtable *hash = bat_priv->bla.backbone_hash;
-	struct batadv_bla_backbone_gw *backbone_gw;
-	struct batadv_hard_iface *primary_if;
-	struct hlist_head *head;
-	int secs, msecs;
-	u16 backbone_crc;
-	u32 i;
-	bool is_own;
-	u8 *primary_addr;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		goto out;
-
-	primary_addr = primary_if->net_dev->dev_addr;
-	seq_printf(seq,
-		   "Backbones announced for the mesh %s (orig %pM, group id %#.4x)\n",
-		   net_dev->name, primary_addr,
-		   ntohs(bat_priv->bla.claim_dest.group));
-	seq_puts(seq, "   Originator           VID   last seen (CRC   )\n");
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(backbone_gw, head, hash_entry) {
-			msecs = jiffies_to_msecs(jiffies -
-						 backbone_gw->lasttime);
-			secs = msecs / 1000;
-			msecs = msecs % 1000;
-
-			is_own = batadv_compare_eth(backbone_gw->orig,
-						    primary_addr);
-			if (is_own)
-				continue;
-
-			spin_lock_bh(&backbone_gw->crc_lock);
-			backbone_crc = backbone_gw->crc;
-			spin_unlock_bh(&backbone_gw->crc_lock);
-
-			seq_printf(seq, " * %pM on %5d %4i.%03is (%#.4x)\n",
-				   backbone_gw->orig,
-				   batadv_print_vid(backbone_gw->vid), secs,
-				   msecs, backbone_crc);
-		}
-		rcu_read_unlock();
-	}
-out:
-	if (primary_if)
-		batadv_hardif_put(primary_if);
-	return 0;
-}
-#endif
-
 /**
  * batadv_bla_backbone_dump_entry() - dump one entry of the backbone table to a
  *  netlink socket
diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h
index a81c41b636f9..7dc6d3571925 100644
--- a/net/batman-adv/bridge_loop_avoidance.h
+++ b/net/batman-adv/bridge_loop_avoidance.h
@@ -12,7 +12,6 @@
 #include <linux/compiler.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/stddef.h>
 #include <linux/types.h>
@@ -41,10 +40,7 @@ bool batadv_bla_tx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 bool batadv_bla_is_backbone_gw(struct sk_buff *skb,
 			       struct batadv_orig_node *orig_node,
 			       int hdr_size);
-int batadv_bla_claim_table_seq_print_text(struct seq_file *seq, void *offset);
 int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb);
-int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq,
-					     void *offset);
 int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb);
 bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig,
 				    unsigned short vid);
@@ -84,18 +80,6 @@ static inline bool batadv_bla_is_backbone_gw(struct sk_buff *skb,
 	return false;
 }
 
-static inline int batadv_bla_claim_table_seq_print_text(struct seq_file *seq,
-							void *offset)
-{
-	return 0;
-}
-
-static inline int batadv_bla_backbone_table_seq_print_text(struct seq_file *seq,
-							   void *offset)
-{
-	return 0;
-}
-
 static inline bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv,
 						  u8 *orig, unsigned short vid)
 {
diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
deleted file mode 100644
index 452856c27d20..000000000000
--- a/net/batman-adv/debugfs.c
+++ /dev/null
@@ -1,442 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2010-2020  B.A.T.M.A.N. contributors:
- *
- * Marek Lindner
- */
-
-#include "debugfs.h"
-#include "main.h"
-
-#include <asm/current.h>
-#include <linux/dcache.h>
-#include <linux/debugfs.h>
-#include <linux/errno.h>
-#include <linux/export.h>
-#include <linux/fs.h>
-#include <linux/netdevice.h>
-#include <linux/printk.h>
-#include <linux/sched.h>
-#include <linux/seq_file.h>
-#include <linux/stat.h>
-#include <linux/stddef.h>
-#include <linux/stringify.h>
-#include <linux/sysfs.h>
-#include <net/net_namespace.h>
-
-#include "bat_algo.h"
-#include "bridge_loop_avoidance.h"
-#include "distributed-arp-table.h"
-#include "gateway_client.h"
-#include "icmp_socket.h"
-#include "log.h"
-#include "multicast.h"
-#include "network-coding.h"
-#include "originator.h"
-#include "translation-table.h"
-
-static struct dentry *batadv_debugfs;
-
-/**
- * batadv_debugfs_deprecated() - Log use of deprecated batadv debugfs access
- * @file: file which was accessed
- * @alt: explanation what can be used as alternative
- */
-void batadv_debugfs_deprecated(struct file *file, const char *alt)
-{
-	struct dentry *dentry = file_dentry(file);
-	const char *name = dentry->d_name.name;
-
-	pr_warn_ratelimited(DEPRECATED "%s (pid %d) Use of debugfs file \"%s\".\n%s",
-			    current->comm, task_pid_nr(current), name, alt);
-}
-
-static int batadv_algorithms_open(struct inode *inode, struct file *file)
-{
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_ROUTING_ALGOS instead\n");
-	return single_open(file, batadv_algo_seq_print_text, NULL);
-}
-
-static int neighbors_open(struct inode *inode, struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_NEIGHBORS instead\n");
-	return single_open(file, batadv_hardif_neigh_seq_print_text, net_dev);
-}
-
-static int batadv_originators_open(struct inode *inode, struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_ORIGINATORS instead\n");
-	return single_open(file, batadv_orig_seq_print_text, net_dev);
-}
-
-/**
- * batadv_originators_hardif_open() - handles debugfs output for the originator
- *  table of an hard interface
- * @inode: inode pointer to debugfs file
- * @file: pointer to the seq_file
- *
- * Return: 0 on success or negative error number in case of failure
- */
-static int batadv_originators_hardif_open(struct inode *inode,
-					  struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_HARDIFS instead\n");
-	return single_open(file, batadv_orig_hardif_seq_print_text, net_dev);
-}
-
-static int batadv_gateways_open(struct inode *inode, struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_GATEWAYS instead\n");
-	return single_open(file, batadv_gw_client_seq_print_text, net_dev);
-}
-
-static int batadv_transtable_global_open(struct inode *inode, struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_TRANSTABLE_GLOBAL instead\n");
-	return single_open(file, batadv_tt_global_seq_print_text, net_dev);
-}
-
-#ifdef CONFIG_BATMAN_ADV_BLA
-static int batadv_bla_claim_table_open(struct inode *inode, struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_BLA_CLAIM instead\n");
-	return single_open(file, batadv_bla_claim_table_seq_print_text,
-			   net_dev);
-}
-
-static int batadv_bla_backbone_table_open(struct inode *inode,
-					  struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_BLA_BACKBONE instead\n");
-	return single_open(file, batadv_bla_backbone_table_seq_print_text,
-			   net_dev);
-}
-
-#endif
-
-#ifdef CONFIG_BATMAN_ADV_DAT
-/**
- * batadv_dat_cache_open() - Prepare file handler for reads from dat_cache
- * @inode: inode which was opened
- * @file: file handle to be initialized
- *
- * Return: 0 on success or negative error number in case of failure
- */
-static int batadv_dat_cache_open(struct inode *inode, struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_DAT_CACHE instead\n");
-	return single_open(file, batadv_dat_cache_seq_print_text, net_dev);
-}
-#endif
-
-static int batadv_transtable_local_open(struct inode *inode, struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_TRANSTABLE_LOCAL instead\n");
-	return single_open(file, batadv_tt_local_seq_print_text, net_dev);
-}
-
-struct batadv_debuginfo {
-	struct attribute attr;
-	const struct file_operations fops;
-};
-
-#ifdef CONFIG_BATMAN_ADV_NC
-static int batadv_nc_nodes_open(struct inode *inode, struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file, "");
-	return single_open(file, batadv_nc_nodes_seq_print_text, net_dev);
-}
-#endif
-
-#ifdef CONFIG_BATMAN_ADV_MCAST
-/**
- * batadv_mcast_flags_open() - prepare file handler for reads from mcast_flags
- * @inode: inode which was opened
- * @file: file handle to be initialized
- *
- * Return: 0 on success or negative error number in case of failure
- */
-static int batadv_mcast_flags_open(struct inode *inode, struct file *file)
-{
-	struct net_device *net_dev = (struct net_device *)inode->i_private;
-
-	batadv_debugfs_deprecated(file,
-				  "Use genl command BATADV_CMD_GET_MCAST_FLAGS instead\n");
-	return single_open(file, batadv_mcast_flags_seq_print_text, net_dev);
-}
-#endif
-
-#define BATADV_DEBUGINFO(_name, _mode, _open)		\
-struct batadv_debuginfo batadv_debuginfo_##_name = {	\
-	.attr = {					\
-		.name = __stringify(_name),		\
-		.mode = _mode,				\
-	},						\
-	.fops = {					\
-		.owner = THIS_MODULE,			\
-		.open = _open,				\
-		.read	= seq_read,			\
-		.llseek = seq_lseek,			\
-		.release = single_release,		\
-	},						\
-}
-
-/* the following attributes are general and therefore they will be directly
- * placed in the BATADV_DEBUGFS_SUBDIR subdirectory of debugfs
- */
-static BATADV_DEBUGINFO(routing_algos, 0444, batadv_algorithms_open);
-
-static struct batadv_debuginfo *batadv_general_debuginfos[] = {
-	&batadv_debuginfo_routing_algos,
-	NULL,
-};
-
-/* The following attributes are per soft interface */
-static BATADV_DEBUGINFO(neighbors, 0444, neighbors_open);
-static BATADV_DEBUGINFO(originators, 0444, batadv_originators_open);
-static BATADV_DEBUGINFO(gateways, 0444, batadv_gateways_open);
-static BATADV_DEBUGINFO(transtable_global, 0444, batadv_transtable_global_open);
-#ifdef CONFIG_BATMAN_ADV_BLA
-static BATADV_DEBUGINFO(bla_claim_table, 0444, batadv_bla_claim_table_open);
-static BATADV_DEBUGINFO(bla_backbone_table, 0444,
-			batadv_bla_backbone_table_open);
-#endif
-#ifdef CONFIG_BATMAN_ADV_DAT
-static BATADV_DEBUGINFO(dat_cache, 0444, batadv_dat_cache_open);
-#endif
-static BATADV_DEBUGINFO(transtable_local, 0444, batadv_transtable_local_open);
-#ifdef CONFIG_BATMAN_ADV_NC
-static BATADV_DEBUGINFO(nc_nodes, 0444, batadv_nc_nodes_open);
-#endif
-#ifdef CONFIG_BATMAN_ADV_MCAST
-static BATADV_DEBUGINFO(mcast_flags, 0444, batadv_mcast_flags_open);
-#endif
-
-static struct batadv_debuginfo *batadv_mesh_debuginfos[] = {
-	&batadv_debuginfo_neighbors,
-	&batadv_debuginfo_originators,
-	&batadv_debuginfo_gateways,
-	&batadv_debuginfo_transtable_global,
-#ifdef CONFIG_BATMAN_ADV_BLA
-	&batadv_debuginfo_bla_claim_table,
-	&batadv_debuginfo_bla_backbone_table,
-#endif
-#ifdef CONFIG_BATMAN_ADV_DAT
-	&batadv_debuginfo_dat_cache,
-#endif
-	&batadv_debuginfo_transtable_local,
-#ifdef CONFIG_BATMAN_ADV_NC
-	&batadv_debuginfo_nc_nodes,
-#endif
-#ifdef CONFIG_BATMAN_ADV_MCAST
-	&batadv_debuginfo_mcast_flags,
-#endif
-	NULL,
-};
-
-#define BATADV_HARDIF_DEBUGINFO(_name, _mode, _open)		\
-struct batadv_debuginfo batadv_hardif_debuginfo_##_name = {	\
-	.attr = {						\
-		.name = __stringify(_name),			\
-		.mode = _mode,					\
-	},							\
-	.fops = {						\
-		.owner = THIS_MODULE,				\
-		.open = _open,					\
-		.read	= seq_read,				\
-		.llseek = seq_lseek,				\
-		.release = single_release,			\
-	},							\
-}
-
-static BATADV_HARDIF_DEBUGINFO(originators, 0444,
-			       batadv_originators_hardif_open);
-
-static struct batadv_debuginfo *batadv_hardif_debuginfos[] = {
-	&batadv_hardif_debuginfo_originators,
-	NULL,
-};
-
-/**
- * batadv_debugfs_init() - Initialize soft interface independent debugfs entries
- */
-void batadv_debugfs_init(void)
-{
-	struct batadv_debuginfo **bat_debug;
-
-	batadv_debugfs = debugfs_create_dir(BATADV_DEBUGFS_SUBDIR, NULL);
-
-	for (bat_debug = batadv_general_debuginfos; *bat_debug; ++bat_debug)
-		debugfs_create_file(((*bat_debug)->attr).name,
-				    S_IFREG | ((*bat_debug)->attr).mode,
-				    batadv_debugfs, NULL, &(*bat_debug)->fops);
-}
-
-/**
- * batadv_debugfs_destroy() - Remove all debugfs entries
- */
-void batadv_debugfs_destroy(void)
-{
-	debugfs_remove_recursive(batadv_debugfs);
-	batadv_debugfs = NULL;
-}
-
-/**
- * batadv_debugfs_add_hardif() - creates the base directory for a hard interface
- *  in debugfs.
- * @hard_iface: hard interface which should be added.
- */
-void batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
-{
-	struct net *net = dev_net(hard_iface->net_dev);
-	struct batadv_debuginfo **bat_debug;
-
-	if (net != &init_net)
-		return;
-
-	hard_iface->debug_dir = debugfs_create_dir(hard_iface->net_dev->name,
-						   batadv_debugfs);
-
-	for (bat_debug = batadv_hardif_debuginfos; *bat_debug; ++bat_debug)
-		debugfs_create_file(((*bat_debug)->attr).name,
-				    S_IFREG | ((*bat_debug)->attr).mode,
-				    hard_iface->debug_dir, hard_iface->net_dev,
-				    &(*bat_debug)->fops);
-}
-
-/**
- * batadv_debugfs_rename_hardif() - Fix debugfs path for renamed hardif
- * @hard_iface: hard interface which was renamed
- */
-void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface)
-{
-	const char *name = hard_iface->net_dev->name;
-	struct dentry *dir;
-
-	dir = hard_iface->debug_dir;
-	if (!dir)
-		return;
-
-	debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
-}
-
-/**
- * batadv_debugfs_del_hardif() - delete the base directory for a hard interface
- *  in debugfs.
- * @hard_iface: hard interface which is deleted.
- */
-void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface)
-{
-	struct net *net = dev_net(hard_iface->net_dev);
-
-	if (net != &init_net)
-		return;
-
-	if (batadv_debugfs) {
-		debugfs_remove_recursive(hard_iface->debug_dir);
-		hard_iface->debug_dir = NULL;
-	}
-}
-
-/**
- * batadv_debugfs_add_meshif() - Initialize interface dependent debugfs entries
- * @dev: netdev struct of the soft interface
- *
- * Return: 0 on success or negative error number in case of failure
- */
-int batadv_debugfs_add_meshif(struct net_device *dev)
-{
-	struct batadv_priv *bat_priv = netdev_priv(dev);
-	struct batadv_debuginfo **bat_debug;
-	struct net *net = dev_net(dev);
-
-	if (net != &init_net)
-		return 0;
-
-	bat_priv->debug_dir = debugfs_create_dir(dev->name, batadv_debugfs);
-
-	batadv_socket_setup(bat_priv);
-
-	if (batadv_debug_log_setup(bat_priv) < 0)
-		goto rem_attr;
-
-	for (bat_debug = batadv_mesh_debuginfos; *bat_debug; ++bat_debug)
-		debugfs_create_file(((*bat_debug)->attr).name,
-				    S_IFREG | ((*bat_debug)->attr).mode,
-				    bat_priv->debug_dir, dev,
-				    &(*bat_debug)->fops);
-
-	batadv_nc_init_debugfs(bat_priv);
-
-	return 0;
-rem_attr:
-	debugfs_remove_recursive(bat_priv->debug_dir);
-	bat_priv->debug_dir = NULL;
-	return -ENOMEM;
-}
-
-/**
- * batadv_debugfs_rename_meshif() - Fix debugfs path for renamed softif
- * @dev: net_device which was renamed
- */
-void batadv_debugfs_rename_meshif(struct net_device *dev)
-{
-	struct batadv_priv *bat_priv = netdev_priv(dev);
-	const char *name = dev->name;
-	struct dentry *dir;
-
-	dir = bat_priv->debug_dir;
-	if (!dir)
-		return;
-
-	debugfs_rename(dir->d_parent, dir, dir->d_parent, name);
-}
-
-/**
- * batadv_debugfs_del_meshif() - Remove interface dependent debugfs entries
- * @dev: netdev struct of the soft interface
- */
-void batadv_debugfs_del_meshif(struct net_device *dev)
-{
-	struct batadv_priv *bat_priv = netdev_priv(dev);
-	struct net *net = dev_net(dev);
-
-	if (net != &init_net)
-		return;
-
-	batadv_debug_log_cleanup(bat_priv);
-
-	if (batadv_debugfs) {
-		debugfs_remove_recursive(bat_priv->debug_dir);
-		bat_priv->debug_dir = NULL;
-	}
-}
diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h
deleted file mode 100644
index 7e2e8f586f42..000000000000
--- a/net/batman-adv/debugfs.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2010-2020  B.A.T.M.A.N. contributors:
- *
- * Marek Lindner
- */
-
-#ifndef _NET_BATMAN_ADV_DEBUGFS_H_
-#define _NET_BATMAN_ADV_DEBUGFS_H_
-
-#include "main.h"
-
-#include <linux/fs.h>
-#include <linux/netdevice.h>
-
-#define BATADV_DEBUGFS_SUBDIR "batman_adv"
-
-#if IS_ENABLED(CONFIG_BATMAN_ADV_DEBUGFS)
-
-void batadv_debugfs_deprecated(struct file *file, const char *alt);
-void batadv_debugfs_init(void);
-void batadv_debugfs_destroy(void);
-int batadv_debugfs_add_meshif(struct net_device *dev);
-void batadv_debugfs_rename_meshif(struct net_device *dev);
-void batadv_debugfs_del_meshif(struct net_device *dev);
-void batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface);
-void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface);
-void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface);
-
-#else
-
-static inline void batadv_debugfs_deprecated(struct file *file, const char *alt)
-{
-}
-
-static inline void batadv_debugfs_init(void)
-{
-}
-
-static inline void batadv_debugfs_destroy(void)
-{
-}
-
-static inline int batadv_debugfs_add_meshif(struct net_device *dev)
-{
-	return 0;
-}
-
-static inline void batadv_debugfs_rename_meshif(struct net_device *dev)
-{
-}
-
-static inline void batadv_debugfs_del_meshif(struct net_device *dev)
-{
-}
-
-static inline
-void batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface)
-{
-}
-
-static inline
-void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface)
-{
-}
-
-static inline
-void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface)
-{
-}
-
-#endif
-
-#endif /* _NET_BATMAN_ADV_DEBUGFS_H_ */
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 0e6e53e9b5f3..fd7ba6bbdf85 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -26,7 +26,6 @@
 #include <linux/netlink.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -842,60 +841,6 @@ void batadv_dat_free(struct batadv_priv *bat_priv)
 	batadv_dat_hash_free(bat_priv);
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_dat_cache_seq_print_text() - print the local DAT hash table
- * @seq: seq file to print on
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hashtable *hash = bat_priv->dat.hash;
-	struct batadv_dat_entry *dat_entry;
-	struct batadv_hard_iface *primary_if;
-	struct hlist_head *head;
-	unsigned long last_seen_jiffies;
-	int last_seen_msecs, last_seen_secs, last_seen_mins;
-	u32 i;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		goto out;
-
-	seq_printf(seq, "Distributed ARP Table (%s):\n", net_dev->name);
-	seq_puts(seq,
-		 "          IPv4             MAC        VID   last-seen\n");
-
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(dat_entry, head, hash_entry) {
-			last_seen_jiffies = jiffies - dat_entry->last_update;
-			last_seen_msecs = jiffies_to_msecs(last_seen_jiffies);
-			last_seen_mins = last_seen_msecs / 60000;
-			last_seen_msecs = last_seen_msecs % 60000;
-			last_seen_secs = last_seen_msecs / 1000;
-
-			seq_printf(seq, " * %15pI4 %pM %4i %6i:%02i\n",
-				   &dat_entry->ip, dat_entry->mac_addr,
-				   batadv_print_vid(dat_entry->vid),
-				   last_seen_mins, last_seen_secs);
-		}
-		rcu_read_unlock();
-	}
-
-out:
-	if (primary_if)
-		batadv_hardif_put(primary_if);
-	return 0;
-}
-#endif
-
 /**
  * batadv_dat_cache_dump_entry() - dump one entry of the DAT cache table to a
  *  netlink socket
diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h
index 4e031661682a..e980fb45693a 100644
--- a/net/batman-adv/distributed-arp-table.h
+++ b/net/batman-adv/distributed-arp-table.h
@@ -12,7 +12,6 @@
 #include <linux/compiler.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
 #include <uapi/linux/batadv_packet.h>
@@ -74,7 +73,6 @@ batadv_dat_init_own_addr(struct batadv_priv *bat_priv,
 
 int batadv_dat_init(struct batadv_priv *bat_priv);
 void batadv_dat_free(struct batadv_priv *bat_priv);
-int batadv_dat_cache_seq_print_text(struct seq_file *seq, void *offset);
 int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb);
 
 /**
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 9fdbe3068153..e522f1fcfd9a 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -14,8 +14,8 @@
 #include <linux/gfp.h>
 #include <linux/if_ether.h>
 #include <linux/jiffies.h>
-#include <linux/kernel.h>
 #include <linux/lockdep.h>
+#include <linux/minmax.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
@@ -27,7 +27,6 @@
 #include "originator.h"
 #include "routing.h"
 #include "send.h"
-#include "soft-interface.h"
 
 /**
  * batadv_frag_clear_chain() - delete entries in the fragment buffer chain
@@ -306,7 +305,7 @@ free:
  * set *skb to merged packet; 2) Packet is buffered: Return true and set *skb
  * to NULL; 3) Error: Return false and free skb.
  *
- * Return: true when the packet is merged or buffered, false when skb is not not
+ * Return: true when the packet is merged or buffered, false when skb is not
  * used.
  */
 bool batadv_frag_skb_buffer(struct sk_buff **skb,
@@ -391,6 +390,7 @@ out:
 
 /**
  * batadv_frag_create() - create a fragment from skb
+ * @net_dev: outgoing device for fragment
  * @skb: skb to create fragment from
  * @frag_head: header to use in new fragment
  * @fragment_size: size of new fragment
@@ -401,22 +401,25 @@ out:
  *
  * Return: the new fragment, NULL on error.
  */
-static struct sk_buff *batadv_frag_create(struct sk_buff *skb,
+static struct sk_buff *batadv_frag_create(struct net_device *net_dev,
+					  struct sk_buff *skb,
 					  struct batadv_frag_packet *frag_head,
 					  unsigned int fragment_size)
 {
+	unsigned int ll_reserved = LL_RESERVED_SPACE(net_dev);
+	unsigned int tailroom = net_dev->needed_tailroom;
 	struct sk_buff *skb_fragment;
 	unsigned int header_size = sizeof(*frag_head);
 	unsigned int mtu = fragment_size + header_size;
 
-	skb_fragment = netdev_alloc_skb(NULL, mtu + ETH_HLEN);
+	skb_fragment = dev_alloc_skb(ll_reserved + mtu + tailroom);
 	if (!skb_fragment)
 		goto err;
 
 	skb_fragment->priority = skb->priority;
 
 	/* Eat the last mtu-bytes of the skb */
-	skb_reserve(skb_fragment, header_size + ETH_HLEN);
+	skb_reserve(skb_fragment, ll_reserved + header_size);
 	skb_split(skb, skb_fragment, skb->len - fragment_size);
 
 	/* Add the header */
@@ -439,11 +442,12 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 			    struct batadv_orig_node *orig_node,
 			    struct batadv_neigh_node *neigh_node)
 {
+	struct net_device *net_dev = neigh_node->if_incoming->net_dev;
 	struct batadv_priv *bat_priv;
 	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_frag_packet frag_header;
 	struct sk_buff *skb_fragment;
-	unsigned int mtu = neigh_node->if_incoming->net_dev->mtu;
+	unsigned int mtu = net_dev->mtu;
 	unsigned int header_size = sizeof(frag_header);
 	unsigned int max_fragment_size, num_fragments;
 	int ret;
@@ -503,7 +507,7 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 			goto put_primary_if;
 		}
 
-		skb_fragment = batadv_frag_create(skb, &frag_header,
+		skb_fragment = batadv_frag_create(net_dev, skb, &frag_header,
 						  max_fragment_size);
 		if (!skb_fragment) {
 			ret = -ENOMEM;
@@ -522,13 +526,14 @@ int batadv_frag_send_packet(struct sk_buff *skb,
 		frag_header.no++;
 	}
 
-	/* Make room for the fragment header. */
-	if (batadv_skb_head_push(skb, header_size) < 0 ||
-	    pskb_expand_head(skb, header_size + ETH_HLEN, 0, GFP_ATOMIC) < 0) {
-		ret = -ENOMEM;
+	/* make sure that there is at least enough head for the fragmentation
+	 * and ethernet headers
+	 */
+	ret = skb_cow_head(skb, ETH_HLEN + header_size);
+	if (ret < 0)
 		goto put_primary_if;
-	}
 
+	skb_push(skb, header_size);
 	memcpy(skb->data, &frag_header, header_size);
 
 	/* Send the last fragment */
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index ef3f85b576c4..cffe72f4edd7 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -25,7 +25,6 @@
 #include <linux/netlink.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -511,44 +510,6 @@ void batadv_gw_node_free(struct batadv_priv *bat_priv)
 	spin_unlock_bh(&bat_priv->gw.list_lock);
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-
-/**
- * batadv_gw_client_seq_print_text() - Print the gateway table in a seq file
- * @seq: seq file to print on
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hard_iface *primary_if;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		return 0;
-
-	seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n",
-		   BATADV_SOURCE_VERSION, primary_if->net_dev->name,
-		   primary_if->net_dev->dev_addr, net_dev->name,
-		   bat_priv->algo_ops->name);
-
-	batadv_hardif_put(primary_if);
-
-	if (!bat_priv->algo_ops->gw.print) {
-		seq_puts(seq,
-			 "No printing function for this routing protocol\n");
-		return 0;
-	}
-
-	bat_priv->algo_ops->gw.print(bat_priv, seq);
-
-	return 0;
-}
-#endif
-
 /**
  * batadv_gw_dump() - Dump gateways into a message
  * @msg: Netlink message to dump into
diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h
index 88b5dba84354..2fbc500f0ac1 100644
--- a/net/batman-adv/gateway_client.h
+++ b/net/batman-adv/gateway_client.h
@@ -10,7 +10,6 @@
 #include "main.h"
 
 #include <linux/netlink.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
 #include <uapi/linux/batadv_packet.h>
@@ -31,7 +30,6 @@ void batadv_gw_node_free(struct batadv_priv *bat_priv);
 void batadv_gw_node_put(struct batadv_gw_node *gw_node);
 struct batadv_gw_node *
 batadv_gw_get_selected_gw_node(struct batadv_priv *bat_priv);
-int batadv_gw_client_seq_print_text(struct seq_file *seq, void *offset);
 int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb);
 bool batadv_gw_out_of_range(struct batadv_priv *bat_priv, struct sk_buff *skb);
 enum batadv_dhcp_recipient
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index fa06b51c0144..0f186ddc15e3 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -18,6 +18,7 @@
 #include <linux/kref.h>
 #include <linux/limits.h>
 #include <linux/list.h>
+#include <linux/minmax.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/printk.h>
@@ -31,14 +32,12 @@
 
 #include "bat_v.h"
 #include "bridge_loop_avoidance.h"
-#include "debugfs.h"
 #include "distributed-arp-table.h"
 #include "gateway_client.h"
 #include "log.h"
 #include "originator.h"
 #include "send.h"
 #include "soft-interface.h"
-#include "sysfs.h"
 #include "translation-table.h"
 
 /**
@@ -554,6 +553,9 @@ static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface)
 	needed_headroom = lower_headroom + (lower_header_len - ETH_HLEN);
 	needed_headroom += batadv_max_header_len();
 
+	/* fragmentation headers don't strip the unicast/... header */
+	needed_headroom += sizeof(struct batadv_frag_packet);
+
 	soft_iface->needed_headroom = needed_headroom;
 	soft_iface->needed_tailroom = lower_tailroom;
 }
@@ -599,7 +601,7 @@ out:
 	/* report to the other components the maximum amount of bytes that
 	 * batman-adv can send over the wire (without considering the payload
 	 * overhead). For example, this value is used by TT to compute the
-	 * maximum local table table size
+	 * maximum local table size
 	 */
 	atomic_set(&bat_priv->packet_size_max, min_mtu);
 
@@ -843,11 +845,8 @@ static size_t batadv_hardif_cnt(const struct net_device *soft_iface)
 /**
  * batadv_hardif_disable_interface() - Remove hard interface from soft interface
  * @hard_iface: hard interface to be removed
- * @autodel: whether to delete soft interface when it doesn't contain any other
- *  slave interfaces
  */
-void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
-				     enum batadv_hard_if_cleanup autodel)
+void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface)
 {
 	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
 	struct batadv_hard_iface *primary_if = NULL;
@@ -885,13 +884,9 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
 	batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface);
 
 	/* nobody uses this interface anymore */
-	if (batadv_hardif_cnt(hard_iface->soft_iface) <= 1) {
+	if (batadv_hardif_cnt(hard_iface->soft_iface) <= 1)
 		batadv_gw_check_client_stop(bat_priv);
 
-		if (autodel == BATADV_IF_CLEANUP_AUTO)
-			batadv_softif_destroy_sysfs(hard_iface->soft_iface);
-	}
-
 	hard_iface->soft_iface = NULL;
 	batadv_hardif_put(hard_iface);
 
@@ -904,7 +899,6 @@ static struct batadv_hard_iface *
 batadv_hardif_add_interface(struct net_device *net_dev)
 {
 	struct batadv_hard_iface *hard_iface;
-	int ret;
 
 	ASSERT_RTNL();
 
@@ -917,16 +911,10 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 	if (!hard_iface)
 		goto release_dev;
 
-	ret = batadv_sysfs_add_hardif(&hard_iface->hardif_obj, net_dev);
-	if (ret)
-		goto free_if;
-
 	hard_iface->net_dev = net_dev;
 	hard_iface->soft_iface = NULL;
 	hard_iface->if_status = BATADV_IF_NOT_IN_USE;
 
-	batadv_debugfs_add_hardif(hard_iface);
-
 	INIT_LIST_HEAD(&hard_iface->list);
 	INIT_HLIST_HEAD(&hard_iface->neigh_list);
 
@@ -950,8 +938,6 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 
 	return hard_iface;
 
-free_if:
-	kfree(hard_iface);
 release_dev:
 	dev_put(net_dev);
 out:
@@ -964,36 +950,16 @@ static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface)
 
 	/* first deactivate interface */
 	if (hard_iface->if_status != BATADV_IF_NOT_IN_USE)
-		batadv_hardif_disable_interface(hard_iface,
-						BATADV_IF_CLEANUP_KEEP);
+		batadv_hardif_disable_interface(hard_iface);
 
 	if (hard_iface->if_status != BATADV_IF_NOT_IN_USE)
 		return;
 
 	hard_iface->if_status = BATADV_IF_TO_BE_REMOVED;
-	batadv_debugfs_del_hardif(hard_iface);
-	batadv_sysfs_del_hardif(&hard_iface->hardif_obj);
 	batadv_hardif_put(hard_iface);
 }
 
 /**
- * batadv_hardif_remove_interfaces() - Remove all hard interfaces
- */
-void batadv_hardif_remove_interfaces(void)
-{
-	struct batadv_hard_iface *hard_iface, *hard_iface_tmp;
-
-	rtnl_lock();
-	list_for_each_entry_safe(hard_iface, hard_iface_tmp,
-				 &batadv_hardif_list, list) {
-		list_del_rcu(&hard_iface->list);
-		batadv_hardif_generation++;
-		batadv_hardif_remove_interface(hard_iface);
-	}
-	rtnl_unlock();
-}
-
-/**
  * batadv_hard_if_event_softif() - Handle events for soft interfaces
  * @event: NETDEV_* event to handle
  * @net_dev: net_device which generated an event
@@ -1007,13 +973,9 @@ static int batadv_hard_if_event_softif(unsigned long event,
 
 	switch (event) {
 	case NETDEV_REGISTER:
-		batadv_sysfs_add_meshif(net_dev);
 		bat_priv = netdev_priv(net_dev);
 		batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS);
 		break;
-	case NETDEV_CHANGENAME:
-		batadv_debugfs_rename_meshif(net_dev);
-		break;
 	}
 
 	return NOTIFY_DONE;
@@ -1078,9 +1040,6 @@ static int batadv_hard_if_event(struct notifier_block *this,
 		if (batadv_is_wifi_hardif(hard_iface))
 			hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS;
 		break;
-	case NETDEV_CHANGENAME:
-		batadv_debugfs_rename_hardif(hard_iface);
-		break;
 	default:
 		break;
 	}
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index bad2e50135e8..f4b8e9efef19 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -42,12 +42,6 @@ enum batadv_hard_if_state {
 
 	/** @BATADV_IF_TO_BE_ACTIVATED: interface is getting activated */
 	BATADV_IF_TO_BE_ACTIVATED,
-
-	/**
-	 * @BATADV_IF_I_WANT_YOU: interface is queued up (using sysfs) for being
-	 * added as slave interface of a batman-adv soft interface
-	 */
-	BATADV_IF_I_WANT_YOU,
 };
 
 /**
@@ -73,22 +67,6 @@ enum batadv_hard_if_bcast {
 	BATADV_HARDIF_BCAST_DUPORIG,
 };
 
-/**
- * enum batadv_hard_if_cleanup - Cleanup modi for soft_iface after slave removal
- */
-enum batadv_hard_if_cleanup {
-	/**
-	 * @BATADV_IF_CLEANUP_KEEP: Don't automatically delete soft-interface
-	 */
-	BATADV_IF_CLEANUP_KEEP,
-
-	/**
-	 * @BATADV_IF_CLEANUP_AUTO: Delete soft-interface after last slave was
-	 *  removed
-	 */
-	BATADV_IF_CLEANUP_AUTO,
-};
-
 extern struct notifier_block batadv_hard_if_notifier;
 
 struct net_device *batadv_get_real_netdev(struct net_device *net_device);
@@ -98,9 +76,7 @@ struct batadv_hard_iface*
 batadv_hardif_get_by_netdev(const struct net_device *net_dev);
 int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 				   struct net *net, const char *iface_name);
-void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface,
-				     enum batadv_hard_if_cleanup autodel);
-void batadv_hardif_remove_interfaces(void);
+void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface);
 int batadv_hardif_min_mtu(struct net_device *soft_iface);
 void batadv_update_min_mtu(struct net_device *soft_iface);
 void batadv_hardif_release(struct kref *ref);
diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c
deleted file mode 100644
index 8bdabc03b0b2..000000000000
--- a/net/batman-adv/icmp_socket.c
+++ /dev/null
@@ -1,392 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2007-2020  B.A.T.M.A.N. contributors:
- *
- * Marek Lindner
- */
-
-#include "icmp_socket.h"
-#include "main.h"
-
-#include <linux/atomic.h>
-#include <linux/compiler.h>
-#include <linux/debugfs.h>
-#include <linux/errno.h>
-#include <linux/etherdevice.h>
-#include <linux/eventpoll.h>
-#include <linux/export.h>
-#include <linux/fcntl.h>
-#include <linux/fs.h>
-#include <linux/gfp.h>
-#include <linux/if_ether.h>
-#include <linux/kernel.h>
-#include <linux/list.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/pkt_sched.h>
-#include <linux/poll.h>
-#include <linux/printk.h>
-#include <linux/sched.h> /* for linux/wait.h */
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/stddef.h>
-#include <linux/string.h>
-#include <linux/uaccess.h>
-#include <linux/wait.h>
-#include <uapi/linux/batadv_packet.h>
-
-#include "debugfs.h"
-#include "hard-interface.h"
-#include "log.h"
-#include "originator.h"
-#include "send.h"
-
-static struct batadv_socket_client *batadv_socket_client_hash[256];
-
-static void batadv_socket_add_packet(struct batadv_socket_client *socket_client,
-				     struct batadv_icmp_header *icmph,
-				     size_t icmp_len);
-
-/**
- * batadv_socket_init() - Initialize soft interface independent socket data
- */
-void batadv_socket_init(void)
-{
-	memset(batadv_socket_client_hash, 0, sizeof(batadv_socket_client_hash));
-}
-
-static int batadv_socket_open(struct inode *inode, struct file *file)
-{
-	unsigned int i;
-	struct batadv_socket_client *socket_client;
-
-	if (!try_module_get(THIS_MODULE))
-		return -EBUSY;
-
-	batadv_debugfs_deprecated(file, "");
-
-	stream_open(inode, file);
-
-	socket_client = kmalloc(sizeof(*socket_client), GFP_KERNEL);
-	if (!socket_client) {
-		module_put(THIS_MODULE);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(batadv_socket_client_hash); i++) {
-		if (!batadv_socket_client_hash[i]) {
-			batadv_socket_client_hash[i] = socket_client;
-			break;
-		}
-	}
-
-	if (i == ARRAY_SIZE(batadv_socket_client_hash)) {
-		pr_err("Error - can't add another packet client: maximum number of clients reached\n");
-		kfree(socket_client);
-		module_put(THIS_MODULE);
-		return -EXFULL;
-	}
-
-	INIT_LIST_HEAD(&socket_client->queue_list);
-	socket_client->queue_len = 0;
-	socket_client->index = i;
-	socket_client->bat_priv = inode->i_private;
-	spin_lock_init(&socket_client->lock);
-	init_waitqueue_head(&socket_client->queue_wait);
-
-	file->private_data = socket_client;
-
-	return 0;
-}
-
-static int batadv_socket_release(struct inode *inode, struct file *file)
-{
-	struct batadv_socket_client *client = file->private_data;
-	struct batadv_socket_packet *packet, *tmp;
-
-	spin_lock_bh(&client->lock);
-
-	/* for all packets in the queue ... */
-	list_for_each_entry_safe(packet, tmp, &client->queue_list, list) {
-		list_del(&packet->list);
-		kfree(packet);
-	}
-
-	batadv_socket_client_hash[client->index] = NULL;
-	spin_unlock_bh(&client->lock);
-
-	kfree(client);
-	module_put(THIS_MODULE);
-
-	return 0;
-}
-
-static ssize_t batadv_socket_read(struct file *file, char __user *buf,
-				  size_t count, loff_t *ppos)
-{
-	struct batadv_socket_client *socket_client = file->private_data;
-	struct batadv_socket_packet *socket_packet;
-	size_t packet_len;
-	int error;
-
-	if ((file->f_flags & O_NONBLOCK) && socket_client->queue_len == 0)
-		return -EAGAIN;
-
-	if (!buf || count < sizeof(struct batadv_icmp_packet))
-		return -EINVAL;
-
-	error = wait_event_interruptible(socket_client->queue_wait,
-					 socket_client->queue_len);
-
-	if (error)
-		return error;
-
-	spin_lock_bh(&socket_client->lock);
-
-	socket_packet = list_first_entry(&socket_client->queue_list,
-					 struct batadv_socket_packet, list);
-	list_del(&socket_packet->list);
-	socket_client->queue_len--;
-
-	spin_unlock_bh(&socket_client->lock);
-
-	packet_len = min(count, socket_packet->icmp_len);
-	error = copy_to_user(buf, &socket_packet->icmp_packet, packet_len);
-
-	kfree(socket_packet);
-
-	if (error)
-		return -EFAULT;
-
-	return packet_len;
-}
-
-static ssize_t batadv_socket_write(struct file *file, const char __user *buff,
-				   size_t len, loff_t *off)
-{
-	struct batadv_socket_client *socket_client = file->private_data;
-	struct batadv_priv *bat_priv = socket_client->bat_priv;
-	struct batadv_hard_iface *primary_if = NULL;
-	struct sk_buff *skb;
-	struct batadv_icmp_packet_rr *icmp_packet_rr;
-	struct batadv_icmp_header *icmp_header;
-	struct batadv_orig_node *orig_node = NULL;
-	struct batadv_neigh_node *neigh_node = NULL;
-	size_t packet_len = sizeof(struct batadv_icmp_packet);
-	u8 *addr;
-
-	if (len < sizeof(struct batadv_icmp_header)) {
-		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-			   "Error - can't send packet from char device: invalid packet size\n");
-		return -EINVAL;
-	}
-
-	primary_if = batadv_primary_if_get_selected(bat_priv);
-
-	if (!primary_if) {
-		len = -EFAULT;
-		goto out;
-	}
-
-	if (len >= BATADV_ICMP_MAX_PACKET_SIZE)
-		packet_len = BATADV_ICMP_MAX_PACKET_SIZE;
-	else
-		packet_len = len;
-
-	skb = netdev_alloc_skb_ip_align(NULL, packet_len + ETH_HLEN);
-	if (!skb) {
-		len = -ENOMEM;
-		goto out;
-	}
-
-	skb->priority = TC_PRIO_CONTROL;
-	skb_reserve(skb, ETH_HLEN);
-	icmp_header = skb_put(skb, packet_len);
-
-	if (copy_from_user(icmp_header, buff, packet_len)) {
-		len = -EFAULT;
-		goto free_skb;
-	}
-
-	if (icmp_header->packet_type != BATADV_ICMP) {
-		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-			   "Error - can't send packet from char device: got bogus packet type (expected: BAT_ICMP)\n");
-		len = -EINVAL;
-		goto free_skb;
-	}
-
-	switch (icmp_header->msg_type) {
-	case BATADV_ECHO_REQUEST:
-		if (len < sizeof(struct batadv_icmp_packet)) {
-			batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-				   "Error - can't send packet from char device: invalid packet size\n");
-			len = -EINVAL;
-			goto free_skb;
-		}
-
-		if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
-			goto dst_unreach;
-
-		orig_node = batadv_orig_hash_find(bat_priv, icmp_header->dst);
-		if (!orig_node)
-			goto dst_unreach;
-
-		neigh_node = batadv_orig_router_get(orig_node,
-						    BATADV_IF_DEFAULT);
-		if (!neigh_node)
-			goto dst_unreach;
-
-		if (!neigh_node->if_incoming)
-			goto dst_unreach;
-
-		if (neigh_node->if_incoming->if_status != BATADV_IF_ACTIVE)
-			goto dst_unreach;
-
-		icmp_packet_rr = (struct batadv_icmp_packet_rr *)icmp_header;
-		if (packet_len == sizeof(*icmp_packet_rr)) {
-			addr = neigh_node->if_incoming->net_dev->dev_addr;
-			ether_addr_copy(icmp_packet_rr->rr[0], addr);
-		}
-
-		break;
-	default:
-		batadv_dbg(BATADV_DBG_BATMAN, bat_priv,
-			   "Error - can't send packet from char device: got unknown message type\n");
-		len = -EINVAL;
-		goto free_skb;
-	}
-
-	icmp_header->uid = socket_client->index;
-
-	if (icmp_header->version != BATADV_COMPAT_VERSION) {
-		icmp_header->msg_type = BATADV_PARAMETER_PROBLEM;
-		icmp_header->version = BATADV_COMPAT_VERSION;
-		batadv_socket_add_packet(socket_client, icmp_header,
-					 packet_len);
-		goto free_skb;
-	}
-
-	ether_addr_copy(icmp_header->orig, primary_if->net_dev->dev_addr);
-
-	batadv_send_unicast_skb(skb, neigh_node);
-	goto out;
-
-dst_unreach:
-	icmp_header->msg_type = BATADV_DESTINATION_UNREACHABLE;
-	batadv_socket_add_packet(socket_client, icmp_header, packet_len);
-free_skb:
-	kfree_skb(skb);
-out:
-	if (primary_if)
-		batadv_hardif_put(primary_if);
-	if (neigh_node)
-		batadv_neigh_node_put(neigh_node);
-	if (orig_node)
-		batadv_orig_node_put(orig_node);
-	return len;
-}
-
-static __poll_t batadv_socket_poll(struct file *file, poll_table *wait)
-{
-	struct batadv_socket_client *socket_client = file->private_data;
-
-	poll_wait(file, &socket_client->queue_wait, wait);
-
-	if (socket_client->queue_len > 0)
-		return EPOLLIN | EPOLLRDNORM;
-
-	return 0;
-}
-
-static const struct file_operations batadv_fops = {
-	.owner = THIS_MODULE,
-	.open = batadv_socket_open,
-	.release = batadv_socket_release,
-	.read = batadv_socket_read,
-	.write = batadv_socket_write,
-	.poll = batadv_socket_poll,
-	.llseek = no_llseek,
-};
-
-/**
- * batadv_socket_setup() - Create debugfs "socket" file
- * @bat_priv: the bat priv with all the soft interface information
- */
-void batadv_socket_setup(struct batadv_priv *bat_priv)
-{
-	debugfs_create_file(BATADV_ICMP_SOCKET, 0600, bat_priv->debug_dir,
-			    bat_priv, &batadv_fops);
-}
-
-/**
- * batadv_socket_add_packet() - schedule an icmp packet to be sent to
- *  userspace on an icmp socket.
- * @socket_client: the socket this packet belongs to
- * @icmph: pointer to the header of the icmp packet
- * @icmp_len: total length of the icmp packet
- */
-static void batadv_socket_add_packet(struct batadv_socket_client *socket_client,
-				     struct batadv_icmp_header *icmph,
-				     size_t icmp_len)
-{
-	struct batadv_socket_packet *socket_packet;
-	size_t len;
-
-	socket_packet = kmalloc(sizeof(*socket_packet), GFP_ATOMIC);
-
-	if (!socket_packet)
-		return;
-
-	len = icmp_len;
-	/* check the maximum length before filling the buffer */
-	if (len > sizeof(socket_packet->icmp_packet))
-		len = sizeof(socket_packet->icmp_packet);
-
-	INIT_LIST_HEAD(&socket_packet->list);
-	memcpy(&socket_packet->icmp_packet, icmph, len);
-	socket_packet->icmp_len = len;
-
-	spin_lock_bh(&socket_client->lock);
-
-	/* while waiting for the lock the socket_client could have been
-	 * deleted
-	 */
-	if (!batadv_socket_client_hash[icmph->uid]) {
-		spin_unlock_bh(&socket_client->lock);
-		kfree(socket_packet);
-		return;
-	}
-
-	list_add_tail(&socket_packet->list, &socket_client->queue_list);
-	socket_client->queue_len++;
-
-	if (socket_client->queue_len > 100) {
-		socket_packet = list_first_entry(&socket_client->queue_list,
-						 struct batadv_socket_packet,
-						 list);
-
-		list_del(&socket_packet->list);
-		kfree(socket_packet);
-		socket_client->queue_len--;
-	}
-
-	spin_unlock_bh(&socket_client->lock);
-
-	wake_up(&socket_client->queue_wait);
-}
-
-/**
- * batadv_socket_receive_packet() - schedule an icmp packet to be received
- *  locally and sent to userspace.
- * @icmph: pointer to the header of the icmp packet
- * @icmp_len: total length of the icmp packet
- */
-void batadv_socket_receive_packet(struct batadv_icmp_header *icmph,
-				  size_t icmp_len)
-{
-	struct batadv_socket_client *hash;
-
-	hash = batadv_socket_client_hash[icmph->uid];
-	if (hash)
-		batadv_socket_add_packet(hash, icmph, icmp_len);
-}
diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h
deleted file mode 100644
index 6abd0f4742ef..000000000000
--- a/net/batman-adv/icmp_socket.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2007-2020  B.A.T.M.A.N. contributors:
- *
- * Marek Lindner
- */
-
-#ifndef _NET_BATMAN_ADV_ICMP_SOCKET_H_
-#define _NET_BATMAN_ADV_ICMP_SOCKET_H_
-
-#include "main.h"
-
-#include <linux/types.h>
-#include <uapi/linux/batadv_packet.h>
-
-#define BATADV_ICMP_SOCKET "socket"
-
-void batadv_socket_setup(struct batadv_priv *bat_priv);
-
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-
-void batadv_socket_init(void);
-void batadv_socket_receive_packet(struct batadv_icmp_header *icmph,
-				  size_t icmp_len);
-
-#else
-
-static inline void batadv_socket_init(void)
-{
-}
-
-static inline void
-batadv_socket_receive_packet(struct batadv_icmp_header *icmph, size_t icmp_len)
-{
-}
-
-#endif
-
-#endif /* _NET_BATMAN_ADV_ICMP_SOCKET_H_ */
diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
index a67b2b091447..b7e9923b11a2 100644
--- a/net/batman-adv/log.c
+++ b/net/batman-adv/log.c
@@ -7,213 +7,10 @@
 #include "log.h"
 #include "main.h"
 
-#include <linux/compiler.h>
-#include <linux/debugfs.h>
-#include <linux/errno.h>
-#include <linux/eventpoll.h>
-#include <linux/export.h>
-#include <linux/fcntl.h>
-#include <linux/fs.h>
-#include <linux/gfp.h>
-#include <linux/jiffies.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/poll.h>
-#include <linux/sched.h> /* for linux/wait.h */
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/stddef.h>
-#include <linux/types.h>
-#include <linux/uaccess.h>
-#include <linux/wait.h>
 #include <stdarg.h>
 
-#include "debugfs.h"
 #include "trace.h"
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-
-#define BATADV_LOG_BUFF_MASK (batadv_log_buff_len - 1)
-
-static const int batadv_log_buff_len = BATADV_LOG_BUF_LEN;
-
-static char *batadv_log_char_addr(struct batadv_priv_debug_log *debug_log,
-				  size_t idx)
-{
-	return &debug_log->log_buff[idx & BATADV_LOG_BUFF_MASK];
-}
-
-static void batadv_emit_log_char(struct batadv_priv_debug_log *debug_log,
-				 char c)
-{
-	char *char_addr;
-
-	char_addr = batadv_log_char_addr(debug_log, debug_log->log_end);
-	*char_addr = c;
-	debug_log->log_end++;
-
-	if (debug_log->log_end - debug_log->log_start > batadv_log_buff_len)
-		debug_log->log_start = debug_log->log_end - batadv_log_buff_len;
-}
-
-__printf(2, 3)
-static int batadv_fdebug_log(struct batadv_priv_debug_log *debug_log,
-			     const char *fmt, ...)
-{
-	va_list args;
-	static char debug_log_buf[256];
-	char *p;
-
-	if (!debug_log)
-		return 0;
-
-	spin_lock_bh(&debug_log->lock);
-	va_start(args, fmt);
-	vscnprintf(debug_log_buf, sizeof(debug_log_buf), fmt, args);
-	va_end(args);
-
-	for (p = debug_log_buf; *p != 0; p++)
-		batadv_emit_log_char(debug_log, *p);
-
-	spin_unlock_bh(&debug_log->lock);
-
-	wake_up(&debug_log->queue_wait);
-
-	return 0;
-}
-
-static int batadv_log_open(struct inode *inode, struct file *file)
-{
-	if (!try_module_get(THIS_MODULE))
-		return -EBUSY;
-
-	batadv_debugfs_deprecated(file,
-				  "Use tracepoint batadv:batadv_dbg instead\n");
-
-	stream_open(inode, file);
-	file->private_data = inode->i_private;
-	return 0;
-}
-
-static int batadv_log_release(struct inode *inode, struct file *file)
-{
-	module_put(THIS_MODULE);
-	return 0;
-}
-
-static bool batadv_log_empty(struct batadv_priv_debug_log *debug_log)
-{
-	return !(debug_log->log_start - debug_log->log_end);
-}
-
-static ssize_t batadv_log_read(struct file *file, char __user *buf,
-			       size_t count, loff_t *ppos)
-{
-	struct batadv_priv *bat_priv = file->private_data;
-	struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
-	int error, i = 0;
-	char *char_addr;
-	char c;
-
-	if ((file->f_flags & O_NONBLOCK) && batadv_log_empty(debug_log))
-		return -EAGAIN;
-
-	if (!buf)
-		return -EINVAL;
-
-	if (count == 0)
-		return 0;
-
-	if (!access_ok(buf, count))
-		return -EFAULT;
-
-	error = wait_event_interruptible(debug_log->queue_wait,
-					 (!batadv_log_empty(debug_log)));
-
-	if (error)
-		return error;
-
-	spin_lock_bh(&debug_log->lock);
-
-	while ((!error) && (i < count) &&
-	       (debug_log->log_start != debug_log->log_end)) {
-		char_addr = batadv_log_char_addr(debug_log,
-						 debug_log->log_start);
-		c = *char_addr;
-
-		debug_log->log_start++;
-
-		spin_unlock_bh(&debug_log->lock);
-
-		error = __put_user(c, buf);
-
-		spin_lock_bh(&debug_log->lock);
-
-		buf++;
-		i++;
-	}
-
-	spin_unlock_bh(&debug_log->lock);
-
-	if (!error)
-		return i;
-
-	return error;
-}
-
-static __poll_t batadv_log_poll(struct file *file, poll_table *wait)
-{
-	struct batadv_priv *bat_priv = file->private_data;
-	struct batadv_priv_debug_log *debug_log = bat_priv->debug_log;
-
-	poll_wait(file, &debug_log->queue_wait, wait);
-
-	if (!batadv_log_empty(debug_log))
-		return EPOLLIN | EPOLLRDNORM;
-
-	return 0;
-}
-
-static const struct file_operations batadv_log_fops = {
-	.open           = batadv_log_open,
-	.release        = batadv_log_release,
-	.read           = batadv_log_read,
-	.poll           = batadv_log_poll,
-	.llseek         = no_llseek,
-};
-
-/**
- * batadv_debug_log_setup() - Initialize debug log
- * @bat_priv: the bat priv with all the soft interface information
- *
- * Return: 0 on success or negative error number in case of failure
- */
-int batadv_debug_log_setup(struct batadv_priv *bat_priv)
-{
-	bat_priv->debug_log = kzalloc(sizeof(*bat_priv->debug_log), GFP_ATOMIC);
-	if (!bat_priv->debug_log)
-		return -ENOMEM;
-
-	spin_lock_init(&bat_priv->debug_log->lock);
-	init_waitqueue_head(&bat_priv->debug_log->queue_wait);
-
-	debugfs_create_file("log", 0400, bat_priv->debug_dir, bat_priv,
-			    &batadv_log_fops);
-	return 0;
-}
-
-/**
- * batadv_debug_log_cleanup() - Destroy debug log
- * @bat_priv: the bat priv with all the soft interface information
- */
-void batadv_debug_log_cleanup(struct batadv_priv *bat_priv)
-{
-	kfree(bat_priv->debug_log);
-	bat_priv->debug_log = NULL;
-}
-
-#endif /* CONFIG_BATMAN_ADV_DEBUGFS */
-
 /**
  * batadv_debug_log() - Add debug log entry
  * @bat_priv: the bat priv with all the soft interface information
@@ -231,11 +28,6 @@ int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...)
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-	batadv_fdebug_log(bat_priv->debug_log, "[%10u] %pV",
-			  jiffies_to_msecs(jiffies), &vaf);
-#endif
-
 	trace_batadv_dbg(bat_priv, &vaf);
 
 	va_end(args);
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 519c08c2cfba..ed9d87ce3407 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -23,12 +23,12 @@
 #include <linux/kobject.h>
 #include <linux/kref.h>
 #include <linux/list.h>
+#include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/printk.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -44,12 +44,10 @@
 #include "bat_iv_ogm.h"
 #include "bat_v.h"
 #include "bridge_loop_avoidance.h"
-#include "debugfs.h"
 #include "distributed-arp-table.h"
 #include "gateway_client.h"
 #include "gateway_common.h"
 #include "hard-interface.h"
-#include "icmp_socket.h"
 #include "log.h"
 #include "multicast.h"
 #include "netlink.h"
@@ -113,9 +111,6 @@ static int __init batadv_init(void)
 	if (!batadv_event_workqueue)
 		goto err_create_wq;
 
-	batadv_socket_init();
-	batadv_debugfs_init();
-
 	register_netdevice_notifier(&batadv_hard_if_notifier);
 	rtnl_link_register(&batadv_link_ops);
 	batadv_netlink_register();
@@ -133,11 +128,9 @@ err_create_wq:
 
 static void __exit batadv_exit(void)
 {
-	batadv_debugfs_destroy();
 	batadv_netlink_unregister();
 	rtnl_link_unregister(&batadv_link_ops);
 	unregister_netdevice_notifier(&batadv_hard_if_notifier);
-	batadv_hardif_remove_interfaces();
 
 	flush_workqueue(batadv_event_workqueue);
 	destroy_workqueue(batadv_event_workqueue);
@@ -306,44 +299,6 @@ bool batadv_is_my_mac(struct batadv_priv *bat_priv, const u8 *addr)
 	return is_my_mac;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_seq_print_text_primary_if_get() - called from debugfs table printing
- *  function that requires the primary interface
- * @seq: debugfs table seq_file struct
- *
- * Return: primary interface if found or NULL otherwise.
- */
-struct batadv_hard_iface *
-batadv_seq_print_text_primary_if_get(struct seq_file *seq)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hard_iface *primary_if;
-
-	primary_if = batadv_primary_if_get_selected(bat_priv);
-
-	if (!primary_if) {
-		seq_printf(seq,
-			   "BATMAN mesh %s disabled - please specify interfaces to enable it\n",
-			   net_dev->name);
-		goto out;
-	}
-
-	if (primary_if->if_status == BATADV_IF_ACTIVE)
-		goto out;
-
-	seq_printf(seq,
-		   "BATMAN mesh %s disabled - primary interface not active\n",
-		   net_dev->name);
-	batadv_hardif_put(primary_if);
-	primary_if = NULL;
-
-out:
-	return primary_if;
-}
-#endif
-
 /**
  * batadv_max_header_len() - calculate maximum encapsulation overhead for a
  *  payload packet
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 0393bb9ed3d0..288201630ceb 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -13,7 +13,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2020.3"
+#define BATADV_SOURCE_VERSION "2021.0"
 #endif
 
 /* B.A.T.M.A.N. parameters */
@@ -212,7 +212,6 @@ enum batadv_uev_type {
 #include <linux/jiffies.h>
 #include <linux/netdevice.h>
 #include <linux/percpu.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
 #include <uapi/linux/batadv_packet.h>
@@ -243,8 +242,6 @@ extern struct workqueue_struct *batadv_event_workqueue;
 int batadv_mesh_init(struct net_device *soft_iface);
 void batadv_mesh_free(struct net_device *soft_iface);
 bool batadv_is_my_mac(struct batadv_priv *bat_priv, const u8 *addr);
-struct batadv_hard_iface *
-batadv_seq_print_text_primary_if_get(struct seq_file *seq);
 int batadv_max_header_len(void);
 void batadv_skb_set_priority(struct sk_buff *skb, int offset);
 int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev,
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index ca24a2e522b7..854e5ff28a3f 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -33,7 +33,6 @@
 #include <linux/printk.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -208,7 +207,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
 		return BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6;
 
 	/* TODO: ask the bridge if a multicast router is present (the bridge
-	 * is capable of performing proper RFC4286 multicast multicast router
+	 * is capable of performing proper RFC4286 multicast router
 	 * discovery) instead of searching for a ff02::2 listener here
 	 */
 	ret = br_multicast_list_adjacent(dev, &bridge_mcast_list);
@@ -221,7 +220,7 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
 		 * address here, only IPv6 ones
 		 */
 		if (br_ip_entry->addr.proto == htons(ETH_P_IPV6) &&
-		    ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.u.ip6))
+		    ipv6_addr_is_ll_all_routers(&br_ip_entry->addr.dst.ip6))
 			flags &= ~BATADV_MCAST_WANT_NO_RTR6;
 
 		list_del(&br_ip_entry->list);
@@ -562,10 +561,10 @@ out:
 static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
 {
 	if (src->proto == htons(ETH_P_IP))
-		ip_eth_mc_map(src->u.ip4, dst);
+		ip_eth_mc_map(src->dst.ip4, dst);
 #if IS_ENABLED(CONFIG_IPV6)
 	else if (src->proto == htons(ETH_P_IPV6))
-		ipv6_eth_mc_map(&src->u.ip6, dst);
+		ipv6_eth_mc_map(&src->dst.ip6, dst);
 #endif
 	else
 		eth_zero_addr(dst);
@@ -609,11 +608,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
 				continue;
 
 			if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
-			    ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+			    ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
 				continue;
 
 			if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR4) &&
-			    !ipv4_is_local_multicast(br_ip_entry->addr.u.ip4))
+			    !ipv4_is_local_multicast(br_ip_entry->addr.dst.ip4))
 				continue;
 		}
 
@@ -623,11 +622,11 @@ static int batadv_mcast_mla_bridge_get(struct net_device *dev,
 				continue;
 
 			if (tvlv_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
-			    ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.u.ip6))
+			    ipv6_addr_is_ll_all_nodes(&br_ip_entry->addr.dst.ip6))
 				continue;
 
 			if (!(tvlv_flags & BATADV_MCAST_WANT_NO_RTR6) &&
-			    IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.u.ip6) >
+			    IPV6_ADDR_MC_SCOPE(&br_ip_entry->addr.dst.ip6) >
 			    IPV6_ADDR_SCOPE_LINKLOCAL)
 				continue;
 		}
@@ -2074,116 +2073,6 @@ void batadv_mcast_init(struct batadv_priv *bat_priv)
 	batadv_mcast_start_timer(bat_priv);
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_mcast_flags_print_header() - print own mcast flags to debugfs table
- * @bat_priv: the bat priv with all the soft interface information
- * @seq: debugfs table seq_file struct
- *
- * Prints our own multicast flags including a more specific reason why
- * they are set, that is prints the bridge and querier state too, to
- * the debugfs table specified via @seq.
- */
-static void batadv_mcast_flags_print_header(struct batadv_priv *bat_priv,
-					    struct seq_file *seq)
-{
-	struct batadv_mcast_mla_flags *mla_flags = &bat_priv->mcast.mla_flags;
-	char querier4, querier6, shadowing4, shadowing6;
-	bool bridged = mla_flags->bridged;
-	u8 flags = mla_flags->tvlv_flags;
-
-	if (bridged) {
-		querier4 = mla_flags->querier_ipv4.exists ? '.' : '4';
-		querier6 = mla_flags->querier_ipv6.exists ? '.' : '6';
-		shadowing4 = mla_flags->querier_ipv4.shadowing ? '4' : '.';
-		shadowing6 = mla_flags->querier_ipv6.shadowing ? '6' : '.';
-	} else {
-		querier4 = '?';
-		querier6 = '?';
-		shadowing4 = '?';
-		shadowing6 = '?';
-	}
-
-	seq_printf(seq, "Multicast flags (own flags: [%c%c%c%s%s])\n",
-		   (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) ? 'U' : '.',
-		   (flags & BATADV_MCAST_WANT_ALL_IPV4) ? '4' : '.',
-		   (flags & BATADV_MCAST_WANT_ALL_IPV6) ? '6' : '.',
-		   !(flags & BATADV_MCAST_WANT_NO_RTR4) ? "R4" : ". ",
-		   !(flags & BATADV_MCAST_WANT_NO_RTR6) ? "R6" : ". ");
-	seq_printf(seq, "* Bridged [U]\t\t\t\t%c\n", bridged ? 'U' : '.');
-	seq_printf(seq, "* No IGMP/MLD Querier [4/6]:\t\t%c/%c\n",
-		   querier4, querier6);
-	seq_printf(seq, "* Shadowing IGMP/MLD Querier [4/6]:\t%c/%c\n",
-		   shadowing4, shadowing6);
-	seq_puts(seq, "-------------------------------------------\n");
-	seq_printf(seq, "       %-10s %s\n", "Originator", "Flags");
-}
-
-/**
- * batadv_mcast_flags_seq_print_text() - print the mcast flags of other nodes
- * @seq: seq file to print on
- * @offset: not used
- *
- * This prints a table of (primary) originators and their according
- * multicast flags, including (in the header) our own.
- *
- * Return: always 0
- */
-int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hard_iface *primary_if;
-	struct batadv_hashtable *hash = bat_priv->orig_hash;
-	struct batadv_orig_node *orig_node;
-	struct hlist_head *head;
-	u8 flags;
-	u32 i;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		return 0;
-
-	batadv_mcast_flags_print_header(bat_priv, seq);
-
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
-			if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST,
-				      &orig_node->capa_initialized))
-				continue;
-
-			if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST,
-				      &orig_node->capabilities)) {
-				seq_printf(seq, "%pM -\n", orig_node->orig);
-				continue;
-			}
-
-			flags = orig_node->mcast_flags;
-
-			seq_printf(seq, "%pM [%c%c%c%s%s]\n", orig_node->orig,
-				   (flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)
-				   ? 'U' : '.',
-				   (flags & BATADV_MCAST_WANT_ALL_IPV4)
-				   ? '4' : '.',
-				   (flags & BATADV_MCAST_WANT_ALL_IPV6)
-				   ? '6' : '.',
-				   !(flags & BATADV_MCAST_WANT_NO_RTR4)
-				   ? "R4" : ". ",
-				   !(flags & BATADV_MCAST_WANT_NO_RTR6)
-				   ? "R6" : ". ");
-		}
-		rcu_read_unlock();
-	}
-
-	batadv_hardif_put(primary_if);
-
-	return 0;
-}
-#endif
-
 /**
  * batadv_mcast_mesh_info_put() - put multicast info into a netlink message
  * @msg: buffer for the message
diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h
index 3e114bc5ca3b..d61593d02072 100644
--- a/net/batman-adv/multicast.h
+++ b/net/batman-adv/multicast.h
@@ -10,7 +10,6 @@
 #include "main.h"
 
 #include <linux/netlink.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 
 /**
@@ -56,8 +55,6 @@ int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 void batadv_mcast_init(struct batadv_priv *bat_priv);
 
-int batadv_mcast_flags_seq_print_text(struct seq_file *seq, void *offset);
-
 int batadv_mcast_mesh_info_put(struct sk_buff *msg,
 			       struct batadv_priv *bat_priv);
 
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index dc193618a761..97bcf149633d 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/limits.h>
 #include <linux/list.h>
+#include <linux/minmax.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/printk.h>
@@ -1350,7 +1351,7 @@ static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
 	}
 }
 
-static const struct genl_ops batadv_netlink_ops[] = {
+static const struct genl_small_ops batadv_netlink_ops[] = {
 	{
 		.cmd = BATADV_CMD_GET_MESH,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -1484,8 +1485,8 @@ struct genl_family batadv_netlink_family __ro_after_init = {
 	.pre_doit = batadv_pre_doit,
 	.post_doit = batadv_post_doit,
 	.module = THIS_MODULE,
-	.ops = batadv_netlink_ops,
-	.n_ops = ARRAY_SIZE(batadv_netlink_ops),
+	.small_ops = batadv_netlink_ops,
+	.n_small_ops = ARRAY_SIZE(batadv_netlink_ops),
 	.mcgrps = batadv_netlink_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(batadv_netlink_mcgrps),
 };
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 48d707850f3e..0cec108b7a99 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -11,7 +11,6 @@
 #include <linux/bitops.h>
 #include <linux/byteorder/generic.h>
 #include <linux/compiler.h>
-#include <linux/debugfs.h>
 #include <linux/errno.h>
 #include <linux/etherdevice.h>
 #include <linux/gfp.h>
@@ -26,11 +25,10 @@
 #include <linux/lockdep.h>
 #include <linux/net.h>
 #include <linux/netdevice.h>
+#include <linux/prandom.h>
 #include <linux/printk.h>
-#include <linux/random.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -39,7 +37,6 @@
 #include <linux/workqueue.h>
 #include <uapi/linux/batadv_packet.h>
 
-#include "hard-interface.h"
 #include "hash.h"
 #include "log.h"
 #include "originator.h"
@@ -250,7 +247,7 @@ static void batadv_nc_path_put(struct batadv_nc_path *nc_path)
 /**
  * batadv_nc_packet_free() - frees nc packet
  * @nc_packet: the nc packet to free
- * @dropped: whether the packet is freed because is is dropped
+ * @dropped: whether the packet is freed because is dropped
  */
 static void batadv_nc_packet_free(struct batadv_nc_packet *nc_packet,
 				  bool dropped)
@@ -1876,87 +1873,3 @@ void batadv_nc_mesh_free(struct batadv_priv *bat_priv)
 	batadv_nc_purge_paths(bat_priv, bat_priv->nc.decoding_hash, NULL);
 	batadv_hash_destroy(bat_priv->nc.decoding_hash);
 }
-
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_nc_nodes_seq_print_text() - print the nc node information
- * @seq: seq file to print on
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hashtable *hash = bat_priv->orig_hash;
-	struct batadv_hard_iface *primary_if;
-	struct hlist_head *head;
-	struct batadv_orig_node *orig_node;
-	struct batadv_nc_node *nc_node;
-	int i;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		goto out;
-
-	/* Traverse list of originators */
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		/* For each orig_node in this bin */
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(orig_node, head, hash_entry) {
-			/* no need to print the orig node if it does not have
-			 * network coding neighbors
-			 */
-			if (list_empty(&orig_node->in_coding_list) &&
-			    list_empty(&orig_node->out_coding_list))
-				continue;
-
-			seq_printf(seq, "Node:      %pM\n", orig_node->orig);
-
-			seq_puts(seq, " Ingoing:  ");
-			/* For each in_nc_node to this orig_node */
-			list_for_each_entry_rcu(nc_node,
-						&orig_node->in_coding_list,
-						list)
-				seq_printf(seq, "%pM ",
-					   nc_node->addr);
-			seq_puts(seq, "\n Outgoing: ");
-			/* For out_nc_node to this orig_node */
-			list_for_each_entry_rcu(nc_node,
-						&orig_node->out_coding_list,
-						list)
-				seq_printf(seq, "%pM ",
-					   nc_node->addr);
-			seq_puts(seq, "\n\n");
-		}
-		rcu_read_unlock();
-	}
-
-out:
-	if (primary_if)
-		batadv_hardif_put(primary_if);
-	return 0;
-}
-
-/**
- * batadv_nc_init_debugfs() - create nc folder and related files in debugfs
- * @bat_priv: the bat priv with all the soft interface information
- */
-void batadv_nc_init_debugfs(struct batadv_priv *bat_priv)
-{
-	struct dentry *nc_dir;
-
-	nc_dir = debugfs_create_dir("nc", bat_priv->debug_dir);
-
-	debugfs_create_u8("min_tq", 0644, nc_dir, &bat_priv->nc.min_tq);
-
-	debugfs_create_u32("max_fwd_delay", 0644, nc_dir,
-			   &bat_priv->nc.max_fwd_delay);
-
-	debugfs_create_u32("max_buffer_time", 0644, nc_dir,
-			   &bat_priv->nc.max_buffer_time);
-}
-#endif
diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h
index 334289084127..8fb2c01e7837 100644
--- a/net/batman-adv/network-coding.h
+++ b/net/batman-adv/network-coding.h
@@ -10,7 +10,6 @@
 #include "main.h"
 
 #include <linux/netdevice.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
 #include <uapi/linux/batadv_packet.h>
@@ -38,8 +37,6 @@ void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
 				      struct sk_buff *skb);
 void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
 					 struct sk_buff *skb);
-int batadv_nc_nodes_seq_print_text(struct seq_file *seq, void *offset);
-void batadv_nc_init_debugfs(struct batadv_priv *bat_priv);
 
 #else /* ifdef CONFIG_BATMAN_ADV_NC */
 
@@ -104,16 +101,6 @@ batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
 {
 }
 
-static inline int batadv_nc_nodes_seq_print_text(struct seq_file *seq,
-						 void *offset)
-{
-	return 0;
-}
-
-static inline void batadv_nc_init_debugfs(struct batadv_priv *bat_priv)
-{
-}
-
 #endif /* ifdef CONFIG_BATMAN_ADV_NC */
 
 #endif /* _NET_BATMAN_ADV_NETWORK_CODING_H_ */
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 805d8969bdfb..77431e59b228 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -20,7 +20,6 @@
 #include <linux/netlink.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -733,42 +732,6 @@ batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node,
 	return batadv_neigh_node_create(orig_node, hard_iface, neigh_addr);
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_hardif_neigh_seq_print_text() - print the single hop neighbour list
- * @seq: neighbour table seq_file struct
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hard_iface *primary_if;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		return 0;
-
-	seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n",
-		   BATADV_SOURCE_VERSION, primary_if->net_dev->name,
-		   primary_if->net_dev->dev_addr, net_dev->name,
-		   bat_priv->algo_ops->name);
-
-	batadv_hardif_put(primary_if);
-
-	if (!bat_priv->algo_ops->neigh.print) {
-		seq_puts(seq,
-			 "No printing function for this routing protocol\n");
-		return 0;
-	}
-
-	bat_priv->algo_ops->neigh.print(bat_priv, seq);
-	return 0;
-}
-#endif
-
 /**
  * batadv_hardif_neigh_dump() - Dump to netlink the neighbor infos for a
  *  specific outgoing interface
@@ -1382,90 +1345,6 @@ static void batadv_purge_orig(struct work_struct *work)
 			   msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD));
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-
-/**
- * batadv_orig_seq_print_text() - Print the originator table in a seq file
- * @seq: seq file to print on
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_orig_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hard_iface *primary_if;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		return 0;
-
-	seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s %s)]\n",
-		   BATADV_SOURCE_VERSION, primary_if->net_dev->name,
-		   primary_if->net_dev->dev_addr, net_dev->name,
-		   bat_priv->algo_ops->name);
-
-	batadv_hardif_put(primary_if);
-
-	if (!bat_priv->algo_ops->orig.print) {
-		seq_puts(seq,
-			 "No printing function for this routing protocol\n");
-		return 0;
-	}
-
-	bat_priv->algo_ops->orig.print(bat_priv, seq, BATADV_IF_DEFAULT);
-
-	return 0;
-}
-
-/**
- * batadv_orig_hardif_seq_print_text() - writes originator infos for a specific
- *  outgoing interface
- * @seq: debugfs table seq_file struct
- * @offset: not used
- *
- * Return: 0
- */
-int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_hard_iface *hard_iface;
-	struct batadv_priv *bat_priv;
-
-	hard_iface = batadv_hardif_get_by_netdev(net_dev);
-
-	if (!hard_iface || !hard_iface->soft_iface) {
-		seq_puts(seq, "Interface not known to B.A.T.M.A.N.\n");
-		goto out;
-	}
-
-	bat_priv = netdev_priv(hard_iface->soft_iface);
-	if (!bat_priv->algo_ops->orig.print) {
-		seq_puts(seq,
-			 "No printing function for this routing protocol\n");
-		goto out;
-	}
-
-	if (hard_iface->if_status != BATADV_IF_ACTIVE) {
-		seq_puts(seq, "Interface not active\n");
-		goto out;
-	}
-
-	seq_printf(seq, "[B.A.T.M.A.N. adv %s, IF/MAC: %s/%pM (%s %s)]\n",
-		   BATADV_SOURCE_VERSION, hard_iface->net_dev->name,
-		   hard_iface->net_dev->dev_addr,
-		   hard_iface->soft_iface->name, bat_priv->algo_ops->name);
-
-	bat_priv->algo_ops->orig.print(bat_priv, seq, hard_iface);
-
-out:
-	if (hard_iface)
-		batadv_hardif_put(hard_iface);
-	return 0;
-}
-#endif
-
 /**
  * batadv_orig_dump() - Dump to netlink the originator infos for a specific
  *  outgoing interface
diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h
index 7bc01c138b3a..e75d4c4d11f5 100644
--- a/net/batman-adv/originator.h
+++ b/net/batman-adv/originator.h
@@ -13,7 +13,6 @@
 #include <linux/if_ether.h>
 #include <linux/jhash.h>
 #include <linux/netlink.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
 
@@ -46,7 +45,6 @@ batadv_neigh_ifinfo_get(struct batadv_neigh_node *neigh,
 void batadv_neigh_ifinfo_put(struct batadv_neigh_ifinfo *neigh_ifinfo);
 
 int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb);
-int batadv_hardif_neigh_seq_print_text(struct seq_file *seq, void *offset);
 
 struct batadv_orig_ifinfo *
 batadv_orig_ifinfo_get(struct batadv_orig_node *orig_node,
@@ -56,9 +54,7 @@ batadv_orig_ifinfo_new(struct batadv_orig_node *orig_node,
 		       struct batadv_hard_iface *if_outgoing);
 void batadv_orig_ifinfo_put(struct batadv_orig_ifinfo *orig_ifinfo);
 
-int batadv_orig_seq_print_text(struct seq_file *seq, void *offset);
 int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb);
-int batadv_orig_hardif_seq_print_text(struct seq_file *seq, void *offset);
 struct batadv_orig_node_vlan *
 batadv_orig_node_vlan_new(struct batadv_orig_node *orig_node,
 			  unsigned short vid);
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index 9e5c71e406ff..49cbca4aa428 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -29,7 +29,6 @@
 #include "distributed-arp-table.h"
 #include "fragmentation.h"
 #include "hard-interface.h"
-#include "icmp_socket.h"
 #include "log.h"
 #include "network-coding.h"
 #include "originator.h"
@@ -227,15 +226,6 @@ static int batadv_recv_my_icmp_packet(struct batadv_priv *bat_priv,
 	icmph = (struct batadv_icmp_header *)skb->data;
 
 	switch (icmph->msg_type) {
-	case BATADV_ECHO_REPLY:
-	case BATADV_DESTINATION_UNREACHABLE:
-	case BATADV_TTL_EXCEEDED:
-		/* receive the packet */
-		if (skb_linearize(skb) < 0)
-			break;
-
-		batadv_socket_receive_packet(icmph, skb->len);
-		break;
 	case BATADV_ECHO_REQUEST:
 		/* answer echo request (ping) */
 		primary_if = batadv_primary_if_get_selected(bat_priv);
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index d267b94800d6..87017332b567 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -461,7 +461,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb,
 /**
  * batadv_forw_packet_free() - free a forwarding packet
  * @forw_packet: The packet to free
- * @dropped: whether the packet is freed because is is dropped
+ * @dropped: whether the packet is freed because is dropped
  *
  * This frees a forwarding packet and releases any resources it might
  * have claimed.
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index cdde943c1b83..97118efbe678 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -30,7 +30,6 @@
 #include <linux/random.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/rtnetlink.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
@@ -38,12 +37,12 @@
 #include <linux/stddef.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <net/netlink.h>
 #include <uapi/linux/batadv_packet.h>
 #include <uapi/linux/batman_adv.h>
 
 #include "bat_algo.h"
 #include "bridge_loop_avoidance.h"
-#include "debugfs.h"
 #include "distributed-arp-table.h"
 #include "gateway_client.h"
 #include "hard-interface.h"
@@ -51,7 +50,6 @@
 #include "network-coding.h"
 #include "originator.h"
 #include "send.h"
-#include "sysfs.h"
 #include "translation-table.h"
 
 /**
@@ -574,7 +572,6 @@ struct batadv_softif_vlan *batadv_softif_vlan_get(struct batadv_priv *bat_priv,
 int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 {
 	struct batadv_softif_vlan *vlan;
-	int err;
 
 	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
 
@@ -601,19 +598,6 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 	hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
 	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
 
-	/* batadv_sysfs_add_vlan cannot be in the spinlock section due to the
-	 * sleeping behavior of the sysfs functions and the fs_reclaim lock
-	 */
-	err = batadv_sysfs_add_vlan(bat_priv->soft_iface, vlan);
-	if (err) {
-		/* ref for the function */
-		batadv_softif_vlan_put(vlan);
-
-		/* ref for the list */
-		batadv_softif_vlan_put(vlan);
-		return err;
-	}
-
 	/* add a new TT local entry. This one will be marked with the NOPURGE
 	 * flag
 	 */
@@ -641,14 +625,13 @@ static void batadv_softif_destroy_vlan(struct batadv_priv *bat_priv,
 	batadv_tt_local_remove(bat_priv, bat_priv->soft_iface->dev_addr,
 			       vlan->vid, "vlan interface destroyed", false);
 
-	batadv_sysfs_del_vlan(bat_priv, vlan);
 	batadv_softif_vlan_put(vlan);
 }
 
 /**
  * batadv_interface_add_vid() - ndo_add_vid API implementation
  * @dev: the netdev of the mesh interface
- * @proto: protocol of the the vlan id
+ * @proto: protocol of the vlan id
  * @vid: identifier of the new vlan
  *
  * Set up all the internal structures for handling the new vlan on top of the
@@ -661,7 +644,6 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
 {
 	struct batadv_priv *bat_priv = netdev_priv(dev);
 	struct batadv_softif_vlan *vlan;
-	int ret;
 
 	/* only 802.1Q vlans are supported.
 	 * batman-adv does not know how to handle other types
@@ -681,17 +663,6 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
 	if (!vlan)
 		return batadv_softif_create_vlan(bat_priv, vid);
 
-	/* recreate the sysfs object if it was already destroyed (and it should
-	 * be since we received a kill_vid() for this vlan
-	 */
-	if (!vlan->kobj) {
-		ret = batadv_sysfs_add_vlan(bat_priv->soft_iface, vlan);
-		if (ret) {
-			batadv_softif_vlan_put(vlan);
-			return ret;
-		}
-	}
-
 	/* add a new TT local entry. This one will be marked with the NOPURGE
 	 * flag. This must be added again, even if the vlan object already
 	 * exists, because the entry was deleted by kill_vid()
@@ -706,7 +677,7 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
 /**
  * batadv_interface_kill_vid() - ndo_kill_vid API implementation
  * @dev: the netdev of the mesh interface
- * @proto: protocol of the the vlan id
+ * @proto: protocol of the vlan id
  * @vid: identifier of the deleted vlan
  *
  * Destroy all the internal structures used to handle the vlan identified by vid
@@ -845,22 +816,18 @@ static int batadv_softif_init_late(struct net_device *dev)
 
 	batadv_nc_init_bat_priv(bat_priv);
 
-	ret = batadv_algo_select(bat_priv, batadv_routing_algo);
-	if (ret < 0)
-		goto free_bat_counters;
-
-	ret = batadv_debugfs_add_meshif(dev);
-	if (ret < 0)
-		goto free_bat_counters;
+	if (!bat_priv->algo_ops) {
+		ret = batadv_algo_select(bat_priv, batadv_routing_algo);
+		if (ret < 0)
+			goto free_bat_counters;
+	}
 
 	ret = batadv_mesh_init(dev);
 	if (ret < 0)
-		goto unreg_debugfs;
+		goto free_bat_counters;
 
 	return 0;
 
-unreg_debugfs:
-	batadv_debugfs_del_meshif(dev);
 free_bat_counters:
 	free_percpu(bat_priv->bat_counters);
 	bat_priv->bat_counters = NULL;
@@ -914,7 +881,7 @@ static int batadv_softif_slave_del(struct net_device *dev,
 	if (!hard_iface || hard_iface->soft_iface != dev)
 		goto out;
 
-	batadv_hardif_disable_interface(hard_iface, BATADV_IF_CLEANUP_KEEP);
+	batadv_hardif_disable_interface(hard_iface);
 	ret = 0;
 
 out:
@@ -1037,7 +1004,6 @@ static const struct ethtool_ops batadv_ethtool_ops = {
  */
 static void batadv_softif_free(struct net_device *dev)
 {
-	batadv_debugfs_del_meshif(dev);
 	batadv_mesh_free(dev);
 
 	/* some scheduled RCU callbacks need the bat_priv struct to accomplish
@@ -1074,6 +1040,59 @@ static void batadv_softif_init_early(struct net_device *dev)
 }
 
 /**
+ * batadv_softif_validate() - validate configuration of new batadv link
+ * @tb: IFLA_INFO_DATA netlink attributes
+ * @data: enum batadv_ifla_attrs attributes
+ * @extack: extended ACK report struct
+ *
+ * Return: 0 if successful or error otherwise.
+ */
+static int batadv_softif_validate(struct nlattr *tb[], struct nlattr *data[],
+				  struct netlink_ext_ack *extack)
+{
+	struct batadv_algo_ops *algo_ops;
+
+	if (!data)
+		return 0;
+
+	if (data[IFLA_BATADV_ALGO_NAME]) {
+		algo_ops = batadv_algo_get(nla_data(data[IFLA_BATADV_ALGO_NAME]));
+		if (!algo_ops)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * batadv_softif_newlink() - pre-initialize and register new batadv link
+ * @src_net: the applicable net namespace
+ * @dev: network device to register
+ * @tb: IFLA_INFO_DATA netlink attributes
+ * @data: enum batadv_ifla_attrs attributes
+ * @extack: extended ACK report struct
+ *
+ * Return: 0 if successful or error otherwise.
+ */
+static int batadv_softif_newlink(struct net *src_net, struct net_device *dev,
+				 struct nlattr *tb[], struct nlattr *data[],
+				 struct netlink_ext_ack *extack)
+{
+	struct batadv_priv *bat_priv = netdev_priv(dev);
+	const char *algo_name;
+	int err;
+
+	if (data && data[IFLA_BATADV_ALGO_NAME]) {
+		algo_name = nla_data(data[IFLA_BATADV_ALGO_NAME]);
+		err = batadv_algo_select(bat_priv, algo_name);
+		if (err)
+			return -EINVAL;
+	}
+
+	return register_netdevice(dev);
+}
+
+/**
  * batadv_softif_create() - Create and register soft interface
  * @net: the applicable net namespace
  * @name: name of the new soft interface
@@ -1106,28 +1125,6 @@ struct net_device *batadv_softif_create(struct net *net, const char *name)
 }
 
 /**
- * batadv_softif_destroy_sysfs() - deletion of batadv_soft_interface via sysfs
- * @soft_iface: the to-be-removed batman-adv interface
- */
-void batadv_softif_destroy_sysfs(struct net_device *soft_iface)
-{
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
-	struct batadv_softif_vlan *vlan;
-
-	ASSERT_RTNL();
-
-	/* destroy the "untagged" VLAN */
-	vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS);
-	if (vlan) {
-		batadv_softif_destroy_vlan(bat_priv, vlan);
-		batadv_softif_vlan_put(vlan);
-	}
-
-	batadv_sysfs_del_meshif(soft_iface);
-	unregister_netdevice(soft_iface);
-}
-
-/**
  * batadv_softif_destroy_netlink() - deletion of batadv_soft_interface via
  *  netlink
  * @soft_iface: the to-be-removed batman-adv interface
@@ -1142,8 +1139,7 @@ static void batadv_softif_destroy_netlink(struct net_device *soft_iface,
 
 	list_for_each_entry(hard_iface, &batadv_hardif_list, list) {
 		if (hard_iface->soft_iface == soft_iface)
-			batadv_hardif_disable_interface(hard_iface,
-							BATADV_IF_CLEANUP_KEEP);
+			batadv_hardif_disable_interface(hard_iface);
 	}
 
 	/* destroy the "untagged" VLAN */
@@ -1153,7 +1149,6 @@ static void batadv_softif_destroy_netlink(struct net_device *soft_iface,
 		batadv_softif_vlan_put(vlan);
 	}
 
-	batadv_sysfs_del_meshif(soft_iface);
 	unregister_netdevice_queue(soft_iface, head);
 }
 
@@ -1171,9 +1166,17 @@ bool batadv_softif_is_valid(const struct net_device *net_dev)
 	return false;
 }
 
+static const struct nla_policy batadv_ifla_policy[IFLA_BATADV_MAX + 1] = {
+	[IFLA_BATADV_ALGO_NAME]	= { .type = NLA_NUL_STRING },
+};
+
 struct rtnl_link_ops batadv_link_ops __read_mostly = {
 	.kind		= "batadv",
 	.priv_size	= sizeof(struct batadv_priv),
 	.setup		= batadv_softif_init_early,
+	.maxtype	= IFLA_BATADV_MAX,
+	.policy		= batadv_ifla_policy,
+	.validate	= batadv_softif_validate,
+	.newlink	= batadv_softif_newlink,
 	.dellink	= batadv_softif_destroy_netlink,
 };
diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h
index 534e08d6ad91..74716d9ca4f6 100644
--- a/net/batman-adv/soft-interface.h
+++ b/net/batman-adv/soft-interface.h
@@ -20,7 +20,6 @@ void batadv_interface_rx(struct net_device *soft_iface,
 			 struct sk_buff *skb, int hdr_size,
 			 struct batadv_orig_node *orig_node);
 struct net_device *batadv_softif_create(struct net *net, const char *name);
-void batadv_softif_destroy_sysfs(struct net_device *soft_iface);
 bool batadv_softif_is_valid(const struct net_device *net_dev);
 extern struct rtnl_link_ops batadv_link_ops;
 int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid);
diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c
deleted file mode 100644
index 0f962dcd239e..000000000000
--- a/net/batman-adv/sysfs.c
+++ /dev/null
@@ -1,1272 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (C) 2010-2020  B.A.T.M.A.N. contributors:
- *
- * Marek Lindner
- */
-
-#include "sysfs.h"
-#include "main.h"
-
-#include <asm/current.h>
-#include <linux/atomic.h>
-#include <linux/compiler.h>
-#include <linux/device.h>
-#include <linux/errno.h>
-#include <linux/gfp.h>
-#include <linux/if.h>
-#include <linux/if_vlan.h>
-#include <linux/kernel.h>
-#include <linux/kobject.h>
-#include <linux/kref.h>
-#include <linux/limits.h>
-#include <linux/netdevice.h>
-#include <linux/printk.h>
-#include <linux/rculist.h>
-#include <linux/rcupdate.h>
-#include <linux/rtnetlink.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/stddef.h>
-#include <linux/string.h>
-#include <linux/stringify.h>
-#include <linux/workqueue.h>
-#include <uapi/linux/batadv_packet.h>
-#include <uapi/linux/batman_adv.h>
-
-#include "bridge_loop_avoidance.h"
-#include "distributed-arp-table.h"
-#include "gateway_client.h"
-#include "gateway_common.h"
-#include "hard-interface.h"
-#include "log.h"
-#include "netlink.h"
-#include "network-coding.h"
-#include "soft-interface.h"
-
-/**
- * batadv_sysfs_deprecated() - Log use of deprecated batadv sysfs access
- * @attr: attribute which was accessed
- */
-static void batadv_sysfs_deprecated(struct attribute *attr)
-{
-	pr_warn_ratelimited(DEPRECATED "%s (pid %d) Use of sysfs file \"%s\".\nUse batadv genl family instead",
-			    current->comm, task_pid_nr(current), attr->name);
-}
-
-static struct net_device *batadv_kobj_to_netdev(struct kobject *obj)
-{
-	struct device *dev = container_of(obj->parent, struct device, kobj);
-
-	return to_net_dev(dev);
-}
-
-static struct batadv_priv *batadv_kobj_to_batpriv(struct kobject *obj)
-{
-	struct net_device *net_dev = batadv_kobj_to_netdev(obj);
-
-	return netdev_priv(net_dev);
-}
-
-/**
- * batadv_vlan_kobj_to_batpriv() - convert a vlan kobj in the associated batpriv
- * @obj: kobject to covert
- *
- * Return: the associated batadv_priv struct.
- */
-static struct batadv_priv *batadv_vlan_kobj_to_batpriv(struct kobject *obj)
-{
-	/* VLAN specific attributes are located in the root sysfs folder if they
-	 * refer to the untagged VLAN..
-	 */
-	if (!strcmp(BATADV_SYSFS_IF_MESH_SUBDIR, obj->name))
-		return batadv_kobj_to_batpriv(obj);
-
-	/* ..while the attributes for the tagged vlans are located in
-	 * the in the corresponding "vlan%VID" subfolder
-	 */
-	return batadv_kobj_to_batpriv(obj->parent);
-}
-
-/**
- * batadv_kobj_to_vlan() - convert a kobj in the associated softif_vlan struct
- * @bat_priv: the bat priv with all the soft interface information
- * @obj: kobject to covert
- *
- * Return: the associated softif_vlan struct if found, NULL otherwise.
- */
-static struct batadv_softif_vlan *
-batadv_kobj_to_vlan(struct batadv_priv *bat_priv, struct kobject *obj)
-{
-	struct batadv_softif_vlan *vlan_tmp, *vlan = NULL;
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(vlan_tmp, &bat_priv->softif_vlan_list, list) {
-		if (vlan_tmp->kobj != obj)
-			continue;
-
-		if (!kref_get_unless_zero(&vlan_tmp->refcount))
-			continue;
-
-		vlan = vlan_tmp;
-		break;
-	}
-	rcu_read_unlock();
-
-	return vlan;
-}
-
-/* Use this, if you have customized show and store functions for vlan attrs */
-#define BATADV_ATTR_VLAN(_name, _mode, _show, _store)	\
-struct batadv_attribute batadv_attr_vlan_##_name = {	\
-	.attr = {.name = __stringify(_name),		\
-		 .mode = _mode },			\
-	.show   = _show,				\
-	.store  = _store,				\
-}
-
-/* Use this, if you have customized show and store functions */
-#define BATADV_ATTR(_name, _mode, _show, _store)	\
-struct batadv_attribute batadv_attr_##_name = {		\
-	.attr = {.name = __stringify(_name),		\
-		 .mode = _mode },			\
-	.show   = _show,				\
-	.store  = _store,				\
-}
-
-#define BATADV_ATTR_SIF_STORE_BOOL(_name, _post_func)			\
-ssize_t batadv_store_##_name(struct kobject *kobj,			\
-			     struct attribute *attr, char *buff,	\
-			     size_t count)				\
-{									\
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);	\
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);		\
-	ssize_t length;							\
-									\
-	batadv_sysfs_deprecated(attr);					\
-	length = __batadv_store_bool_attr(buff, count, _post_func, attr,\
-					  &bat_priv->_name, net_dev);	\
-									\
-	batadv_netlink_notify_mesh(bat_priv);				\
-									\
-	return length;							\
-}
-
-#define BATADV_ATTR_SIF_SHOW_BOOL(_name)				\
-ssize_t batadv_show_##_name(struct kobject *kobj,			\
-			    struct attribute *attr, char *buff)		\
-{									\
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);	\
-									\
-	batadv_sysfs_deprecated(attr);					\
-	return sprintf(buff, "%s\n",					\
-		       atomic_read(&bat_priv->_name) == 0 ?		\
-		       "disabled" : "enabled");				\
-}									\
-
-/* Use this, if you are going to turn a [name] in the soft-interface
- * (bat_priv) on or off
- */
-#define BATADV_ATTR_SIF_BOOL(_name, _mode, _post_func)			\
-	static BATADV_ATTR_SIF_STORE_BOOL(_name, _post_func)		\
-	static BATADV_ATTR_SIF_SHOW_BOOL(_name)				\
-	static BATADV_ATTR(_name, _mode, batadv_show_##_name,		\
-			   batadv_store_##_name)
-
-#define BATADV_ATTR_SIF_STORE_UINT(_name, _var, _min, _max, _post_func)	\
-ssize_t batadv_store_##_name(struct kobject *kobj,			\
-			     struct attribute *attr, char *buff,	\
-			     size_t count)				\
-{									\
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);	\
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);		\
-	ssize_t length;							\
-									\
-	batadv_sysfs_deprecated(attr);					\
-	length = __batadv_store_uint_attr(buff, count, _min, _max,	\
-					  _post_func, attr,		\
-					  &bat_priv->_var, net_dev,	\
-					  NULL);			\
-									\
-	batadv_netlink_notify_mesh(bat_priv);				\
-									\
-	return length;							\
-}
-
-#define BATADV_ATTR_SIF_SHOW_UINT(_name, _var)				\
-ssize_t batadv_show_##_name(struct kobject *kobj,			\
-			    struct attribute *attr, char *buff)		\
-{									\
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);	\
-									\
-	batadv_sysfs_deprecated(attr);					\
-	return sprintf(buff, "%i\n", atomic_read(&bat_priv->_var));	\
-}									\
-
-/* Use this, if you are going to set [name] in the soft-interface
- * (bat_priv) to an unsigned integer value
- */
-#define BATADV_ATTR_SIF_UINT(_name, _var, _mode, _min, _max, _post_func)\
-	static BATADV_ATTR_SIF_STORE_UINT(_name, _var, _min, _max, _post_func)\
-	static BATADV_ATTR_SIF_SHOW_UINT(_name, _var)			\
-	static BATADV_ATTR(_name, _mode, batadv_show_##_name,		\
-			   batadv_store_##_name)
-
-#define BATADV_ATTR_VLAN_STORE_BOOL(_name, _post_func)			\
-ssize_t batadv_store_vlan_##_name(struct kobject *kobj,			\
-				  struct attribute *attr, char *buff,	\
-				  size_t count)				\
-{									\
-	struct batadv_priv *bat_priv = batadv_vlan_kobj_to_batpriv(kobj);\
-	struct batadv_softif_vlan *vlan = batadv_kobj_to_vlan(bat_priv,	\
-							      kobj);	\
-	size_t res = __batadv_store_bool_attr(buff, count, _post_func,	\
-					      attr, &vlan->_name,	\
-					      bat_priv->soft_iface);	\
-									\
-	batadv_sysfs_deprecated(attr);					\
-	if (vlan->vid)							\
-		batadv_netlink_notify_vlan(bat_priv, vlan);		\
-	else								\
-		batadv_netlink_notify_mesh(bat_priv);			\
-									\
-	batadv_softif_vlan_put(vlan);					\
-	return res;							\
-}
-
-#define BATADV_ATTR_VLAN_SHOW_BOOL(_name)				\
-ssize_t batadv_show_vlan_##_name(struct kobject *kobj,			\
-				 struct attribute *attr, char *buff)	\
-{									\
-	struct batadv_priv *bat_priv = batadv_vlan_kobj_to_batpriv(kobj);\
-	struct batadv_softif_vlan *vlan = batadv_kobj_to_vlan(bat_priv,	\
-							      kobj);	\
-	size_t res = sprintf(buff, "%s\n",				\
-			     atomic_read(&vlan->_name) == 0 ?		\
-			     "disabled" : "enabled");			\
-									\
-	batadv_sysfs_deprecated(attr);					\
-	batadv_softif_vlan_put(vlan);					\
-	return res;							\
-}
-
-/* Use this, if you are going to turn a [name] in the vlan struct on or off */
-#define BATADV_ATTR_VLAN_BOOL(_name, _mode, _post_func)			\
-	static BATADV_ATTR_VLAN_STORE_BOOL(_name, _post_func)		\
-	static BATADV_ATTR_VLAN_SHOW_BOOL(_name)			\
-	static BATADV_ATTR_VLAN(_name, _mode, batadv_show_vlan_##_name,	\
-				batadv_store_vlan_##_name)
-
-#define BATADV_ATTR_HIF_STORE_UINT(_name, _var, _min, _max, _post_func)	\
-ssize_t batadv_store_##_name(struct kobject *kobj,			\
-			     struct attribute *attr, char *buff,	\
-			     size_t count)				\
-{									\
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);	\
-	struct batadv_hard_iface *hard_iface;				\
-	struct batadv_priv *bat_priv;					\
-	ssize_t length;							\
-									\
-	batadv_sysfs_deprecated(attr);					\
-	hard_iface = batadv_hardif_get_by_netdev(net_dev);		\
-	if (!hard_iface)						\
-		return 0;						\
-									\
-	length = __batadv_store_uint_attr(buff, count, _min, _max,	\
-					  _post_func, attr,		\
-					  &hard_iface->_var,		\
-					  hard_iface->soft_iface,	\
-					  net_dev);			\
-									\
-	if (hard_iface->soft_iface) {					\
-		bat_priv = netdev_priv(hard_iface->soft_iface);		\
-		batadv_netlink_notify_hardif(bat_priv, hard_iface);	\
-	}								\
-									\
-	batadv_hardif_put(hard_iface);				\
-	return length;							\
-}
-
-#define BATADV_ATTR_HIF_SHOW_UINT(_name, _var)				\
-ssize_t batadv_show_##_name(struct kobject *kobj,			\
-			    struct attribute *attr, char *buff)		\
-{									\
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);	\
-	struct batadv_hard_iface *hard_iface;				\
-	ssize_t length;							\
-									\
-	batadv_sysfs_deprecated(attr);					\
-	hard_iface = batadv_hardif_get_by_netdev(net_dev);		\
-	if (!hard_iface)						\
-		return 0;						\
-									\
-	length = sprintf(buff, "%i\n", atomic_read(&hard_iface->_var));	\
-									\
-	batadv_hardif_put(hard_iface);				\
-	return length;							\
-}
-
-/* Use this, if you are going to set [name] in hard_iface to an
- * unsigned integer value
- */
-#define BATADV_ATTR_HIF_UINT(_name, _var, _mode, _min, _max, _post_func)\
-	static BATADV_ATTR_HIF_STORE_UINT(_name, _var, _min,		\
-					  _max, _post_func)		\
-	static BATADV_ATTR_HIF_SHOW_UINT(_name, _var)			\
-	static BATADV_ATTR(_name, _mode, batadv_show_##_name,		\
-			   batadv_store_##_name)
-
-static int batadv_store_bool_attr(char *buff, size_t count,
-				  struct net_device *net_dev,
-				  const char *attr_name, atomic_t *attr,
-				  bool *changed)
-{
-	int enabled = -1;
-
-	*changed = false;
-
-	if (buff[count - 1] == '\n')
-		buff[count - 1] = '\0';
-
-	if ((strncmp(buff, "1", 2) == 0) ||
-	    (strncmp(buff, "enable", 7) == 0) ||
-	    (strncmp(buff, "enabled", 8) == 0))
-		enabled = 1;
-
-	if ((strncmp(buff, "0", 2) == 0) ||
-	    (strncmp(buff, "disable", 8) == 0) ||
-	    (strncmp(buff, "disabled", 9) == 0))
-		enabled = 0;
-
-	if (enabled < 0) {
-		batadv_info(net_dev, "%s: Invalid parameter received: %s\n",
-			    attr_name, buff);
-		return -EINVAL;
-	}
-
-	if (atomic_read(attr) == enabled)
-		return count;
-
-	batadv_info(net_dev, "%s: Changing from: %s to: %s\n", attr_name,
-		    atomic_read(attr) == 1 ? "enabled" : "disabled",
-		    enabled == 1 ? "enabled" : "disabled");
-
-	*changed = true;
-
-	atomic_set(attr, (unsigned int)enabled);
-	return count;
-}
-
-static inline ssize_t
-__batadv_store_bool_attr(char *buff, size_t count,
-			 void (*post_func)(struct net_device *),
-			 struct attribute *attr,
-			 atomic_t *attr_store, struct net_device *net_dev)
-{
-	bool changed;
-	int ret;
-
-	ret = batadv_store_bool_attr(buff, count, net_dev, attr->name,
-				     attr_store, &changed);
-	if (post_func && changed)
-		post_func(net_dev);
-
-	return ret;
-}
-
-static int batadv_store_uint_attr(const char *buff, size_t count,
-				  struct net_device *net_dev,
-				  struct net_device *slave_dev,
-				  const char *attr_name,
-				  unsigned int min, unsigned int max,
-				  atomic_t *attr)
-{
-	char ifname[IFNAMSIZ + 3] = "";
-	unsigned long uint_val;
-	int ret;
-
-	ret = kstrtoul(buff, 10, &uint_val);
-	if (ret) {
-		batadv_info(net_dev, "%s: Invalid parameter received: %s\n",
-			    attr_name, buff);
-		return -EINVAL;
-	}
-
-	if (uint_val < min) {
-		batadv_info(net_dev, "%s: Value is too small: %lu min: %u\n",
-			    attr_name, uint_val, min);
-		return -EINVAL;
-	}
-
-	if (uint_val > max) {
-		batadv_info(net_dev, "%s: Value is too big: %lu max: %u\n",
-			    attr_name, uint_val, max);
-		return -EINVAL;
-	}
-
-	if (atomic_read(attr) == uint_val)
-		return count;
-
-	if (slave_dev)
-		snprintf(ifname, sizeof(ifname), "%s: ", slave_dev->name);
-
-	batadv_info(net_dev, "%s: %sChanging from: %i to: %lu\n",
-		    attr_name, ifname, atomic_read(attr), uint_val);
-
-	atomic_set(attr, uint_val);
-	return count;
-}
-
-static ssize_t __batadv_store_uint_attr(const char *buff, size_t count,
-					int min, int max,
-					void (*post_func)(struct net_device *),
-					const struct attribute *attr,
-					atomic_t *attr_store,
-					struct net_device *net_dev,
-					struct net_device *slave_dev)
-{
-	int ret;
-
-	ret = batadv_store_uint_attr(buff, count, net_dev, slave_dev,
-				     attr->name, min, max, attr_store);
-	if (post_func && ret)
-		post_func(net_dev);
-
-	return ret;
-}
-
-static ssize_t batadv_show_bat_algo(struct kobject *kobj,
-				    struct attribute *attr, char *buff)
-{
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
-
-	batadv_sysfs_deprecated(attr);
-	return sprintf(buff, "%s\n", bat_priv->algo_ops->name);
-}
-
-static void batadv_post_gw_reselect(struct net_device *net_dev)
-{
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-
-	batadv_gw_reselect(bat_priv);
-}
-
-static ssize_t batadv_show_gw_mode(struct kobject *kobj, struct attribute *attr,
-				   char *buff)
-{
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
-	int bytes_written;
-
-	batadv_sysfs_deprecated(attr);
-
-	/* GW mode is not available if the routing algorithm in use does not
-	 * implement the GW API
-	 */
-	if (!bat_priv->algo_ops->gw.get_best_gw_node ||
-	    !bat_priv->algo_ops->gw.is_eligible)
-		return -ENOENT;
-
-	switch (atomic_read(&bat_priv->gw.mode)) {
-	case BATADV_GW_MODE_CLIENT:
-		bytes_written = sprintf(buff, "%s\n",
-					BATADV_GW_MODE_CLIENT_NAME);
-		break;
-	case BATADV_GW_MODE_SERVER:
-		bytes_written = sprintf(buff, "%s\n",
-					BATADV_GW_MODE_SERVER_NAME);
-		break;
-	default:
-		bytes_written = sprintf(buff, "%s\n",
-					BATADV_GW_MODE_OFF_NAME);
-		break;
-	}
-
-	return bytes_written;
-}
-
-static ssize_t batadv_store_gw_mode(struct kobject *kobj,
-				    struct attribute *attr, char *buff,
-				    size_t count)
-{
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	char *curr_gw_mode_str;
-	int gw_mode_tmp = -1;
-
-	batadv_sysfs_deprecated(attr);
-
-	/* toggling GW mode is allowed only if the routing algorithm in use
-	 * provides the GW API
-	 */
-	if (!bat_priv->algo_ops->gw.get_best_gw_node ||
-	    !bat_priv->algo_ops->gw.is_eligible)
-		return -EINVAL;
-
-	if (buff[count - 1] == '\n')
-		buff[count - 1] = '\0';
-
-	if (strncmp(buff, BATADV_GW_MODE_OFF_NAME,
-		    strlen(BATADV_GW_MODE_OFF_NAME)) == 0)
-		gw_mode_tmp = BATADV_GW_MODE_OFF;
-
-	if (strncmp(buff, BATADV_GW_MODE_CLIENT_NAME,
-		    strlen(BATADV_GW_MODE_CLIENT_NAME)) == 0)
-		gw_mode_tmp = BATADV_GW_MODE_CLIENT;
-
-	if (strncmp(buff, BATADV_GW_MODE_SERVER_NAME,
-		    strlen(BATADV_GW_MODE_SERVER_NAME)) == 0)
-		gw_mode_tmp = BATADV_GW_MODE_SERVER;
-
-	if (gw_mode_tmp < 0) {
-		batadv_info(net_dev,
-			    "Invalid parameter for 'gw mode' setting received: %s\n",
-			    buff);
-		return -EINVAL;
-	}
-
-	if (atomic_read(&bat_priv->gw.mode) == gw_mode_tmp)
-		return count;
-
-	switch (atomic_read(&bat_priv->gw.mode)) {
-	case BATADV_GW_MODE_CLIENT:
-		curr_gw_mode_str = BATADV_GW_MODE_CLIENT_NAME;
-		break;
-	case BATADV_GW_MODE_SERVER:
-		curr_gw_mode_str = BATADV_GW_MODE_SERVER_NAME;
-		break;
-	default:
-		curr_gw_mode_str = BATADV_GW_MODE_OFF_NAME;
-		break;
-	}
-
-	batadv_info(net_dev, "Changing gw mode from: %s to: %s\n",
-		    curr_gw_mode_str, buff);
-
-	/* Invoking batadv_gw_reselect() is not enough to really de-select the
-	 * current GW. It will only instruct the gateway client code to perform
-	 * a re-election the next time that this is needed.
-	 *
-	 * When gw client mode is being switched off the current GW must be
-	 * de-selected explicitly otherwise no GW_ADD uevent is thrown on
-	 * client mode re-activation. This is operation is performed in
-	 * batadv_gw_check_client_stop().
-	 */
-	batadv_gw_reselect(bat_priv);
-	/* always call batadv_gw_check_client_stop() before changing the gateway
-	 * state
-	 */
-	batadv_gw_check_client_stop(bat_priv);
-	atomic_set(&bat_priv->gw.mode, (unsigned int)gw_mode_tmp);
-	batadv_gw_tvlv_container_update(bat_priv);
-
-	batadv_netlink_notify_mesh(bat_priv);
-
-	return count;
-}
-
-static ssize_t batadv_show_gw_sel_class(struct kobject *kobj,
-					struct attribute *attr, char *buff)
-{
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
-
-	batadv_sysfs_deprecated(attr);
-
-	/* GW selection class is not available if the routing algorithm in use
-	 * does not implement the GW API
-	 */
-	if (!bat_priv->algo_ops->gw.get_best_gw_node ||
-	    !bat_priv->algo_ops->gw.is_eligible)
-		return -ENOENT;
-
-	if (bat_priv->algo_ops->gw.show_sel_class)
-		return bat_priv->algo_ops->gw.show_sel_class(bat_priv, buff);
-
-	return sprintf(buff, "%i\n", atomic_read(&bat_priv->gw.sel_class));
-}
-
-static ssize_t batadv_store_gw_sel_class(struct kobject *kobj,
-					 struct attribute *attr, char *buff,
-					 size_t count)
-{
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
-	ssize_t length;
-
-	batadv_sysfs_deprecated(attr);
-
-	/* setting the GW selection class is allowed only if the routing
-	 * algorithm in use implements the GW API
-	 */
-	if (!bat_priv->algo_ops->gw.get_best_gw_node ||
-	    !bat_priv->algo_ops->gw.is_eligible)
-		return -EINVAL;
-
-	if (buff[count - 1] == '\n')
-		buff[count - 1] = '\0';
-
-	if (bat_priv->algo_ops->gw.store_sel_class)
-		return bat_priv->algo_ops->gw.store_sel_class(bat_priv, buff,
-							      count);
-
-	length = __batadv_store_uint_attr(buff, count, 1, BATADV_TQ_MAX_VALUE,
-					  batadv_post_gw_reselect, attr,
-					  &bat_priv->gw.sel_class,
-					  bat_priv->soft_iface, NULL);
-
-	batadv_netlink_notify_mesh(bat_priv);
-
-	return length;
-}
-
-static ssize_t batadv_show_gw_bwidth(struct kobject *kobj,
-				     struct attribute *attr, char *buff)
-{
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
-	u32 down, up;
-
-	batadv_sysfs_deprecated(attr);
-
-	down = atomic_read(&bat_priv->gw.bandwidth_down);
-	up = atomic_read(&bat_priv->gw.bandwidth_up);
-
-	return sprintf(buff, "%u.%u/%u.%u MBit\n", down / 10,
-		       down % 10, up / 10, up % 10);
-}
-
-static ssize_t batadv_store_gw_bwidth(struct kobject *kobj,
-				      struct attribute *attr, char *buff,
-				      size_t count)
-{
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
-	ssize_t length;
-
-	batadv_sysfs_deprecated(attr);
-
-	if (buff[count - 1] == '\n')
-		buff[count - 1] = '\0';
-
-	length = batadv_gw_bandwidth_set(net_dev, buff, count);
-
-	batadv_netlink_notify_mesh(bat_priv);
-
-	return length;
-}
-
-/**
- * batadv_show_isolation_mark() - print the current isolation mark/mask
- * @kobj: kobject representing the private mesh sysfs directory
- * @attr: the batman-adv attribute the user is interacting with
- * @buff: the buffer that will contain the data to send back to the user
- *
- * Return: the number of bytes written into 'buff' on success or a negative
- * error code in case of failure
- */
-static ssize_t batadv_show_isolation_mark(struct kobject *kobj,
-					  struct attribute *attr, char *buff)
-{
-	struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj);
-
-	batadv_sysfs_deprecated(attr);
-	return sprintf(buff, "%#.8x/%#.8x\n", bat_priv->isolation_mark,
-		       bat_priv->isolation_mark_mask);
-}
-
-/**
- * batadv_store_isolation_mark() - parse and store the isolation mark/mask
- *  entered by the user
- * @kobj: kobject representing the private mesh sysfs directory
- * @attr: the batman-adv attribute the user is interacting with
- * @buff: the buffer containing the user data
- * @count: number of bytes in the buffer
- *
- * Return: 'count' on success or a negative error code in case of failure
- */
-static ssize_t batadv_store_isolation_mark(struct kobject *kobj,
-					   struct attribute *attr, char *buff,
-					   size_t count)
-{
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	u32 mark, mask;
-	char *mask_ptr;
-
-	batadv_sysfs_deprecated(attr);
-
-	/* parse the mask if it has been specified, otherwise assume the mask is
-	 * the biggest possible
-	 */
-	mask = 0xFFFFFFFF;
-	mask_ptr = strchr(buff, '/');
-	if (mask_ptr) {
-		*mask_ptr = '\0';
-		mask_ptr++;
-
-		/* the mask must be entered in hex base as it is going to be a
-		 * bitmask and not a prefix length
-		 */
-		if (kstrtou32(mask_ptr, 16, &mask) < 0)
-			return -EINVAL;
-	}
-
-	/* the mark can be entered in any base */
-	if (kstrtou32(buff, 0, &mark) < 0)
-		return -EINVAL;
-
-	bat_priv->isolation_mark_mask = mask;
-	/* erase bits not covered by the mask */
-	bat_priv->isolation_mark = mark & bat_priv->isolation_mark_mask;
-
-	batadv_info(net_dev,
-		    "New skb mark for extended isolation: %#.8x/%#.8x\n",
-		    bat_priv->isolation_mark, bat_priv->isolation_mark_mask);
-
-	batadv_netlink_notify_mesh(bat_priv);
-
-	return count;
-}
-
-BATADV_ATTR_SIF_BOOL(aggregated_ogms, 0644, NULL);
-BATADV_ATTR_SIF_BOOL(bonding, 0644, NULL);
-#ifdef CONFIG_BATMAN_ADV_BLA
-BATADV_ATTR_SIF_BOOL(bridge_loop_avoidance, 0644, batadv_bla_status_update);
-#endif
-#ifdef CONFIG_BATMAN_ADV_DAT
-BATADV_ATTR_SIF_BOOL(distributed_arp_table, 0644, batadv_dat_status_update);
-#endif
-BATADV_ATTR_SIF_BOOL(fragmentation, 0644, batadv_update_min_mtu);
-static BATADV_ATTR(routing_algo, 0444, batadv_show_bat_algo, NULL);
-static BATADV_ATTR(gw_mode, 0644, batadv_show_gw_mode, batadv_store_gw_mode);
-BATADV_ATTR_SIF_UINT(orig_interval, orig_interval, 0644, 2 * BATADV_JITTER,
-		     INT_MAX, NULL);
-BATADV_ATTR_SIF_UINT(hop_penalty, hop_penalty, 0644, 0, BATADV_TQ_MAX_VALUE,
-		     NULL);
-static BATADV_ATTR(gw_sel_class, 0644, batadv_show_gw_sel_class,
-		   batadv_store_gw_sel_class);
-static BATADV_ATTR(gw_bandwidth, 0644, batadv_show_gw_bwidth,
-		   batadv_store_gw_bwidth);
-#ifdef CONFIG_BATMAN_ADV_MCAST
-BATADV_ATTR_SIF_BOOL(multicast_mode, 0644, NULL);
-#endif
-#ifdef CONFIG_BATMAN_ADV_DEBUG
-BATADV_ATTR_SIF_UINT(log_level, log_level, 0644, 0, BATADV_DBG_ALL, NULL);
-#endif
-#ifdef CONFIG_BATMAN_ADV_NC
-BATADV_ATTR_SIF_BOOL(network_coding, 0644, batadv_nc_status_update);
-#endif
-static BATADV_ATTR(isolation_mark, 0644, batadv_show_isolation_mark,
-		   batadv_store_isolation_mark);
-
-static struct batadv_attribute *batadv_mesh_attrs[] = {
-	&batadv_attr_aggregated_ogms,
-	&batadv_attr_bonding,
-#ifdef CONFIG_BATMAN_ADV_BLA
-	&batadv_attr_bridge_loop_avoidance,
-#endif
-#ifdef CONFIG_BATMAN_ADV_DAT
-	&batadv_attr_distributed_arp_table,
-#endif
-#ifdef CONFIG_BATMAN_ADV_MCAST
-	&batadv_attr_multicast_mode,
-#endif
-	&batadv_attr_fragmentation,
-	&batadv_attr_routing_algo,
-	&batadv_attr_gw_mode,
-	&batadv_attr_orig_interval,
-	&batadv_attr_hop_penalty,
-	&batadv_attr_gw_sel_class,
-	&batadv_attr_gw_bandwidth,
-#ifdef CONFIG_BATMAN_ADV_DEBUG
-	&batadv_attr_log_level,
-#endif
-#ifdef CONFIG_BATMAN_ADV_NC
-	&batadv_attr_network_coding,
-#endif
-	&batadv_attr_isolation_mark,
-	NULL,
-};
-
-BATADV_ATTR_VLAN_BOOL(ap_isolation, 0644, NULL);
-
-/* array of vlan specific sysfs attributes */
-static struct batadv_attribute *batadv_vlan_attrs[] = {
-	&batadv_attr_vlan_ap_isolation,
-	NULL,
-};
-
-/**
- * batadv_sysfs_add_meshif() - Add soft interface specific sysfs entries
- * @dev: netdev struct of the soft interface
- *
- * Return: 0 on success or negative error number in case of failure
- */
-int batadv_sysfs_add_meshif(struct net_device *dev)
-{
-	struct kobject *batif_kobject = &dev->dev.kobj;
-	struct batadv_priv *bat_priv = netdev_priv(dev);
-	struct batadv_attribute **bat_attr;
-	int err;
-
-	bat_priv->mesh_obj = kobject_create_and_add(BATADV_SYSFS_IF_MESH_SUBDIR,
-						    batif_kobject);
-	if (!bat_priv->mesh_obj) {
-		batadv_err(dev, "Can't add sysfs directory: %s/%s\n", dev->name,
-			   BATADV_SYSFS_IF_MESH_SUBDIR);
-		goto out;
-	}
-
-	for (bat_attr = batadv_mesh_attrs; *bat_attr; ++bat_attr) {
-		err = sysfs_create_file(bat_priv->mesh_obj,
-					&((*bat_attr)->attr));
-		if (err) {
-			batadv_err(dev, "Can't add sysfs file: %s/%s/%s\n",
-				   dev->name, BATADV_SYSFS_IF_MESH_SUBDIR,
-				   ((*bat_attr)->attr).name);
-			goto rem_attr;
-		}
-	}
-
-	return 0;
-
-rem_attr:
-	for (bat_attr = batadv_mesh_attrs; *bat_attr; ++bat_attr)
-		sysfs_remove_file(bat_priv->mesh_obj, &((*bat_attr)->attr));
-
-	kobject_uevent(bat_priv->mesh_obj, KOBJ_REMOVE);
-	kobject_del(bat_priv->mesh_obj);
-	kobject_put(bat_priv->mesh_obj);
-	bat_priv->mesh_obj = NULL;
-out:
-	return -ENOMEM;
-}
-
-/**
- * batadv_sysfs_del_meshif() - Remove soft interface specific sysfs entries
- * @dev: netdev struct of the soft interface
- */
-void batadv_sysfs_del_meshif(struct net_device *dev)
-{
-	struct batadv_priv *bat_priv = netdev_priv(dev);
-	struct batadv_attribute **bat_attr;
-
-	for (bat_attr = batadv_mesh_attrs; *bat_attr; ++bat_attr)
-		sysfs_remove_file(bat_priv->mesh_obj, &((*bat_attr)->attr));
-
-	kobject_uevent(bat_priv->mesh_obj, KOBJ_REMOVE);
-	kobject_del(bat_priv->mesh_obj);
-	kobject_put(bat_priv->mesh_obj);
-	bat_priv->mesh_obj = NULL;
-}
-
-/**
- * batadv_sysfs_add_vlan() - add all the needed sysfs objects for the new vlan
- * @dev: netdev of the mesh interface
- * @vlan: private data of the newly added VLAN interface
- *
- * Return: 0 on success and -ENOMEM if any of the structure allocations fails.
- */
-int batadv_sysfs_add_vlan(struct net_device *dev,
-			  struct batadv_softif_vlan *vlan)
-{
-	char vlan_subdir[sizeof(BATADV_SYSFS_VLAN_SUBDIR_PREFIX) + 5];
-	struct batadv_priv *bat_priv = netdev_priv(dev);
-	struct batadv_attribute **bat_attr;
-	int err;
-
-	if (vlan->vid & BATADV_VLAN_HAS_TAG) {
-		sprintf(vlan_subdir, BATADV_SYSFS_VLAN_SUBDIR_PREFIX "%hu",
-			vlan->vid & VLAN_VID_MASK);
-
-		vlan->kobj = kobject_create_and_add(vlan_subdir,
-						    bat_priv->mesh_obj);
-		if (!vlan->kobj) {
-			batadv_err(dev, "Can't add sysfs directory: %s/%s\n",
-				   dev->name, vlan_subdir);
-			goto out;
-		}
-	} else {
-		/* the untagged LAN uses the root folder to store its "VLAN
-		 * specific attributes"
-		 */
-		vlan->kobj = bat_priv->mesh_obj;
-		kobject_get(bat_priv->mesh_obj);
-	}
-
-	for (bat_attr = batadv_vlan_attrs; *bat_attr; ++bat_attr) {
-		err = sysfs_create_file(vlan->kobj,
-					&((*bat_attr)->attr));
-		if (err) {
-			batadv_err(dev, "Can't add sysfs file: %s/%s/%s\n",
-				   dev->name, vlan_subdir,
-				   ((*bat_attr)->attr).name);
-			goto rem_attr;
-		}
-	}
-
-	return 0;
-
-rem_attr:
-	for (bat_attr = batadv_vlan_attrs; *bat_attr; ++bat_attr)
-		sysfs_remove_file(vlan->kobj, &((*bat_attr)->attr));
-
-	if (vlan->kobj != bat_priv->mesh_obj) {
-		kobject_uevent(vlan->kobj, KOBJ_REMOVE);
-		kobject_del(vlan->kobj);
-	}
-	kobject_put(vlan->kobj);
-	vlan->kobj = NULL;
-out:
-	return -ENOMEM;
-}
-
-/**
- * batadv_sysfs_del_vlan() - remove all the sysfs objects for a given VLAN
- * @bat_priv: the bat priv with all the soft interface information
- * @vlan: the private data of the VLAN to destroy
- */
-void batadv_sysfs_del_vlan(struct batadv_priv *bat_priv,
-			   struct batadv_softif_vlan *vlan)
-{
-	struct batadv_attribute **bat_attr;
-
-	for (bat_attr = batadv_vlan_attrs; *bat_attr; ++bat_attr)
-		sysfs_remove_file(vlan->kobj, &((*bat_attr)->attr));
-
-	if (vlan->kobj != bat_priv->mesh_obj) {
-		kobject_uevent(vlan->kobj, KOBJ_REMOVE);
-		kobject_del(vlan->kobj);
-	}
-	kobject_put(vlan->kobj);
-	vlan->kobj = NULL;
-}
-
-static ssize_t batadv_show_mesh_iface(struct kobject *kobj,
-				      struct attribute *attr, char *buff)
-{
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
-	struct batadv_hard_iface *hard_iface;
-	ssize_t length;
-	const char *ifname;
-
-	batadv_sysfs_deprecated(attr);
-
-	hard_iface = batadv_hardif_get_by_netdev(net_dev);
-	if (!hard_iface)
-		return 0;
-
-	if (hard_iface->if_status == BATADV_IF_NOT_IN_USE)
-		ifname =  "none";
-	else
-		ifname = hard_iface->soft_iface->name;
-
-	length = sprintf(buff, "%s\n", ifname);
-
-	batadv_hardif_put(hard_iface);
-
-	return length;
-}
-
-/**
- * batadv_store_mesh_iface_finish() - store new hardif mesh_iface state
- * @net_dev: netdevice to add/remove to/from batman-adv soft-interface
- * @ifname: name of soft-interface to modify
- *
- * Changes the parts of the hard+soft interface which can not be modified under
- * sysfs lock (to prevent deadlock situations).
- *
- * Return: 0 on success, 0 < on failure
- */
-static int batadv_store_mesh_iface_finish(struct net_device *net_dev,
-					  char ifname[IFNAMSIZ])
-{
-	struct net *net = dev_net(net_dev);
-	struct batadv_hard_iface *hard_iface;
-	int status_tmp;
-	int ret = 0;
-
-	ASSERT_RTNL();
-
-	hard_iface = batadv_hardif_get_by_netdev(net_dev);
-	if (!hard_iface)
-		return 0;
-
-	if (strncmp(ifname, "none", 4) == 0)
-		status_tmp = BATADV_IF_NOT_IN_USE;
-	else
-		status_tmp = BATADV_IF_I_WANT_YOU;
-
-	if (hard_iface->if_status == status_tmp)
-		goto out;
-
-	if (hard_iface->soft_iface &&
-	    strncmp(hard_iface->soft_iface->name, ifname, IFNAMSIZ) == 0)
-		goto out;
-
-	if (status_tmp == BATADV_IF_NOT_IN_USE) {
-		batadv_hardif_disable_interface(hard_iface,
-						BATADV_IF_CLEANUP_AUTO);
-		goto out;
-	}
-
-	/* if the interface already is in use */
-	if (hard_iface->if_status != BATADV_IF_NOT_IN_USE)
-		batadv_hardif_disable_interface(hard_iface,
-						BATADV_IF_CLEANUP_AUTO);
-
-	ret = batadv_hardif_enable_interface(hard_iface, net, ifname);
-out:
-	batadv_hardif_put(hard_iface);
-	return ret;
-}
-
-/**
- * batadv_store_mesh_iface_work() - store new hardif mesh_iface state
- * @work: work queue item
- *
- * Changes the parts of the hard+soft interface which can not be modified under
- * sysfs lock (to prevent deadlock situations).
- */
-static void batadv_store_mesh_iface_work(struct work_struct *work)
-{
-	struct batadv_store_mesh_work *store_work;
-	int ret;
-
-	store_work = container_of(work, struct batadv_store_mesh_work, work);
-
-	rtnl_lock();
-	ret = batadv_store_mesh_iface_finish(store_work->net_dev,
-					     store_work->soft_iface_name);
-	rtnl_unlock();
-
-	if (ret < 0)
-		pr_err("Failed to store new mesh_iface state %s for %s: %d\n",
-		       store_work->soft_iface_name, store_work->net_dev->name,
-		       ret);
-
-	dev_put(store_work->net_dev);
-	kfree(store_work);
-}
-
-static ssize_t batadv_store_mesh_iface(struct kobject *kobj,
-				       struct attribute *attr, char *buff,
-				       size_t count)
-{
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
-	struct batadv_store_mesh_work *store_work;
-
-	batadv_sysfs_deprecated(attr);
-
-	if (buff[count - 1] == '\n')
-		buff[count - 1] = '\0';
-
-	if (strlen(buff) >= IFNAMSIZ) {
-		pr_err("Invalid parameter for 'mesh_iface' setting received: interface name too long '%s'\n",
-		       buff);
-		return -EINVAL;
-	}
-
-	store_work = kmalloc(sizeof(*store_work), GFP_KERNEL);
-	if (!store_work)
-		return -ENOMEM;
-
-	dev_hold(net_dev);
-	INIT_WORK(&store_work->work, batadv_store_mesh_iface_work);
-	store_work->net_dev = net_dev;
-	strscpy(store_work->soft_iface_name, buff,
-		sizeof(store_work->soft_iface_name));
-
-	queue_work(batadv_event_workqueue, &store_work->work);
-
-	return count;
-}
-
-static ssize_t batadv_show_iface_status(struct kobject *kobj,
-					struct attribute *attr, char *buff)
-{
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
-	struct batadv_hard_iface *hard_iface;
-	ssize_t length;
-
-	batadv_sysfs_deprecated(attr);
-
-	hard_iface = batadv_hardif_get_by_netdev(net_dev);
-	if (!hard_iface)
-		return 0;
-
-	switch (hard_iface->if_status) {
-	case BATADV_IF_TO_BE_REMOVED:
-		length = sprintf(buff, "disabling\n");
-		break;
-	case BATADV_IF_INACTIVE:
-		length = sprintf(buff, "inactive\n");
-		break;
-	case BATADV_IF_ACTIVE:
-		length = sprintf(buff, "active\n");
-		break;
-	case BATADV_IF_TO_BE_ACTIVATED:
-		length = sprintf(buff, "enabling\n");
-		break;
-	case BATADV_IF_NOT_IN_USE:
-	default:
-		length = sprintf(buff, "not in use\n");
-		break;
-	}
-
-	batadv_hardif_put(hard_iface);
-
-	return length;
-}
-
-#ifdef CONFIG_BATMAN_ADV_BATMAN_V
-
-/**
- * batadv_store_throughput_override() - parse and store throughput override
- *  entered by the user
- * @kobj: kobject representing the private mesh sysfs directory
- * @attr: the batman-adv attribute the user is interacting with
- * @buff: the buffer containing the user data
- * @count: number of bytes in the buffer
- *
- * Return: 'count' on success or a negative error code in case of failure
- */
-static ssize_t batadv_store_throughput_override(struct kobject *kobj,
-						struct attribute *attr,
-						char *buff, size_t count)
-{
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
-	struct batadv_hard_iface *hard_iface;
-	struct batadv_priv *bat_priv;
-	u32 tp_override;
-	u32 old_tp_override;
-	bool ret;
-
-	batadv_sysfs_deprecated(attr);
-
-	hard_iface = batadv_hardif_get_by_netdev(net_dev);
-	if (!hard_iface)
-		return -EINVAL;
-
-	if (buff[count - 1] == '\n')
-		buff[count - 1] = '\0';
-
-	ret = batadv_parse_throughput(net_dev, buff, "throughput_override",
-				      &tp_override);
-	if (!ret)
-		goto out;
-
-	old_tp_override = atomic_read(&hard_iface->bat_v.throughput_override);
-	if (old_tp_override == tp_override)
-		goto out;
-
-	batadv_info(hard_iface->soft_iface,
-		    "%s: %s: Changing from: %u.%u MBit to: %u.%u MBit\n",
-		    "throughput_override", net_dev->name,
-		    old_tp_override / 10, old_tp_override % 10,
-		    tp_override / 10, tp_override % 10);
-
-	atomic_set(&hard_iface->bat_v.throughput_override, tp_override);
-
-	if (hard_iface->soft_iface) {
-		bat_priv = netdev_priv(hard_iface->soft_iface);
-		batadv_netlink_notify_hardif(bat_priv, hard_iface);
-	}
-
-out:
-	batadv_hardif_put(hard_iface);
-	return count;
-}
-
-static ssize_t batadv_show_throughput_override(struct kobject *kobj,
-					       struct attribute *attr,
-					       char *buff)
-{
-	struct net_device *net_dev = batadv_kobj_to_netdev(kobj);
-	struct batadv_hard_iface *hard_iface;
-	u32 tp_override;
-
-	batadv_sysfs_deprecated(attr);
-
-	hard_iface = batadv_hardif_get_by_netdev(net_dev);
-	if (!hard_iface)
-		return -EINVAL;
-
-	tp_override = atomic_read(&hard_iface->bat_v.throughput_override);
-
-	batadv_hardif_put(hard_iface);
-	return sprintf(buff, "%u.%u MBit\n", tp_override / 10,
-		       tp_override % 10);
-}
-
-#endif
-
-static BATADV_ATTR(mesh_iface, 0644, batadv_show_mesh_iface,
-		   batadv_store_mesh_iface);
-static BATADV_ATTR(iface_status, 0444, batadv_show_iface_status, NULL);
-#ifdef CONFIG_BATMAN_ADV_BATMAN_V
-BATADV_ATTR_HIF_UINT(elp_interval, bat_v.elp_interval, 0644,
-		     2 * BATADV_JITTER, INT_MAX, NULL);
-static BATADV_ATTR(throughput_override, 0644, batadv_show_throughput_override,
-		   batadv_store_throughput_override);
-#endif
-
-static struct batadv_attribute *batadv_batman_attrs[] = {
-	&batadv_attr_mesh_iface,
-	&batadv_attr_iface_status,
-#ifdef CONFIG_BATMAN_ADV_BATMAN_V
-	&batadv_attr_elp_interval,
-	&batadv_attr_throughput_override,
-#endif
-	NULL,
-};
-
-/**
- * batadv_sysfs_add_hardif() - Add hard interface specific sysfs entries
- * @hardif_obj: address where to store the pointer to new sysfs folder
- * @dev: netdev struct of the hard interface
- *
- * Return: 0 on success or negative error number in case of failure
- */
-int batadv_sysfs_add_hardif(struct kobject **hardif_obj, struct net_device *dev)
-{
-	struct kobject *hardif_kobject = &dev->dev.kobj;
-	struct batadv_attribute **bat_attr;
-	int err;
-
-	*hardif_obj = kobject_create_and_add(BATADV_SYSFS_IF_BAT_SUBDIR,
-					     hardif_kobject);
-
-	if (!*hardif_obj) {
-		batadv_err(dev, "Can't add sysfs directory: %s/%s\n", dev->name,
-			   BATADV_SYSFS_IF_BAT_SUBDIR);
-		goto out;
-	}
-
-	for (bat_attr = batadv_batman_attrs; *bat_attr; ++bat_attr) {
-		err = sysfs_create_file(*hardif_obj, &((*bat_attr)->attr));
-		if (err) {
-			batadv_err(dev, "Can't add sysfs file: %s/%s/%s\n",
-				   dev->name, BATADV_SYSFS_IF_BAT_SUBDIR,
-				   ((*bat_attr)->attr).name);
-			goto rem_attr;
-		}
-	}
-
-	return 0;
-
-rem_attr:
-	for (bat_attr = batadv_batman_attrs; *bat_attr; ++bat_attr)
-		sysfs_remove_file(*hardif_obj, &((*bat_attr)->attr));
-out:
-	return -ENOMEM;
-}
-
-/**
- * batadv_sysfs_del_hardif() - Remove hard interface specific sysfs entries
- * @hardif_obj: address to the pointer to which stores batman-adv sysfs folder
- *  of the hard interface
- */
-void batadv_sysfs_del_hardif(struct kobject **hardif_obj)
-{
-	kobject_uevent(*hardif_obj, KOBJ_REMOVE);
-	kobject_del(*hardif_obj);
-	kobject_put(*hardif_obj);
-	*hardif_obj = NULL;
-}
diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h
deleted file mode 100644
index d987f8b30a98..000000000000
--- a/net/batman-adv/sysfs.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2010-2020  B.A.T.M.A.N. contributors:
- *
- * Marek Lindner
- */
-
-#ifndef _NET_BATMAN_ADV_SYSFS_H_
-#define _NET_BATMAN_ADV_SYSFS_H_
-
-#include "main.h"
-
-#include <linux/kobject.h>
-#include <linux/netdevice.h>
-#include <linux/sysfs.h>
-#include <linux/types.h>
-
-#define BATADV_SYSFS_IF_MESH_SUBDIR "mesh"
-#define BATADV_SYSFS_IF_BAT_SUBDIR "batman_adv"
-/**
- * BATADV_SYSFS_VLAN_SUBDIR_PREFIX - prefix of the subfolder that will be
- *  created in the sysfs hierarchy for each VLAN interface. The subfolder will
- *  be named "BATADV_SYSFS_VLAN_SUBDIR_PREFIX%vid".
- */
-#define BATADV_SYSFS_VLAN_SUBDIR_PREFIX "vlan"
-
-/**
- * struct batadv_attribute - sysfs export helper for batman-adv attributes
- */
-struct batadv_attribute {
-	/** @attr: sysfs attribute file */
-	struct attribute attr;
-
-	/**
-	 * @show: function to export the current attribute's content to sysfs
-	 */
-	ssize_t (*show)(struct kobject *kobj, struct attribute *attr,
-			char *buf);
-
-	/**
-	 * @store: function to load new value from character buffer and save it
-	 * in batman-adv attribute
-	 */
-	ssize_t (*store)(struct kobject *kobj, struct attribute *attr,
-			 char *buf, size_t count);
-};
-
-#ifdef CONFIG_BATMAN_ADV_SYSFS
-
-int batadv_sysfs_add_meshif(struct net_device *dev);
-void batadv_sysfs_del_meshif(struct net_device *dev);
-int batadv_sysfs_add_hardif(struct kobject **hardif_obj,
-			    struct net_device *dev);
-void batadv_sysfs_del_hardif(struct kobject **hardif_obj);
-int batadv_sysfs_add_vlan(struct net_device *dev,
-			  struct batadv_softif_vlan *vlan);
-void batadv_sysfs_del_vlan(struct batadv_priv *bat_priv,
-			   struct batadv_softif_vlan *vlan);
-
-#else
-
-static inline int batadv_sysfs_add_meshif(struct net_device *dev)
-{
-	return 0;
-}
-
-static inline void batadv_sysfs_del_meshif(struct net_device *dev)
-{
-}
-
-static inline int batadv_sysfs_add_hardif(struct kobject **hardif_obj,
-					  struct net_device *dev)
-{
-	return 0;
-}
-
-static inline void batadv_sysfs_del_hardif(struct kobject **hardif_obj)
-{
-}
-
-static inline int batadv_sysfs_add_vlan(struct net_device *dev,
-					struct batadv_softif_vlan *vlan)
-{
-	return 0;
-}
-
-static inline void batadv_sysfs_del_vlan(struct batadv_priv *bat_priv,
-					 struct batadv_softif_vlan *vlan)
-{
-}
-
-#endif
-
-#endif /* _NET_BATMAN_ADV_SYSFS_H_ */
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index db7e3774825b..d4e10005df6c 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -23,6 +23,7 @@
 #include <linux/kthread.h>
 #include <linux/limits.h>
 #include <linux/list.h>
+#include <linux/minmax.h>
 #include <linux/netdevice.h>
 #include <linux/param.h>
 #include <linux/printk.h>
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 98a0aaaf0d50..cd09916f97fe 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -30,7 +30,6 @@
 #include <linux/netlink.h>
 #include <linux/rculist.h>
 #include <linux/rcupdate.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
@@ -1062,84 +1061,6 @@ container_register:
 	kfree(tt_data);
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-
-/**
- * batadv_tt_local_seq_print_text() - Print the local tt table in a seq file
- * @seq: seq file to print on
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hashtable *hash = bat_priv->tt.local_hash;
-	struct batadv_tt_common_entry *tt_common_entry;
-	struct batadv_tt_local_entry *tt_local;
-	struct batadv_hard_iface *primary_if;
-	struct hlist_head *head;
-	u32 i;
-	int last_seen_secs;
-	int last_seen_msecs;
-	unsigned long last_seen_jiffies;
-	bool no_purge;
-	u16 np_flag = BATADV_TT_CLIENT_NOPURGE;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		goto out;
-
-	seq_printf(seq,
-		   "Locally retrieved addresses (from %s) announced via TT (TTVN: %u):\n",
-		   net_dev->name, (u8)atomic_read(&bat_priv->tt.vn));
-	seq_puts(seq,
-		 "       Client         VID Flags    Last seen (CRC       )\n");
-
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(tt_common_entry,
-					 head, hash_entry) {
-			tt_local = container_of(tt_common_entry,
-						struct batadv_tt_local_entry,
-						common);
-			last_seen_jiffies = jiffies - tt_local->last_seen;
-			last_seen_msecs = jiffies_to_msecs(last_seen_jiffies);
-			last_seen_secs = last_seen_msecs / 1000;
-			last_seen_msecs = last_seen_msecs % 1000;
-
-			no_purge = tt_common_entry->flags & np_flag;
-			seq_printf(seq,
-				   " * %pM %4i [%c%c%c%c%c%c] %3u.%03u   (%#.8x)\n",
-				   tt_common_entry->addr,
-				   batadv_print_vid(tt_common_entry->vid),
-				   ((tt_common_entry->flags &
-				     BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
-				   no_purge ? 'P' : '.',
-				   ((tt_common_entry->flags &
-				     BATADV_TT_CLIENT_NEW) ? 'N' : '.'),
-				   ((tt_common_entry->flags &
-				     BATADV_TT_CLIENT_PENDING) ? 'X' : '.'),
-				   ((tt_common_entry->flags &
-				     BATADV_TT_CLIENT_WIFI) ? 'W' : '.'),
-				   ((tt_common_entry->flags &
-				     BATADV_TT_CLIENT_ISOLA) ? 'I' : '.'),
-				   no_purge ? 0 : last_seen_secs,
-				   no_purge ? 0 : last_seen_msecs,
-				   tt_local->vlan->tt.crc);
-		}
-		rcu_read_unlock();
-	}
-out:
-	if (primary_if)
-		batadv_hardif_put(primary_if);
-	return 0;
-}
-#endif
-
 /**
  * batadv_tt_local_dump_entry() - Dump one TT local entry into a message
  * @msg :Netlink message to dump into
@@ -1879,139 +1800,6 @@ batadv_transtable_best_orig(struct batadv_priv *bat_priv,
 	return best_entry;
 }
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-/**
- * batadv_tt_global_print_entry() - print all orig nodes who announce the
- *  address for this global entry
- * @bat_priv: the bat priv with all the soft interface information
- * @tt_global_entry: global translation table entry to be printed
- * @seq: debugfs table seq_file struct
- *
- * This function assumes the caller holds rcu_read_lock().
- */
-static void
-batadv_tt_global_print_entry(struct batadv_priv *bat_priv,
-			     struct batadv_tt_global_entry *tt_global_entry,
-			     struct seq_file *seq)
-{
-	struct batadv_tt_orig_list_entry *orig_entry, *best_entry;
-	struct batadv_tt_common_entry *tt_common_entry;
-	struct batadv_orig_node_vlan *vlan;
-	struct hlist_head *head;
-	u8 last_ttvn;
-	u16 flags;
-
-	tt_common_entry = &tt_global_entry->common;
-	flags = tt_common_entry->flags;
-
-	best_entry = batadv_transtable_best_orig(bat_priv, tt_global_entry);
-	if (best_entry) {
-		vlan = batadv_orig_node_vlan_get(best_entry->orig_node,
-						 tt_common_entry->vid);
-		if (!vlan) {
-			seq_printf(seq,
-				   " * Cannot retrieve VLAN %d for originator %pM\n",
-				   batadv_print_vid(tt_common_entry->vid),
-				   best_entry->orig_node->orig);
-			goto print_list;
-		}
-
-		last_ttvn = atomic_read(&best_entry->orig_node->last_ttvn);
-		seq_printf(seq,
-			   " %c %pM %4i   (%3u) via %pM     (%3u)   (%#.8x) [%c%c%c%c]\n",
-			   '*', tt_global_entry->common.addr,
-			   batadv_print_vid(tt_global_entry->common.vid),
-			   best_entry->ttvn, best_entry->orig_node->orig,
-			   last_ttvn, vlan->tt.crc,
-			   ((flags & BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
-			   ((flags & BATADV_TT_CLIENT_WIFI) ? 'W' : '.'),
-			   ((flags & BATADV_TT_CLIENT_ISOLA) ? 'I' : '.'),
-			   ((flags & BATADV_TT_CLIENT_TEMP) ? 'T' : '.'));
-
-		batadv_orig_node_vlan_put(vlan);
-	}
-
-print_list:
-	head = &tt_global_entry->orig_list;
-
-	hlist_for_each_entry_rcu(orig_entry, head, list) {
-		if (best_entry == orig_entry)
-			continue;
-
-		vlan = batadv_orig_node_vlan_get(orig_entry->orig_node,
-						 tt_common_entry->vid);
-		if (!vlan) {
-			seq_printf(seq,
-				   " + Cannot retrieve VLAN %d for originator %pM\n",
-				   batadv_print_vid(tt_common_entry->vid),
-				   orig_entry->orig_node->orig);
-			continue;
-		}
-
-		last_ttvn = atomic_read(&orig_entry->orig_node->last_ttvn);
-		seq_printf(seq,
-			   " %c %pM %4d   (%3u) via %pM     (%3u)   (%#.8x) [%c%c%c%c]\n",
-			   '+', tt_global_entry->common.addr,
-			   batadv_print_vid(tt_global_entry->common.vid),
-			   orig_entry->ttvn, orig_entry->orig_node->orig,
-			   last_ttvn, vlan->tt.crc,
-			   ((flags & BATADV_TT_CLIENT_ROAM) ? 'R' : '.'),
-			   ((flags & BATADV_TT_CLIENT_WIFI) ? 'W' : '.'),
-			   ((flags & BATADV_TT_CLIENT_ISOLA) ? 'I' : '.'),
-			   ((flags & BATADV_TT_CLIENT_TEMP) ? 'T' : '.'));
-
-		batadv_orig_node_vlan_put(vlan);
-	}
-}
-
-/**
- * batadv_tt_global_seq_print_text() - Print the global tt table in a seq file
- * @seq: seq file to print on
- * @offset: not used
- *
- * Return: always 0
- */
-int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset)
-{
-	struct net_device *net_dev = (struct net_device *)seq->private;
-	struct batadv_priv *bat_priv = netdev_priv(net_dev);
-	struct batadv_hashtable *hash = bat_priv->tt.global_hash;
-	struct batadv_tt_common_entry *tt_common_entry;
-	struct batadv_tt_global_entry *tt_global;
-	struct batadv_hard_iface *primary_if;
-	struct hlist_head *head;
-	u32 i;
-
-	primary_if = batadv_seq_print_text_primary_if_get(seq);
-	if (!primary_if)
-		goto out;
-
-	seq_printf(seq,
-		   "Globally announced TT entries received via the mesh %s\n",
-		   net_dev->name);
-	seq_puts(seq,
-		 "       Client         VID  (TTVN)       Originator      (Curr TTVN) (CRC       ) Flags\n");
-
-	for (i = 0; i < hash->size; i++) {
-		head = &hash->table[i];
-
-		rcu_read_lock();
-		hlist_for_each_entry_rcu(tt_common_entry,
-					 head, hash_entry) {
-			tt_global = container_of(tt_common_entry,
-						 struct batadv_tt_global_entry,
-						 common);
-			batadv_tt_global_print_entry(bat_priv, tt_global, seq);
-		}
-		rcu_read_unlock();
-	}
-out:
-	if (primary_if)
-		batadv_hardif_put(primary_if);
-	return 0;
-}
-#endif
-
 /**
  * batadv_tt_global_dump_subentry() - Dump all TT local entries into a message
  * @msg: Netlink message to dump into
diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h
index b24d35b9226a..57192c817229 100644
--- a/net/batman-adv/translation-table.h
+++ b/net/batman-adv/translation-table.h
@@ -11,7 +11,6 @@
 
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
 
@@ -21,8 +20,6 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 u16 batadv_tt_local_remove(struct batadv_priv *bat_priv,
 			   const u8 *addr, unsigned short vid,
 			   const char *message, bool roaming);
-int batadv_tt_local_seq_print_text(struct seq_file *seq, void *offset);
-int batadv_tt_global_seq_print_text(struct seq_file *seq, void *offset);
 int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb);
 int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb);
 void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index ed519efa3c36..2f96e96a5ca4 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -21,7 +21,6 @@
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <linux/sched.h> /* for linux/wait.h */
-#include <linux/seq_file.h>
 #include <linux/skbuff.h>
 #include <linux/spinlock.h>
 #include <linux/timer.h>
@@ -187,9 +186,6 @@ struct batadv_hard_iface {
 	/** @net_dev: pointer to the net_device */
 	struct net_device *net_dev;
 
-	/** @hardif_obj: kobject of the per interface sysfs "mesh" directory */
-	struct kobject *hardif_obj;
-
 	/** @refcount: number of contexts the object is used */
 	struct kref refcount;
 
@@ -222,13 +218,6 @@ struct batadv_hard_iface {
 	struct batadv_hard_iface_bat_v bat_v;
 #endif
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-	/**
-	 * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs
-	 */
-	struct dentry *debug_dir;
-#endif
-
 	/**
 	 * @neigh_list: list of unique single hop neighbors via this interface
 	 */
@@ -1306,13 +1295,6 @@ struct batadv_priv_nc {
 	/** @work: work queue callback item for cleanup */
 	struct delayed_work work;
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-	/**
-	 * @debug_dir: dentry for nc subdir in batman-adv directory in debugfs
-	 */
-	struct dentry *debug_dir;
-#endif
-
 	/**
 	 * @min_tq: only consider neighbors for encoding if neigh_tq > min_tq
 	 */
@@ -1492,7 +1474,7 @@ struct batadv_tp_vars {
 	/** @unacked_lock: protect unacked_list */
 	spinlock_t unacked_lock;
 
-	/** @last_recv_time: time time (jiffies) a msg was received */
+	/** @last_recv_time: time (jiffies) a msg was received */
 	unsigned long last_recv_time;
 
 	/** @refcount: number of context where the object is used */
@@ -1512,9 +1494,6 @@ struct batadv_softif_vlan {
 	/** @vid: VLAN identifier */
 	unsigned short vid;
 
-	/** @kobj: kobject for sysfs vlan subdirectory */
-	struct kobject *kobj;
-
 	/** @ap_isolation: AP isolation state */
 	atomic_t ap_isolation;		/* boolean */
 
@@ -1667,14 +1646,6 @@ struct batadv_priv {
 	/** @batman_queue_left: number of remaining OGM packet slots */
 	atomic_t batman_queue_left;
 
-	/** @mesh_obj: kobject for sysfs mesh subdirectory */
-	struct kobject *mesh_obj;
-
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-	/** @debug_dir: dentry for debugfs batman-adv subdirectory */
-	struct dentry *debug_dir;
-#endif
-
 	/** @forw_bat_list: list of aggregated OGMs that will be forwarded */
 	struct hlist_head forw_bat_list;
 
@@ -1996,7 +1967,7 @@ struct batadv_tt_change_node {
  */
 struct batadv_tt_req_node {
 	/**
-	 * @addr: mac address address of the originator this request was sent to
+	 * @addr: mac address of the originator this request was sent to
 	 */
 	u8 addr[ETH_ALEN];
 
@@ -2234,11 +2205,6 @@ struct batadv_algo_neigh_ops {
 				     struct batadv_neigh_node *neigh2,
 				     struct batadv_hard_iface *if_outgoing2);
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-	/** @print: print the single hop neighbor list (optional) */
-	void (*print)(struct batadv_priv *priv, struct seq_file *seq);
-#endif
-
 	/** @dump: dump neighbors to a netlink socket (optional) */
 	void (*dump)(struct sk_buff *msg, struct netlink_callback *cb,
 		     struct batadv_priv *priv,
@@ -2249,12 +2215,6 @@ struct batadv_algo_neigh_ops {
  * struct batadv_algo_orig_ops - mesh algorithm callbacks (originator specific)
  */
 struct batadv_algo_orig_ops {
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-	/** @print: print the originator table (optional) */
-	void (*print)(struct batadv_priv *priv, struct seq_file *seq,
-		      struct batadv_hard_iface *hard_iface);
-#endif
-
 	/** @dump: dump originators to a netlink socket (optional) */
 	void (*dump)(struct sk_buff *msg, struct netlink_callback *cb,
 		     struct batadv_priv *priv,
@@ -2274,10 +2234,6 @@ struct batadv_algo_gw_ops {
 	 */
 	ssize_t (*store_sel_class)(struct batadv_priv *bat_priv, char *buff,
 				   size_t count);
-
-	/** @show_sel_class: prints the current GW selection class (optional) */
-	ssize_t (*show_sel_class)(struct batadv_priv *bat_priv, char *buff);
-
 	/**
 	 * @get_best_gw_node: select the best GW from the list of available
 	 *  nodes (optional)
@@ -2293,11 +2249,6 @@ struct batadv_algo_gw_ops {
 			    struct batadv_orig_node *curr_gw_orig,
 			    struct batadv_orig_node *orig_node);
 
-#ifdef CONFIG_BATMAN_ADV_DEBUGFS
-	/** @print: print the gateway table (optional) */
-	void (*print)(struct batadv_priv *bat_priv, struct seq_file *seq);
-#endif
-
 	/** @dump: dump gateways to a netlink socket (optional) */
 	void (*dump)(struct sk_buff *msg, struct netlink_callback *cb,
 		     struct batadv_priv *priv);
@@ -2456,21 +2407,4 @@ enum batadv_tvlv_handler_flags {
 	BATADV_TVLV_HANDLER_OGM_CALLED = BIT(2),
 };
 
-/**
- * struct batadv_store_mesh_work - Work queue item to detach add/del interface
- *  from sysfs locks
- */
-struct batadv_store_mesh_work {
-	/**
-	 * @net_dev: netdevice to add/remove to/from batman-adv soft-interface
-	 */
-	struct net_device *net_dev;
-
-	/** @soft_iface_name: name of soft-interface to modify */
-	char soft_iface_name[IFNAMSIZ];
-
-	/** @work: work queue item */
-	struct work_struct work;
-};
-
 #endif /* _NET_BATMAN_ADV_TYPES_H_ */
diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig
index e2497d764e97..64e669acd42f 100644
--- a/net/bluetooth/Kconfig
+++ b/net/bluetooth/Kconfig
@@ -64,7 +64,6 @@ source "net/bluetooth/hidp/Kconfig"
 config BT_HS
 	bool "Bluetooth High Speed (HS) features"
 	depends on BT_BREDR
-	default y
 	help
 	  Bluetooth High Speed includes support for off-loading
 	  Bluetooth connections via 802.11 (wifi) physical layer
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 26526be579c7..da7fd7c8c2dc 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -226,6 +226,9 @@ static int a2mp_discover_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 			struct a2mp_info_req req;
 
 			found = true;
+
+			memset(&req, 0, sizeof(req));
+
 			req.id = cl->id;
 			a2mp_send(mgr, A2MP_GETINFO_REQ, __next_ident(mgr),
 				  sizeof(req), &req);
@@ -305,6 +308,8 @@ static int a2mp_getinfo_req(struct amp_mgr *mgr, struct sk_buff *skb,
 	if (!hdev || hdev->dev_type != HCI_AMP) {
 		struct a2mp_info_rsp rsp;
 
+		memset(&rsp, 0, sizeof(rsp));
+
 		rsp.id = req->id;
 		rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
 
@@ -348,6 +353,8 @@ static int a2mp_getinfo_rsp(struct amp_mgr *mgr, struct sk_buff *skb,
 	if (!ctrl)
 		return -ENOMEM;
 
+	memset(&req, 0, sizeof(req));
+
 	req.id = rsp->id;
 	a2mp_send(mgr, A2MP_GETAMPASSOC_REQ, __next_ident(mgr), sizeof(req),
 		  &req);
@@ -376,6 +383,8 @@ static int a2mp_getampassoc_req(struct amp_mgr *mgr, struct sk_buff *skb,
 		struct a2mp_amp_assoc_rsp rsp;
 		rsp.id = req->id;
 
+		memset(&rsp, 0, sizeof(rsp));
+
 		if (tmp) {
 			rsp.status = A2MP_STATUS_COLLISION_OCCURED;
 			amp_mgr_put(tmp);
@@ -464,7 +473,6 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 				   struct a2mp_cmd *hdr)
 {
 	struct a2mp_physlink_req *req = (void *) skb->data;
-
 	struct a2mp_physlink_rsp rsp;
 	struct hci_dev *hdev;
 	struct hci_conn *hcon;
@@ -475,6 +483,8 @@ static int a2mp_createphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("local_id %d, remote_id %d", req->local_id, req->remote_id);
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	rsp.local_id = req->remote_id;
 	rsp.remote_id = req->local_id;
 
@@ -553,6 +563,8 @@ static int a2mp_discphyslink_req(struct amp_mgr *mgr, struct sk_buff *skb,
 
 	BT_DBG("local_id %d remote_id %d", req->local_id, req->remote_id);
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	rsp.local_id = req->remote_id;
 	rsp.remote_id = req->local_id;
 	rsp.status = A2MP_STATUS_SUCCESS;
@@ -675,6 +687,8 @@ static int a2mp_chan_recv_cb(struct l2cap_chan *chan, struct sk_buff *skb)
 	if (err) {
 		struct a2mp_cmd_rej rej;
 
+		memset(&rej, 0, sizeof(rej));
+
 		rej.reason = cpu_to_le16(0);
 		hdr = (void *) skb->data;
 
@@ -898,6 +912,8 @@ void a2mp_send_getinfo_rsp(struct hci_dev *hdev)
 
 	BT_DBG("%s mgr %p", hdev->name, mgr);
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	rsp.id = hdev->id;
 	rsp.status = A2MP_STATUS_INVALID_CTRL_ID;
 
@@ -995,6 +1011,8 @@ void a2mp_send_create_phy_link_rsp(struct hci_dev *hdev, u8 status)
 	if (!mgr)
 		return;
 
+	memset(&rsp, 0, sizeof(rsp));
+
 	hs_hcon = hci_conn_hash_lookup_state(hdev, AMP_LINK, BT_CONNECT);
 	if (!hs_hcon) {
 		rsp.status = A2MP_STATUS_UNABLE_START_LINK_CREATION;
@@ -1027,6 +1045,8 @@ void a2mp_discover_amp(struct l2cap_chan *chan)
 
 	mgr->bredr_chan = chan;
 
+	memset(&req, 0, sizeof(req));
+
 	req.mtu = cpu_to_le16(L2CAP_A2MP_DEFAULT_MTU);
 	req.ext_feat = 0;
 	a2mp_send(mgr, A2MP_DISCOVER_REQ, 1, sizeof(req), &req);
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 9832f8445d43..4f1cd8063e72 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -758,6 +758,9 @@ static void create_le_conn_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 
 	conn = hci_lookup_le_connect(hdev);
 
+	if (hdev->adv_instance_cnt)
+		hci_req_resume_adv_instances(hdev);
+
 	if (!status) {
 		hci_connect_le_scan_cleanup(conn);
 		goto done;
@@ -1067,10 +1070,11 @@ struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst,
 	 * connections most controllers will refuse to connect if
 	 * advertising is enabled, and for slave role connections we
 	 * anyway have to disable it in order to start directed
-	 * advertising.
+	 * advertising. Any registered advertisements will be
+	 * re-enabled after the connection attempt is finished.
 	 */
 	if (hci_dev_test_flag(hdev, HCI_LE_ADV))
-		 __hci_req_disable_advertising(&req);
+		__hci_req_pause_adv_instances(&req);
 
 	/* If requested to connect as slave use directed advertising */
 	if (conn->role == HCI_ROLE_SLAVE) {
@@ -1118,6 +1122,10 @@ create_conn:
 	err = hci_req_run(&req, create_le_conn_complete);
 	if (err) {
 		hci_conn_del(conn);
+
+		if (hdev->adv_instance_cnt)
+			hci_req_resume_adv_instances(hdev);
+
 		return ERR_PTR(err);
 	}
 
@@ -1388,7 +1396,7 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type)
 	return 0;
 }
 
-/* Encrypt the the link */
+/* Encrypt the link */
 static void hci_conn_encrypt(struct hci_conn *conn)
 {
 	BT_DBG("hcon %p", conn);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 68bfe57b6625..9d2c9a1c552f 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -741,6 +741,12 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 			hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL);
 		}
 
+		if (hdev->commands[38] & 0x80) {
+			/* Read LE Min/Max Tx Power*/
+			hci_req_add(req, HCI_OP_LE_READ_TRANSMIT_POWER,
+				    0, NULL);
+		}
+
 		if (hdev->commands[26] & 0x40) {
 			/* Read LE White List Size */
 			hci_req_add(req, HCI_OP_LE_READ_WHITE_LIST_SIZE,
@@ -763,7 +769,7 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 			hci_req_add(req, HCI_OP_LE_CLEAR_RESOLV_LIST, 0, NULL);
 		}
 
-		if (hdev->commands[35] & 0x40) {
+		if (hdev->commands[35] & 0x04) {
 			__le16 rpa_timeout = cpu_to_le16(hdev->rpa_timeout);
 
 			/* Set RPA timeout */
@@ -808,7 +814,7 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt)
 	 * Delete Stored Link Key command. They are clearly indicating its
 	 * absence in the bit mask of supported commands.
 	 *
-	 * Check the supported commands and only if the the command is marked
+	 * Check the supported commands and only if the command is marked
 	 * as supported send it. If not supported assume that the controller
 	 * does not have actual support for stored link keys which makes this
 	 * command redundant anyway.
@@ -2951,7 +2957,8 @@ static void adv_instance_rpa_expired(struct work_struct *work)
 int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 			 u16 adv_data_len, u8 *adv_data,
 			 u16 scan_rsp_len, u8 *scan_rsp_data,
-			 u16 timeout, u16 duration)
+			 u16 timeout, u16 duration, s8 tx_power,
+			 u32 min_interval, u32 max_interval)
 {
 	struct adv_info *adv_instance;
 
@@ -2963,7 +2970,7 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 		       sizeof(adv_instance->scan_rsp_data));
 	} else {
 		if (hdev->adv_instance_cnt >= hdev->le_num_of_adv_sets ||
-		    instance < 1 || instance > HCI_MAX_ADV_INSTANCES)
+		    instance < 1 || instance > hdev->le_num_of_adv_sets)
 			return -EOVERFLOW;
 
 		adv_instance = kzalloc(sizeof(*adv_instance), GFP_KERNEL);
@@ -2979,6 +2986,9 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 	adv_instance->flags = flags;
 	adv_instance->adv_data_len = adv_data_len;
 	adv_instance->scan_rsp_len = scan_rsp_len;
+	adv_instance->min_interval = min_interval;
+	adv_instance->max_interval = max_interval;
+	adv_instance->tx_power = tx_power;
 
 	if (adv_data_len)
 		memcpy(adv_instance->adv_data, adv_data, adv_data_len);
@@ -2995,8 +3005,6 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 	else
 		adv_instance->duration = duration;
 
-	adv_instance->tx_power = HCI_TX_POWER_INVALID;
-
 	INIT_DELAYED_WORK(&adv_instance->rpa_expired_cb,
 			  adv_instance_rpa_expired);
 
@@ -3006,6 +3014,37 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 }
 
 /* This function requires the caller holds hdev->lock */
+int hci_set_adv_instance_data(struct hci_dev *hdev, u8 instance,
+			      u16 adv_data_len, u8 *adv_data,
+			      u16 scan_rsp_len, u8 *scan_rsp_data)
+{
+	struct adv_info *adv_instance;
+
+	adv_instance = hci_find_adv_instance(hdev, instance);
+
+	/* If advertisement doesn't exist, we can't modify its data */
+	if (!adv_instance)
+		return -ENOENT;
+
+	if (adv_data_len) {
+		memset(adv_instance->adv_data, 0,
+		       sizeof(adv_instance->adv_data));
+		memcpy(adv_instance->adv_data, adv_data, adv_data_len);
+		adv_instance->adv_data_len = adv_data_len;
+	}
+
+	if (scan_rsp_len) {
+		memset(adv_instance->scan_rsp_data, 0,
+		       sizeof(adv_instance->scan_rsp_data));
+		memcpy(adv_instance->scan_rsp_data,
+		       scan_rsp_data, scan_rsp_len);
+		adv_instance->scan_rsp_len = scan_rsp_len;
+	}
+
+	return 0;
+}
+
+/* This function requires the caller holds hdev->lock */
 void hci_adv_monitors_clear(struct hci_dev *hdev)
 {
 	struct adv_monitor *monitor;
@@ -3061,6 +3100,7 @@ static int free_adv_monitor(int id, void *ptr, void *data)
 
 	idr_remove(&hdev->adv_monitors_idr, monitor->handle);
 	hci_free_adv_monitor(monitor);
+	hdev->adv_monitors_cnt--;
 
 	return 0;
 }
@@ -3077,6 +3117,7 @@ int hci_remove_adv_monitor(struct hci_dev *hdev, u16 handle)
 
 		idr_remove(&hdev->adv_monitors_idr, monitor->handle);
 		hci_free_adv_monitor(monitor);
+		hdev->adv_monitors_cnt--;
 	} else {
 		/* Remove all monitors if handle is 0. */
 		idr_for_each(&hdev->adv_monitors_idr, &free_adv_monitor, hdev);
@@ -3442,6 +3483,16 @@ void hci_copy_identity_address(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	}
 }
 
+static void hci_suspend_clear_tasks(struct hci_dev *hdev)
+{
+	int i;
+
+	for (i = 0; i < __SUSPEND_NUM_TASKS; i++)
+		clear_bit(i, hdev->suspend_tasks);
+
+	wake_up(&hdev->suspend_wait_q);
+}
+
 static int hci_suspend_wait_event(struct hci_dev *hdev)
 {
 #define WAKE_COND                                                              \
@@ -3487,12 +3538,24 @@ static int hci_change_suspend_state(struct hci_dev *hdev,
 	return hci_suspend_wait_event(hdev);
 }
 
+static void hci_clear_wake_reason(struct hci_dev *hdev)
+{
+	hci_dev_lock(hdev);
+
+	hdev->wake_reason = 0;
+	bacpy(&hdev->wake_addr, BDADDR_ANY);
+	hdev->wake_addr_type = 0;
+
+	hci_dev_unlock(hdev);
+}
+
 static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
 				void *data)
 {
 	struct hci_dev *hdev =
 		container_of(nb, struct hci_dev, suspend_notifier);
 	int ret = 0;
+	u8 state = BT_RUNNING;
 
 	/* If powering down, wait for completion. */
 	if (mgmt_powering_down(hdev)) {
@@ -3513,15 +3576,27 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
 		 *  - Second, program event filter/whitelist and enable scan
 		 */
 		ret = hci_change_suspend_state(hdev, BT_SUSPEND_DISCONNECT);
+		if (!ret)
+			state = BT_SUSPEND_DISCONNECT;
 
 		/* Only configure whitelist if disconnect succeeded and wake
 		 * isn't being prevented.
 		 */
-		if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev)))
+		if (!ret && !(hdev->prevent_wake && hdev->prevent_wake(hdev))) {
 			ret = hci_change_suspend_state(hdev,
 						BT_SUSPEND_CONFIGURE_WAKE);
+			if (!ret)
+				state = BT_SUSPEND_CONFIGURE_WAKE;
+		}
+
+		hci_clear_wake_reason(hdev);
+		mgmt_suspending(hdev, state);
+
 	} else if (action == PM_POST_SUSPEND) {
 		ret = hci_change_suspend_state(hdev, BT_RUNNING);
+
+		mgmt_resuming(hdev, hdev->wake_reason, &hdev->wake_addr,
+			      hdev->wake_addr_type);
 	}
 
 done:
@@ -3556,6 +3631,10 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->cur_adv_instance = 0x00;
 	hdev->adv_instance_timeout = 0;
 
+	hdev->advmon_allowlist_duration = 300;
+	hdev->advmon_no_filter_duration = 500;
+	hdev->enable_advmon_interleave_scan = 0x00;	/* Default to disable */
+
 	hdev->sniff_max_interval = 800;
 	hdev->sniff_min_interval = 80;
 
@@ -3587,6 +3666,8 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->le_num_of_adv_sets = HCI_MAX_ADV_INSTANCES;
 	hdev->def_multi_adv_rotation_duration = HCI_DEFAULT_ADV_DURATION;
 	hdev->def_le_autoconnect_timeout = HCI_LE_AUTOCONN_TIMEOUT;
+	hdev->min_le_tx_power = HCI_TX_POWER_INVALID;
+	hdev->max_le_tx_power = HCI_TX_POWER_INVALID;
 
 	hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT;
 	hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT;
@@ -3784,6 +3865,7 @@ void hci_unregister_dev(struct hci_dev *hdev)
 
 	cancel_work_sync(&hdev->power_on);
 
+	hci_suspend_clear_tasks(hdev);
 	unregister_pm_notifier(&hdev->suspend_notifier);
 	cancel_work_sync(&hdev->suspend_prepare);
 
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index 5e8af2658e44..4626e0289a97 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -494,6 +494,45 @@ static int auto_accept_delay_get(void *data, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(auto_accept_delay_fops, auto_accept_delay_get,
 			auto_accept_delay_set, "%llu\n");
 
+static ssize_t force_bredr_smp_read(struct file *file,
+				    char __user *user_buf,
+				    size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	char buf[3];
+
+	buf[0] = hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP) ? 'Y' : 'N';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
+}
+
+static ssize_t force_bredr_smp_write(struct file *file,
+				     const char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	struct hci_dev *hdev = file->private_data;
+	bool enable;
+	int err;
+
+	err = kstrtobool_from_user(user_buf, count, &enable);
+	if (err)
+		return err;
+
+	err = smp_force_bredr(hdev, enable);
+	if (err)
+		return err;
+
+	return count;
+}
+
+static const struct file_operations force_bredr_smp_fops = {
+	.open		= simple_open,
+	.read		= force_bredr_smp_read,
+	.write		= force_bredr_smp_write,
+	.llseek		= default_llseek,
+};
+
 static int idle_timeout_set(void *data, u64 val)
 {
 	struct hci_dev *hdev = data;
@@ -589,6 +628,17 @@ void hci_debugfs_create_bredr(struct hci_dev *hdev)
 	debugfs_create_file("voice_setting", 0444, hdev->debugfs, hdev,
 			    &voice_setting_fops);
 
+	/* If the controller does not support BR/EDR Secure Connections
+	 * feature, then the BR/EDR SMP channel shall not be present.
+	 *
+	 * To test this with Bluetooth 4.0 controllers, create a debugfs
+	 * switch that allows forcing BR/EDR SMP support and accepting
+	 * cross-transport pairing on non-AES encrypted connections.
+	 */
+	if (!lmp_sc_capable(hdev))
+		debugfs_create_file("force_bredr_smp", 0644, hdev->debugfs,
+				    hdev, &force_bredr_smp_fops);
+
 	if (lmp_ssp_capable(hdev)) {
 		debugfs_create_file("ssp_debug_mode", 0444, hdev->debugfs,
 				    hdev, &ssp_debug_mode_fops);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 4b7fc430793c..67668be3461e 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1202,6 +1202,20 @@ static void hci_cc_le_set_adv_set_random_addr(struct hci_dev *hdev,
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_le_read_transmit_power(struct hci_dev *hdev,
+					  struct sk_buff *skb)
+{
+	struct hci_rp_le_read_transmit_power *rp = (void *)skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	hdev->min_le_tx_power = rp->min_le_tx_power;
+	hdev->max_le_tx_power = rp->max_le_tx_power;
+}
+
 static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 *sent, status = *((__u8 *) skb->data);
@@ -1752,6 +1766,7 @@ static void hci_cc_set_ext_adv_param(struct hci_dev *hdev, struct sk_buff *skb)
 	}
 	/* Update adv data as tx power is known now */
 	hci_req_update_adv_data(hdev, hdev->cur_adv_instance);
+
 	hci_dev_unlock(hdev);
 }
 
@@ -2569,7 +2584,6 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb)
 static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_ev_conn_complete *ev = (void *) skb->data;
-	struct inquiry_entry *ie;
 	struct hci_conn *conn;
 
 	BT_DBG("%s", hdev->name);
@@ -2578,13 +2592,19 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	conn = hci_conn_hash_lookup_ba(hdev, ev->link_type, &ev->bdaddr);
 	if (!conn) {
-		/* Connection may not exist if auto-connected. Check the inquiry
-		 * cache to see if we've already discovered this bdaddr before.
-		 * If found and link is an ACL type, create a connection class
+		/* Connection may not exist if auto-connected. Check the bredr
+		 * allowlist to see if this device is allowed to auto connect.
+		 * If link is an ACL type, create a connection class
 		 * automatically.
+		 *
+		 * Auto-connect will only occur if the event filter is
+		 * programmed with a given address. Right now, event filter is
+		 * only used during suspend.
 		 */
-		ie = hci_inquiry_cache_lookup(hdev, &ev->bdaddr);
-		if (ie && ev->link_type == ACL_LINK) {
+		if (ev->link_type == ACL_LINK &&
+		    hci_bdaddr_list_lookup_with_flags(&hdev->whitelist,
+						      &ev->bdaddr,
+						      BDADDR_BREDR)) {
 			conn = hci_conn_add(hdev, ev->link_type, &ev->bdaddr,
 					    HCI_ROLE_SLAVE);
 			if (!conn) {
@@ -3576,6 +3596,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cc_le_set_adv_set_random_addr(hdev, skb);
 		break;
 
+	case HCI_OP_LE_READ_TRANSMIT_POWER:
+		hci_cc_le_read_transmit_power(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode);
 		break;
@@ -4931,15 +4955,15 @@ static void hci_phy_link_complete_evt(struct hci_dev *hdev,
 	hci_dev_lock(hdev);
 
 	hcon = hci_conn_hash_lookup_handle(hdev, ev->phy_handle);
-	if (!hcon) {
-		hci_dev_unlock(hdev);
-		return;
-	}
+	if (!hcon)
+		goto unlock;
+
+	if (!hcon->amp_mgr)
+		goto unlock;
 
 	if (ev->status) {
 		hci_conn_del(hcon);
-		hci_dev_unlock(hdev);
-		return;
+		goto unlock;
 	}
 
 	bredr_hcon = hcon->amp_mgr->l2cap_conn->hcon;
@@ -4956,6 +4980,7 @@ static void hci_phy_link_complete_evt(struct hci_dev *hdev,
 
 	amp_physical_cfm(bredr_hcon, hcon);
 
+unlock:
 	hci_dev_unlock(hdev);
 }
 
@@ -5863,21 +5888,19 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev,
 					 struct sk_buff *skb)
 {
 	u8 num_reports = skb->data[0];
-	void *ptr = &skb->data[1];
+	struct hci_ev_le_direct_adv_info *ev = (void *)&skb->data[1];
 
-	hci_dev_lock(hdev);
+	if (!num_reports || skb->len < num_reports * sizeof(*ev) + 1)
+		return;
 
-	while (num_reports--) {
-		struct hci_ev_le_direct_adv_info *ev = ptr;
+	hci_dev_lock(hdev);
 
+	for (; num_reports; num_reports--, ev++)
 		process_adv_report(hdev, ev->evt_type, &ev->bdaddr,
 				   ev->bdaddr_type, &ev->direct_addr,
 				   ev->direct_addr_type, ev->rssi, NULL, 0,
 				   false);
 
-		ptr += sizeof(*ev);
-	}
-
 	hci_dev_unlock(hdev);
 }
 
@@ -6012,6 +6035,75 @@ static bool hci_get_cmd_complete(struct hci_dev *hdev, u16 opcode,
 	return true;
 }
 
+static void hci_store_wake_reason(struct hci_dev *hdev, u8 event,
+				  struct sk_buff *skb)
+{
+	struct hci_ev_le_advertising_info *adv;
+	struct hci_ev_le_direct_adv_info *direct_adv;
+	struct hci_ev_le_ext_adv_report *ext_adv;
+	const struct hci_ev_conn_complete *conn_complete = (void *)skb->data;
+	const struct hci_ev_conn_request *conn_request = (void *)skb->data;
+
+	hci_dev_lock(hdev);
+
+	/* If we are currently suspended and this is the first BT event seen,
+	 * save the wake reason associated with the event.
+	 */
+	if (!hdev->suspended || hdev->wake_reason)
+		goto unlock;
+
+	/* Default to remote wake. Values for wake_reason are documented in the
+	 * Bluez mgmt api docs.
+	 */
+	hdev->wake_reason = MGMT_WAKE_REASON_REMOTE_WAKE;
+
+	/* Once configured for remote wakeup, we should only wake up for
+	 * reconnections. It's useful to see which device is waking us up so
+	 * keep track of the bdaddr of the connection event that woke us up.
+	 */
+	if (event == HCI_EV_CONN_REQUEST) {
+		bacpy(&hdev->wake_addr, &conn_complete->bdaddr);
+		hdev->wake_addr_type = BDADDR_BREDR;
+	} else if (event == HCI_EV_CONN_COMPLETE) {
+		bacpy(&hdev->wake_addr, &conn_request->bdaddr);
+		hdev->wake_addr_type = BDADDR_BREDR;
+	} else if (event == HCI_EV_LE_META) {
+		struct hci_ev_le_meta *le_ev = (void *)skb->data;
+		u8 subevent = le_ev->subevent;
+		u8 *ptr = &skb->data[sizeof(*le_ev)];
+		u8 num_reports = *ptr;
+
+		if ((subevent == HCI_EV_LE_ADVERTISING_REPORT ||
+		     subevent == HCI_EV_LE_DIRECT_ADV_REPORT ||
+		     subevent == HCI_EV_LE_EXT_ADV_REPORT) &&
+		    num_reports) {
+			adv = (void *)(ptr + 1);
+			direct_adv = (void *)(ptr + 1);
+			ext_adv = (void *)(ptr + 1);
+
+			switch (subevent) {
+			case HCI_EV_LE_ADVERTISING_REPORT:
+				bacpy(&hdev->wake_addr, &adv->bdaddr);
+				hdev->wake_addr_type = adv->bdaddr_type;
+				break;
+			case HCI_EV_LE_DIRECT_ADV_REPORT:
+				bacpy(&hdev->wake_addr, &direct_adv->bdaddr);
+				hdev->wake_addr_type = direct_adv->bdaddr_type;
+				break;
+			case HCI_EV_LE_EXT_ADV_REPORT:
+				bacpy(&hdev->wake_addr, &ext_adv->bdaddr);
+				hdev->wake_addr_type = ext_adv->bdaddr_type;
+				break;
+			}
+		}
+	} else {
+		hdev->wake_reason = MGMT_WAKE_REASON_UNEXPECTED;
+	}
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_event_hdr *hdr = (void *) skb->data;
@@ -6045,6 +6137,9 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb)
 
 	skb_pull(skb, HCI_EVENT_HDR_SIZE);
 
+	/* Store wake reason if we're suspended */
+	hci_store_wake_reason(hdev, event, skb);
+
 	switch (event) {
 	case HCI_EV_INQUIRY_COMPLETE:
 		hci_inquiry_complete_evt(hdev, skb);
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index e0269192f2e5..71bffd745472 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -58,7 +58,7 @@ static int req_run(struct hci_request *req, hci_req_complete_t complete,
 	struct sk_buff *skb;
 	unsigned long flags;
 
-	BT_DBG("length %u", skb_queue_len(&req->cmd_q));
+	bt_dev_dbg(hdev, "length %u", skb_queue_len(&req->cmd_q));
 
 	/* If an error occurred during request building, remove all HCI
 	 * commands queued on the HCI request queue.
@@ -102,7 +102,7 @@ int hci_req_run_skb(struct hci_request *req, hci_req_complete_skb_t complete)
 static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode,
 				  struct sk_buff *skb)
 {
-	BT_DBG("%s result 0x%2.2x", hdev->name, result);
+	bt_dev_dbg(hdev, "result 0x%2.2x", result);
 
 	if (hdev->req_status == HCI_REQ_PEND) {
 		hdev->req_result = result;
@@ -115,7 +115,7 @@ static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode,
 
 void hci_req_sync_cancel(struct hci_dev *hdev, int err)
 {
-	BT_DBG("%s err 0x%2.2x", hdev->name, err);
+	bt_dev_dbg(hdev, "err 0x%2.2x", err);
 
 	if (hdev->req_status == HCI_REQ_PEND) {
 		hdev->req_result = err;
@@ -131,7 +131,7 @@ struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen,
 	struct sk_buff *skb;
 	int err = 0;
 
-	BT_DBG("%s", hdev->name);
+	bt_dev_dbg(hdev, "");
 
 	hci_req_init(&req, hdev);
 
@@ -167,7 +167,7 @@ struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen,
 	skb = hdev->req_skb;
 	hdev->req_skb = NULL;
 
-	BT_DBG("%s end: err %d", hdev->name, err);
+	bt_dev_dbg(hdev, "end: err %d", err);
 
 	if (err < 0) {
 		kfree_skb(skb);
@@ -196,7 +196,7 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req,
 	struct hci_request req;
 	int err = 0;
 
-	BT_DBG("%s start", hdev->name);
+	bt_dev_dbg(hdev, "start");
 
 	hci_req_init(&req, hdev);
 
@@ -260,7 +260,7 @@ int __hci_req_sync(struct hci_dev *hdev, int (*func)(struct hci_request *req,
 	hdev->req_skb = NULL;
 	hdev->req_status = hdev->req_result = 0;
 
-	BT_DBG("%s end: err %d", hdev->name, err);
+	bt_dev_dbg(hdev, "end: err %d", err);
 
 	return err;
 }
@@ -300,7 +300,7 @@ struct sk_buff *hci_prepare_cmd(struct hci_dev *hdev, u16 opcode, u32 plen,
 	if (plen)
 		skb_put_data(skb, param, plen);
 
-	BT_DBG("skb len %d", skb->len);
+	bt_dev_dbg(hdev, "skb len %d", skb->len);
 
 	hci_skb_pkt_type(skb) = HCI_COMMAND_PKT;
 	hci_skb_opcode(skb) = opcode;
@@ -315,7 +315,7 @@ void hci_req_add_ev(struct hci_request *req, u16 opcode, u32 plen,
 	struct hci_dev *hdev = req->hdev;
 	struct sk_buff *skb;
 
-	BT_DBG("%s opcode 0x%4.4x plen %d", hdev->name, opcode, plen);
+	bt_dev_dbg(hdev, "opcode 0x%4.4x plen %d", opcode, plen);
 
 	/* If an error occurred during request building, there is no point in
 	 * queueing the HCI command. We can simply return.
@@ -378,6 +378,53 @@ void __hci_req_write_fast_connectable(struct hci_request *req, bool enable)
 		hci_req_add(req, HCI_OP_WRITE_PAGE_SCAN_TYPE, 1, &type);
 }
 
+static void start_interleave_scan(struct hci_dev *hdev)
+{
+	hdev->interleave_scan_state = INTERLEAVE_SCAN_NO_FILTER;
+	queue_delayed_work(hdev->req_workqueue,
+			   &hdev->interleave_scan, 0);
+}
+
+static bool is_interleave_scanning(struct hci_dev *hdev)
+{
+	return hdev->interleave_scan_state != INTERLEAVE_SCAN_NONE;
+}
+
+static void cancel_interleave_scan(struct hci_dev *hdev)
+{
+	bt_dev_dbg(hdev, "cancelling interleave scan");
+
+	cancel_delayed_work_sync(&hdev->interleave_scan);
+
+	hdev->interleave_scan_state = INTERLEAVE_SCAN_NONE;
+}
+
+/* Return true if interleave_scan wasn't started until exiting this function,
+ * otherwise, return false
+ */
+static bool __hci_update_interleaved_scan(struct hci_dev *hdev)
+{
+	/* If there is at least one ADV monitors and one pending LE connection
+	 * or one device to be scanned for, we should alternate between
+	 * allowlist scan and one without any filters to save power.
+	 */
+	bool use_interleaving = hci_is_adv_monitoring(hdev) &&
+				!(list_empty(&hdev->pend_le_conns) &&
+				  list_empty(&hdev->pend_le_reports));
+	bool is_interleaving = is_interleave_scanning(hdev);
+
+	if (use_interleaving && !is_interleaving) {
+		start_interleave_scan(hdev);
+		bt_dev_dbg(hdev, "starting interleave scan");
+		return true;
+	}
+
+	if (!use_interleaving && is_interleaving)
+		cancel_interleave_scan(hdev);
+
+	return false;
+}
+
 /* This function controls the background scanning based on hdev->pend_le_conns
  * list. If there are pending LE connection we start the background scanning,
  * otherwise we stop it.
@@ -413,8 +460,8 @@ static void __hci_update_background_scan(struct hci_request *req)
 	 */
 	hci_discovery_filter_clear(hdev);
 
-	BT_DBG("%s ADV monitoring is %s", hdev->name,
-	       hci_is_adv_monitoring(hdev) ? "on" : "off");
+	bt_dev_dbg(hdev, "ADV monitoring is %s",
+		   hci_is_adv_monitoring(hdev) ? "on" : "off");
 
 	if (list_empty(&hdev->pend_le_conns) &&
 	    list_empty(&hdev->pend_le_reports) &&
@@ -430,7 +477,7 @@ static void __hci_update_background_scan(struct hci_request *req)
 
 		hci_req_add_le_scan_disable(req, false);
 
-		BT_DBG("%s stopping background scanning", hdev->name);
+		bt_dev_dbg(hdev, "stopping background scanning");
 	} else {
 		/* If there is at least one pending LE connection, we should
 		 * keep the background scan running.
@@ -450,8 +497,7 @@ static void __hci_update_background_scan(struct hci_request *req)
 			hci_req_add_le_scan_disable(req, false);
 
 		hci_req_add_le_passive_scan(req);
-
-		BT_DBG("%s starting background scanning", hdev->name);
+		bt_dev_dbg(hdev, "starting background scanning");
 	}
 }
 
@@ -661,6 +707,9 @@ void hci_req_add_le_scan_disable(struct hci_request *req, bool rpa_le_conn)
 		return;
 	}
 
+	if (hdev->suspended)
+		set_bit(SUSPEND_SCAN_DISABLE, hdev->suspend_tasks);
+
 	if (use_ext_scan(hdev)) {
 		struct hci_cp_le_set_ext_scan_enable cp;
 
@@ -698,7 +747,8 @@ static void del_from_white_list(struct hci_request *req, bdaddr_t *bdaddr,
 		   cp.bdaddr_type);
 	hci_req_add(req, HCI_OP_LE_DEL_FROM_WHITE_LIST, sizeof(cp), &cp);
 
-	if (use_ll_privacy(req->hdev)) {
+	if (use_ll_privacy(req->hdev) &&
+	    hci_dev_test_flag(req->hdev, HCI_ENABLE_LL_PRIVACY)) {
 		struct smp_irk *irk;
 
 		irk = hci_find_irk_by_addr(req->hdev, bdaddr, bdaddr_type);
@@ -732,7 +782,8 @@ static int add_to_white_list(struct hci_request *req,
 		return -1;
 
 	/* White list can not be used with RPAs */
-	if (!allow_rpa && !use_ll_privacy(hdev) &&
+	if (!allow_rpa &&
+	    !hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) &&
 	    hci_find_irk_by_addr(hdev, &params->addr, params->addr_type)) {
 		return -1;
 	}
@@ -750,7 +801,8 @@ static int add_to_white_list(struct hci_request *req,
 		   cp.bdaddr_type);
 	hci_req_add(req, HCI_OP_LE_ADD_TO_WHITE_LIST, sizeof(cp), &cp);
 
-	if (use_ll_privacy(hdev)) {
+	if (use_ll_privacy(hdev) &&
+	    hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY)) {
 		struct smp_irk *irk;
 
 		irk = hci_find_irk_by_addr(hdev, &params->addr,
@@ -812,7 +864,8 @@ static u8 update_white_list(struct hci_request *req)
 		}
 
 		/* White list can not be used with RPAs */
-		if (!allow_rpa && !use_ll_privacy(hdev) &&
+		if (!allow_rpa &&
+		    !hci_dev_test_flag(hdev, HCI_ENABLE_LL_PRIVACY) &&
 		    hci_find_irk_by_addr(hdev, &b->bdaddr, b->bdaddr_type)) {
 			return 0x00;
 		}
@@ -844,12 +897,17 @@ static u8 update_white_list(struct hci_request *req)
 			return 0x00;
 	}
 
-	/* Once the controller offloading of advertisement monitor is in place,
-	 * the if condition should include the support of MSFT extension
-	 * support. If suspend is ongoing, whitelist should be the default to
-	 * prevent waking by random advertisements.
+	/* Use the allowlist unless the following conditions are all true:
+	 * - We are not currently suspending
+	 * - There are 1 or more ADV monitors registered
+	 * - Interleaved scanning is not currently using the allowlist
+	 *
+	 * Once the controller offloading of advertisement monitor is in place,
+	 * the above condition should include the support of MSFT extension
+	 * support.
 	 */
-	if (!idr_is_empty(&hdev->adv_monitors_idr) && !hdev->suspended)
+	if (!idr_is_empty(&hdev->adv_monitors_idr) && !hdev->suspended &&
+	    hdev->interleave_scan_state != INTERLEAVE_SCAN_ALLOWLIST)
 		return 0x00;
 
 	/* Select filter policy to use white list */
@@ -1002,6 +1060,11 @@ void hci_req_add_le_passive_scan(struct hci_request *req)
 				      &own_addr_type))
 		return;
 
+	if (hdev->enable_advmon_interleave_scan &&
+	    __hci_update_interleaved_scan(hdev))
+		return;
+
+	bt_dev_dbg(hdev, "interleave state %d", hdev->interleave_scan_state);
 	/* Adding or removing entries from the white list must
 	 * happen before enabling scanning. The controller does
 	 * not allow white list modification while scanning.
@@ -1027,6 +1090,9 @@ void hci_req_add_le_passive_scan(struct hci_request *req)
 	} else if (hci_is_le_conn_scanning(hdev)) {
 		window = hdev->le_scan_window_connect;
 		interval = hdev->le_scan_int_connect;
+	} else if (hci_is_adv_monitoring(hdev)) {
+		window = hdev->le_scan_window_adv_monitor;
+		interval = hdev->le_scan_int_adv_monitor;
 	} else {
 		window = hdev->le_scan_window;
 		interval = hdev->le_scan_interval;
@@ -1037,22 +1103,23 @@ void hci_req_add_le_passive_scan(struct hci_request *req)
 			   own_addr_type, filter_policy, addr_resolv);
 }
 
-static u8 get_adv_instance_scan_rsp_len(struct hci_dev *hdev, u8 instance)
+static bool adv_instance_is_scannable(struct hci_dev *hdev, u8 instance)
 {
 	struct adv_info *adv_instance;
 
 	/* Instance 0x00 always set local name */
 	if (instance == 0x00)
-		return 1;
+		return true;
 
 	adv_instance = hci_find_adv_instance(hdev, instance);
 	if (!adv_instance)
-		return 0;
+		return false;
 
-	/* TODO: Take into account the "appearance" and "local-name" flags here.
-	 * These are currently being ignored as they are not supported.
-	 */
-	return adv_instance->scan_rsp_len;
+	if (adv_instance->flags & MGMT_ADV_FLAG_APPEARANCE ||
+	    adv_instance->flags & MGMT_ADV_FLAG_LOCAL_NAME)
+		return true;
+
+	return adv_instance->scan_rsp_len ? true : false;
 }
 
 static void hci_req_clear_event_filter(struct hci_request *req)
@@ -1095,6 +1162,11 @@ static void hci_req_set_event_filter(struct hci_request *req)
 		scan = SCAN_PAGE;
 	}
 
+	if (scan)
+		set_bit(SUSPEND_SCAN_ENABLE, hdev->suspend_tasks);
+	else
+		set_bit(SUSPEND_SCAN_DISABLE, hdev->suspend_tasks);
+
 	hci_req_add(req, HCI_OP_WRITE_SCAN_ENABLE, 1, &scan);
 }
 
@@ -1111,6 +1183,64 @@ static void hci_req_config_le_suspend_scan(struct hci_request *req)
 	set_bit(SUSPEND_SCAN_ENABLE, req->hdev->suspend_tasks);
 }
 
+static void cancel_adv_timeout(struct hci_dev *hdev)
+{
+	if (hdev->adv_instance_timeout) {
+		hdev->adv_instance_timeout = 0;
+		cancel_delayed_work(&hdev->adv_instance_expire);
+	}
+}
+
+/* This function requires the caller holds hdev->lock */
+void __hci_req_pause_adv_instances(struct hci_request *req)
+{
+	bt_dev_dbg(req->hdev, "Pausing advertising instances");
+
+	/* Call to disable any advertisements active on the controller.
+	 * This will succeed even if no advertisements are configured.
+	 */
+	__hci_req_disable_advertising(req);
+
+	/* If we are using software rotation, pause the loop */
+	if (!ext_adv_capable(req->hdev))
+		cancel_adv_timeout(req->hdev);
+}
+
+/* This function requires the caller holds hdev->lock */
+static void __hci_req_resume_adv_instances(struct hci_request *req)
+{
+	struct adv_info *adv;
+
+	bt_dev_dbg(req->hdev, "Resuming advertising instances");
+
+	if (ext_adv_capable(req->hdev)) {
+		/* Call for each tracked instance to be re-enabled */
+		list_for_each_entry(adv, &req->hdev->adv_instances, list) {
+			__hci_req_enable_ext_advertising(req,
+							 adv->instance);
+		}
+
+	} else {
+		/* Schedule for most recent instance to be restarted and begin
+		 * the software rotation loop
+		 */
+		__hci_req_schedule_adv_instance(req,
+						req->hdev->cur_adv_instance,
+						true);
+	}
+}
+
+/* This function requires the caller holds hdev->lock */
+int hci_req_resume_adv_instances(struct hci_dev *hdev)
+{
+	struct hci_request req;
+
+	hci_req_init(&req, hdev);
+	__hci_req_resume_adv_instances(&req);
+
+	return hci_req_run(&req, NULL);
+}
+
 static void suspend_req_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	bt_dev_dbg(hdev, "Request complete opcode=0x%x, status=0x%x", opcode,
@@ -1153,7 +1283,7 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next)
 		hdev->discovery_paused = true;
 		hdev->discovery_old_state = old_state;
 
-		/* Stop advertising */
+		/* Stop directed advertising */
 		old_state = hci_dev_test_flag(hdev, HCI_ADVERTISING);
 		if (old_state) {
 			set_bit(SUSPEND_PAUSE_ADVERTISING, hdev->suspend_tasks);
@@ -1162,6 +1292,10 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next)
 					   &hdev->discov_off, 0);
 		}
 
+		/* Pause other advertisements */
+		if (hdev->adv_instance_cnt)
+			__hci_req_pause_adv_instances(&req);
+
 		hdev->advertising_paused = true;
 		hdev->advertising_old_state = old_state;
 		/* Disable page scan */
@@ -1169,8 +1303,10 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next)
 		hci_req_add(&req, HCI_OP_WRITE_SCAN_ENABLE, 1, &page_scan);
 
 		/* Disable LE passive scan if enabled */
-		if (hci_dev_test_flag(hdev, HCI_LE_SCAN))
+		if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) {
+			cancel_interleave_scan(hdev);
 			hci_req_add_le_scan_disable(&req, false);
+		}
 
 		/* Mark task needing completion */
 		set_bit(SUSPEND_SCAN_DISABLE, hdev->suspend_tasks);
@@ -1212,7 +1348,7 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next)
 		/* Reset passive/background scanning to normal */
 		hci_req_config_le_suspend_scan(&req);
 
-		/* Unpause advertising */
+		/* Unpause directed advertising */
 		hdev->advertising_paused = false;
 		if (hdev->advertising_old_state) {
 			set_bit(SUSPEND_UNPAUSE_ADVERTISING,
@@ -1223,6 +1359,10 @@ void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next)
 			hdev->advertising_old_state = 0;
 		}
 
+		/* Resume other advertisements */
+		if (hdev->adv_instance_cnt)
+			__hci_req_resume_adv_instances(&req);
+
 		/* Unpause discovery */
 		hdev->discovery_paused = false;
 		if (hdev->discovery_old_state != DISCOVERY_STOPPED &&
@@ -1242,23 +1382,9 @@ done:
 	wake_up(&hdev->suspend_wait_q);
 }
 
-static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev)
+static bool adv_cur_instance_is_scannable(struct hci_dev *hdev)
 {
-	u8 instance = hdev->cur_adv_instance;
-	struct adv_info *adv_instance;
-
-	/* Instance 0x00 always set local name */
-	if (instance == 0x00)
-		return 1;
-
-	adv_instance = hci_find_adv_instance(hdev, instance);
-	if (!adv_instance)
-		return 0;
-
-	/* TODO: Take into account the "appearance" and "local-name" flags here.
-	 * These are currently being ignored as they are not supported.
-	 */
-	return adv_instance->scan_rsp_len;
+	return adv_instance_is_scannable(hdev, hdev->cur_adv_instance);
 }
 
 void __hci_req_disable_advertising(struct hci_request *req)
@@ -1370,6 +1496,7 @@ static bool is_advertising_allowed(struct hci_dev *hdev, bool connectable)
 void __hci_req_enable_advertising(struct hci_request *req)
 {
 	struct hci_dev *hdev = req->hdev;
+	struct adv_info *adv_instance;
 	struct hci_cp_le_set_adv_param cp;
 	u8 own_addr_type, enable = 0x01;
 	bool connectable;
@@ -1377,6 +1504,7 @@ void __hci_req_enable_advertising(struct hci_request *req)
 	u32 flags;
 
 	flags = get_adv_instance_flags(hdev, hdev->cur_adv_instance);
+	adv_instance = hci_find_adv_instance(hdev, hdev->cur_adv_instance);
 
 	/* If the "connectable" instance flag was not set, then choose between
 	 * ADV_IND and ADV_NONCONN_IND based on the global connectable setting.
@@ -1408,13 +1536,18 @@ void __hci_req_enable_advertising(struct hci_request *req)
 
 	memset(&cp, 0, sizeof(cp));
 
-	if (connectable) {
-		cp.type = LE_ADV_IND;
-
+	if (adv_instance) {
+		adv_min_interval = adv_instance->min_interval;
+		adv_max_interval = adv_instance->max_interval;
+	} else {
 		adv_min_interval = hdev->le_adv_min_interval;
 		adv_max_interval = hdev->le_adv_max_interval;
+	}
+
+	if (connectable) {
+		cp.type = LE_ADV_IND;
 	} else {
-		if (get_cur_adv_instance_scan_rsp_len(hdev))
+		if (adv_cur_instance_is_scannable(hdev))
 			cp.type = LE_ADV_SCAN_IND;
 		else
 			cp.type = LE_ADV_NONCONN_IND;
@@ -1423,9 +1556,6 @@ void __hci_req_enable_advertising(struct hci_request *req)
 		    hci_dev_test_flag(hdev, HCI_LIMITED_DISCOVERABLE)) {
 			adv_min_interval = DISCOV_LE_FAST_ADV_INT_MIN;
 			adv_max_interval = DISCOV_LE_FAST_ADV_INT_MAX;
-		} else {
-			adv_min_interval = hdev->le_adv_min_interval;
-			adv_max_interval = hdev->le_adv_max_interval;
 		}
 	}
 
@@ -1750,7 +1880,7 @@ void hci_req_disable_address_resolution(struct hci_dev *hdev)
 
 static void adv_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
-	BT_DBG("%s status %u", hdev->name, status);
+	bt_dev_dbg(hdev, "status %u", status);
 }
 
 void hci_req_reenable_advertising(struct hci_dev *hdev)
@@ -1787,7 +1917,7 @@ static void adv_timeout_expire(struct work_struct *work)
 	struct hci_request req;
 	u8 instance;
 
-	BT_DBG("%s", hdev->name);
+	bt_dev_dbg(hdev, "");
 
 	hci_dev_lock(hdev);
 
@@ -1810,6 +1940,62 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static int hci_req_add_le_interleaved_scan(struct hci_request *req,
+					   unsigned long opt)
+{
+	struct hci_dev *hdev = req->hdev;
+	int ret = 0;
+
+	hci_dev_lock(hdev);
+
+	if (hci_dev_test_flag(hdev, HCI_LE_SCAN))
+		hci_req_add_le_scan_disable(req, false);
+	hci_req_add_le_passive_scan(req);
+
+	switch (hdev->interleave_scan_state) {
+	case INTERLEAVE_SCAN_ALLOWLIST:
+		bt_dev_dbg(hdev, "next state: allowlist");
+		hdev->interleave_scan_state = INTERLEAVE_SCAN_NO_FILTER;
+		break;
+	case INTERLEAVE_SCAN_NO_FILTER:
+		bt_dev_dbg(hdev, "next state: no filter");
+		hdev->interleave_scan_state = INTERLEAVE_SCAN_ALLOWLIST;
+		break;
+	case INTERLEAVE_SCAN_NONE:
+		BT_ERR("unexpected error");
+		ret = -1;
+	}
+
+	hci_dev_unlock(hdev);
+
+	return ret;
+}
+
+static void interleave_scan_work(struct work_struct *work)
+{
+	struct hci_dev *hdev = container_of(work, struct hci_dev,
+					    interleave_scan.work);
+	u8 status;
+	unsigned long timeout;
+
+	if (hdev->interleave_scan_state == INTERLEAVE_SCAN_ALLOWLIST) {
+		timeout = msecs_to_jiffies(hdev->advmon_allowlist_duration);
+	} else if (hdev->interleave_scan_state == INTERLEAVE_SCAN_NO_FILTER) {
+		timeout = msecs_to_jiffies(hdev->advmon_no_filter_duration);
+	} else {
+		bt_dev_err(hdev, "unexpected error");
+		return;
+	}
+
+	hci_req_sync(hdev, hci_req_add_le_interleaved_scan, 0,
+		     HCI_CMD_TIMEOUT, &status);
+
+	/* Don't continue interleaving if it was canceled */
+	if (is_interleave_scanning(hdev))
+		queue_delayed_work(hdev->req_workqueue,
+				   &hdev->interleave_scan, timeout);
+}
+
 int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
 			   bool use_rpa, struct adv_info *adv_instance,
 			   u8 *own_addr_type, bdaddr_t *rand_addr)
@@ -1824,7 +2010,13 @@ int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
 	if (use_rpa) {
 		int to;
 
-		*own_addr_type = ADDR_LE_DEV_RANDOM;
+		/* If Controller supports LL Privacy use own address type is
+		 * 0x03
+		 */
+		if (use_ll_privacy(hdev))
+			*own_addr_type = ADDR_LE_DEV_RANDOM_RESOLVED;
+		else
+			*own_addr_type = ADDR_LE_DEV_RANDOM;
 
 		if (adv_instance) {
 			if (!adv_instance->rpa_expired &&
@@ -1939,9 +2131,15 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 
 	memset(&cp, 0, sizeof(cp));
 
-	/* In ext adv set param interval is 3 octets */
-	hci_cpu_to_le24(hdev->le_adv_min_interval, cp.min_interval);
-	hci_cpu_to_le24(hdev->le_adv_max_interval, cp.max_interval);
+	if (adv_instance) {
+		hci_cpu_to_le24(adv_instance->min_interval, cp.min_interval);
+		hci_cpu_to_le24(adv_instance->max_interval, cp.max_interval);
+		cp.tx_power = adv_instance->tx_power;
+	} else {
+		hci_cpu_to_le24(hdev->le_adv_min_interval, cp.min_interval);
+		hci_cpu_to_le24(hdev->le_adv_max_interval, cp.max_interval);
+		cp.tx_power = HCI_ADV_TX_POWER_NO_PREFERENCE;
+	}
 
 	secondary_adv = (flags & MGMT_ADV_FLAG_SEC_MASK);
 
@@ -1950,7 +2148,7 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 			cp.evt_properties = cpu_to_le16(LE_EXT_ADV_CONN_IND);
 		else
 			cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_IND);
-	} else if (get_adv_instance_scan_rsp_len(hdev, instance)) {
+	} else if (adv_instance_is_scannable(hdev, instance)) {
 		if (secondary_adv)
 			cp.evt_properties = cpu_to_le16(LE_EXT_ADV_SCAN_IND);
 		else
@@ -1964,7 +2162,6 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 
 	cp.own_addr_type = own_addr_type;
 	cp.channel_map = hdev->le_adv_channel_map;
-	cp.tx_power = 127;
 	cp.handle = instance;
 
 	if (flags & MGMT_ADV_FLAG_SEC_2M) {
@@ -2183,14 +2380,6 @@ int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance,
 	return 0;
 }
 
-static void cancel_adv_timeout(struct hci_dev *hdev)
-{
-	if (hdev->adv_instance_timeout) {
-		hdev->adv_instance_timeout = 0;
-		cancel_delayed_work(&hdev->adv_instance_expire);
-	}
-}
-
 /* For a single instance:
  * - force == true: The instance will be removed even when its remaining
  *   lifetime is not zero.
@@ -2273,7 +2462,7 @@ static void set_random_addr(struct hci_request *req, bdaddr_t *rpa)
 	 */
 	if (hci_dev_test_flag(hdev, HCI_LE_ADV) ||
 	    hci_lookup_le_connect(hdev)) {
-		BT_DBG("Deferring random address update");
+		bt_dev_dbg(hdev, "Deferring random address update");
 		hci_dev_set_flag(hdev, HCI_RPA_EXPIRED);
 		return;
 	}
@@ -2498,7 +2687,7 @@ void __hci_req_update_class(struct hci_request *req)
 	struct hci_dev *hdev = req->hdev;
 	u8 cod[3];
 
-	BT_DBG("%s", hdev->name);
+	bt_dev_dbg(hdev, "");
 
 	if (!hdev_is_powered(hdev))
 		return;
@@ -2667,7 +2856,7 @@ void __hci_abort_conn(struct hci_request *req, struct hci_conn *conn,
 static void abort_conn_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 {
 	if (status)
-		BT_DBG("Failed to abort connection: status 0x%2.2x", status);
+		bt_dev_dbg(hdev, "Failed to abort connection: status 0x%2.2x", status);
 }
 
 int hci_abort_conn(struct hci_conn *conn, u8 reason)
@@ -2730,7 +2919,7 @@ static int bredr_inquiry(struct hci_request *req, unsigned long opt)
 	const u8 liac[3] = { 0x00, 0x8b, 0x9e };
 	struct hci_cp_inquiry cp;
 
-	BT_DBG("%s", req->hdev->name);
+	bt_dev_dbg(req->hdev, "");
 
 	hci_dev_lock(req->hdev);
 	hci_inquiry_cache_flush(req->hdev);
@@ -2756,7 +2945,7 @@ static void le_scan_disable_work(struct work_struct *work)
 					    le_scan_disable.work);
 	u8 status;
 
-	BT_DBG("%s", hdev->name);
+	bt_dev_dbg(hdev, "");
 
 	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
 		return;
@@ -2852,7 +3041,7 @@ static void le_scan_restart_work(struct work_struct *work)
 	unsigned long timeout, duration, scan_start, now;
 	u8 status;
 
-	BT_DBG("%s", hdev->name);
+	bt_dev_dbg(hdev, "");
 
 	hci_req_sync(hdev, le_scan_restart, 0, HCI_CMD_TIMEOUT, &status);
 	if (status) {
@@ -2906,14 +3095,16 @@ static int active_scan(struct hci_request *req, unsigned long opt)
 	bool addr_resolv = false;
 	int err;
 
-	BT_DBG("%s", hdev->name);
+	bt_dev_dbg(hdev, "");
 
 	/* If controller is scanning, it means the background scanning is
 	 * running. Thus, we should temporarily stop it in order to set the
 	 * discovery scanning parameters.
 	 */
-	if (hci_dev_test_flag(hdev, HCI_LE_SCAN))
+	if (hci_dev_test_flag(hdev, HCI_LE_SCAN)) {
 		hci_req_add_le_scan_disable(req, false);
+		cancel_interleave_scan(hdev);
+	}
 
 	/* All active scans will be done with either a resolvable private
 	 * address (when privacy feature has been enabled) or non-resolvable
@@ -2934,7 +3125,7 @@ static int interleaved_discov(struct hci_request *req, unsigned long opt)
 {
 	int err;
 
-	BT_DBG("%s", req->hdev->name);
+	bt_dev_dbg(req->hdev, "");
 
 	err = active_scan(req, opt);
 	if (err)
@@ -2947,7 +3138,7 @@ static void start_discovery(struct hci_dev *hdev, u8 *status)
 {
 	unsigned long timeout;
 
-	BT_DBG("%s type %u", hdev->name, hdev->discovery.type);
+	bt_dev_dbg(hdev, "type %u", hdev->discovery.type);
 
 	switch (hdev->discovery.type) {
 	case DISCOV_TYPE_BREDR:
@@ -2995,7 +3186,7 @@ static void start_discovery(struct hci_dev *hdev, u8 *status)
 	if (*status)
 		return;
 
-	BT_DBG("%s timeout %u ms", hdev->name, jiffies_to_msecs(timeout));
+	bt_dev_dbg(hdev, "timeout %u ms", jiffies_to_msecs(timeout));
 
 	/* When service discovery is used and the controller has a
 	 * strict duplicate filter, it is important to remember the
@@ -3020,7 +3211,7 @@ bool hci_req_stop_discovery(struct hci_request *req)
 	struct inquiry_entry *e;
 	bool ret = false;
 
-	BT_DBG("%s state %u", hdev->name, hdev->discovery.state);
+	bt_dev_dbg(hdev, "state %u", hdev->discovery.state);
 
 	if (d->state == DISCOVERY_FINDING || d->state == DISCOVERY_STOPPING) {
 		if (test_bit(HCI_INQUIRY, &hdev->flags))
@@ -3100,7 +3291,7 @@ static void discov_off(struct work_struct *work)
 	struct hci_dev *hdev = container_of(work, struct hci_dev,
 					    discov_off.work);
 
-	BT_DBG("%s", hdev->name);
+	bt_dev_dbg(hdev, "");
 
 	hci_dev_lock(hdev);
 
@@ -3239,6 +3430,7 @@ void hci_request_setup(struct hci_dev *hdev)
 	INIT_DELAYED_WORK(&hdev->le_scan_disable, le_scan_disable_work);
 	INIT_DELAYED_WORK(&hdev->le_scan_restart, le_scan_restart_work);
 	INIT_DELAYED_WORK(&hdev->adv_instance_expire, adv_timeout_expire);
+	INIT_DELAYED_WORK(&hdev->interleave_scan, interleave_scan_work);
 }
 
 void hci_request_cancel_all(struct hci_dev *hdev)
@@ -3258,4 +3450,6 @@ void hci_request_cancel_all(struct hci_dev *hdev)
 		cancel_delayed_work_sync(&hdev->adv_instance_expire);
 		hdev->adv_instance_timeout = 0;
 	}
+
+	cancel_interleave_scan(hdev);
 }
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index 6a12e84c66c4..39ee8a18087a 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -71,6 +71,8 @@ void hci_req_add_le_passive_scan(struct hci_request *req);
 void hci_req_prepare_suspend(struct hci_dev *hdev, enum suspended_state next);
 
 void hci_req_disable_address_resolution(struct hci_dev *hdev);
+void __hci_req_pause_adv_instances(struct hci_request *req);
+int hci_req_resume_adv_instances(struct hci_dev *hdev);
 void hci_req_reenable_advertising(struct hci_dev *hdev);
 void __hci_req_enable_advertising(struct hci_request *req);
 void __hci_req_disable_advertising(struct hci_request *req);
diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 3b4fa27a44e6..0db48c812662 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -1290,7 +1290,7 @@ static int hidp_session_thread(void *arg)
 
 	/* cleanup runtime environment */
 	remove_wait_queue(sk_sleep(session->intr_sock->sk), &intr_wait);
-	remove_wait_queue(sk_sleep(session->intr_sock->sk), &ctrl_wait);
+	remove_wait_queue(sk_sleep(session->ctrl_sock->sk), &ctrl_wait);
 	wake_up_interruptible(&session->report_queue);
 	hidp_del_timer(session);
 
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index ade83e224567..17b87b57a175 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1515,8 +1515,14 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon)
 	 * that have no key size requirements. Ensure that the link is
 	 * actually encrypted before enforcing a key size.
 	 */
+	int min_key_size = hcon->hdev->min_enc_key_size;
+
+	/* On FIPS security level, key size must be 16 bytes */
+	if (hcon->sec_level == BT_SECURITY_FIPS)
+		min_key_size = 16;
+
 	return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) ||
-		hcon->enc_key_size >= hcon->hdev->min_enc_key_size);
+		hcon->enc_key_size >= min_key_size);
 }
 
 static void l2cap_do_start(struct l2cap_chan *chan)
@@ -3627,7 +3633,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data, size_t data
 			if (hint)
 				break;
 			result = L2CAP_CONF_UNKNOWN;
-			*((u8 *) ptr++) = type;
+			l2cap_add_conf_opt(&ptr, (u8)type, sizeof(u8), type, endptr - ptr);
 			break;
 		}
 	}
@@ -7301,9 +7307,10 @@ static int l2cap_data_rcv(struct l2cap_chan *chan, struct sk_buff *skb)
 		goto drop;
 	}
 
-	if ((chan->mode == L2CAP_MODE_ERTM ||
-	     chan->mode == L2CAP_MODE_STREAMING) && sk_filter(chan->data, skb))
-		goto drop;
+	if (chan->ops->filter) {
+		if (chan->ops->filter(chan, skb))
+			goto drop;
+	}
 
 	if (!control->sframe) {
 		int err;
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index e1a3e66b1754..f1b1edd0b697 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1521,8 +1521,6 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err)
 
 	parent = bt_sk(sk)->parent;
 
-	sock_set_flag(sk, SOCK_ZAPPED);
-
 	switch (chan->state) {
 	case BT_OPEN:
 	case BT_BOUND:
@@ -1549,8 +1547,11 @@ static void l2cap_sock_teardown_cb(struct l2cap_chan *chan, int err)
 
 		break;
 	}
-
 	release_sock(sk);
+
+	/* Only zap after cleanup to avoid use after free race */
+	sock_set_flag(sk, SOCK_ZAPPED);
+
 }
 
 static void l2cap_sock_state_change_cb(struct l2cap_chan *chan, int state,
@@ -1663,6 +1664,19 @@ static void l2cap_sock_suspend_cb(struct l2cap_chan *chan)
 	sk->sk_state_change(sk);
 }
 
+static int l2cap_sock_filter(struct l2cap_chan *chan, struct sk_buff *skb)
+{
+	struct sock *sk = chan->data;
+
+	switch (chan->mode) {
+	case L2CAP_MODE_ERTM:
+	case L2CAP_MODE_STREAMING:
+		return sk_filter(sk, skb);
+	}
+
+	return 0;
+}
+
 static const struct l2cap_ops l2cap_chan_ops = {
 	.name			= "L2CAP Socket Interface",
 	.new_connection		= l2cap_sock_new_connection_cb,
@@ -1678,6 +1692,7 @@ static const struct l2cap_ops l2cap_chan_ops = {
 	.get_sndtimeo		= l2cap_sock_get_sndtimeo_cb,
 	.get_peer_pid		= l2cap_sock_get_peer_pid_cb,
 	.alloc_skb		= l2cap_sock_alloc_skb_cb,
+	.filter			= l2cap_sock_filter,
 };
 
 static void l2cap_sock_destruct(struct sock *sk)
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 5bbe71002fb9..fa0f7a4a1d2f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -40,7 +40,7 @@
 #include "msft.h"
 
 #define MGMT_VERSION	1
-#define MGMT_REVISION	18
+#define MGMT_REVISION	19
 
 static const u16 mgmt_commands[] = {
 	MGMT_OP_READ_INDEX_LIST,
@@ -110,7 +110,7 @@ static const u16 mgmt_commands[] = {
 	MGMT_OP_SET_APPEARANCE,
 	MGMT_OP_SET_BLOCKED_KEYS,
 	MGMT_OP_SET_WIDEBAND_SPEECH,
-	MGMT_OP_READ_SECURITY_INFO,
+	MGMT_OP_READ_CONTROLLER_CAP,
 	MGMT_OP_READ_EXP_FEATURES_INFO,
 	MGMT_OP_SET_EXP_FEATURE,
 	MGMT_OP_READ_DEF_SYSTEM_CONFIG,
@@ -122,6 +122,8 @@ static const u16 mgmt_commands[] = {
 	MGMT_OP_READ_ADV_MONITOR_FEATURES,
 	MGMT_OP_ADD_ADV_PATTERNS_MONITOR,
 	MGMT_OP_REMOVE_ADV_MONITOR,
+	MGMT_OP_ADD_EXT_ADV_PARAMS,
+	MGMT_OP_ADD_EXT_ADV_DATA,
 };
 
 static const u16 mgmt_events[] = {
@@ -163,6 +165,8 @@ static const u16 mgmt_events[] = {
 	MGMT_EV_PHY_CONFIGURATION_CHANGED,
 	MGMT_EV_EXP_FEATURE_CHANGED,
 	MGMT_EV_DEVICE_FLAGS_CHANGED,
+	MGMT_EV_CONTROLLER_SUSPEND,
+	MGMT_EV_CONTROLLER_RESUME,
 };
 
 static const u16 mgmt_untrusted_commands[] = {
@@ -172,7 +176,7 @@ static const u16 mgmt_untrusted_commands[] = {
 	MGMT_OP_READ_CONFIG_INFO,
 	MGMT_OP_READ_EXT_INDEX_LIST,
 	MGMT_OP_READ_EXT_INFO,
-	MGMT_OP_READ_SECURITY_INFO,
+	MGMT_OP_READ_CONTROLLER_CAP,
 	MGMT_OP_READ_EXP_FEATURES_INFO,
 	MGMT_OP_READ_DEF_SYSTEM_CONFIG,
 	MGMT_OP_READ_DEF_RUNTIME_CONFIG,
@@ -782,7 +786,8 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 
 		if (lmp_ssp_capable(hdev)) {
 			settings |= MGMT_SETTING_SSP;
-			settings |= MGMT_SETTING_HS;
+			if (IS_ENABLED(CONFIG_BT_HS))
+				settings |= MGMT_SETTING_HS;
 		}
 
 		if (lmp_sc_capable(hdev))
@@ -1815,6 +1820,10 @@ static int set_hs(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 
 	bt_dev_dbg(hdev, "sock %p", sk);
 
+	if (!IS_ENABLED(CONFIG_BT_HS))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS,
+				       MGMT_STATUS_NOT_SUPPORTED);
+
 	status = mgmt_bredr_support(hdev);
 	if (status)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_HS, status);
@@ -3380,7 +3389,7 @@ static int set_appearance(struct sock *sk, struct hci_dev *hdev, void *data,
 static int get_phy_configuration(struct sock *sk, struct hci_dev *hdev,
 				 void *data, u16 len)
 {
-	struct mgmt_rp_get_phy_confguration rp;
+	struct mgmt_rp_get_phy_configuration rp;
 
 	bt_dev_dbg(hdev, "sock %p", sk);
 
@@ -3444,7 +3453,7 @@ unlock:
 static int set_phy_configuration(struct sock *sk, struct hci_dev *hdev,
 				 void *data, u16 len)
 {
-	struct mgmt_cp_set_phy_confguration *cp = data;
+	struct mgmt_cp_set_phy_configuration *cp = data;
 	struct hci_cp_le_set_default_phy cp_phy;
 	struct mgmt_pending_cmd *cmd;
 	struct hci_request req;
@@ -3701,13 +3710,14 @@ unlock:
 	return err;
 }
 
-static int read_security_info(struct sock *sk, struct hci_dev *hdev,
-			      void *data, u16 data_len)
+static int read_controller_cap(struct sock *sk, struct hci_dev *hdev,
+			       void *data, u16 data_len)
 {
-	char buf[16];
-	struct mgmt_rp_read_security_info *rp = (void *)buf;
-	u16 sec_len = 0;
+	char buf[20];
+	struct mgmt_rp_read_controller_cap *rp = (void *)buf;
+	u16 cap_len = 0;
 	u8 flags = 0;
+	u8 tx_power_range[2];
 
 	bt_dev_dbg(hdev, "sock %p", sk);
 
@@ -3731,23 +3741,37 @@ static int read_security_info(struct sock *sk, struct hci_dev *hdev,
 
 	flags |= 0x08;		/* Encryption key size enforcement (LE) */
 
-	sec_len = eir_append_data(rp->sec, sec_len, 0x01, &flags, 1);
+	cap_len = eir_append_data(rp->cap, cap_len, MGMT_CAP_SEC_FLAGS,
+				  &flags, 1);
 
 	/* When the Read Simple Pairing Options command is supported, then
 	 * also max encryption key size information is provided.
 	 */
 	if (hdev->commands[41] & 0x08)
-		sec_len = eir_append_le16(rp->sec, sec_len, 0x02,
+		cap_len = eir_append_le16(rp->cap, cap_len,
+					  MGMT_CAP_MAX_ENC_KEY_SIZE,
 					  hdev->max_enc_key_size);
 
-	sec_len = eir_append_le16(rp->sec, sec_len, 0x03, SMP_MAX_ENC_KEY_SIZE);
+	cap_len = eir_append_le16(rp->cap, cap_len,
+				  MGMT_CAP_SMP_MAX_ENC_KEY_SIZE,
+				  SMP_MAX_ENC_KEY_SIZE);
+
+	/* Append the min/max LE tx power parameters if we were able to fetch
+	 * it from the controller
+	 */
+	if (hdev->commands[38] & 0x80) {
+		memcpy(&tx_power_range[0], &hdev->min_le_tx_power, 1);
+		memcpy(&tx_power_range[1], &hdev->max_le_tx_power, 1);
+		cap_len = eir_append_data(rp->cap, cap_len, MGMT_CAP_LE_TX_PWR,
+					  tx_power_range, 2);
+	}
 
-	rp->sec_len = cpu_to_le16(sec_len);
+	rp->cap_len = cpu_to_le16(cap_len);
 
 	hci_dev_unlock(hdev);
 
-	return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_SECURITY_INFO, 0,
-				 rp, sizeof(*rp) + sec_len);
+	return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_READ_CONTROLLER_CAP, 0,
+				 rp, sizeof(*rp) + cap_len);
 }
 
 #ifdef CONFIG_BT_FEATURE_DEBUG
@@ -4157,7 +4181,7 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev,
 {
 	struct adv_monitor *monitor = NULL;
 	struct mgmt_rp_read_adv_monitor_features *rp = NULL;
-	int handle;
+	int handle, err;
 	size_t rp_size = 0;
 	__u32 supported = 0;
 	__u16 num_handles = 0;
@@ -4192,9 +4216,13 @@ static int read_adv_mon_features(struct sock *sk, struct hci_dev *hdev,
 	if (num_handles)
 		memcpy(&rp->handles, &handles, (num_handles * sizeof(u16)));
 
-	return mgmt_cmd_complete(sk, hdev->id,
-				 MGMT_OP_READ_ADV_MONITOR_FEATURES,
-				 MGMT_STATUS_SUCCESS, rp, rp_size);
+	err = mgmt_cmd_complete(sk, hdev->id,
+				MGMT_OP_READ_ADV_MONITOR_FEATURES,
+				MGMT_STATUS_SUCCESS, rp, rp_size);
+
+	kfree(rp);
+
+	return err;
 }
 
 static int add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev,
@@ -7192,6 +7220,10 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev)
 	flags |= MGMT_ADV_FLAG_MANAGED_FLAGS;
 	flags |= MGMT_ADV_FLAG_APPEARANCE;
 	flags |= MGMT_ADV_FLAG_LOCAL_NAME;
+	flags |= MGMT_ADV_PARAM_DURATION;
+	flags |= MGMT_ADV_PARAM_TIMEOUT;
+	flags |= MGMT_ADV_PARAM_INTERVALS;
+	flags |= MGMT_ADV_PARAM_TX_POWER;
 
 	/* In extended adv TX_POWER returned from Set Adv Param
 	 * will be always valid.
@@ -7202,6 +7234,8 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev)
 
 	if (ext_adv_capable(hdev)) {
 		flags |= MGMT_ADV_FLAG_SEC_1M;
+		flags |= MGMT_ADV_FLAG_HW_OFFLOAD;
+		flags |= MGMT_ADV_FLAG_CAN_SET_TX_POWER;
 
 		if (hdev->le_features[1] & HCI_LE_PHY_2M)
 			flags |= MGMT_ADV_FLAG_SEC_2M;
@@ -7250,7 +7284,7 @@ static int read_adv_features(struct sock *sk, struct hci_dev *hdev,
 	rp->supported_flags = cpu_to_le32(supported_flags);
 	rp->max_adv_data_len = HCI_MAX_AD_LENGTH;
 	rp->max_scan_rsp_len = HCI_MAX_AD_LENGTH;
-	rp->max_instances = HCI_MAX_ADV_INSTANCES;
+	rp->max_instances = hdev->le_num_of_adv_sets;
 	rp->num_instances = hdev->adv_instance_cnt;
 
 	instance = rp->instance;
@@ -7364,6 +7398,31 @@ static bool tlv_data_is_valid(struct hci_dev *hdev, u32 adv_flags, u8 *data,
 	return true;
 }
 
+static bool requested_adv_flags_are_valid(struct hci_dev *hdev, u32 adv_flags)
+{
+	u32 supported_flags, phy_flags;
+
+	/* The current implementation only supports a subset of the specified
+	 * flags. Also need to check mutual exclusiveness of sec flags.
+	 */
+	supported_flags = get_supported_adv_flags(hdev);
+	phy_flags = adv_flags & MGMT_ADV_FLAG_SEC_MASK;
+	if (adv_flags & ~supported_flags ||
+	    ((phy_flags && (phy_flags ^ (phy_flags & -phy_flags)))))
+		return false;
+
+	return true;
+}
+
+static bool adv_busy(struct hci_dev *hdev)
+{
+	return (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) ||
+		pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) ||
+		pending_find(MGMT_OP_SET_LE, hdev) ||
+		pending_find(MGMT_OP_ADD_EXT_ADV_PARAMS, hdev) ||
+		pending_find(MGMT_OP_ADD_EXT_ADV_DATA, hdev));
+}
+
 static void add_advertising_complete(struct hci_dev *hdev, u8 status,
 				     u16 opcode)
 {
@@ -7378,6 +7437,8 @@ static void add_advertising_complete(struct hci_dev *hdev, u8 status,
 	hci_dev_lock(hdev);
 
 	cmd = pending_find(MGMT_OP_ADD_ADVERTISING, hdev);
+	if (!cmd)
+		cmd = pending_find(MGMT_OP_ADD_EXT_ADV_DATA, hdev);
 
 	list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) {
 		if (!adv_instance->pending)
@@ -7422,7 +7483,6 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 	struct mgmt_cp_add_advertising *cp = data;
 	struct mgmt_rp_add_advertising rp;
 	u32 flags;
-	u32 supported_flags, phy_flags;
 	u8 status;
 	u16 timeout, duration;
 	unsigned int prev_instance_cnt = hdev->adv_instance_cnt;
@@ -7446,7 +7506,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_SET_ADVERTISING,
 				       MGMT_STATUS_NOT_SUPPORTED);
 
-	if (cp->instance < 1 || cp->instance > HCI_MAX_ADV_INSTANCES)
+	if (cp->instance < 1 || cp->instance > hdev->le_num_of_adv_sets)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
 				       MGMT_STATUS_INVALID_PARAMS);
 
@@ -7458,13 +7518,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 	timeout = __le16_to_cpu(cp->timeout);
 	duration = __le16_to_cpu(cp->duration);
 
-	/* The current implementation only supports a subset of the specified
-	 * flags. Also need to check mutual exclusiveness of sec flags.
-	 */
-	supported_flags = get_supported_adv_flags(hdev);
-	phy_flags = flags & MGMT_ADV_FLAG_SEC_MASK;
-	if (flags & ~supported_flags ||
-	    ((phy_flags && (phy_flags ^ (phy_flags & -phy_flags)))))
+	if (!requested_adv_flags_are_valid(hdev, flags))
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
 				       MGMT_STATUS_INVALID_PARAMS);
 
@@ -7476,9 +7530,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 		goto unlock;
 	}
 
-	if (pending_find(MGMT_OP_ADD_ADVERTISING, hdev) ||
-	    pending_find(MGMT_OP_REMOVE_ADVERTISING, hdev) ||
-	    pending_find(MGMT_OP_SET_LE, hdev)) {
+	if (adv_busy(hdev)) {
 		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
 				      MGMT_STATUS_BUSY);
 		goto unlock;
@@ -7496,7 +7548,10 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 				   cp->adv_data_len, cp->data,
 				   cp->scan_rsp_len,
 				   cp->data + cp->adv_data_len,
-				   timeout, duration);
+				   timeout, duration,
+				   HCI_ADV_TX_POWER_NO_PREFERENCE,
+				   hdev->le_adv_min_interval,
+				   hdev->le_adv_max_interval);
 	if (err < 0) {
 		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
 				      MGMT_STATUS_FAILED);
@@ -7569,6 +7624,338 @@ unlock:
 	return err;
 }
 
+static void add_ext_adv_params_complete(struct hci_dev *hdev, u8 status,
+					u16 opcode)
+{
+	struct mgmt_pending_cmd *cmd;
+	struct mgmt_cp_add_ext_adv_params *cp;
+	struct mgmt_rp_add_ext_adv_params rp;
+	struct adv_info *adv_instance;
+	u32 flags;
+
+	BT_DBG("%s", hdev->name);
+
+	hci_dev_lock(hdev);
+
+	cmd = pending_find(MGMT_OP_ADD_EXT_ADV_PARAMS, hdev);
+	if (!cmd)
+		goto unlock;
+
+	cp = cmd->param;
+	adv_instance = hci_find_adv_instance(hdev, cp->instance);
+	if (!adv_instance)
+		goto unlock;
+
+	rp.instance = cp->instance;
+	rp.tx_power = adv_instance->tx_power;
+
+	/* While we're at it, inform userspace of the available space for this
+	 * advertisement, given the flags that will be used.
+	 */
+	flags = __le32_to_cpu(cp->flags);
+	rp.max_adv_data_len = tlv_data_max_len(hdev, flags, true);
+	rp.max_scan_rsp_len = tlv_data_max_len(hdev, flags, false);
+
+	if (status) {
+		/* If this advertisement was previously advertising and we
+		 * failed to update it, we signal that it has been removed and
+		 * delete its structure
+		 */
+		if (!adv_instance->pending)
+			mgmt_advertising_removed(cmd->sk, hdev, cp->instance);
+
+		hci_remove_adv_instance(hdev, cp->instance);
+
+		mgmt_cmd_status(cmd->sk, cmd->index, cmd->opcode,
+				mgmt_status(status));
+
+	} else {
+		mgmt_cmd_complete(cmd->sk, cmd->index, cmd->opcode,
+				  mgmt_status(status), &rp, sizeof(rp));
+	}
+
+unlock:
+	if (cmd)
+		mgmt_pending_remove(cmd);
+
+	hci_dev_unlock(hdev);
+}
+
+static int add_ext_adv_params(struct sock *sk, struct hci_dev *hdev,
+			      void *data, u16 data_len)
+{
+	struct mgmt_cp_add_ext_adv_params *cp = data;
+	struct mgmt_rp_add_ext_adv_params rp;
+	struct mgmt_pending_cmd *cmd = NULL;
+	struct adv_info *adv_instance;
+	struct hci_request req;
+	u32 flags, min_interval, max_interval;
+	u16 timeout, duration;
+	u8 status;
+	s8 tx_power;
+	int err;
+
+	BT_DBG("%s", hdev->name);
+
+	status = mgmt_le_support(hdev);
+	if (status)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_PARAMS,
+				       status);
+
+	if (cp->instance < 1 || cp->instance > hdev->le_num_of_adv_sets)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_PARAMS,
+				       MGMT_STATUS_INVALID_PARAMS);
+
+	/* The purpose of breaking add_advertising into two separate MGMT calls
+	 * for params and data is to allow more parameters to be added to this
+	 * structure in the future. For this reason, we verify that we have the
+	 * bare minimum structure we know of when the interface was defined. Any
+	 * extra parameters we don't know about will be ignored in this request.
+	 */
+	if (data_len < MGMT_ADD_EXT_ADV_PARAMS_MIN_SIZE)
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
+				       MGMT_STATUS_INVALID_PARAMS);
+
+	flags = __le32_to_cpu(cp->flags);
+
+	if (!requested_adv_flags_are_valid(hdev, flags))
+		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_PARAMS,
+				       MGMT_STATUS_INVALID_PARAMS);
+
+	hci_dev_lock(hdev);
+
+	/* In new interface, we require that we are powered to register */
+	if (!hdev_is_powered(hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_PARAMS,
+				      MGMT_STATUS_REJECTED);
+		goto unlock;
+	}
+
+	if (adv_busy(hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_PARAMS,
+				      MGMT_STATUS_BUSY);
+		goto unlock;
+	}
+
+	/* Parse defined parameters from request, use defaults otherwise */
+	timeout = (flags & MGMT_ADV_PARAM_TIMEOUT) ?
+		  __le16_to_cpu(cp->timeout) : 0;
+
+	duration = (flags & MGMT_ADV_PARAM_DURATION) ?
+		   __le16_to_cpu(cp->duration) :
+		   hdev->def_multi_adv_rotation_duration;
+
+	min_interval = (flags & MGMT_ADV_PARAM_INTERVALS) ?
+		       __le32_to_cpu(cp->min_interval) :
+		       hdev->le_adv_min_interval;
+
+	max_interval = (flags & MGMT_ADV_PARAM_INTERVALS) ?
+		       __le32_to_cpu(cp->max_interval) :
+		       hdev->le_adv_max_interval;
+
+	tx_power = (flags & MGMT_ADV_PARAM_TX_POWER) ?
+		   cp->tx_power :
+		   HCI_ADV_TX_POWER_NO_PREFERENCE;
+
+	/* Create advertising instance with no advertising or response data */
+	err = hci_add_adv_instance(hdev, cp->instance, flags,
+				   0, NULL, 0, NULL, timeout, duration,
+				   tx_power, min_interval, max_interval);
+
+	if (err < 0) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_PARAMS,
+				      MGMT_STATUS_FAILED);
+		goto unlock;
+	}
+
+	hdev->cur_adv_instance = cp->instance;
+	/* Submit request for advertising params if ext adv available */
+	if (ext_adv_capable(hdev)) {
+		hci_req_init(&req, hdev);
+		adv_instance = hci_find_adv_instance(hdev, cp->instance);
+
+		/* Updating parameters of an active instance will return a
+		 * Command Disallowed error, so we must first disable the
+		 * instance if it is active.
+		 */
+		if (!adv_instance->pending)
+			__hci_req_disable_ext_adv_instance(&req, cp->instance);
+
+		__hci_req_setup_ext_adv_instance(&req, cp->instance);
+
+		err = hci_req_run(&req, add_ext_adv_params_complete);
+
+		if (!err)
+			cmd = mgmt_pending_add(sk, MGMT_OP_ADD_EXT_ADV_PARAMS,
+					       hdev, data, data_len);
+		if (!cmd) {
+			err = -ENOMEM;
+			hci_remove_adv_instance(hdev, cp->instance);
+			goto unlock;
+		}
+
+	} else {
+		rp.instance = cp->instance;
+		rp.tx_power = HCI_ADV_TX_POWER_NO_PREFERENCE;
+		rp.max_adv_data_len = tlv_data_max_len(hdev, flags, true);
+		rp.max_scan_rsp_len = tlv_data_max_len(hdev, flags, false);
+		err = mgmt_cmd_complete(sk, hdev->id,
+					MGMT_OP_ADD_EXT_ADV_PARAMS,
+					MGMT_STATUS_SUCCESS, &rp, sizeof(rp));
+	}
+
+unlock:
+	hci_dev_unlock(hdev);
+
+	return err;
+}
+
+static int add_ext_adv_data(struct sock *sk, struct hci_dev *hdev, void *data,
+			    u16 data_len)
+{
+	struct mgmt_cp_add_ext_adv_data *cp = data;
+	struct mgmt_rp_add_ext_adv_data rp;
+	u8 schedule_instance = 0;
+	struct adv_info *next_instance;
+	struct adv_info *adv_instance;
+	int err = 0;
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
+
+	BT_DBG("%s", hdev->name);
+
+	hci_dev_lock(hdev);
+
+	adv_instance = hci_find_adv_instance(hdev, cp->instance);
+
+	if (!adv_instance) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_DATA,
+				      MGMT_STATUS_INVALID_PARAMS);
+		goto unlock;
+	}
+
+	/* In new interface, we require that we are powered to register */
+	if (!hdev_is_powered(hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_DATA,
+				      MGMT_STATUS_REJECTED);
+		goto clear_new_instance;
+	}
+
+	if (adv_busy(hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_DATA,
+				      MGMT_STATUS_BUSY);
+		goto clear_new_instance;
+	}
+
+	/* Validate new data */
+	if (!tlv_data_is_valid(hdev, adv_instance->flags, cp->data,
+			       cp->adv_data_len, true) ||
+	    !tlv_data_is_valid(hdev, adv_instance->flags, cp->data +
+			       cp->adv_data_len, cp->scan_rsp_len, false)) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_DATA,
+				      MGMT_STATUS_INVALID_PARAMS);
+		goto clear_new_instance;
+	}
+
+	/* Set the data in the advertising instance */
+	hci_set_adv_instance_data(hdev, cp->instance, cp->adv_data_len,
+				  cp->data, cp->scan_rsp_len,
+				  cp->data + cp->adv_data_len);
+
+	/* We're good to go, update advertising data, parameters, and start
+	 * advertising.
+	 */
+
+	hci_req_init(&req, hdev);
+
+	hci_req_add(&req, HCI_OP_READ_LOCAL_NAME, 0, NULL);
+
+	if (ext_adv_capable(hdev)) {
+		__hci_req_update_adv_data(&req, cp->instance);
+		__hci_req_update_scan_rsp_data(&req, cp->instance);
+		__hci_req_enable_ext_advertising(&req, cp->instance);
+
+	} else {
+		/* If using software rotation, determine next instance to use */
+
+		if (hdev->cur_adv_instance == cp->instance) {
+			/* If the currently advertised instance is being changed
+			 * then cancel the current advertising and schedule the
+			 * next instance. If there is only one instance then the
+			 * overridden advertising data will be visible right
+			 * away
+			 */
+			cancel_adv_timeout(hdev);
+
+			next_instance = hci_get_next_instance(hdev,
+							      cp->instance);
+			if (next_instance)
+				schedule_instance = next_instance->instance;
+		} else if (!hdev->adv_instance_timeout) {
+			/* Immediately advertise the new instance if no other
+			 * instance is currently being advertised.
+			 */
+			schedule_instance = cp->instance;
+		}
+
+		/* If the HCI_ADVERTISING flag is set or there is no instance to
+		 * be advertised then we have no HCI communication to make.
+		 * Simply return.
+		 */
+		if (hci_dev_test_flag(hdev, HCI_ADVERTISING) ||
+		    !schedule_instance) {
+			if (adv_instance->pending) {
+				mgmt_advertising_added(sk, hdev, cp->instance);
+				adv_instance->pending = false;
+			}
+			rp.instance = cp->instance;
+			err = mgmt_cmd_complete(sk, hdev->id,
+						MGMT_OP_ADD_EXT_ADV_DATA,
+						MGMT_STATUS_SUCCESS, &rp,
+						sizeof(rp));
+			goto unlock;
+		}
+
+		err = __hci_req_schedule_adv_instance(&req, schedule_instance,
+						      true);
+	}
+
+	cmd = mgmt_pending_add(sk, MGMT_OP_ADD_EXT_ADV_DATA, hdev, data,
+			       data_len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto clear_new_instance;
+	}
+
+	if (!err)
+		err = hci_req_run(&req, add_advertising_complete);
+
+	if (err < 0) {
+		err = mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_EXT_ADV_DATA,
+				      MGMT_STATUS_FAILED);
+		mgmt_pending_remove(cmd);
+		goto clear_new_instance;
+	}
+
+	/* We were successful in updating data, so trigger advertising_added
+	 * event if this is an instance that wasn't previously advertising. If
+	 * a failure occurs in the requests we initiated, we will remove the
+	 * instance again in add_advertising_complete
+	 */
+	if (adv_instance->pending)
+		mgmt_advertising_added(sk, hdev, cp->instance);
+
+	goto unlock;
+
+clear_new_instance:
+	hci_remove_adv_instance(hdev, cp->instance);
+
+unlock:
+	hci_dev_unlock(hdev);
+
+	return err;
+}
+
 static void remove_advertising_complete(struct hci_dev *hdev, u8 status,
 					u16 opcode)
 {
@@ -7699,7 +8086,7 @@ static int get_adv_size_info(struct sock *sk, struct hci_dev *hdev,
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_GET_ADV_SIZE_INFO,
 				       MGMT_STATUS_REJECTED);
 
-	if (cp->instance < 1 || cp->instance > HCI_MAX_ADV_INSTANCES)
+	if (cp->instance < 1 || cp->instance > hdev->le_num_of_adv_sets)
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_GET_ADV_SIZE_INFO,
 				       MGMT_STATUS_INVALID_PARAMS);
 
@@ -7821,7 +8208,7 @@ static const struct hci_mgmt_handler mgmt_handlers[] = {
 	{ set_blocked_keys,	   MGMT_OP_SET_BLOCKED_KEYS_SIZE,
 						HCI_MGMT_VAR_LEN },
 	{ set_wideband_speech,	   MGMT_SETTING_SIZE },
-	{ read_security_info,      MGMT_READ_SECURITY_INFO_SIZE,
+	{ read_controller_cap,     MGMT_READ_CONTROLLER_CAP_SIZE,
 						HCI_MGMT_UNTRUSTED },
 	{ read_exp_features_info,  MGMT_READ_EXP_FEATURES_INFO_SIZE,
 						HCI_MGMT_UNTRUSTED |
@@ -7843,6 +8230,10 @@ static const struct hci_mgmt_handler mgmt_handlers[] = {
 	{ add_adv_patterns_monitor,MGMT_ADD_ADV_PATTERNS_MONITOR_SIZE,
 						HCI_MGMT_VAR_LEN },
 	{ remove_adv_monitor,      MGMT_REMOVE_ADV_MONITOR_SIZE },
+	{ add_ext_adv_params,      MGMT_ADD_EXT_ADV_PARAMS_MIN_SIZE,
+						HCI_MGMT_VAR_LEN },
+	{ add_ext_adv_data,        MGMT_ADD_EXT_ADV_DATA_SIZE,
+						HCI_MGMT_VAR_LEN },
 };
 
 void mgmt_index_added(struct hci_dev *hdev)
@@ -8262,6 +8653,10 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	ev.addr.type = link_to_bdaddr(link_type, addr_type);
 	ev.reason = reason;
 
+	/* Report disconnects due to suspend */
+	if (hdev->suspended)
+		ev.reason = MGMT_DEV_DISCONN_LOCAL_HOST_SUSPEND;
+
 	mgmt_event(MGMT_EV_DEVICE_DISCONNECTED, hdev, &ev, sizeof(ev), sk);
 
 	if (sk)
@@ -8868,6 +9263,30 @@ void mgmt_discovering(struct hci_dev *hdev, u8 discovering)
 	mgmt_event(MGMT_EV_DISCOVERING, hdev, &ev, sizeof(ev), NULL);
 }
 
+void mgmt_suspending(struct hci_dev *hdev, u8 state)
+{
+	struct mgmt_ev_controller_suspend ev;
+
+	ev.suspend_state = state;
+	mgmt_event(MGMT_EV_CONTROLLER_SUSPEND, hdev, &ev, sizeof(ev), NULL);
+}
+
+void mgmt_resuming(struct hci_dev *hdev, u8 reason, bdaddr_t *bdaddr,
+		   u8 addr_type)
+{
+	struct mgmt_ev_controller_resume ev;
+
+	ev.wake_reason = reason;
+	if (bdaddr) {
+		bacpy(&ev.addr.bdaddr, bdaddr);
+		ev.addr.type = addr_type;
+	} else {
+		memset(&ev.addr, 0, sizeof(ev.addr));
+	}
+
+	mgmt_event(MGMT_EV_CONTROLLER_RESUME, hdev, &ev, sizeof(ev), NULL);
+}
+
 static struct hci_mgmt_chan chan = {
 	.channel	= HCI_CHANNEL_CONTROL,
 	.handler_count	= ARRAY_SIZE(mgmt_handlers),
diff --git a/net/bluetooth/mgmt_config.c b/net/bluetooth/mgmt_config.c
index b30b571f8caf..1deb0ca7a929 100644
--- a/net/bluetooth/mgmt_config.c
+++ b/net/bluetooth/mgmt_config.c
@@ -11,74 +11,119 @@
 #include "mgmt_util.h"
 #include "mgmt_config.h"
 
-#define HDEV_PARAM_U16(_param_code_, _param_name_) \
-{ \
-	{ cpu_to_le16(_param_code_), sizeof(__u16) }, \
-	{ cpu_to_le16(hdev->_param_name_) } \
-}
+#define HDEV_PARAM_U16(_param_name_) \
+	struct {\
+		struct mgmt_tlv entry; \
+		__le16 value; \
+	} __packed _param_name_
 
-#define HDEV_PARAM_U16_JIFFIES_TO_MSECS(_param_code_, _param_name_) \
-{ \
-	{ cpu_to_le16(_param_code_), sizeof(__u16) }, \
-	{ cpu_to_le16(jiffies_to_msecs(hdev->_param_name_)) } \
-}
+#define HDEV_PARAM_U8(_param_name_) \
+	struct {\
+		struct mgmt_tlv entry; \
+		__u8 value; \
+	} __packed _param_name_
+
+#define TLV_SET_U16(_param_code_, _param_name_) \
+	{ \
+		{ cpu_to_le16(_param_code_), sizeof(__u16) }, \
+		cpu_to_le16(hdev->_param_name_) \
+	}
+
+#define TLV_SET_U8(_param_code_, _param_name_) \
+	{ \
+		{ cpu_to_le16(_param_code_), sizeof(__u8) }, \
+		hdev->_param_name_ \
+	}
+
+#define TLV_SET_U16_JIFFIES_TO_MSECS(_param_code_, _param_name_) \
+	{ \
+		{ cpu_to_le16(_param_code_), sizeof(__u16) }, \
+		cpu_to_le16(jiffies_to_msecs(hdev->_param_name_)) \
+	}
 
 int read_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data,
 			   u16 data_len)
 {
-	struct {
-		struct mgmt_tlv entry;
-		union {
-			/* This is a simplification for now since all values
-			 * are 16 bits.  In the future, this code may need
-			 * refactoring to account for variable length values
-			 * and properly calculate the required buffer size.
-			 */
-			__le16 value;
-		};
-	} __packed params[] = {
+	int ret;
+	struct mgmt_rp_read_def_system_config {
 		/* Please see mgmt-api.txt for documentation of these values */
-		HDEV_PARAM_U16(0x0000, def_page_scan_type),
-		HDEV_PARAM_U16(0x0001, def_page_scan_int),
-		HDEV_PARAM_U16(0x0002, def_page_scan_window),
-		HDEV_PARAM_U16(0x0003, def_inq_scan_type),
-		HDEV_PARAM_U16(0x0004, def_inq_scan_int),
-		HDEV_PARAM_U16(0x0005, def_inq_scan_window),
-		HDEV_PARAM_U16(0x0006, def_br_lsto),
-		HDEV_PARAM_U16(0x0007, def_page_timeout),
-		HDEV_PARAM_U16(0x0008, sniff_min_interval),
-		HDEV_PARAM_U16(0x0009, sniff_max_interval),
-		HDEV_PARAM_U16(0x000a, le_adv_min_interval),
-		HDEV_PARAM_U16(0x000b, le_adv_max_interval),
-		HDEV_PARAM_U16(0x000c, def_multi_adv_rotation_duration),
-		HDEV_PARAM_U16(0x000d, le_scan_interval),
-		HDEV_PARAM_U16(0x000e, le_scan_window),
-		HDEV_PARAM_U16(0x000f, le_scan_int_suspend),
-		HDEV_PARAM_U16(0x0010, le_scan_window_suspend),
-		HDEV_PARAM_U16(0x0011, le_scan_int_discovery),
-		HDEV_PARAM_U16(0x0012, le_scan_window_discovery),
-		HDEV_PARAM_U16(0x0013, le_scan_int_adv_monitor),
-		HDEV_PARAM_U16(0x0014, le_scan_window_adv_monitor),
-		HDEV_PARAM_U16(0x0015, le_scan_int_connect),
-		HDEV_PARAM_U16(0x0016, le_scan_window_connect),
-		HDEV_PARAM_U16(0x0017, le_conn_min_interval),
-		HDEV_PARAM_U16(0x0018, le_conn_max_interval),
-		HDEV_PARAM_U16(0x0019, le_conn_latency),
-		HDEV_PARAM_U16(0x001a, le_supv_timeout),
-		HDEV_PARAM_U16_JIFFIES_TO_MSECS(0x001b,
-						def_le_autoconnect_timeout),
+		HDEV_PARAM_U16(def_page_scan_type);
+		HDEV_PARAM_U16(def_page_scan_int);
+		HDEV_PARAM_U16(def_page_scan_window);
+		HDEV_PARAM_U16(def_inq_scan_type);
+		HDEV_PARAM_U16(def_inq_scan_int);
+		HDEV_PARAM_U16(def_inq_scan_window);
+		HDEV_PARAM_U16(def_br_lsto);
+		HDEV_PARAM_U16(def_page_timeout);
+		HDEV_PARAM_U16(sniff_min_interval);
+		HDEV_PARAM_U16(sniff_max_interval);
+		HDEV_PARAM_U16(le_adv_min_interval);
+		HDEV_PARAM_U16(le_adv_max_interval);
+		HDEV_PARAM_U16(def_multi_adv_rotation_duration);
+		HDEV_PARAM_U16(le_scan_interval);
+		HDEV_PARAM_U16(le_scan_window);
+		HDEV_PARAM_U16(le_scan_int_suspend);
+		HDEV_PARAM_U16(le_scan_window_suspend);
+		HDEV_PARAM_U16(le_scan_int_discovery);
+		HDEV_PARAM_U16(le_scan_window_discovery);
+		HDEV_PARAM_U16(le_scan_int_adv_monitor);
+		HDEV_PARAM_U16(le_scan_window_adv_monitor);
+		HDEV_PARAM_U16(le_scan_int_connect);
+		HDEV_PARAM_U16(le_scan_window_connect);
+		HDEV_PARAM_U16(le_conn_min_interval);
+		HDEV_PARAM_U16(le_conn_max_interval);
+		HDEV_PARAM_U16(le_conn_latency);
+		HDEV_PARAM_U16(le_supv_timeout);
+		HDEV_PARAM_U16(def_le_autoconnect_timeout);
+		HDEV_PARAM_U16(advmon_allowlist_duration);
+		HDEV_PARAM_U16(advmon_no_filter_duration);
+		HDEV_PARAM_U8(enable_advmon_interleave_scan);
+	} __packed rp = {
+		TLV_SET_U16(0x0000, def_page_scan_type),
+		TLV_SET_U16(0x0001, def_page_scan_int),
+		TLV_SET_U16(0x0002, def_page_scan_window),
+		TLV_SET_U16(0x0003, def_inq_scan_type),
+		TLV_SET_U16(0x0004, def_inq_scan_int),
+		TLV_SET_U16(0x0005, def_inq_scan_window),
+		TLV_SET_U16(0x0006, def_br_lsto),
+		TLV_SET_U16(0x0007, def_page_timeout),
+		TLV_SET_U16(0x0008, sniff_min_interval),
+		TLV_SET_U16(0x0009, sniff_max_interval),
+		TLV_SET_U16(0x000a, le_adv_min_interval),
+		TLV_SET_U16(0x000b, le_adv_max_interval),
+		TLV_SET_U16(0x000c, def_multi_adv_rotation_duration),
+		TLV_SET_U16(0x000d, le_scan_interval),
+		TLV_SET_U16(0x000e, le_scan_window),
+		TLV_SET_U16(0x000f, le_scan_int_suspend),
+		TLV_SET_U16(0x0010, le_scan_window_suspend),
+		TLV_SET_U16(0x0011, le_scan_int_discovery),
+		TLV_SET_U16(0x0012, le_scan_window_discovery),
+		TLV_SET_U16(0x0013, le_scan_int_adv_monitor),
+		TLV_SET_U16(0x0014, le_scan_window_adv_monitor),
+		TLV_SET_U16(0x0015, le_scan_int_connect),
+		TLV_SET_U16(0x0016, le_scan_window_connect),
+		TLV_SET_U16(0x0017, le_conn_min_interval),
+		TLV_SET_U16(0x0018, le_conn_max_interval),
+		TLV_SET_U16(0x0019, le_conn_latency),
+		TLV_SET_U16(0x001a, le_supv_timeout),
+		TLV_SET_U16_JIFFIES_TO_MSECS(0x001b,
+					     def_le_autoconnect_timeout),
+		TLV_SET_U16(0x001d, advmon_allowlist_duration),
+		TLV_SET_U16(0x001e, advmon_no_filter_duration),
+		TLV_SET_U8(0x001f, enable_advmon_interleave_scan),
 	};
-	struct mgmt_rp_read_def_system_config *rp = (void *)params;
 
 	bt_dev_dbg(hdev, "sock %p", sk);
 
-	return mgmt_cmd_complete(sk, hdev->id,
-				 MGMT_OP_READ_DEF_SYSTEM_CONFIG,
-				 0, rp, sizeof(params));
+	ret = mgmt_cmd_complete(sk, hdev->id,
+				MGMT_OP_READ_DEF_SYSTEM_CONFIG,
+				0, &rp, sizeof(rp));
+	return ret;
 }
 
 #define TO_TLV(x)		((struct mgmt_tlv *)(x))
 #define TLV_GET_LE16(tlv)	le16_to_cpu(*((__le16 *)(TO_TLV(tlv)->value)))
+#define TLV_GET_U8(tlv)		(*((__u8 *)(TO_TLV(tlv)->value)))
 
 int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data,
 			  u16 data_len)
@@ -95,6 +140,7 @@ int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data,
 	/* First pass to validate the tlv */
 	while (buffer_left >= sizeof(struct mgmt_tlv)) {
 		const u8 len = TO_TLV(buffer)->length;
+		size_t exp_type_len;
 		const u16 exp_len = sizeof(struct mgmt_tlv) +
 				    len;
 		const u16 type = le16_to_cpu(TO_TLV(buffer)->type);
@@ -138,20 +184,28 @@ int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data,
 		case 0x0019:
 		case 0x001a:
 		case 0x001b:
-			if (len != sizeof(u16)) {
-				bt_dev_warn(hdev, "invalid length %d, exp %zu for type %d",
-					    len, sizeof(u16), type);
-
-				return mgmt_cmd_status(sk, hdev->id,
-					MGMT_OP_SET_DEF_SYSTEM_CONFIG,
-					MGMT_STATUS_INVALID_PARAMS);
-			}
+		case 0x001d:
+		case 0x001e:
+			exp_type_len = sizeof(u16);
+			break;
+		case 0x001f:
+			exp_type_len = sizeof(u8);
 			break;
 		default:
+			exp_type_len = 0;
 			bt_dev_warn(hdev, "unsupported parameter %u", type);
 			break;
 		}
 
+		if (exp_type_len && len != exp_type_len) {
+			bt_dev_warn(hdev, "invalid length %d, exp %zu for type %d",
+				    len, exp_type_len, type);
+
+			return mgmt_cmd_status(sk, hdev->id,
+				MGMT_OP_SET_DEF_SYSTEM_CONFIG,
+				MGMT_STATUS_INVALID_PARAMS);
+		}
+
 		buffer_left -= exp_len;
 		buffer += exp_len;
 	}
@@ -251,6 +305,15 @@ int set_def_system_config(struct sock *sk, struct hci_dev *hdev, void *data,
 			hdev->def_le_autoconnect_timeout =
 					msecs_to_jiffies(TLV_GET_LE16(buffer));
 			break;
+		case 0x0001d:
+			hdev->advmon_allowlist_duration = TLV_GET_LE16(buffer);
+			break;
+		case 0x0001e:
+			hdev->advmon_no_filter_duration = TLV_GET_LE16(buffer);
+			break;
+		case 0x0001f:
+			hdev->enable_advmon_interleave_scan = TLV_GET_U8(buffer);
+			break;
 		default:
 			bt_dev_warn(hdev, "unsupported parameter %u", type);
 			break;
diff --git a/net/bluetooth/msft.c b/net/bluetooth/msft.c
index 8579bfeb2836..4b39534a14a1 100644
--- a/net/bluetooth/msft.c
+++ b/net/bluetooth/msft.c
@@ -12,12 +12,13 @@
 struct msft_cp_read_supported_features {
 	__u8   sub_opcode;
 } __packed;
+
 struct msft_rp_read_supported_features {
 	__u8   status;
 	__u8   sub_opcode;
 	__le64 features;
 	__u8   evt_prefix_len;
-	__u8   evt_prefix[0];
+	__u8   evt_prefix[];
 } __packed;
 
 struct msft_data {
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index dcf7f96ff417..22a110f37abc 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1001,6 +1001,17 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname,
 			err = -EFAULT;
 		break;
 
+	case BT_SNDMTU:
+	case BT_RCVMTU:
+		if (sk->sk_state != BT_CONNECTED) {
+			err = -ENOTCONN;
+			break;
+		}
+
+		if (put_user(sco_pi(sk)->conn->mtu, (u32 __user *)optval))
+			err = -EFAULT;
+		break;
+
 	default:
 		err = -ENOPROTOOPT;
 		break;
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index bf4bef13d935..c659c464f7ca 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -3353,31 +3353,8 @@ static void smp_del_chan(struct l2cap_chan *chan)
 	l2cap_chan_put(chan);
 }
 
-static ssize_t force_bredr_smp_read(struct file *file,
-				    char __user *user_buf,
-				    size_t count, loff_t *ppos)
+int smp_force_bredr(struct hci_dev *hdev, bool enable)
 {
-	struct hci_dev *hdev = file->private_data;
-	char buf[3];
-
-	buf[0] = hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP) ? 'Y': 'N';
-	buf[1] = '\n';
-	buf[2] = '\0';
-	return simple_read_from_buffer(user_buf, count, ppos, buf, 2);
-}
-
-static ssize_t force_bredr_smp_write(struct file *file,
-				     const char __user *user_buf,
-				     size_t count, loff_t *ppos)
-{
-	struct hci_dev *hdev = file->private_data;
-	bool enable;
-	int err;
-
-	err = kstrtobool_from_user(user_buf, count, &enable);
-	if (err)
-		return err;
-
 	if (enable == hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP))
 		return -EALREADY;
 
@@ -3399,16 +3376,9 @@ static ssize_t force_bredr_smp_write(struct file *file,
 
 	hci_dev_change_flag(hdev, HCI_FORCE_BREDR_SMP);
 
-	return count;
+	return 0;
 }
 
-static const struct file_operations force_bredr_smp_fops = {
-	.open		= simple_open,
-	.read		= force_bredr_smp_read,
-	.write		= force_bredr_smp_write,
-	.llseek		= default_llseek,
-};
-
 int smp_register(struct hci_dev *hdev)
 {
 	struct l2cap_chan *chan;
@@ -3433,17 +3403,7 @@ int smp_register(struct hci_dev *hdev)
 
 	hdev->smp_data = chan;
 
-	/* If the controller does not support BR/EDR Secure Connections
-	 * feature, then the BR/EDR SMP channel shall not be present.
-	 *
-	 * To test this with Bluetooth 4.0 controllers, create a debugfs
-	 * switch that allows forcing BR/EDR SMP support and accepting
-	 * cross-transport pairing on non-AES encrypted connections.
-	 */
 	if (!lmp_sc_capable(hdev)) {
-		debugfs_create_file("force_bredr_smp", 0644, hdev->debugfs,
-				    hdev, &force_bredr_smp_fops);
-
 		/* Flag can be already set here (due to power toggle) */
 		if (!hci_dev_test_flag(hdev, HCI_FORCE_BREDR_SMP))
 			return 0;
diff --git a/net/bluetooth/smp.h b/net/bluetooth/smp.h
index 121edadd5f8d..fc35a8bf358e 100644
--- a/net/bluetooth/smp.h
+++ b/net/bluetooth/smp.h
@@ -193,6 +193,8 @@ bool smp_irk_matches(struct hci_dev *hdev, const u8 irk[16],
 int smp_generate_rpa(struct hci_dev *hdev, const u8 irk[16], bdaddr_t *rpa);
 int smp_generate_oob(struct hci_dev *hdev, u8 hash[16], u8 rand[16]);
 
+int smp_force_bredr(struct hci_dev *hdev, bool enable);
+
 int smp_register(struct hci_dev *hdev);
 void smp_unregister(struct hci_dev *hdev);
 
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index a66f211726e7..8b796c499cbb 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -11,6 +11,7 @@
 #include <net/sock.h>
 #include <net/tcp.h>
 #include <linux/error-injection.h>
+#include <linux/smp.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/bpf_test_run.h>
@@ -204,6 +205,9 @@ int bpf_prog_test_run_tracing(struct bpf_prog *prog,
 	int b = 2, err = -EFAULT;
 	u32 retval = 0;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	switch (prog->expected_attach_type) {
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
@@ -236,6 +240,85 @@ out:
 	return err;
 }
 
+struct bpf_raw_tp_test_run_info {
+	struct bpf_prog *prog;
+	void *ctx;
+	u32 retval;
+};
+
+static void
+__bpf_prog_test_run_raw_tp(void *data)
+{
+	struct bpf_raw_tp_test_run_info *info = data;
+
+	rcu_read_lock();
+	info->retval = BPF_PROG_RUN(info->prog, info->ctx);
+	rcu_read_unlock();
+}
+
+int bpf_prog_test_run_raw_tp(struct bpf_prog *prog,
+			     const union bpf_attr *kattr,
+			     union bpf_attr __user *uattr)
+{
+	void __user *ctx_in = u64_to_user_ptr(kattr->test.ctx_in);
+	__u32 ctx_size_in = kattr->test.ctx_size_in;
+	struct bpf_raw_tp_test_run_info info;
+	int cpu = kattr->test.cpu, err = 0;
+	int current_cpu;
+
+	/* doesn't support data_in/out, ctx_out, duration, or repeat */
+	if (kattr->test.data_in || kattr->test.data_out ||
+	    kattr->test.ctx_out || kattr->test.duration ||
+	    kattr->test.repeat)
+		return -EINVAL;
+
+	if (ctx_size_in < prog->aux->max_ctx_offset ||
+	    ctx_size_in > MAX_BPF_FUNC_ARGS * sizeof(u64))
+		return -EINVAL;
+
+	if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 && cpu != 0)
+		return -EINVAL;
+
+	if (ctx_size_in) {
+		info.ctx = kzalloc(ctx_size_in, GFP_USER);
+		if (!info.ctx)
+			return -ENOMEM;
+		if (copy_from_user(info.ctx, ctx_in, ctx_size_in)) {
+			err = -EFAULT;
+			goto out;
+		}
+	} else {
+		info.ctx = NULL;
+	}
+
+	info.prog = prog;
+
+	current_cpu = get_cpu();
+	if ((kattr->test.flags & BPF_F_TEST_RUN_ON_CPU) == 0 ||
+	    cpu == current_cpu) {
+		__bpf_prog_test_run_raw_tp(&info);
+	} else if (cpu >= nr_cpu_ids || !cpu_online(cpu)) {
+		/* smp_call_function_single() also checks cpu_online()
+		 * after csd_lock(). However, since cpu is from user
+		 * space, let's do an extra quick check to filter out
+		 * invalid value before smp_call_function_single().
+		 */
+		err = -ENXIO;
+	} else {
+		err = smp_call_function_single(cpu, __bpf_prog_test_run_raw_tp,
+					       &info, 1);
+	}
+	put_cpu();
+
+	if (!err &&
+	    copy_to_user(&uattr->test.retval, &info.retval, sizeof(u32)))
+		err = -EFAULT;
+
+out:
+	kfree(info.ctx);
+	return err;
+}
+
 static void *bpf_ctx_init(const union bpf_attr *kattr, u32 max_size)
 {
 	void __user *data_in = u64_to_user_ptr(kattr->test.ctx_in);
@@ -410,6 +493,9 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
 	void *data;
 	int ret;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN,
 			     SKB_DATA_ALIGN(sizeof(struct skb_shared_info)));
 	if (IS_ERR(data))
@@ -607,6 +693,9 @@ int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
 	if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR)
 		return -EINVAL;
 
+	if (kattr->test.flags || kattr->test.cpu)
+		return -EINVAL;
+
 	if (size < ETH_HLEN)
 		return -EINVAL;
 
diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
index 73d0b12789f1..8ad0233ce497 100644
--- a/net/bpfilter/Kconfig
+++ b/net/bpfilter/Kconfig
@@ -2,6 +2,7 @@
 menuconfig BPFILTER
 	bool "BPF based packet filtering framework (BPFILTER)"
 	depends on NET && BPF && INET
+	select USERMODE_DRIVER
 	help
 	  This builds experimental bpfilter framework that is aiming to
 	  provide netfilter compatible functionality via BPF
diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig
index 80879196560c..3c8ded7d3e84 100644
--- a/net/bridge/Kconfig
+++ b/net/bridge/Kconfig
@@ -73,3 +73,14 @@ config BRIDGE_MRP
 	  Say N to exclude this support and reduce the binary size.
 
 	  If unsure, say N.
+
+config BRIDGE_CFM
+	bool "CFM protocol"
+	depends on BRIDGE
+	help
+	  If you say Y here, then the Ethernet bridge will be able to run CFM
+	  protocol according to 802.1Q section 12.14
+
+	  Say N to exclude this support and reduce the binary size.
+
+	  If unsure, say N.
diff --git a/net/bridge/Makefile b/net/bridge/Makefile
index ccb394236fbd..4702702a74d3 100644
--- a/net/bridge/Makefile
+++ b/net/bridge/Makefile
@@ -27,3 +27,5 @@ bridge-$(CONFIG_NET_SWITCHDEV) += br_switchdev.o
 obj-$(CONFIG_NETFILTER) += netfilter/
 
 bridge-$(CONFIG_BRIDGE_MRP)	+= br_mrp_switchdev.o br_mrp.o br_mrp_netlink.o
+
+bridge-$(CONFIG_BRIDGE_CFM)	+= br_cfm.o br_cfm_netlink.o
diff --git a/net/bridge/br.c b/net/bridge/br.c
index b6fe30e3768f..1b169f8e7491 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -43,7 +43,10 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v
 
 		if (event == NETDEV_REGISTER) {
 			/* register of bridge completed, add sysfs entries */
-			br_sysfs_addbr(dev);
+			err = br_sysfs_addbr(dev);
+			if (err)
+				return notifier_from_errno(err);
+
 			return NOTIFY_DONE;
 		}
 	}
@@ -183,6 +186,11 @@ static int br_switchdev_event(struct notifier_block *unused,
 		br_fdb_offloaded_set(br, p, fdb_info->addr,
 				     fdb_info->vid, fdb_info->offloaded);
 		break;
+	case SWITCHDEV_FDB_FLUSH_TO_BRIDGE:
+		fdb_info = ptr;
+		/* Don't delete static entries */
+		br_fdb_delete_by_port(br, p, fdb_info->vid, 0);
+		break;
 	}
 
 out:
diff --git a/net/bridge/br_cfm.c b/net/bridge/br_cfm.c
new file mode 100644
index 000000000000..001064f7583d
--- /dev/null
+++ b/net/bridge/br_cfm.c
@@ -0,0 +1,867 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/cfm_bridge.h>
+#include <uapi/linux/cfm_bridge.h>
+#include "br_private_cfm.h"
+
+static struct br_cfm_mep *br_mep_find(struct net_bridge *br, u32 instance)
+{
+	struct br_cfm_mep *mep;
+
+	hlist_for_each_entry(mep, &br->mep_list, head)
+		if (mep->instance == instance)
+			return mep;
+
+	return NULL;
+}
+
+static struct br_cfm_mep *br_mep_find_ifindex(struct net_bridge *br,
+					      u32 ifindex)
+{
+	struct br_cfm_mep *mep;
+
+	hlist_for_each_entry_rcu(mep, &br->mep_list, head,
+				 lockdep_rtnl_is_held())
+		if (mep->create.ifindex == ifindex)
+			return mep;
+
+	return NULL;
+}
+
+static struct br_cfm_peer_mep *br_peer_mep_find(struct br_cfm_mep *mep,
+						u32 mepid)
+{
+	struct br_cfm_peer_mep *peer_mep;
+
+	hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head,
+				 lockdep_rtnl_is_held())
+		if (peer_mep->mepid == mepid)
+			return peer_mep;
+
+	return NULL;
+}
+
+static struct net_bridge_port *br_mep_get_port(struct net_bridge *br,
+					       u32 ifindex)
+{
+	struct net_bridge_port *port;
+
+	list_for_each_entry(port, &br->port_list, list)
+		if (port->dev->ifindex == ifindex)
+			return port;
+
+	return NULL;
+}
+
+/* Calculate the CCM interval in us. */
+static u32 interval_to_us(enum br_cfm_ccm_interval interval)
+{
+	switch (interval) {
+	case BR_CFM_CCM_INTERVAL_NONE:
+		return 0;
+	case BR_CFM_CCM_INTERVAL_3_3_MS:
+		return 3300;
+	case BR_CFM_CCM_INTERVAL_10_MS:
+		return 10 * 1000;
+	case BR_CFM_CCM_INTERVAL_100_MS:
+		return 100 * 1000;
+	case BR_CFM_CCM_INTERVAL_1_SEC:
+		return 1000 * 1000;
+	case BR_CFM_CCM_INTERVAL_10_SEC:
+		return 10 * 1000 * 1000;
+	case BR_CFM_CCM_INTERVAL_1_MIN:
+		return 60 * 1000 * 1000;
+	case BR_CFM_CCM_INTERVAL_10_MIN:
+		return 10 * 60 * 1000 * 1000;
+	}
+	return 0;
+}
+
+/* Convert the interface interval to CCM PDU value. */
+static u32 interval_to_pdu(enum br_cfm_ccm_interval interval)
+{
+	switch (interval) {
+	case BR_CFM_CCM_INTERVAL_NONE:
+		return 0;
+	case BR_CFM_CCM_INTERVAL_3_3_MS:
+		return 1;
+	case BR_CFM_CCM_INTERVAL_10_MS:
+		return 2;
+	case BR_CFM_CCM_INTERVAL_100_MS:
+		return 3;
+	case BR_CFM_CCM_INTERVAL_1_SEC:
+		return 4;
+	case BR_CFM_CCM_INTERVAL_10_SEC:
+		return 5;
+	case BR_CFM_CCM_INTERVAL_1_MIN:
+		return 6;
+	case BR_CFM_CCM_INTERVAL_10_MIN:
+		return 7;
+	}
+	return 0;
+}
+
+/* Convert the CCM PDU value to interval on interface. */
+static u32 pdu_to_interval(u32 value)
+{
+	switch (value) {
+	case 0:
+		return BR_CFM_CCM_INTERVAL_NONE;
+	case 1:
+		return BR_CFM_CCM_INTERVAL_3_3_MS;
+	case 2:
+		return BR_CFM_CCM_INTERVAL_10_MS;
+	case 3:
+		return BR_CFM_CCM_INTERVAL_100_MS;
+	case 4:
+		return BR_CFM_CCM_INTERVAL_1_SEC;
+	case 5:
+		return BR_CFM_CCM_INTERVAL_10_SEC;
+	case 6:
+		return BR_CFM_CCM_INTERVAL_1_MIN;
+	case 7:
+		return BR_CFM_CCM_INTERVAL_10_MIN;
+	}
+	return BR_CFM_CCM_INTERVAL_NONE;
+}
+
+static void ccm_rx_timer_start(struct br_cfm_peer_mep *peer_mep)
+{
+	u32 interval_us;
+
+	interval_us = interval_to_us(peer_mep->mep->cc_config.exp_interval);
+	/* Function ccm_rx_dwork must be called with 1/4
+	 * of the configured CC 'expected_interval'
+	 * in order to detect CCM defect after 3.25 interval.
+	 */
+	queue_delayed_work(system_wq, &peer_mep->ccm_rx_dwork,
+			   usecs_to_jiffies(interval_us / 4));
+}
+
+static void br_cfm_notify(int event, const struct net_bridge_port *port)
+{
+	u32 filter = RTEXT_FILTER_CFM_STATUS;
+
+	return br_info_notify(event, port->br, NULL, filter);
+}
+
+static void cc_peer_enable(struct br_cfm_peer_mep *peer_mep)
+{
+	memset(&peer_mep->cc_status, 0, sizeof(peer_mep->cc_status));
+	peer_mep->ccm_rx_count_miss = 0;
+
+	ccm_rx_timer_start(peer_mep);
+}
+
+static void cc_peer_disable(struct br_cfm_peer_mep *peer_mep)
+{
+	cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork);
+}
+
+static struct sk_buff *ccm_frame_build(struct br_cfm_mep *mep,
+				       const struct br_cfm_cc_ccm_tx_info *const tx_info)
+
+{
+	struct br_cfm_common_hdr *common_hdr;
+	struct net_bridge_port *b_port;
+	struct br_cfm_maid *maid;
+	u8 *itu_reserved, *e_tlv;
+	struct ethhdr *eth_hdr;
+	struct sk_buff *skb;
+	__be32 *status_tlv;
+	__be32 *snumber;
+	__be16 *mepid;
+
+	skb = dev_alloc_skb(CFM_CCM_MAX_FRAME_LENGTH);
+	if (!skb)
+		return NULL;
+
+	rcu_read_lock();
+	b_port = rcu_dereference(mep->b_port);
+	if (!b_port) {
+		kfree_skb(skb);
+		rcu_read_unlock();
+		return NULL;
+	}
+	skb->dev = b_port->dev;
+	rcu_read_unlock();
+	/* The device cannot be deleted until the work_queue functions has
+	 * completed. This function is called from ccm_tx_work_expired()
+	 * that is a work_queue functions.
+	 */
+
+	skb->protocol = htons(ETH_P_CFM);
+	skb->priority = CFM_FRAME_PRIO;
+
+	/* Ethernet header */
+	eth_hdr = skb_put(skb, sizeof(*eth_hdr));
+	ether_addr_copy(eth_hdr->h_dest, tx_info->dmac.addr);
+	ether_addr_copy(eth_hdr->h_source, mep->config.unicast_mac.addr);
+	eth_hdr->h_proto = htons(ETH_P_CFM);
+
+	/* Common CFM Header */
+	common_hdr = skb_put(skb, sizeof(*common_hdr));
+	common_hdr->mdlevel_version = mep->config.mdlevel << 5;
+	common_hdr->opcode = BR_CFM_OPCODE_CCM;
+	common_hdr->flags = (mep->rdi << 7) |
+			    interval_to_pdu(mep->cc_config.exp_interval);
+	common_hdr->tlv_offset = CFM_CCM_TLV_OFFSET;
+
+	/* Sequence number */
+	snumber = skb_put(skb, sizeof(*snumber));
+	if (tx_info->seq_no_update) {
+		*snumber = cpu_to_be32(mep->ccm_tx_snumber);
+		mep->ccm_tx_snumber += 1;
+	} else {
+		*snumber = 0;
+	}
+
+	mepid = skb_put(skb, sizeof(*mepid));
+	*mepid = cpu_to_be16((u16)mep->config.mepid);
+
+	maid = skb_put(skb, sizeof(*maid));
+	memcpy(maid->data, mep->cc_config.exp_maid.data, sizeof(maid->data));
+
+	/* ITU reserved (CFM_CCM_ITU_RESERVED_SIZE octets) */
+	itu_reserved = skb_put(skb, CFM_CCM_ITU_RESERVED_SIZE);
+	memset(itu_reserved, 0, CFM_CCM_ITU_RESERVED_SIZE);
+
+	/* Generel CFM TLV format:
+	 * TLV type:		one byte
+	 * TLV value length:	two bytes
+	 * TLV value:		'TLV value length' bytes
+	 */
+
+	/* Port status TLV. The value length is 1. Total of 4 bytes. */
+	if (tx_info->port_tlv) {
+		status_tlv = skb_put(skb, sizeof(*status_tlv));
+		*status_tlv = cpu_to_be32((CFM_PORT_STATUS_TLV_TYPE << 24) |
+					  (1 << 8) |	/* Value length */
+					  (tx_info->port_tlv_value & 0xFF));
+	}
+
+	/* Interface status TLV. The value length is 1. Total of 4 bytes. */
+	if (tx_info->if_tlv) {
+		status_tlv = skb_put(skb, sizeof(*status_tlv));
+		*status_tlv = cpu_to_be32((CFM_IF_STATUS_TLV_TYPE << 24) |
+					  (1 << 8) |	/* Value length */
+					  (tx_info->if_tlv_value & 0xFF));
+	}
+
+	/* End TLV */
+	e_tlv = skb_put(skb, sizeof(*e_tlv));
+	*e_tlv = CFM_ENDE_TLV_TYPE;
+
+	return skb;
+}
+
+static void ccm_frame_tx(struct sk_buff *skb)
+{
+	skb_reset_network_header(skb);
+	dev_queue_xmit(skb);
+}
+
+/* This function is called with the configured CC 'expected_interval'
+ * in order to drive CCM transmission when enabled.
+ */
+static void ccm_tx_work_expired(struct work_struct *work)
+{
+	struct delayed_work *del_work;
+	struct br_cfm_mep *mep;
+	struct sk_buff *skb;
+	u32 interval_us;
+
+	del_work = to_delayed_work(work);
+	mep = container_of(del_work, struct br_cfm_mep, ccm_tx_dwork);
+
+	if (time_before_eq(mep->ccm_tx_end, jiffies)) {
+		/* Transmission period has ended */
+		mep->cc_ccm_tx_info.period = 0;
+		return;
+	}
+
+	skb = ccm_frame_build(mep, &mep->cc_ccm_tx_info);
+	if (skb)
+		ccm_frame_tx(skb);
+
+	interval_us = interval_to_us(mep->cc_config.exp_interval);
+	queue_delayed_work(system_wq, &mep->ccm_tx_dwork,
+			   usecs_to_jiffies(interval_us));
+}
+
+/* This function is called with 1/4 of the configured CC 'expected_interval'
+ * in order to detect CCM defect after 3.25 interval.
+ */
+static void ccm_rx_work_expired(struct work_struct *work)
+{
+	struct br_cfm_peer_mep *peer_mep;
+	struct net_bridge_port *b_port;
+	struct delayed_work *del_work;
+
+	del_work = to_delayed_work(work);
+	peer_mep = container_of(del_work, struct br_cfm_peer_mep, ccm_rx_dwork);
+
+	/* After 13 counts (4 * 3,25) then 3.25 intervals are expired */
+	if (peer_mep->ccm_rx_count_miss < 13) {
+		/* 3.25 intervals are NOT expired without CCM reception */
+		peer_mep->ccm_rx_count_miss++;
+
+		/* Start timer again */
+		ccm_rx_timer_start(peer_mep);
+	} else {
+		/* 3.25 intervals are expired without CCM reception.
+		 * CCM defect detected
+		 */
+		peer_mep->cc_status.ccm_defect = true;
+
+		/* Change in CCM defect status - notify */
+		rcu_read_lock();
+		b_port = rcu_dereference(peer_mep->mep->b_port);
+		if (b_port)
+			br_cfm_notify(RTM_NEWLINK, b_port);
+		rcu_read_unlock();
+	}
+}
+
+static u32 ccm_tlv_extract(struct sk_buff *skb, u32 index,
+			   struct br_cfm_peer_mep *peer_mep)
+{
+	__be32 *s_tlv;
+	__be32 _s_tlv;
+	u32 h_s_tlv;
+	u8 *e_tlv;
+	u8 _e_tlv;
+
+	e_tlv = skb_header_pointer(skb, index, sizeof(_e_tlv), &_e_tlv);
+	if (!e_tlv)
+		return 0;
+
+	/* TLV is present - get the status TLV */
+	s_tlv = skb_header_pointer(skb,
+				   index,
+				   sizeof(_s_tlv), &_s_tlv);
+	if (!s_tlv)
+		return 0;
+
+	h_s_tlv = ntohl(*s_tlv);
+	if ((h_s_tlv >> 24) == CFM_IF_STATUS_TLV_TYPE) {
+		/* Interface status TLV */
+		peer_mep->cc_status.tlv_seen = true;
+		peer_mep->cc_status.if_tlv_value = (h_s_tlv & 0xFF);
+	}
+
+	if ((h_s_tlv >> 24) == CFM_PORT_STATUS_TLV_TYPE) {
+		/* Port status TLV */
+		peer_mep->cc_status.tlv_seen = true;
+		peer_mep->cc_status.port_tlv_value = (h_s_tlv & 0xFF);
+	}
+
+	/* The Sender ID TLV is not handled */
+	/* The Organization-Specific TLV is not handled */
+
+	/* Return the length of this tlv.
+	 * This is the length of the value field plus 3 bytes for size of type
+	 * field and length field
+	 */
+	return ((h_s_tlv >> 8) & 0xFFFF) + 3;
+}
+
+/* note: already called with rcu_read_lock */
+static int br_cfm_frame_rx(struct net_bridge_port *port, struct sk_buff *skb)
+{
+	u32 mdlevel, interval, size, index, max;
+	const struct br_cfm_common_hdr *hdr;
+	struct br_cfm_peer_mep *peer_mep;
+	const struct br_cfm_maid *maid;
+	struct br_cfm_common_hdr _hdr;
+	struct br_cfm_maid _maid;
+	struct br_cfm_mep *mep;
+	struct net_bridge *br;
+	__be32 *snumber;
+	__be32 _snumber;
+	__be16 *mepid;
+	__be16 _mepid;
+
+	if (port->state == BR_STATE_DISABLED)
+		return 0;
+
+	hdr = skb_header_pointer(skb, 0, sizeof(_hdr), &_hdr);
+	if (!hdr)
+		return 1;
+
+	br = port->br;
+	mep = br_mep_find_ifindex(br, port->dev->ifindex);
+	if (unlikely(!mep))
+		/* No MEP on this port - must be forwarded */
+		return 0;
+
+	mdlevel = hdr->mdlevel_version >> 5;
+	if (mdlevel > mep->config.mdlevel)
+		/* The level is above this MEP level - must be forwarded */
+		return 0;
+
+	if ((hdr->mdlevel_version & 0x1F) != 0) {
+		/* Invalid version */
+		mep->status.version_unexp_seen = true;
+		return 1;
+	}
+
+	if (mdlevel < mep->config.mdlevel) {
+		/* The level is below this MEP level */
+		mep->status.rx_level_low_seen = true;
+		return 1;
+	}
+
+	if (hdr->opcode == BR_CFM_OPCODE_CCM) {
+		/* CCM PDU received. */
+		/* MA ID is after common header + sequence number + MEP ID */
+		maid = skb_header_pointer(skb,
+					  CFM_CCM_PDU_MAID_OFFSET,
+					  sizeof(_maid), &_maid);
+		if (!maid)
+			return 1;
+		if (memcmp(maid->data, mep->cc_config.exp_maid.data,
+			   sizeof(maid->data)))
+			/* MA ID not as expected */
+			return 1;
+
+		/* MEP ID is after common header + sequence number */
+		mepid = skb_header_pointer(skb,
+					   CFM_CCM_PDU_MEPID_OFFSET,
+					   sizeof(_mepid), &_mepid);
+		if (!mepid)
+			return 1;
+		peer_mep = br_peer_mep_find(mep, (u32)ntohs(*mepid));
+		if (!peer_mep)
+			return 1;
+
+		/* Interval is in common header flags */
+		interval = hdr->flags & 0x07;
+		if (mep->cc_config.exp_interval != pdu_to_interval(interval))
+			/* Interval not as expected */
+			return 1;
+
+		/* A valid CCM frame is received */
+		if (peer_mep->cc_status.ccm_defect) {
+			peer_mep->cc_status.ccm_defect = false;
+
+			/* Change in CCM defect status - notify */
+			br_cfm_notify(RTM_NEWLINK, port);
+
+			/* Start CCM RX timer */
+			ccm_rx_timer_start(peer_mep);
+		}
+
+		peer_mep->cc_status.seen = true;
+		peer_mep->ccm_rx_count_miss = 0;
+
+		/* RDI is in common header flags */
+		peer_mep->cc_status.rdi = (hdr->flags & 0x80) ? true : false;
+
+		/* Sequence number is after common header */
+		snumber = skb_header_pointer(skb,
+					     CFM_CCM_PDU_SEQNR_OFFSET,
+					     sizeof(_snumber), &_snumber);
+		if (!snumber)
+			return 1;
+		if (ntohl(*snumber) != (mep->ccm_rx_snumber + 1))
+			/* Unexpected sequence number */
+			peer_mep->cc_status.seq_unexp_seen = true;
+
+		mep->ccm_rx_snumber = ntohl(*snumber);
+
+		/* TLV end is after common header + sequence number + MEP ID +
+		 * MA ID + ITU reserved
+		 */
+		index = CFM_CCM_PDU_TLV_OFFSET;
+		max = 0;
+		do { /* Handle all TLVs */
+			size = ccm_tlv_extract(skb, index, peer_mep);
+			index += size;
+			max += 1;
+		} while (size != 0 && max < 4); /* Max four TLVs possible */
+
+		return 1;
+	}
+
+	mep->status.opcode_unexp_seen = true;
+
+	return 1;
+}
+
+static struct br_frame_type cfm_frame_type __read_mostly = {
+	.type = cpu_to_be16(ETH_P_CFM),
+	.frame_handler = br_cfm_frame_rx,
+};
+
+int br_cfm_mep_create(struct net_bridge *br,
+		      const u32 instance,
+		      struct br_cfm_mep_create *const create,
+		      struct netlink_ext_ack *extack)
+{
+	struct net_bridge_port *p;
+	struct br_cfm_mep *mep;
+
+	ASSERT_RTNL();
+
+	if (create->domain == BR_CFM_VLAN) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "VLAN domain not supported");
+		return -EINVAL;
+	}
+	if (create->domain != BR_CFM_PORT) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Invalid domain value");
+		return -EINVAL;
+	}
+	if (create->direction == BR_CFM_MEP_DIRECTION_UP) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Up-MEP not supported");
+		return -EINVAL;
+	}
+	if (create->direction != BR_CFM_MEP_DIRECTION_DOWN) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Invalid direction value");
+		return -EINVAL;
+	}
+	p = br_mep_get_port(br, create->ifindex);
+	if (!p) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Port is not related to bridge");
+		return -EINVAL;
+	}
+	mep = br_mep_find(br, instance);
+	if (mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "MEP instance already exists");
+		return -EEXIST;
+	}
+
+	/* In PORT domain only one instance can be created per port */
+	if (create->domain == BR_CFM_PORT) {
+		mep = br_mep_find_ifindex(br, create->ifindex);
+		if (mep) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Only one Port MEP on a port allowed");
+			return -EINVAL;
+		}
+	}
+
+	mep = kzalloc(sizeof(*mep), GFP_KERNEL);
+	if (!mep)
+		return -ENOMEM;
+
+	mep->create = *create;
+	mep->instance = instance;
+	rcu_assign_pointer(mep->b_port, p);
+
+	INIT_HLIST_HEAD(&mep->peer_mep_list);
+	INIT_DELAYED_WORK(&mep->ccm_tx_dwork, ccm_tx_work_expired);
+
+	if (hlist_empty(&br->mep_list))
+		br_add_frame(br, &cfm_frame_type);
+
+	hlist_add_tail_rcu(&mep->head, &br->mep_list);
+
+	return 0;
+}
+
+static void mep_delete_implementation(struct net_bridge *br,
+				      struct br_cfm_mep *mep)
+{
+	struct br_cfm_peer_mep *peer_mep;
+	struct hlist_node *n_store;
+
+	ASSERT_RTNL();
+
+	/* Empty and free peer MEP list */
+	hlist_for_each_entry_safe(peer_mep, n_store, &mep->peer_mep_list, head) {
+		cancel_delayed_work_sync(&peer_mep->ccm_rx_dwork);
+		hlist_del_rcu(&peer_mep->head);
+		kfree_rcu(peer_mep, rcu);
+	}
+
+	cancel_delayed_work_sync(&mep->ccm_tx_dwork);
+
+	RCU_INIT_POINTER(mep->b_port, NULL);
+	hlist_del_rcu(&mep->head);
+	kfree_rcu(mep, rcu);
+
+	if (hlist_empty(&br->mep_list))
+		br_del_frame(br, &cfm_frame_type);
+}
+
+int br_cfm_mep_delete(struct net_bridge *br,
+		      const u32 instance,
+		      struct netlink_ext_ack *extack)
+{
+	struct br_cfm_mep *mep;
+
+	ASSERT_RTNL();
+
+	mep = br_mep_find(br, instance);
+	if (!mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "MEP instance does not exists");
+		return -ENOENT;
+	}
+
+	mep_delete_implementation(br, mep);
+
+	return 0;
+}
+
+int br_cfm_mep_config_set(struct net_bridge *br,
+			  const u32 instance,
+			  const struct br_cfm_mep_config *const config,
+			  struct netlink_ext_ack *extack)
+{
+	struct br_cfm_mep *mep;
+
+	ASSERT_RTNL();
+
+	mep = br_mep_find(br, instance);
+	if (!mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "MEP instance does not exists");
+		return -ENOENT;
+	}
+
+	mep->config = *config;
+
+	return 0;
+}
+
+int br_cfm_cc_config_set(struct net_bridge *br,
+			 const u32 instance,
+			 const struct br_cfm_cc_config *const config,
+			 struct netlink_ext_ack *extack)
+{
+	struct br_cfm_peer_mep *peer_mep;
+	struct br_cfm_mep *mep;
+
+	ASSERT_RTNL();
+
+	mep = br_mep_find(br, instance);
+	if (!mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "MEP instance does not exists");
+		return -ENOENT;
+	}
+
+	/* Check for no change in configuration */
+	if (memcmp(config, &mep->cc_config, sizeof(*config)) == 0)
+		return 0;
+
+	if (config->enable && !mep->cc_config.enable)
+		/* CC is enabled */
+		hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head)
+			cc_peer_enable(peer_mep);
+
+	if (!config->enable && mep->cc_config.enable)
+		/* CC is disabled */
+		hlist_for_each_entry(peer_mep, &mep->peer_mep_list, head)
+			cc_peer_disable(peer_mep);
+
+	mep->cc_config = *config;
+	mep->ccm_rx_snumber = 0;
+	mep->ccm_tx_snumber = 1;
+
+	return 0;
+}
+
+int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance,
+			   u32 mepid,
+			   struct netlink_ext_ack *extack)
+{
+	struct br_cfm_peer_mep *peer_mep;
+	struct br_cfm_mep *mep;
+
+	ASSERT_RTNL();
+
+	mep = br_mep_find(br, instance);
+	if (!mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "MEP instance does not exists");
+		return -ENOENT;
+	}
+
+	peer_mep = br_peer_mep_find(mep, mepid);
+	if (peer_mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Peer MEP-ID already exists");
+		return -EEXIST;
+	}
+
+	peer_mep = kzalloc(sizeof(*peer_mep), GFP_KERNEL);
+	if (!peer_mep)
+		return -ENOMEM;
+
+	peer_mep->mepid = mepid;
+	peer_mep->mep = mep;
+	INIT_DELAYED_WORK(&peer_mep->ccm_rx_dwork, ccm_rx_work_expired);
+
+	if (mep->cc_config.enable)
+		cc_peer_enable(peer_mep);
+
+	hlist_add_tail_rcu(&peer_mep->head, &mep->peer_mep_list);
+
+	return 0;
+}
+
+int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance,
+			      u32 mepid,
+			      struct netlink_ext_ack *extack)
+{
+	struct br_cfm_peer_mep *peer_mep;
+	struct br_cfm_mep *mep;
+
+	ASSERT_RTNL();
+
+	mep = br_mep_find(br, instance);
+	if (!mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "MEP instance does not exists");
+		return -ENOENT;
+	}
+
+	peer_mep = br_peer_mep_find(mep, mepid);
+	if (!peer_mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Peer MEP-ID does not exists");
+		return -ENOENT;
+	}
+
+	cc_peer_disable(peer_mep);
+
+	hlist_del_rcu(&peer_mep->head);
+	kfree_rcu(peer_mep, rcu);
+
+	return 0;
+}
+
+int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance,
+		      const bool rdi, struct netlink_ext_ack *extack)
+{
+	struct br_cfm_mep *mep;
+
+	ASSERT_RTNL();
+
+	mep = br_mep_find(br, instance);
+	if (!mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "MEP instance does not exists");
+		return -ENOENT;
+	}
+
+	mep->rdi = rdi;
+
+	return 0;
+}
+
+int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance,
+		     const struct br_cfm_cc_ccm_tx_info *const tx_info,
+		     struct netlink_ext_ack *extack)
+{
+	struct br_cfm_mep *mep;
+
+	ASSERT_RTNL();
+
+	mep = br_mep_find(br, instance);
+	if (!mep) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "MEP instance does not exists");
+		return -ENOENT;
+	}
+
+	if (memcmp(tx_info, &mep->cc_ccm_tx_info, sizeof(*tx_info)) == 0) {
+		/* No change in tx_info. */
+		if (mep->cc_ccm_tx_info.period == 0)
+			/* Transmission is not enabled - just return */
+			return 0;
+
+		/* Transmission is ongoing, the end time is recalculated */
+		mep->ccm_tx_end = jiffies +
+				  usecs_to_jiffies(tx_info->period * 1000000);
+		return 0;
+	}
+
+	if (tx_info->period == 0 && mep->cc_ccm_tx_info.period == 0)
+		/* Some change in info and transmission is not ongoing */
+		goto save;
+
+	if (tx_info->period != 0 && mep->cc_ccm_tx_info.period != 0) {
+		/* Some change in info and transmission is ongoing
+		 * The end time is recalculated
+		 */
+		mep->ccm_tx_end = jiffies +
+				  usecs_to_jiffies(tx_info->period * 1000000);
+
+		goto save;
+	}
+
+	if (tx_info->period == 0 && mep->cc_ccm_tx_info.period != 0) {
+		cancel_delayed_work_sync(&mep->ccm_tx_dwork);
+		goto save;
+	}
+
+	/* Start delayed work to transmit CCM frames. It is done with zero delay
+	 * to send first frame immediately
+	 */
+	mep->ccm_tx_end = jiffies + usecs_to_jiffies(tx_info->period * 1000000);
+	queue_delayed_work(system_wq, &mep->ccm_tx_dwork, 0);
+
+save:
+	mep->cc_ccm_tx_info = *tx_info;
+
+	return 0;
+}
+
+int br_cfm_mep_count(struct net_bridge *br, u32 *count)
+{
+	struct br_cfm_mep *mep;
+
+	*count = 0;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mep, &br->mep_list, head)
+		*count += 1;
+	rcu_read_unlock();
+
+	return 0;
+}
+
+int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count)
+{
+	struct br_cfm_peer_mep *peer_mep;
+	struct br_cfm_mep *mep;
+
+	*count = 0;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mep, &br->mep_list, head)
+		hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head)
+			*count += 1;
+	rcu_read_unlock();
+
+	return 0;
+}
+
+bool br_cfm_created(struct net_bridge *br)
+{
+	return !hlist_empty(&br->mep_list);
+}
+
+/* Deletes the CFM instances on a specific bridge port
+ */
+void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *port)
+{
+	struct hlist_node *n_store;
+	struct br_cfm_mep *mep;
+
+	ASSERT_RTNL();
+
+	hlist_for_each_entry_safe(mep, n_store, &br->mep_list, head)
+		if (mep->create.ifindex == port->dev->ifindex)
+			mep_delete_implementation(br, mep);
+}
diff --git a/net/bridge/br_cfm_netlink.c b/net/bridge/br_cfm_netlink.c
new file mode 100644
index 000000000000..5c4c369f8536
--- /dev/null
+++ b/net/bridge/br_cfm_netlink.c
@@ -0,0 +1,726 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <net/genetlink.h>
+
+#include "br_private.h"
+#include "br_private_cfm.h"
+
+static const struct nla_policy
+br_cfm_mep_create_policy[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1] = {
+	[IFLA_BRIDGE_CFM_MEP_CREATE_UNSPEC]	= { .type = NLA_REJECT },
+	[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]	= { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]	= { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]	= { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]	= { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+br_cfm_mep_delete_policy[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1] = {
+	[IFLA_BRIDGE_CFM_MEP_DELETE_UNSPEC]	= { .type = NLA_REJECT },
+	[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]	= { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+br_cfm_mep_config_policy[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1] = {
+	[IFLA_BRIDGE_CFM_MEP_CONFIG_UNSPEC]	 = { .type = NLA_REJECT },
+	[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]	 = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC] = NLA_POLICY_ETH_ADDR,
+	[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]	 = NLA_POLICY_MAX(NLA_U32, 7),
+	[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]	 = NLA_POLICY_MAX(NLA_U32, 0x1FFF),
+};
+
+static const struct nla_policy
+br_cfm_cc_config_policy[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1] = {
+	[IFLA_BRIDGE_CFM_CC_CONFIG_UNSPEC]	 = { .type = NLA_REJECT },
+	[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]	 = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]	 = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL] = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID]	 = {
+	.type = NLA_BINARY, .len = CFM_MAID_LENGTH },
+};
+
+static const struct nla_policy
+br_cfm_cc_peer_mep_policy[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1] = {
+	[IFLA_BRIDGE_CFM_CC_PEER_MEP_UNSPEC]	= { .type = NLA_REJECT },
+	[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]	= { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_PEER_MEPID]		= NLA_POLICY_MAX(NLA_U32, 0x1FFF),
+};
+
+static const struct nla_policy
+br_cfm_cc_rdi_policy[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1] = {
+	[IFLA_BRIDGE_CFM_CC_RDI_UNSPEC]		= { .type = NLA_REJECT },
+	[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]	= { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_RDI_RDI]		= { .type = NLA_U32 },
+};
+
+static const struct nla_policy
+br_cfm_cc_ccm_tx_policy[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1] = {
+	[IFLA_BRIDGE_CFM_CC_CCM_TX_UNSPEC]	   = { .type = NLA_REJECT },
+	[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]	   = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC]	   = NLA_POLICY_ETH_ADDR,
+	[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]  = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]	   = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]	   = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]   = { .type = NLA_U8 },
+	[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]	   = { .type = NLA_U32 },
+	[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE] = { .type = NLA_U8 },
+};
+
+static const struct nla_policy
+br_cfm_policy[IFLA_BRIDGE_CFM_MAX + 1] = {
+	[IFLA_BRIDGE_CFM_UNSPEC]		= { .type = NLA_REJECT },
+	[IFLA_BRIDGE_CFM_MEP_CREATE]		=
+				NLA_POLICY_NESTED(br_cfm_mep_create_policy),
+	[IFLA_BRIDGE_CFM_MEP_DELETE]		=
+				NLA_POLICY_NESTED(br_cfm_mep_delete_policy),
+	[IFLA_BRIDGE_CFM_MEP_CONFIG]		=
+				NLA_POLICY_NESTED(br_cfm_mep_config_policy),
+	[IFLA_BRIDGE_CFM_CC_CONFIG]		=
+				NLA_POLICY_NESTED(br_cfm_cc_config_policy),
+	[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD]	=
+				NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy),
+	[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE]	=
+				NLA_POLICY_NESTED(br_cfm_cc_peer_mep_policy),
+	[IFLA_BRIDGE_CFM_CC_RDI]		=
+				NLA_POLICY_NESTED(br_cfm_cc_rdi_policy),
+	[IFLA_BRIDGE_CFM_CC_CCM_TX]		=
+				NLA_POLICY_NESTED(br_cfm_cc_ccm_tx_policy),
+};
+
+static int br_mep_create_parse(struct net_bridge *br, struct nlattr *attr,
+			       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CREATE_MAX + 1];
+	struct br_cfm_mep_create create;
+	u32 instance;
+	int err;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CREATE_MAX, attr,
+			       br_cfm_mep_create_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing DOMAIN attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing DIRECTION attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing IFINDEX attribute");
+		return -EINVAL;
+	}
+
+	memset(&create, 0, sizeof(create));
+
+	instance =  nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE]);
+	create.domain = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN]);
+	create.direction = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION]);
+	create.ifindex = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX]);
+
+	return br_cfm_mep_create(br, instance, &create, extack);
+}
+
+static int br_mep_delete_parse(struct net_bridge *br, struct nlattr *attr,
+			       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_DELETE_MAX + 1];
+	u32 instance;
+	int err;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_DELETE_MAX, attr,
+			       br_cfm_mep_delete_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Missing INSTANCE attribute");
+		return -EINVAL;
+	}
+
+	instance =  nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_DELETE_INSTANCE]);
+
+	return br_cfm_mep_delete(br, instance, extack);
+}
+
+static int br_mep_config_parse(struct net_bridge *br, struct nlattr *attr,
+			       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MAX + 1];
+	struct br_cfm_mep_config config;
+	u32 instance;
+	int err;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MEP_CONFIG_MAX, attr,
+			       br_cfm_mep_config_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing UNICAST_MAC attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing MDLEVEL attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing MEPID attribute");
+		return -EINVAL;
+	}
+
+	memset(&config, 0, sizeof(config));
+
+	instance =  nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE]);
+	nla_memcpy(&config.unicast_mac.addr,
+		   tb[IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC],
+		   sizeof(config.unicast_mac.addr));
+	config.mdlevel = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL]);
+	config.mepid = nla_get_u32(tb[IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID]);
+
+	return br_cfm_mep_config_set(br, instance, &config, extack);
+}
+
+static int br_cc_config_parse(struct net_bridge *br, struct nlattr *attr,
+			      struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CONFIG_MAX + 1];
+	struct br_cfm_cc_config config;
+	u32 instance;
+	int err;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CONFIG_MAX, attr,
+			       br_cfm_cc_config_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing ENABLE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing INTERVAL attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing MAID attribute");
+		return -EINVAL;
+	}
+
+	memset(&config, 0, sizeof(config));
+
+	instance =  nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE]);
+	config.enable = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE]);
+	config.exp_interval = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL]);
+	nla_memcpy(&config.exp_maid.data, tb[IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID],
+		   sizeof(config.exp_maid.data));
+
+	return br_cfm_cc_config_set(br, instance, &config, extack);
+}
+
+static int br_cc_peer_mep_add_parse(struct net_bridge *br, struct nlattr *attr,
+				    struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1];
+	u32 instance, peer_mep_id;
+	int err;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr,
+			       br_cfm_cc_peer_mep_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute");
+		return -EINVAL;
+	}
+
+	instance =  nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]);
+	peer_mep_id =  nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]);
+
+	return br_cfm_cc_peer_mep_add(br, instance, peer_mep_id, extack);
+}
+
+static int br_cc_peer_mep_remove_parse(struct net_bridge *br, struct nlattr *attr,
+				       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX + 1];
+	u32 instance, peer_mep_id;
+	int err;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_PEER_MEP_MAX, attr,
+			       br_cfm_cc_peer_mep_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing PEER_MEP_ID attribute");
+		return -EINVAL;
+	}
+
+	instance =  nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE]);
+	peer_mep_id =  nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_PEER_MEPID]);
+
+	return br_cfm_cc_peer_mep_remove(br, instance, peer_mep_id, extack);
+}
+
+static int br_cc_rdi_parse(struct net_bridge *br, struct nlattr *attr,
+			   struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_BRIDGE_CFM_CC_RDI_MAX + 1];
+	u32 instance, rdi;
+	int err;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_RDI_MAX, attr,
+			       br_cfm_cc_rdi_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing RDI attribute");
+		return -EINVAL;
+	}
+
+	instance =  nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]);
+	rdi =  nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_RDI]);
+
+	return br_cfm_cc_rdi_set(br, instance, rdi, extack);
+}
+
+static int br_cc_ccm_tx_parse(struct net_bridge *br, struct nlattr *attr,
+			      struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_BRIDGE_CFM_CC_CCM_TX_MAX + 1];
+	struct br_cfm_cc_ccm_tx_info tx_info;
+	u32 instance;
+	int err;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_CC_CCM_TX_MAX, attr,
+			       br_cfm_cc_ccm_tx_policy, extack);
+	if (err)
+		return err;
+
+	if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing INSTANCE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing DMAC attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing SEQ_NO_UPDATE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing PERIOD attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing IF_TLV_VALUE attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV attribute");
+		return -EINVAL;
+	}
+	if (!tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing PORT_TLV_VALUE attribute");
+		return -EINVAL;
+	}
+
+	memset(&tx_info, 0, sizeof(tx_info));
+
+	instance = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_RDI_INSTANCE]);
+	nla_memcpy(&tx_info.dmac.addr,
+		   tb[IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC],
+		   sizeof(tx_info.dmac.addr));
+	tx_info.seq_no_update = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE]);
+	tx_info.period = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD]);
+	tx_info.if_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV]);
+	tx_info.if_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE]);
+	tx_info.port_tlv = nla_get_u32(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV]);
+	tx_info.port_tlv_value = nla_get_u8(tb[IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE]);
+
+	return br_cfm_cc_ccm_tx(br, instance, &tx_info, extack);
+}
+
+int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p,
+		 struct nlattr *attr, int cmd, struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[IFLA_BRIDGE_CFM_MAX + 1];
+	int err;
+
+	/* When this function is called for a port then the br pointer is
+	 * invalid, therefor set the br to point correctly
+	 */
+	if (p)
+		br = p->br;
+
+	err = nla_parse_nested(tb, IFLA_BRIDGE_CFM_MAX, attr,
+			       br_cfm_policy, extack);
+	if (err)
+		return err;
+
+	if (tb[IFLA_BRIDGE_CFM_MEP_CREATE]) {
+		err = br_mep_create_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CREATE],
+					  extack);
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRIDGE_CFM_MEP_DELETE]) {
+		err = br_mep_delete_parse(br, tb[IFLA_BRIDGE_CFM_MEP_DELETE],
+					  extack);
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRIDGE_CFM_MEP_CONFIG]) {
+		err = br_mep_config_parse(br, tb[IFLA_BRIDGE_CFM_MEP_CONFIG],
+					  extack);
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRIDGE_CFM_CC_CONFIG]) {
+		err = br_cc_config_parse(br, tb[IFLA_BRIDGE_CFM_CC_CONFIG],
+					 extack);
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD]) {
+		err = br_cc_peer_mep_add_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_ADD],
+					       extack);
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE]) {
+		err = br_cc_peer_mep_remove_parse(br, tb[IFLA_BRIDGE_CFM_CC_PEER_MEP_REMOVE],
+						  extack);
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRIDGE_CFM_CC_RDI]) {
+		err = br_cc_rdi_parse(br, tb[IFLA_BRIDGE_CFM_CC_RDI],
+				      extack);
+		if (err)
+			return err;
+	}
+
+	if (tb[IFLA_BRIDGE_CFM_CC_CCM_TX]) {
+		err = br_cc_ccm_tx_parse(br, tb[IFLA_BRIDGE_CFM_CC_CCM_TX],
+					 extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br)
+{
+	struct br_cfm_peer_mep *peer_mep;
+	struct br_cfm_mep *mep;
+	struct nlattr *tb;
+
+	hlist_for_each_entry_rcu(mep, &br->mep_list, head) {
+		tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INFO);
+		if (!tb)
+			goto nla_info_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_INSTANCE,
+				mep->instance))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DOMAIN,
+				mep->create.domain))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_DIRECTION,
+				mep->create.direction))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CREATE_IFINDEX,
+				mep->create.ifindex))
+			goto nla_put_failure;
+
+		nla_nest_end(skb, tb);
+
+		tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INFO);
+
+		if (!tb)
+			goto nla_info_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_INSTANCE,
+				mep->instance))
+			goto nla_put_failure;
+
+		if (nla_put(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_UNICAST_MAC,
+			    sizeof(mep->config.unicast_mac.addr),
+			    mep->config.unicast_mac.addr))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MDLEVEL,
+				mep->config.mdlevel))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_CONFIG_MEPID,
+				mep->config.mepid))
+			goto nla_put_failure;
+
+		nla_nest_end(skb, tb);
+
+		tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INFO);
+
+		if (!tb)
+			goto nla_info_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_INSTANCE,
+				mep->instance))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_ENABLE,
+				mep->cc_config.enable))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_INTERVAL,
+				mep->cc_config.exp_interval))
+			goto nla_put_failure;
+
+		if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CONFIG_EXP_MAID,
+			    sizeof(mep->cc_config.exp_maid.data),
+			    mep->cc_config.exp_maid.data))
+			goto nla_put_failure;
+
+		nla_nest_end(skb, tb);
+
+		tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_RDI_INFO);
+
+		if (!tb)
+			goto nla_info_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_INSTANCE,
+				mep->instance))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_RDI_RDI,
+				mep->rdi))
+			goto nla_put_failure;
+
+		nla_nest_end(skb, tb);
+
+		tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INFO);
+
+		if (!tb)
+			goto nla_info_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_INSTANCE,
+				mep->instance))
+			goto nla_put_failure;
+
+		if (nla_put(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_DMAC,
+			    sizeof(mep->cc_ccm_tx_info.dmac),
+			    mep->cc_ccm_tx_info.dmac.addr))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_SEQ_NO_UPDATE,
+				mep->cc_ccm_tx_info.seq_no_update))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PERIOD,
+				mep->cc_ccm_tx_info.period))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV,
+				mep->cc_ccm_tx_info.if_tlv))
+			goto nla_put_failure;
+
+		if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_IF_TLV_VALUE,
+			       mep->cc_ccm_tx_info.if_tlv_value))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV,
+				mep->cc_ccm_tx_info.port_tlv))
+			goto nla_put_failure;
+
+		if (nla_put_u8(skb, IFLA_BRIDGE_CFM_CC_CCM_TX_PORT_TLV_VALUE,
+			       mep->cc_ccm_tx_info.port_tlv_value))
+			goto nla_put_failure;
+
+		nla_nest_end(skb, tb);
+
+		hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) {
+			tb = nla_nest_start(skb,
+					    IFLA_BRIDGE_CFM_CC_PEER_MEP_INFO);
+
+			if (!tb)
+				goto nla_info_failure;
+
+			if (nla_put_u32(skb,
+					IFLA_BRIDGE_CFM_CC_PEER_MEP_INSTANCE,
+					mep->instance))
+				goto nla_put_failure;
+
+			if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_MEPID,
+					peer_mep->mepid))
+				goto nla_put_failure;
+
+			nla_nest_end(skb, tb);
+		}
+	}
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, tb);
+
+nla_info_failure:
+	return -EMSGSIZE;
+}
+
+int br_cfm_status_fill_info(struct sk_buff *skb,
+			    struct net_bridge *br,
+			    bool getlink)
+{
+	struct br_cfm_peer_mep *peer_mep;
+	struct br_cfm_mep *mep;
+	struct nlattr *tb;
+
+	hlist_for_each_entry_rcu(mep, &br->mep_list, head) {
+		tb = nla_nest_start(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INFO);
+		if (!tb)
+			goto nla_info_failure;
+
+		if (nla_put_u32(skb, IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE,
+				mep->instance))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb,
+				IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN,
+				mep->status.opcode_unexp_seen))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb,
+				IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN,
+				mep->status.version_unexp_seen))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb,
+				IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN,
+				mep->status.rx_level_low_seen))
+			goto nla_put_failure;
+
+		/* Only clear if this is a GETLINK */
+		if (getlink) {
+			/* Clear all 'seen' indications */
+			mep->status.opcode_unexp_seen = false;
+			mep->status.version_unexp_seen = false;
+			mep->status.rx_level_low_seen = false;
+		}
+
+		nla_nest_end(skb, tb);
+
+		hlist_for_each_entry_rcu(peer_mep, &mep->peer_mep_list, head) {
+			tb = nla_nest_start(skb,
+					    IFLA_BRIDGE_CFM_CC_PEER_STATUS_INFO);
+			if (!tb)
+				goto nla_info_failure;
+
+			if (nla_put_u32(skb,
+					IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE,
+					mep->instance))
+				goto nla_put_failure;
+
+			if (nla_put_u32(skb,
+					IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID,
+					peer_mep->mepid))
+				goto nla_put_failure;
+
+			if (nla_put_u32(skb,
+					IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT,
+					peer_mep->cc_status.ccm_defect))
+				goto nla_put_failure;
+
+			if (nla_put_u32(skb, IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI,
+					peer_mep->cc_status.rdi))
+				goto nla_put_failure;
+
+			if (nla_put_u8(skb,
+				       IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE,
+				       peer_mep->cc_status.port_tlv_value))
+				goto nla_put_failure;
+
+			if (nla_put_u8(skb,
+				       IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE,
+				       peer_mep->cc_status.if_tlv_value))
+				goto nla_put_failure;
+
+			if (nla_put_u32(skb,
+					IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN,
+					peer_mep->cc_status.seen))
+				goto nla_put_failure;
+
+			if (nla_put_u32(skb,
+					IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN,
+					peer_mep->cc_status.tlv_seen))
+				goto nla_put_failure;
+
+			if (nla_put_u32(skb,
+					IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN,
+					peer_mep->cc_status.seq_unexp_seen))
+				goto nla_put_failure;
+
+			if (getlink) { /* Only clear if this is a GETLINK */
+				/* Clear all 'seen' indications */
+				peer_mep->cc_status.seen = false;
+				peer_mep->cc_status.tlv_seen = false;
+				peer_mep->cc_status.seq_unexp_seen = false;
+			}
+
+			nla_nest_end(skb, tb);
+		}
+	}
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, tb);
+
+nla_info_failure:
+	return -EMSGSIZE;
+}
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 9a2fb4aa1a10..3f2f06b4dd27 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -30,7 +30,6 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 	struct net_bridge *br = netdev_priv(dev);
 	struct net_bridge_fdb_entry *dst;
 	struct net_bridge_mdb_entry *mdst;
-	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
 	const struct nf_br_ops *nf_ops;
 	u8 state = BR_STATE_FORWARDING;
 	const unsigned char *dest;
@@ -45,10 +44,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_OK;
 	}
 
-	u64_stats_update_begin(&brstats->syncp);
-	brstats->tx_packets++;
-	brstats->tx_bytes += skb->len;
-	u64_stats_update_end(&brstats->syncp);
+	dev_sw_netstats_tx_add(dev, 1, skb->len);
 
 	br_switchdev_frame_unmark(skb);
 	BR_INPUT_SKB_CB(skb)->brdev = dev;
@@ -93,7 +89,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev)
 
 		mdst = br_mdb_get(br, skb, vid);
 		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
-		    br_multicast_querier_exists(br, eth_hdr(skb)))
+		    br_multicast_querier_exists(br, eth_hdr(skb), mdst))
 			br_multicast_flood(mdst, skb, false, true);
 		else
 			br_flood(br, skb, BR_PKT_MULTICAST, false, true);
@@ -119,26 +115,26 @@ static int br_dev_init(struct net_device *dev)
 	struct net_bridge *br = netdev_priv(dev);
 	int err;
 
-	br->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!br->stats)
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->tstats)
 		return -ENOMEM;
 
 	err = br_fdb_hash_init(br);
 	if (err) {
-		free_percpu(br->stats);
+		free_percpu(dev->tstats);
 		return err;
 	}
 
 	err = br_mdb_hash_init(br);
 	if (err) {
-		free_percpu(br->stats);
+		free_percpu(dev->tstats);
 		br_fdb_hash_fini(br);
 		return err;
 	}
 
 	err = br_vlan_init(br);
 	if (err) {
-		free_percpu(br->stats);
+		free_percpu(dev->tstats);
 		br_mdb_hash_fini(br);
 		br_fdb_hash_fini(br);
 		return err;
@@ -146,7 +142,7 @@ static int br_dev_init(struct net_device *dev)
 
 	err = br_multicast_init_stats(br);
 	if (err) {
-		free_percpu(br->stats);
+		free_percpu(dev->tstats);
 		br_vlan_flush(br);
 		br_mdb_hash_fini(br);
 		br_fdb_hash_fini(br);
@@ -165,7 +161,7 @@ static void br_dev_uninit(struct net_device *dev)
 	br_vlan_flush(br);
 	br_mdb_hash_fini(br);
 	br_fdb_hash_fini(br);
-	free_percpu(br->stats);
+	free_percpu(dev->tstats);
 }
 
 static int br_dev_open(struct net_device *dev)
@@ -177,6 +173,9 @@ static int br_dev_open(struct net_device *dev)
 	br_stp_enable_bridge(br);
 	br_multicast_open(br);
 
+	if (br_opt_get(br, BROPT_MULTICAST_ENABLED))
+		br_multicast_join_snoopers(br);
+
 	return 0;
 }
 
@@ -197,38 +196,14 @@ static int br_dev_stop(struct net_device *dev)
 	br_stp_disable_bridge(br);
 	br_multicast_stop(br);
 
+	if (br_opt_get(br, BROPT_MULTICAST_ENABLED))
+		br_multicast_leave_snoopers(br);
+
 	netif_stop_queue(dev);
 
 	return 0;
 }
 
-static void br_get_stats64(struct net_device *dev,
-			   struct rtnl_link_stats64 *stats)
-{
-	struct net_bridge *br = netdev_priv(dev);
-	struct pcpu_sw_netstats tmp, sum = { 0 };
-	unsigned int cpu;
-
-	for_each_possible_cpu(cpu) {
-		unsigned int start;
-		const struct pcpu_sw_netstats *bstats
-			= per_cpu_ptr(br->stats, cpu);
-		do {
-			start = u64_stats_fetch_begin_irq(&bstats->syncp);
-			memcpy(&tmp, bstats, sizeof(tmp));
-		} while (u64_stats_fetch_retry_irq(&bstats->syncp, start));
-		sum.tx_bytes   += tmp.tx_bytes;
-		sum.tx_packets += tmp.tx_packets;
-		sum.rx_bytes   += tmp.rx_bytes;
-		sum.rx_packets += tmp.rx_packets;
-	}
-
-	stats->tx_bytes   = sum.tx_bytes;
-	stats->tx_packets = sum.tx_packets;
-	stats->rx_bytes   = sum.rx_bytes;
-	stats->rx_packets = sum.rx_packets;
-}
-
 static int br_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct net_bridge *br = netdev_priv(dev);
@@ -422,7 +397,7 @@ static const struct net_device_ops br_netdev_ops = {
 	.ndo_init		 = br_dev_init,
 	.ndo_uninit		 = br_dev_uninit,
 	.ndo_start_xmit		 = br_dev_xmit,
-	.ndo_get_stats64	 = br_get_stats64,
+	.ndo_get_stats64	 = dev_get_tstats64,
 	.ndo_set_mac_address	 = br_set_mac_address,
 	.ndo_set_rx_mode	 = br_dev_set_multicast_list,
 	.ndo_change_rx_flags	 = br_dev_change_rx_flags,
@@ -473,8 +448,12 @@ void br_dev_setup(struct net_device *dev)
 	spin_lock_init(&br->lock);
 	INIT_LIST_HEAD(&br->port_list);
 	INIT_HLIST_HEAD(&br->fdb_list);
+	INIT_HLIST_HEAD(&br->frame_type_list);
 #if IS_ENABLED(CONFIG_BRIDGE_MRP)
-	INIT_LIST_HEAD(&br->mrp_list);
+	INIT_HLIST_HEAD(&br->mrp_list);
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_CFM)
+	INIT_HLIST_HEAD(&br->mep_list);
 #endif
 	spin_lock_init(&br->hash_lock);
 
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 7629b63f6f30..e28ffadd1371 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -274,14 +274,23 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 	struct net_bridge *br = netdev_priv(dev);
 	struct net_bridge_port *prev = NULL;
 	struct net_bridge_port_group *p;
+	bool allow_mode_include = true;
 	struct hlist_node *rp;
 
 	rp = rcu_dereference(hlist_first_rcu(&br->router_list));
-	p = mdst ? rcu_dereference(mdst->ports) : NULL;
+	if (mdst) {
+		p = rcu_dereference(mdst->ports);
+		if (br_multicast_should_handle_mode(br, mdst->addr.proto) &&
+		    br_multicast_is_star_g(&mdst->addr))
+			allow_mode_include = false;
+	} else {
+		p = NULL;
+	}
+
 	while (p || rp) {
 		struct net_bridge_port *port, *lport, *rport;
 
-		lport = p ? p->port : NULL;
+		lport = p ? p->key.port : NULL;
 		rport = hlist_entry_safe(rp, struct net_bridge_port, rlist);
 
 		if ((unsigned long)lport > (unsigned long)rport) {
@@ -292,6 +301,10 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst,
 						   local_orig);
 				goto delivered;
 			}
+			if ((!allow_mode_include &&
+			     p->filter_mode == MCAST_INCLUDE) ||
+			    (p->flags & MDB_PG_FLAGS_BLOCKED))
+				goto delivered;
 		} else {
 			port = rport;
 		}
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index a0e9a7937412..f7d2f472ae24 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -334,6 +334,7 @@ static void del_nbp(struct net_bridge_port *p)
 	spin_unlock_bh(&br->lock);
 
 	br_mrp_port_del(br, p);
+	br_cfm_port_del(br, p);
 
 	br_ifinfo_notify(RTM_DELLINK, NULL, p);
 
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 59a318b9f646..8ca1f1bc6d12 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -35,12 +35,8 @@ static int br_pass_frame_up(struct sk_buff *skb)
 	struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev;
 	struct net_bridge *br = netdev_priv(brdev);
 	struct net_bridge_vlan_group *vg;
-	struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats);
 
-	u64_stats_update_begin(&brstats->syncp);
-	brstats->rx_packets++;
-	brstats->rx_bytes += skb->len;
-	u64_stats_update_end(&brstats->syncp);
+	dev_sw_netstats_rx_add(brdev, skb->len);
 
 	vg = br_vlan_group_rcu(br);
 	/* Bridge is just like any other port.  Make sure the
@@ -134,7 +130,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb
 	case BR_PKT_MULTICAST:
 		mdst = br_mdb_get(br, skb, vid);
 		if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) &&
-		    br_multicast_querier_exists(br, eth_hdr(skb))) {
+		    br_multicast_querier_exists(br, eth_hdr(skb), mdst)) {
 			if ((mdst && mdst->host_joined) ||
 			    br_multicast_is_router(br)) {
 				local_rcv = true;
@@ -254,6 +250,21 @@ frame_finish:
 	return RX_HANDLER_CONSUMED;
 }
 
+/* Return 0 if the frame was not processed otherwise 1
+ * note: already called with rcu_read_lock
+ */
+static int br_process_frame_type(struct net_bridge_port *p,
+				 struct sk_buff *skb)
+{
+	struct br_frame_type *tmp;
+
+	hlist_for_each_entry_rcu(tmp, &p->br->frame_type_list, list)
+		if (unlikely(tmp->type == skb->protocol))
+			return tmp->frame_handler(p, skb);
+
+	return 0;
+}
+
 /*
  * Return NULL if skb is handled
  * note: already called with rcu_read_lock
@@ -343,7 +354,7 @@ static rx_handler_result_t br_handle_frame(struct sk_buff **pskb)
 		}
 	}
 
-	if (unlikely(br_mrp_process(p, skb)))
+	if (unlikely(br_process_frame_type(p, skb)))
 		return RX_HANDLER_PASS;
 
 forward:
@@ -380,3 +391,19 @@ rx_handler_func_t *br_get_rx_handler(const struct net_device *dev)
 
 	return br_handle_frame;
 }
+
+void br_add_frame(struct net_bridge *br, struct br_frame_type *ft)
+{
+	hlist_add_head_rcu(&ft->list, &br->frame_type_list);
+}
+
+void br_del_frame(struct net_bridge *br, struct br_frame_type *ft)
+{
+	struct br_frame_type *tmp;
+
+	hlist_for_each_entry(tmp, &br->frame_type_list, list)
+		if (ft == tmp) {
+			hlist_del_rcu(&ft->list);
+			return;
+		}
+}
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index 5e71fc8b826f..2db800fc27ca 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -103,7 +103,7 @@ static int add_del_if(struct net_bridge *br, int ifindex, int isadd)
 
 /*
  * Legacy ioctl's through SIOCDEVPRIVATE
- * This interface is deprecated because it was too difficult to
+ * This interface is deprecated because it was too difficult
  * to do the translation for 32/64bit ioctl compatibility.
  */
 static int old_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index da5ed4cf9233..8846c5bcd075 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -62,25 +62,98 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags)
 		e->flags |= MDB_FLAGS_OFFLOAD;
 	if (flags & MDB_PG_FLAGS_FAST_LEAVE)
 		e->flags |= MDB_FLAGS_FAST_LEAVE;
+	if (flags & MDB_PG_FLAGS_STAR_EXCL)
+		e->flags |= MDB_FLAGS_STAR_EXCL;
+	if (flags & MDB_PG_FLAGS_BLOCKED)
+		e->flags |= MDB_FLAGS_BLOCKED;
 }
 
-static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip)
+static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
+				 struct nlattr **mdb_attrs)
 {
 	memset(ip, 0, sizeof(struct br_ip));
 	ip->vid = entry->vid;
 	ip->proto = entry->addr.proto;
-	if (ip->proto == htons(ETH_P_IP))
-		ip->u.ip4 = entry->addr.u.ip4;
+	switch (ip->proto) {
+	case htons(ETH_P_IP):
+		ip->dst.ip4 = entry->addr.u.ip4;
+		if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE])
+			ip->src.ip4 = nla_get_in_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
+		break;
 #if IS_ENABLED(CONFIG_IPV6)
-	else
-		ip->u.ip6 = entry->addr.u.ip6;
+	case htons(ETH_P_IPV6):
+		ip->dst.ip6 = entry->addr.u.ip6;
+		if (mdb_attrs && mdb_attrs[MDBE_ATTR_SOURCE])
+			ip->src.ip6 = nla_get_in6_addr(mdb_attrs[MDBE_ATTR_SOURCE]);
+		break;
 #endif
+	default:
+		ether_addr_copy(ip->dst.mac_addr, entry->addr.u.mac_addr);
+	}
+
+}
+
+static int __mdb_fill_srcs(struct sk_buff *skb,
+			   struct net_bridge_port_group *p)
+{
+	struct net_bridge_group_src *ent;
+	struct nlattr *nest, *nest_ent;
+
+	if (hlist_empty(&p->src_list))
+		return 0;
+
+	nest = nla_nest_start(skb, MDBA_MDB_EATTR_SRC_LIST);
+	if (!nest)
+		return -EMSGSIZE;
+
+	hlist_for_each_entry_rcu(ent, &p->src_list, node,
+				 lockdep_is_held(&p->key.port->br->multicast_lock)) {
+		nest_ent = nla_nest_start(skb, MDBA_MDB_SRCLIST_ENTRY);
+		if (!nest_ent)
+			goto out_cancel_err;
+		switch (ent->addr.proto) {
+		case htons(ETH_P_IP):
+			if (nla_put_in_addr(skb, MDBA_MDB_SRCATTR_ADDRESS,
+					    ent->addr.src.ip4)) {
+				nla_nest_cancel(skb, nest_ent);
+				goto out_cancel_err;
+			}
+			break;
+#if IS_ENABLED(CONFIG_IPV6)
+		case htons(ETH_P_IPV6):
+			if (nla_put_in6_addr(skb, MDBA_MDB_SRCATTR_ADDRESS,
+					     &ent->addr.src.ip6)) {
+				nla_nest_cancel(skb, nest_ent);
+				goto out_cancel_err;
+			}
+			break;
+#endif
+		default:
+			nla_nest_cancel(skb, nest_ent);
+			continue;
+		}
+		if (nla_put_u32(skb, MDBA_MDB_SRCATTR_TIMER,
+				br_timer_value(&ent->timer))) {
+			nla_nest_cancel(skb, nest_ent);
+			goto out_cancel_err;
+		}
+		nla_nest_end(skb, nest_ent);
+	}
+
+	nla_nest_end(skb, nest);
+
+	return 0;
+
+out_cancel_err:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
 }
 
 static int __mdb_fill_info(struct sk_buff *skb,
 			   struct net_bridge_mdb_entry *mp,
 			   struct net_bridge_port_group *p)
 {
+	bool dump_srcs_mode = false;
 	struct timer_list *mtimer;
 	struct nlattr *nest_ent;
 	struct br_mdb_entry e;
@@ -89,7 +162,7 @@ static int __mdb_fill_info(struct sk_buff *skb,
 
 	memset(&e, 0, sizeof(e));
 	if (p) {
-		ifindex = p->port->dev->ifindex;
+		ifindex = p->key.port->dev->ifindex;
 		mtimer = &p->timer;
 		flags = p->flags;
 	} else {
@@ -101,11 +174,13 @@ static int __mdb_fill_info(struct sk_buff *skb,
 	e.ifindex = ifindex;
 	e.vid = mp->addr.vid;
 	if (mp->addr.proto == htons(ETH_P_IP))
-		e.addr.u.ip4 = mp->addr.u.ip4;
+		e.addr.u.ip4 = mp->addr.dst.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
-	if (mp->addr.proto == htons(ETH_P_IPV6))
-		e.addr.u.ip6 = mp->addr.u.ip6;
+	else if (mp->addr.proto == htons(ETH_P_IPV6))
+		e.addr.u.ip6 = mp->addr.dst.ip6;
 #endif
+	else
+		ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr);
 	e.addr.proto = mp->addr.proto;
 	nest_ent = nla_nest_start_noflag(skb,
 					 MDBA_MDB_ENTRY_INFO);
@@ -115,19 +190,55 @@ static int __mdb_fill_info(struct sk_buff *skb,
 	if (nla_put_nohdr(skb, sizeof(e), &e) ||
 	    nla_put_u32(skb,
 			MDBA_MDB_EATTR_TIMER,
-			br_timer_value(mtimer))) {
-		nla_nest_cancel(skb, nest_ent);
-		return -EMSGSIZE;
+			br_timer_value(mtimer)))
+		goto nest_err;
+
+	switch (mp->addr.proto) {
+	case htons(ETH_P_IP):
+		dump_srcs_mode = !!(mp->br->multicast_igmp_version == 3);
+		if (mp->addr.src.ip4) {
+			if (nla_put_in_addr(skb, MDBA_MDB_EATTR_SOURCE,
+					    mp->addr.src.ip4))
+				goto nest_err;
+			break;
+		}
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		dump_srcs_mode = !!(mp->br->multicast_mld_version == 2);
+		if (!ipv6_addr_any(&mp->addr.src.ip6)) {
+			if (nla_put_in6_addr(skb, MDBA_MDB_EATTR_SOURCE,
+					     &mp->addr.src.ip6))
+				goto nest_err;
+			break;
+		}
+		break;
+#endif
+	default:
+		ether_addr_copy(e.addr.u.mac_addr, mp->addr.dst.mac_addr);
+	}
+	if (p) {
+		if (nla_put_u8(skb, MDBA_MDB_EATTR_RTPROT, p->rt_protocol))
+			goto nest_err;
+		if (dump_srcs_mode &&
+		    (__mdb_fill_srcs(skb, p) ||
+		     nla_put_u8(skb, MDBA_MDB_EATTR_GROUP_MODE,
+				p->filter_mode)))
+			goto nest_err;
 	}
 	nla_nest_end(skb, nest_ent);
 
 	return 0;
+
+nest_err:
+	nla_nest_cancel(skb, nest_ent);
+	return -EMSGSIZE;
 }
 
 static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 			    struct net_device *dev)
 {
-	int idx = 0, s_idx = cb->args[1], err = 0;
+	int idx = 0, s_idx = cb->args[1], err = 0, pidx = 0, s_pidx = cb->args[2];
 	struct net_bridge *br = netdev_priv(dev);
 	struct net_bridge_mdb_entry *mp;
 	struct nlattr *nest, *nest2;
@@ -152,7 +263,7 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 			break;
 		}
 
-		if (mp->host_joined) {
+		if (!s_pidx && mp->host_joined) {
 			err = __mdb_fill_info(skb, mp, NULL);
 			if (err) {
 				nla_nest_cancel(skb, nest2);
@@ -162,15 +273,21 @@ static int br_mdb_fill_info(struct sk_buff *skb, struct netlink_callback *cb,
 
 		for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL;
 		      pp = &p->next) {
-			if (!p->port)
+			if (!p->key.port)
 				continue;
+			if (pidx < s_pidx)
+				goto skip_pg;
 
 			err = __mdb_fill_info(skb, mp, p);
 			if (err) {
-				nla_nest_cancel(skb, nest2);
+				nla_nest_end(skb, nest2);
 				goto out;
 			}
+skip_pg:
+			pidx++;
 		}
+		pidx = 0;
+		s_pidx = 0;
 		nla_nest_end(skb, nest2);
 skip:
 		idx++;
@@ -178,6 +295,7 @@ skip:
 
 out:
 	cb->args[1] = idx;
+	cb->args[2] = pidx;
 	nla_nest_end(skb, nest);
 	return err;
 }
@@ -263,14 +381,15 @@ out:
 
 static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
 				   struct net_device *dev,
-				   struct br_mdb_entry *entry, u32 pid,
-				   u32 seq, int type, unsigned int flags)
+				   struct net_bridge_mdb_entry *mp,
+				   struct net_bridge_port_group *pg,
+				   int type)
 {
 	struct nlmsghdr *nlh;
 	struct br_port_msg *bpm;
 	struct nlattr *nest, *nest2;
 
-	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*bpm), 0);
+	nlh = nlmsg_put(skb, 0, 0, type, sizeof(*bpm), 0);
 	if (!nlh)
 		return -EMSGSIZE;
 
@@ -285,7 +404,7 @@ static int nlmsg_populate_mdb_fill(struct sk_buff *skb,
 	if (nest2 == NULL)
 		goto end;
 
-	if (nla_put(skb, MDBA_MDB_ENTRY_INFO, sizeof(*entry), entry))
+	if (__mdb_fill_info(skb, mp, pg))
 		goto end;
 
 	nla_nest_end(skb, nest2);
@@ -300,10 +419,58 @@ cancel:
 	return -EMSGSIZE;
 }
 
-static inline size_t rtnl_mdb_nlmsg_size(void)
+static size_t rtnl_mdb_nlmsg_size(struct net_bridge_port_group *pg)
 {
-	return NLMSG_ALIGN(sizeof(struct br_port_msg))
-		+ nla_total_size(sizeof(struct br_mdb_entry));
+	size_t nlmsg_size = NLMSG_ALIGN(sizeof(struct br_port_msg)) +
+			    nla_total_size(sizeof(struct br_mdb_entry)) +
+			    nla_total_size(sizeof(u32));
+	struct net_bridge_group_src *ent;
+	size_t addr_size = 0;
+
+	if (!pg)
+		goto out;
+
+	/* MDBA_MDB_EATTR_RTPROT */
+	nlmsg_size += nla_total_size(sizeof(u8));
+
+	switch (pg->key.addr.proto) {
+	case htons(ETH_P_IP):
+		/* MDBA_MDB_EATTR_SOURCE */
+		if (pg->key.addr.src.ip4)
+			nlmsg_size += nla_total_size(sizeof(__be32));
+		if (pg->key.port->br->multicast_igmp_version == 2)
+			goto out;
+		addr_size = sizeof(__be32);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		/* MDBA_MDB_EATTR_SOURCE */
+		if (!ipv6_addr_any(&pg->key.addr.src.ip6))
+			nlmsg_size += nla_total_size(sizeof(struct in6_addr));
+		if (pg->key.port->br->multicast_mld_version == 1)
+			goto out;
+		addr_size = sizeof(struct in6_addr);
+		break;
+#endif
+	}
+
+	/* MDBA_MDB_EATTR_GROUP_MODE */
+	nlmsg_size += nla_total_size(sizeof(u8));
+
+	/* MDBA_MDB_EATTR_SRC_LIST nested attr */
+	if (!hlist_empty(&pg->src_list))
+		nlmsg_size += nla_total_size(0);
+
+	hlist_for_each_entry(ent, &pg->src_list, node) {
+		/* MDBA_MDB_SRCLIST_ENTRY nested attr +
+		 * MDBA_MDB_SRCATTR_ADDRESS + MDBA_MDB_SRCATTR_TIMER
+		 */
+		nlmsg_size += nla_total_size(0) +
+			      nla_total_size(addr_size) +
+			      nla_total_size(sizeof(u32));
+	}
+out:
+	return nlmsg_size;
 }
 
 struct br_mdb_complete_info {
@@ -329,7 +496,7 @@ static void br_mdb_complete(struct net_device *dev, int err, void *priv)
 		goto out;
 	for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
 	     pp = &p->next) {
-		if (p->port != port)
+		if (p->key.port != port)
 			continue;
 		p->flags |= MDB_PG_FLAGS_OFFLOAD;
 	}
@@ -341,21 +508,22 @@ err:
 
 static void br_mdb_switchdev_host_port(struct net_device *dev,
 				       struct net_device *lower_dev,
-				       struct br_mdb_entry *entry, int type)
+				       struct net_bridge_mdb_entry *mp,
+				       int type)
 {
 	struct switchdev_obj_port_mdb mdb = {
 		.obj = {
 			.id = SWITCHDEV_OBJ_ID_HOST_MDB,
 			.flags = SWITCHDEV_F_DEFER,
 		},
-		.vid = entry->vid,
+		.vid = mp->addr.vid,
 	};
 
-	if (entry->addr.proto == htons(ETH_P_IP))
-		ip_eth_mc_map(entry->addr.u.ip4, mdb.addr);
+	if (mp->addr.proto == htons(ETH_P_IP))
+		ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
 #if IS_ENABLED(CONFIG_IPV6)
 	else
-		ipv6_eth_mc_map(&entry->addr.u.ip6, mdb.addr);
+		ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
 #endif
 
 	mdb.obj.orig_dev = dev;
@@ -370,17 +538,19 @@ static void br_mdb_switchdev_host_port(struct net_device *dev,
 }
 
 static void br_mdb_switchdev_host(struct net_device *dev,
-				  struct br_mdb_entry *entry, int type)
+				  struct net_bridge_mdb_entry *mp, int type)
 {
 	struct net_device *lower_dev;
 	struct list_head *iter;
 
 	netdev_for_each_lower_dev(dev, lower_dev, iter)
-		br_mdb_switchdev_host_port(dev, lower_dev, entry, type);
+		br_mdb_switchdev_host_port(dev, lower_dev, mp, type);
 }
 
-static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p,
-			    struct br_mdb_entry *entry, int type)
+void br_mdb_notify(struct net_device *dev,
+		   struct net_bridge_mdb_entry *mp,
+		   struct net_bridge_port_group *pg,
+		   int type)
 {
 	struct br_mdb_complete_info *complete_info;
 	struct switchdev_obj_port_mdb mdb = {
@@ -388,44 +558,48 @@ static void __br_mdb_notify(struct net_device *dev, struct net_bridge_port *p,
 			.id = SWITCHDEV_OBJ_ID_PORT_MDB,
 			.flags = SWITCHDEV_F_DEFER,
 		},
-		.vid = entry->vid,
+		.vid = mp->addr.vid,
 	};
-	struct net_device *port_dev;
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 
-	port_dev = __dev_get_by_index(net, entry->ifindex);
-	if (entry->addr.proto == htons(ETH_P_IP))
-		ip_eth_mc_map(entry->addr.u.ip4, mdb.addr);
+	if (pg) {
+		if (mp->addr.proto == htons(ETH_P_IP))
+			ip_eth_mc_map(mp->addr.dst.ip4, mdb.addr);
 #if IS_ENABLED(CONFIG_IPV6)
-	else
-		ipv6_eth_mc_map(&entry->addr.u.ip6, mdb.addr);
+		else if (mp->addr.proto == htons(ETH_P_IPV6))
+			ipv6_eth_mc_map(&mp->addr.dst.ip6, mdb.addr);
 #endif
-
-	mdb.obj.orig_dev = port_dev;
-	if (p && port_dev && type == RTM_NEWMDB) {
-		complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC);
-		if (complete_info) {
-			complete_info->port = p;
-			__mdb_entry_to_br_ip(entry, &complete_info->ip);
+		else
+			ether_addr_copy(mdb.addr, mp->addr.dst.mac_addr);
+
+		mdb.obj.orig_dev = pg->key.port->dev;
+		switch (type) {
+		case RTM_NEWMDB:
+			complete_info = kmalloc(sizeof(*complete_info), GFP_ATOMIC);
+			if (!complete_info)
+				break;
+			complete_info->port = pg->key.port;
+			complete_info->ip = mp->addr;
 			mdb.obj.complete_priv = complete_info;
 			mdb.obj.complete = br_mdb_complete;
-			if (switchdev_port_obj_add(port_dev, &mdb.obj, NULL))
+			if (switchdev_port_obj_add(pg->key.port->dev, &mdb.obj, NULL))
 				kfree(complete_info);
+			break;
+		case RTM_DELMDB:
+			switchdev_port_obj_del(pg->key.port->dev, &mdb.obj);
+			break;
 		}
-	} else if (p && port_dev && type == RTM_DELMDB) {
-		switchdev_port_obj_del(port_dev, &mdb.obj);
+	} else {
+		br_mdb_switchdev_host(dev, mp, type);
 	}
 
-	if (!p)
-		br_mdb_switchdev_host(dev, entry, type);
-
-	skb = nlmsg_new(rtnl_mdb_nlmsg_size(), GFP_ATOMIC);
+	skb = nlmsg_new(rtnl_mdb_nlmsg_size(pg), GFP_ATOMIC);
 	if (!skb)
 		goto errout;
 
-	err = nlmsg_populate_mdb_fill(skb, dev, entry, 0, 0, type, NTF_SELF);
+	err = nlmsg_populate_mdb_fill(skb, dev, mp, pg, type);
 	if (err < 0) {
 		kfree_skb(skb);
 		goto errout;
@@ -437,26 +611,6 @@ errout:
 	rtnl_set_sk_err(net, RTNLGRP_MDB, err);
 }
 
-void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
-		   struct br_ip *group, int type, u8 flags)
-{
-	struct br_mdb_entry entry;
-
-	memset(&entry, 0, sizeof(entry));
-	if (port)
-		entry.ifindex = port->dev->ifindex;
-	else
-		entry.ifindex = dev->ifindex;
-	entry.addr.proto = group->proto;
-	entry.addr.u.ip4 = group->u.ip4;
-#if IS_ENABLED(CONFIG_IPV6)
-	entry.addr.u.ip6 = group->u.ip6;
-#endif
-	entry.vid = group->vid;
-	__mdb_entry_fill_flags(&entry, flags);
-	__br_mdb_notify(dev, port, &entry, type);
-}
-
 static int nlmsg_populate_rtr_fill(struct sk_buff *skb,
 				   struct net_device *dev,
 				   int ifindex, u32 pid,
@@ -524,33 +678,100 @@ errout:
 	rtnl_set_sk_err(net, RTNLGRP_MDB, err);
 }
 
-static bool is_valid_mdb_entry(struct br_mdb_entry *entry)
+static bool is_valid_mdb_entry(struct br_mdb_entry *entry,
+			       struct netlink_ext_ack *extack)
 {
-	if (entry->ifindex == 0)
+	if (entry->ifindex == 0) {
+		NL_SET_ERR_MSG_MOD(extack, "Zero entry ifindex is not allowed");
 		return false;
+	}
 
 	if (entry->addr.proto == htons(ETH_P_IP)) {
-		if (!ipv4_is_multicast(entry->addr.u.ip4))
+		if (!ipv4_is_multicast(entry->addr.u.ip4)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is not multicast");
 			return false;
-		if (ipv4_is_local_multicast(entry->addr.u.ip4))
+		}
+		if (ipv4_is_local_multicast(entry->addr.u.ip4)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 entry group address is local multicast");
 			return false;
+		}
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (entry->addr.proto == htons(ETH_P_IPV6)) {
-		if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6))
+		if (ipv6_addr_is_ll_all_nodes(&entry->addr.u.ip6)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 entry group address is link-local all nodes");
 			return false;
+		}
 #endif
-	} else
+	} else if (entry->addr.proto == 0) {
+		/* L2 mdb */
+		if (!is_multicast_ether_addr(entry->addr.u.mac_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "L2 entry group is not multicast");
+			return false;
+		}
+	} else {
+		NL_SET_ERR_MSG_MOD(extack, "Unknown entry protocol");
 		return false;
-	if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY)
+	}
+
+	if (entry->state != MDB_PERMANENT && entry->state != MDB_TEMPORARY) {
+		NL_SET_ERR_MSG_MOD(extack, "Unknown entry state");
 		return false;
-	if (entry->vid >= VLAN_VID_MASK)
+	}
+	if (entry->vid >= VLAN_VID_MASK) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid entry VLAN id");
 		return false;
+	}
 
 	return true;
 }
 
+static bool is_valid_mdb_source(struct nlattr *attr, __be16 proto,
+				struct netlink_ext_ack *extack)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+		if (nla_len(attr) != sizeof(struct in_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 invalid source address length");
+			return false;
+		}
+		if (ipv4_is_multicast(nla_get_in_addr(attr))) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv4 multicast source address is not allowed");
+			return false;
+		}
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6): {
+		struct in6_addr src;
+
+		if (nla_len(attr) != sizeof(struct in6_addr)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 invalid source address length");
+			return false;
+		}
+		src = nla_get_in6_addr(attr);
+		if (ipv6_addr_is_multicast(&src)) {
+			NL_SET_ERR_MSG_MOD(extack, "IPv6 multicast source address is not allowed");
+			return false;
+		}
+		break;
+	}
+#endif
+	default:
+		NL_SET_ERR_MSG_MOD(extack, "Invalid protocol used with source address");
+		return false;
+	}
+
+	return true;
+}
+
+static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = {
+	[MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY,
+					      sizeof(struct in_addr),
+					      sizeof(struct in6_addr)),
+};
+
 static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
-			struct net_device **pdev, struct br_mdb_entry **pentry)
+			struct net_device **pdev, struct br_mdb_entry **pentry,
+			struct nlattr **mdb_attrs, struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
 	struct br_mdb_entry *entry;
@@ -566,51 +787,92 @@ static int br_mdb_parse(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	bpm = nlmsg_data(nlh);
 	if (bpm->ifindex == 0) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with invalid ifindex\n");
+		NL_SET_ERR_MSG_MOD(extack, "Invalid bridge ifindex");
 		return -EINVAL;
 	}
 
 	dev = __dev_get_by_index(net, bpm->ifindex);
 	if (dev == NULL) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with unknown ifindex\n");
+		NL_SET_ERR_MSG_MOD(extack, "Bridge device doesn't exist");
 		return -ENODEV;
 	}
 
 	if (!(dev->priv_flags & IFF_EBRIDGE)) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with non-bridge\n");
+		NL_SET_ERR_MSG_MOD(extack, "Device is not a bridge");
 		return -EOPNOTSUPP;
 	}
 
 	*pdev = dev;
 
-	if (!tb[MDBA_SET_ENTRY] ||
-	    nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with invalid attr\n");
+	if (!tb[MDBA_SET_ENTRY]) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing MDBA_SET_ENTRY attribute");
+		return -EINVAL;
+	}
+	if (nla_len(tb[MDBA_SET_ENTRY]) != sizeof(struct br_mdb_entry)) {
+		NL_SET_ERR_MSG_MOD(extack, "Invalid MDBA_SET_ENTRY attribute length");
 		return -EINVAL;
 	}
 
 	entry = nla_data(tb[MDBA_SET_ENTRY]);
-	if (!is_valid_mdb_entry(entry)) {
-		pr_info("PF_BRIDGE: br_mdb_parse() with invalid entry\n");
+	if (!is_valid_mdb_entry(entry, extack))
 		return -EINVAL;
+	*pentry = entry;
+
+	if (tb[MDBA_SET_ENTRY_ATTRS]) {
+		err = nla_parse_nested(mdb_attrs, MDBE_ATTR_MAX,
+				       tb[MDBA_SET_ENTRY_ATTRS],
+				       br_mdbe_attrs_pol, extack);
+		if (err)
+			return err;
+		if (mdb_attrs[MDBE_ATTR_SOURCE] &&
+		    !is_valid_mdb_source(mdb_attrs[MDBE_ATTR_SOURCE],
+					 entry->addr.proto, extack))
+			return -EINVAL;
+	} else {
+		memset(mdb_attrs, 0,
+		       sizeof(struct nlattr *) * (MDBE_ATTR_MAX + 1));
 	}
 
-	*pentry = entry;
 	return 0;
 }
 
 static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
-			    struct br_ip *group, unsigned char state)
+			    struct br_mdb_entry *entry,
+			    struct nlattr **mdb_attrs,
+			    struct netlink_ext_ack *extack)
 {
-	struct net_bridge_mdb_entry *mp;
+	struct net_bridge_mdb_entry *mp, *star_mp;
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
+	struct br_ip group, star_group;
 	unsigned long now = jiffies;
+	unsigned char flags = 0;
+	u8 filter_mode;
 	int err;
 
-	mp = br_mdb_ip_get(br, group);
+	__mdb_entry_to_br_ip(entry, &group, mdb_attrs);
+
+	/* host join errors which can happen before creating the group */
+	if (!port) {
+		/* don't allow any flags for host-joined groups */
+		if (entry->state) {
+			NL_SET_ERR_MSG_MOD(extack, "Flags are not allowed for host groups");
+			return -EINVAL;
+		}
+		if (!br_multicast_is_star_g(&group)) {
+			NL_SET_ERR_MSG_MOD(extack, "Groups with sources cannot be manually host joined");
+			return -EINVAL;
+		}
+	}
+
+	if (br_group_is_l2(&group) && entry->state != MDB_PERMANENT) {
+		NL_SET_ERR_MSG_MOD(extack, "Only permanent L2 entries allowed");
+		return -EINVAL;
+	}
+
+	mp = br_mdb_ip_get(br, &group);
 	if (!mp) {
-		mp = br_multicast_new_group(br, group);
+		mp = br_multicast_new_group(br, &group);
 		err = PTR_ERR_OR_ZERO(mp);
 		if (err)
 			return err;
@@ -618,13 +880,13 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 
 	/* host join */
 	if (!port) {
-		/* don't allow any flags for host-joined groups */
-		if (state)
-			return -EINVAL;
-		if (mp->host_joined)
+		if (mp->host_joined) {
+			NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host");
 			return -EEXIST;
+		}
 
 		br_multicast_host_join(mp, false);
+		br_mdb_notify(br->dev, mp, NULL, RTM_NEWMDB);
 
 		return 0;
 	}
@@ -632,54 +894,72 @@ static int br_mdb_add_group(struct net_bridge *br, struct net_bridge_port *port,
 	for (pp = &mp->ports;
 	     (p = mlock_dereference(*pp, br)) != NULL;
 	     pp = &p->next) {
-		if (p->port == port)
+		if (p->key.port == port) {
+			NL_SET_ERR_MSG_MOD(extack, "Group is already joined by port");
 			return -EEXIST;
-		if ((unsigned long)p->port < (unsigned long)port)
+		}
+		if ((unsigned long)p->key.port < (unsigned long)port)
 			break;
 	}
 
-	p = br_multicast_new_port_group(port, group, *pp, state, NULL);
-	if (unlikely(!p))
+	filter_mode = br_multicast_is_star_g(&group) ? MCAST_EXCLUDE :
+						       MCAST_INCLUDE;
+
+	if (entry->state == MDB_PERMANENT)
+		flags |= MDB_PG_FLAGS_PERMANENT;
+
+	p = br_multicast_new_port_group(port, &group, *pp, flags, NULL,
+					filter_mode, RTPROT_STATIC);
+	if (unlikely(!p)) {
+		NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new port group");
 		return -ENOMEM;
+	}
 	rcu_assign_pointer(*pp, p);
-	if (state == MDB_TEMPORARY)
+	if (entry->state == MDB_TEMPORARY)
 		mod_timer(&p->timer, now + br->multicast_membership_interval);
+	br_mdb_notify(br->dev, mp, p, RTM_NEWMDB);
+	/* if we are adding a new EXCLUDE port group (*,G) it needs to be also
+	 * added to all S,G entries for proper replication, if we are adding
+	 * a new INCLUDE port (S,G) then all of *,G EXCLUDE ports need to be
+	 * added to it for proper replication
+	 */
+	if (br_multicast_should_handle_mode(br, group.proto)) {
+		switch (filter_mode) {
+		case MCAST_EXCLUDE:
+			br_multicast_star_g_handle_mode(p, MCAST_EXCLUDE);
+			break;
+		case MCAST_INCLUDE:
+			star_group = p->key.addr;
+			memset(&star_group.src, 0, sizeof(star_group.src));
+			star_mp = br_mdb_ip_get(br, &star_group);
+			if (star_mp)
+				br_multicast_sg_add_exclude_ports(star_mp, p);
+			break;
+		}
+	}
 
 	return 0;
 }
 
 static int __br_mdb_add(struct net *net, struct net_bridge *br,
-			struct br_mdb_entry *entry)
+			struct net_bridge_port *p,
+			struct br_mdb_entry *entry,
+			struct nlattr **mdb_attrs,
+			struct netlink_ext_ack *extack)
 {
-	struct br_ip ip;
-	struct net_device *dev;
-	struct net_bridge_port *p = NULL;
 	int ret;
 
-	if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED))
-		return -EINVAL;
-
-	if (entry->ifindex != br->dev->ifindex) {
-		dev = __dev_get_by_index(net, entry->ifindex);
-		if (!dev)
-			return -ENODEV;
-
-		p = br_port_get_rtnl(dev);
-		if (!p || p->br != br || p->state == BR_STATE_DISABLED)
-			return -EINVAL;
-	}
-
-	__mdb_entry_to_br_ip(entry, &ip);
-
 	spin_lock_bh(&br->multicast_lock);
-	ret = br_mdb_add_group(br, p, &ip, entry->state);
+	ret = br_mdb_add_group(br, p, entry, mdb_attrs, extack);
 	spin_unlock_bh(&br->multicast_lock);
+
 	return ret;
 }
 
 static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		      struct netlink_ext_ack *extack)
 {
+	struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p = NULL;
@@ -689,20 +969,43 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_bridge *br;
 	int err;
 
-	err = br_mdb_parse(skb, nlh, &dev, &entry);
+	err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack);
 	if (err < 0)
 		return err;
 
 	br = netdev_priv(dev);
 
+	if (!netif_running(br->dev)) {
+		NL_SET_ERR_MSG_MOD(extack, "Bridge device is not running");
+		return -EINVAL;
+	}
+
+	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) {
+		NL_SET_ERR_MSG_MOD(extack, "Bridge's multicast processing is disabled");
+		return -EINVAL;
+	}
+
 	if (entry->ifindex != br->dev->ifindex) {
 		pdev = __dev_get_by_index(net, entry->ifindex);
-		if (!pdev)
+		if (!pdev) {
+			NL_SET_ERR_MSG_MOD(extack, "Port net device doesn't exist");
 			return -ENODEV;
+		}
 
 		p = br_port_get_rtnl(pdev);
-		if (!p || p->br != br || p->state == BR_STATE_DISABLED)
+		if (!p) {
+			NL_SET_ERR_MSG_MOD(extack, "Net device is not a bridge port");
+			return -EINVAL;
+		}
+
+		if (p->br != br) {
+			NL_SET_ERR_MSG_MOD(extack, "Port belongs to a different bridge device");
 			return -EINVAL;
+		}
+		if (p->state == BR_STATE_DISABLED) {
+			NL_SET_ERR_MSG_MOD(extack, "Port is in disabled state");
+			return -EINVAL;
+		}
 		vg = nbp_vlan_group(p);
 	} else {
 		vg = br_vlan_group(br);
@@ -714,21 +1017,19 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) {
 		list_for_each_entry(v, &vg->vlan_list, vlist) {
 			entry->vid = v->vid;
-			err = __br_mdb_add(net, br, entry);
+			err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack);
 			if (err)
 				break;
-			__br_mdb_notify(dev, p, entry, RTM_NEWMDB);
 		}
 	} else {
-		err = __br_mdb_add(net, br, entry);
-		if (!err)
-			__br_mdb_notify(dev, p, entry, RTM_NEWMDB);
+		err = __br_mdb_add(net, br, p, entry, mdb_attrs, extack);
 	}
 
 	return err;
 }
 
-static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
+static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry,
+			struct nlattr **mdb_attrs)
 {
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
@@ -739,7 +1040,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	if (!netif_running(br->dev) || !br_opt_get(br, BROPT_MULTICAST_ENABLED))
 		return -EINVAL;
 
-	__mdb_entry_to_br_ip(entry, &ip);
+	__mdb_entry_to_br_ip(entry, &ip, mdb_attrs);
 
 	spin_lock_bh(&br->multicast_lock);
 	mp = br_mdb_ip_get(br, &ip);
@@ -750,6 +1051,7 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	if (entry->ifindex == mp->br->dev->ifindex && mp->host_joined) {
 		br_multicast_host_leave(mp, false);
 		err = 0;
+		br_mdb_notify(br->dev, mp, NULL, RTM_DELMDB);
 		if (!mp->ports && netif_running(br->dev))
 			mod_timer(&mp->timer, jiffies);
 		goto unlock;
@@ -758,22 +1060,14 @@ static int __br_mdb_del(struct net_bridge *br, struct br_mdb_entry *entry)
 	for (pp = &mp->ports;
 	     (p = mlock_dereference(*pp, br)) != NULL;
 	     pp = &p->next) {
-		if (!p->port || p->port->dev->ifindex != entry->ifindex)
+		if (!p->key.port || p->key.port->dev->ifindex != entry->ifindex)
 			continue;
 
-		if (p->port->state == BR_STATE_DISABLED)
+		if (p->key.port->state == BR_STATE_DISABLED)
 			goto unlock;
 
-		__mdb_entry_fill_flags(entry, p->flags);
-		rcu_assign_pointer(*pp, p->next);
-		hlist_del_init(&p->mglist);
-		del_timer(&p->timer);
-		kfree_rcu(p, rcu);
+		br_multicast_del_pg(mp, p, pp);
 		err = 0;
-
-		if (!mp->ports && !mp->host_joined &&
-		    netif_running(br->dev))
-			mod_timer(&mp->timer, jiffies);
 		break;
 	}
 
@@ -785,6 +1079,7 @@ unlock:
 static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		      struct netlink_ext_ack *extack)
 {
+	struct nlattr *mdb_attrs[MDBE_ATTR_MAX + 1];
 	struct net *net = sock_net(skb->sk);
 	struct net_bridge_vlan_group *vg;
 	struct net_bridge_port *p = NULL;
@@ -794,7 +1089,7 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net_bridge *br;
 	int err;
 
-	err = br_mdb_parse(skb, nlh, &dev, &entry);
+	err = br_mdb_parse(skb, nlh, &dev, &entry, mdb_attrs, extack);
 	if (err < 0)
 		return err;
 
@@ -819,14 +1114,10 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (br_vlan_enabled(br->dev) && vg && entry->vid == 0) {
 		list_for_each_entry(v, &vg->vlan_list, vlist) {
 			entry->vid = v->vid;
-			err = __br_mdb_del(br, entry);
-			if (!err)
-				__br_mdb_notify(dev, p, entry, RTM_DELMDB);
+			err = __br_mdb_del(br, entry, mdb_attrs);
 		}
 	} else {
-		err = __br_mdb_del(br, entry);
-		if (!err)
-			__br_mdb_notify(dev, p, entry, RTM_DELMDB);
+		err = __br_mdb_del(br, entry, mdb_attrs);
 	}
 
 	return err;
diff --git a/net/bridge/br_mrp.c b/net/bridge/br_mrp.c
index b36689e6e7cb..5aeae6ad17b3 100644
--- a/net/bridge/br_mrp.c
+++ b/net/bridge/br_mrp.c
@@ -6,6 +6,13 @@
 static const u8 mrp_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x1 };
 static const u8 mrp_in_test_dmac[ETH_ALEN] = { 0x1, 0x15, 0x4e, 0x0, 0x0, 0x3 };
 
+static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb);
+
+static struct br_frame_type mrp_frame_type __read_mostly = {
+	.type = cpu_to_be16(ETH_P_MRP),
+	.frame_handler = br_mrp_process,
+};
+
 static bool br_mrp_is_ring_port(struct net_bridge_port *p_port,
 				struct net_bridge_port *s_port,
 				struct net_bridge_port *port)
@@ -47,8 +54,8 @@ static struct br_mrp *br_mrp_find_id(struct net_bridge *br, u32 ring_id)
 	struct br_mrp *res = NULL;
 	struct br_mrp *mrp;
 
-	list_for_each_entry_rcu(mrp, &br->mrp_list, list,
-				lockdep_rtnl_is_held()) {
+	hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+				 lockdep_rtnl_is_held()) {
 		if (mrp->ring_id == ring_id) {
 			res = mrp;
 			break;
@@ -63,8 +70,8 @@ static struct br_mrp *br_mrp_find_in_id(struct net_bridge *br, u32 in_id)
 	struct br_mrp *res = NULL;
 	struct br_mrp *mrp;
 
-	list_for_each_entry_rcu(mrp, &br->mrp_list, list,
-				lockdep_rtnl_is_held()) {
+	hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+				 lockdep_rtnl_is_held()) {
 		if (mrp->in_id == in_id) {
 			res = mrp;
 			break;
@@ -78,8 +85,8 @@ static bool br_mrp_unique_ifindex(struct net_bridge *br, u32 ifindex)
 {
 	struct br_mrp *mrp;
 
-	list_for_each_entry_rcu(mrp, &br->mrp_list, list,
-				lockdep_rtnl_is_held()) {
+	hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+				 lockdep_rtnl_is_held()) {
 		struct net_bridge_port *p;
 
 		p = rtnl_dereference(mrp->p_port);
@@ -104,8 +111,8 @@ static struct br_mrp *br_mrp_find_port(struct net_bridge *br,
 	struct br_mrp *res = NULL;
 	struct br_mrp *mrp;
 
-	list_for_each_entry_rcu(mrp, &br->mrp_list, list,
-				lockdep_rtnl_is_held()) {
+	hlist_for_each_entry_rcu(mrp, &br->mrp_list, list,
+				 lockdep_rtnl_is_held()) {
 		if (rcu_access_pointer(mrp->p_port) == p ||
 		    rcu_access_pointer(mrp->s_port) == p ||
 		    rcu_access_pointer(mrp->i_port) == p) {
@@ -443,8 +450,11 @@ static void br_mrp_del_impl(struct net_bridge *br, struct br_mrp *mrp)
 		rcu_assign_pointer(mrp->i_port, NULL);
 	}
 
-	list_del_rcu(&mrp->list);
+	hlist_del_rcu(&mrp->list);
 	kfree_rcu(mrp, rcu);
+
+	if (hlist_empty(&br->mrp_list))
+		br_del_frame(br, &mrp_frame_type);
 }
 
 /* Adds a new MRP instance.
@@ -493,9 +503,12 @@ int br_mrp_add(struct net_bridge *br, struct br_mrp_instance *instance)
 	spin_unlock_bh(&br->lock);
 	rcu_assign_pointer(mrp->s_port, p);
 
+	if (hlist_empty(&br->mrp_list))
+		br_add_frame(br, &mrp_frame_type);
+
 	INIT_DELAYED_WORK(&mrp->test_work, br_mrp_test_work_expired);
 	INIT_DELAYED_WORK(&mrp->in_test_work, br_mrp_in_test_work_expired);
-	list_add_tail_rcu(&mrp->list, &br->mrp_list);
+	hlist_add_tail_rcu(&mrp->list, &br->mrp_list);
 
 	err = br_mrp_switchdev_add(br, mrp);
 	if (err)
@@ -544,19 +557,22 @@ int br_mrp_del(struct net_bridge *br, struct br_mrp_instance *instance)
 int br_mrp_set_port_state(struct net_bridge_port *p,
 			  enum br_mrp_port_state_type state)
 {
+	u32 port_state;
+
 	if (!p || !(p->flags & BR_MRP_AWARE))
 		return -EINVAL;
 
 	spin_lock_bh(&p->br->lock);
 
 	if (state == BR_MRP_PORT_STATE_FORWARDING)
-		p->state = BR_STATE_FORWARDING;
+		port_state = BR_STATE_FORWARDING;
 	else
-		p->state = BR_STATE_BLOCKING;
+		port_state = BR_STATE_BLOCKING;
 
+	p->state = port_state;
 	spin_unlock_bh(&p->br->lock);
 
-	br_mrp_port_switchdev_set_state(p, state);
+	br_mrp_port_switchdev_set_state(p, port_state);
 
 	return 0;
 }
@@ -845,7 +861,8 @@ static bool br_mrp_in_frame(struct sk_buff *skb)
 	if (hdr->type == BR_MRP_TLV_HEADER_IN_TEST ||
 	    hdr->type == BR_MRP_TLV_HEADER_IN_TOPO ||
 	    hdr->type == BR_MRP_TLV_HEADER_IN_LINK_DOWN ||
-	    hdr->type == BR_MRP_TLV_HEADER_IN_LINK_UP)
+	    hdr->type == BR_MRP_TLV_HEADER_IN_LINK_UP ||
+	    hdr->type == BR_MRP_TLV_HEADER_IN_LINK_STATUS)
 		return true;
 
 	return false;
@@ -1113,9 +1130,9 @@ static int br_mrp_rcv(struct net_bridge_port *p,
 						goto no_forward;
 				}
 			} else {
-				/* MIM should forward IntLinkChange and
+				/* MIM should forward IntLinkChange/Status and
 				 * IntTopoChange between ring ports but MIM
-				 * should not forward IntLinkChange and
+				 * should not forward IntLinkChange/Status and
 				 * IntTopoChange if the frame was received at
 				 * the interconnect port
 				 */
@@ -1142,6 +1159,17 @@ static int br_mrp_rcv(struct net_bridge_port *p,
 			     in_type == BR_MRP_TLV_HEADER_IN_LINK_DOWN))
 				goto forward;
 
+			/* MIC should forward IntLinkStatus frames only to
+			 * interconnect port if it was received on a ring port.
+			 * If it is received on interconnect port then, it
+			 * should be forward on both ring ports
+			 */
+			if (br_mrp_is_ring_port(p_port, s_port, p) &&
+			    in_type == BR_MRP_TLV_HEADER_IN_LINK_STATUS) {
+				p_dst = NULL;
+				s_dst = NULL;
+			}
+
 			/* Should forward the InTopo frames only between the
 			 * ring ports
 			 */
@@ -1172,20 +1200,18 @@ no_forward:
  * normal forwarding.
  * note: already called with rcu_read_lock
  */
-int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
+static int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
 {
 	/* If there is no MRP instance do normal forwarding */
 	if (likely(!(p->flags & BR_MRP_AWARE)))
 		goto out;
 
-	if (unlikely(skb->protocol == htons(ETH_P_MRP)))
-		return br_mrp_rcv(p, skb, p->dev);
-
+	return br_mrp_rcv(p, skb, p->dev);
 out:
 	return 0;
 }
 
 bool br_mrp_enabled(struct net_bridge *br)
 {
-	return !list_empty(&br->mrp_list);
+	return !hlist_empty(&br->mrp_list);
 }
diff --git a/net/bridge/br_mrp_netlink.c b/net/bridge/br_mrp_netlink.c
index 2a2fdf3500c5..ce6f63c77cc0 100644
--- a/net/bridge/br_mrp_netlink.c
+++ b/net/bridge/br_mrp_netlink.c
@@ -453,7 +453,7 @@ int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br)
 	if (!mrp_tb)
 		return -EMSGSIZE;
 
-	list_for_each_entry_rcu(mrp, &br->mrp_list, list) {
+	hlist_for_each_entry_rcu(mrp, &br->mrp_list, list) {
 		struct net_bridge_port *p;
 
 		tb = nla_nest_start_noflag(skb, IFLA_BRIDGE_MRP_INFO);
diff --git a/net/bridge/br_mrp_switchdev.c b/net/bridge/br_mrp_switchdev.c
index ed547e03ace1..75a7e8d0a268 100644
--- a/net/bridge/br_mrp_switchdev.c
+++ b/net/bridge/br_mrp_switchdev.c
@@ -169,13 +169,12 @@ int br_mrp_switchdev_send_in_test(struct net_bridge *br, struct br_mrp *mrp,
 	return err;
 }
 
-int br_mrp_port_switchdev_set_state(struct net_bridge_port *p,
-				    enum br_mrp_port_state_type state)
+int br_mrp_port_switchdev_set_state(struct net_bridge_port *p, u32 state)
 {
 	struct switchdev_attr attr = {
 		.orig_dev = p->dev,
-		.id = SWITCHDEV_ATTR_ID_MRP_PORT_STATE,
-		.u.mrp_port_state = state,
+		.id = SWITCHDEV_ATTR_ID_PORT_STP_STATE,
+		.u.stp_state = state,
 	};
 	int err;
 
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 4c4a93abde68..257ac4e25f6d 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -41,6 +41,13 @@ static const struct rhashtable_params br_mdb_rht_params = {
 	.automatic_shrinking = true,
 };
 
+static const struct rhashtable_params br_sg_port_rht_params = {
+	.head_offset = offsetof(struct net_bridge_port_group, rhnode),
+	.key_offset = offsetof(struct net_bridge_port_group, key),
+	.key_len = sizeof(struct net_bridge_port_group_sg_key),
+	.automatic_shrinking = true,
+};
+
 static void br_multicast_start_querier(struct net_bridge *br,
 				       struct bridge_mcast_own_query *query);
 static void br_multicast_add_router(struct net_bridge *br,
@@ -50,6 +57,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 					 __be32 group,
 					 __u16 vid,
 					 const unsigned char *src);
+static void br_multicast_port_group_rexmit(struct timer_list *t);
 
 static void __del_port_router(struct net_bridge_port *p);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -58,6 +66,26 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 					 const struct in6_addr *group,
 					 __u16 vid, const unsigned char *src);
 #endif
+static struct net_bridge_port_group *
+__br_multicast_add_group(struct net_bridge *br,
+			 struct net_bridge_port *port,
+			 struct br_ip *group,
+			 const unsigned char *src,
+			 u8 filter_mode,
+			 bool igmpv2_mldv1,
+			 bool blocked);
+static void br_multicast_find_del_pg(struct net_bridge *br,
+				     struct net_bridge_port_group *pg);
+
+static struct net_bridge_port_group *
+br_sg_port_find(struct net_bridge *br,
+		struct net_bridge_port_group_sg_key *sg_p)
+{
+	lockdep_assert_held_once(&br->multicast_lock);
+
+	return rhashtable_lookup_fast(&br->sg_port_tbl, sg_p,
+				      br_sg_port_rht_params);
+}
 
 static struct net_bridge_mdb_entry *br_mdb_ip_get_rcu(struct net_bridge *br,
 						      struct br_ip *dst)
@@ -85,7 +113,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br,
 	struct br_ip br_dst;
 
 	memset(&br_dst, 0, sizeof(br_dst));
-	br_dst.u.ip4 = dst;
+	br_dst.dst.ip4 = dst;
 	br_dst.proto = htons(ETH_P_IP);
 	br_dst.vid = vid;
 
@@ -100,7 +128,7 @@ static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br,
 	struct br_ip br_dst;
 
 	memset(&br_dst, 0, sizeof(br_dst));
-	br_dst.u.ip6 = *dst;
+	br_dst.dst.ip6 = *dst;
 	br_dst.proto = htons(ETH_P_IPV6);
 	br_dst.vid = vid;
 
@@ -125,52 +153,471 @@ struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br,
 
 	switch (skb->protocol) {
 	case htons(ETH_P_IP):
-		ip.u.ip4 = ip_hdr(skb)->daddr;
+		ip.dst.ip4 = ip_hdr(skb)->daddr;
+		if (br->multicast_igmp_version == 3) {
+			struct net_bridge_mdb_entry *mdb;
+
+			ip.src.ip4 = ip_hdr(skb)->saddr;
+			mdb = br_mdb_ip_get_rcu(br, &ip);
+			if (mdb)
+				return mdb;
+			ip.src.ip4 = 0;
+		}
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		ip.u.ip6 = ipv6_hdr(skb)->daddr;
+		ip.dst.ip6 = ipv6_hdr(skb)->daddr;
+		if (br->multicast_mld_version == 2) {
+			struct net_bridge_mdb_entry *mdb;
+
+			ip.src.ip6 = ipv6_hdr(skb)->saddr;
+			mdb = br_mdb_ip_get_rcu(br, &ip);
+			if (mdb)
+				return mdb;
+			memset(&ip.src.ip6, 0, sizeof(ip.src.ip6));
+		}
 		break;
 #endif
 	default:
-		return NULL;
+		ip.proto = 0;
+		ether_addr_copy(ip.dst.mac_addr, eth_hdr(skb)->h_dest);
 	}
 
 	return br_mdb_ip_get_rcu(br, &ip);
 }
 
+static bool br_port_group_equal(struct net_bridge_port_group *p,
+				struct net_bridge_port *port,
+				const unsigned char *src)
+{
+	if (p->key.port != port)
+		return false;
+
+	if (!(port->flags & BR_MULTICAST_TO_UNICAST))
+		return true;
+
+	return ether_addr_equal(src, p->eth_addr);
+}
+
+static void __fwd_add_star_excl(struct net_bridge_port_group *pg,
+				struct br_ip *sg_ip)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_port_group *src_pg;
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.port = pg->key.port;
+	sg_key.addr = *sg_ip;
+	if (br_sg_port_find(br, &sg_key))
+		return;
+
+	src_pg = __br_multicast_add_group(br, pg->key.port, sg_ip, pg->eth_addr,
+					  MCAST_INCLUDE, false, false);
+	if (IS_ERR_OR_NULL(src_pg) ||
+	    src_pg->rt_protocol != RTPROT_KERNEL)
+		return;
+
+	src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
+}
+
+static void __fwd_del_star_excl(struct net_bridge_port_group *pg,
+				struct br_ip *sg_ip)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_port_group *src_pg;
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.port = pg->key.port;
+	sg_key.addr = *sg_ip;
+	src_pg = br_sg_port_find(br, &sg_key);
+	if (!src_pg || !(src_pg->flags & MDB_PG_FLAGS_STAR_EXCL) ||
+	    src_pg->rt_protocol != RTPROT_KERNEL)
+		return;
+
+	br_multicast_find_del_pg(br, src_pg);
+}
+
+/* When a port group transitions to (or is added as) EXCLUDE we need to add it
+ * to all other ports' S,G entries which are not blocked by the current group
+ * for proper replication, the assumption is that any S,G blocked entries
+ * are already added so the S,G,port lookup should skip them.
+ * When a port group transitions from EXCLUDE -> INCLUDE mode or is being
+ * deleted we need to remove it from all ports' S,G entries where it was
+ * automatically installed before (i.e. where it's MDB_PG_FLAGS_STAR_EXCL).
+ */
+void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
+				     u8 filter_mode)
+{
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_port_group *pg_lst;
+	struct net_bridge_mdb_entry *mp;
+	struct br_ip sg_ip;
+
+	if (WARN_ON(!br_multicast_is_star_g(&pg->key.addr)))
+		return;
+
+	mp = br_mdb_ip_get(br, &pg->key.addr);
+	if (!mp)
+		return;
+
+	memset(&sg_ip, 0, sizeof(sg_ip));
+	sg_ip = pg->key.addr;
+	for (pg_lst = mlock_dereference(mp->ports, br);
+	     pg_lst;
+	     pg_lst = mlock_dereference(pg_lst->next, br)) {
+		struct net_bridge_group_src *src_ent;
+
+		if (pg_lst == pg)
+			continue;
+		hlist_for_each_entry(src_ent, &pg_lst->src_list, node) {
+			if (!(src_ent->flags & BR_SGRP_F_INSTALLED))
+				continue;
+			sg_ip.src = src_ent->addr.src;
+			switch (filter_mode) {
+			case MCAST_INCLUDE:
+				__fwd_del_star_excl(pg, &sg_ip);
+				break;
+			case MCAST_EXCLUDE:
+				__fwd_add_star_excl(pg, &sg_ip);
+				break;
+			}
+		}
+	}
+}
+
+/* called when adding a new S,G with host_joined == false by default */
+static void br_multicast_sg_host_state(struct net_bridge_mdb_entry *star_mp,
+				       struct net_bridge_port_group *sg)
+{
+	struct net_bridge_mdb_entry *sg_mp;
+
+	if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
+		return;
+	if (!star_mp->host_joined)
+		return;
+
+	sg_mp = br_mdb_ip_get(star_mp->br, &sg->key.addr);
+	if (!sg_mp)
+		return;
+	sg_mp->host_joined = true;
+}
+
+/* set the host_joined state of all of *,G's S,G entries */
+static void br_multicast_star_g_host_state(struct net_bridge_mdb_entry *star_mp)
+{
+	struct net_bridge *br = star_mp->br;
+	struct net_bridge_mdb_entry *sg_mp;
+	struct net_bridge_port_group *pg;
+	struct br_ip sg_ip;
+
+	if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
+		return;
+
+	memset(&sg_ip, 0, sizeof(sg_ip));
+	sg_ip = star_mp->addr;
+	for (pg = mlock_dereference(star_mp->ports, br);
+	     pg;
+	     pg = mlock_dereference(pg->next, br)) {
+		struct net_bridge_group_src *src_ent;
+
+		hlist_for_each_entry(src_ent, &pg->src_list, node) {
+			if (!(src_ent->flags & BR_SGRP_F_INSTALLED))
+				continue;
+			sg_ip.src = src_ent->addr.src;
+			sg_mp = br_mdb_ip_get(br, &sg_ip);
+			if (!sg_mp)
+				continue;
+			sg_mp->host_joined = star_mp->host_joined;
+		}
+	}
+}
+
+static void br_multicast_sg_del_exclude_ports(struct net_bridge_mdb_entry *sgmp)
+{
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_port_group *p;
+
+	/* *,G exclude ports are only added to S,G entries */
+	if (WARN_ON(br_multicast_is_star_g(&sgmp->addr)))
+		return;
+
+	/* we need the STAR_EXCLUDE ports if there are non-STAR_EXCLUDE ports
+	 * we should ignore perm entries since they're managed by user-space
+	 */
+	for (pp = &sgmp->ports;
+	     (p = mlock_dereference(*pp, sgmp->br)) != NULL;
+	     pp = &p->next)
+		if (!(p->flags & (MDB_PG_FLAGS_STAR_EXCL |
+				  MDB_PG_FLAGS_PERMANENT)))
+			return;
+
+	/* currently the host can only have joined the *,G which means
+	 * we treat it as EXCLUDE {}, so for an S,G it's considered a
+	 * STAR_EXCLUDE entry and we can safely leave it
+	 */
+	sgmp->host_joined = false;
+
+	for (pp = &sgmp->ports;
+	     (p = mlock_dereference(*pp, sgmp->br)) != NULL;) {
+		if (!(p->flags & MDB_PG_FLAGS_PERMANENT))
+			br_multicast_del_pg(sgmp, p, pp);
+		else
+			pp = &p->next;
+	}
+}
+
+void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
+				       struct net_bridge_port_group *sg)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge *br = star_mp->br;
+	struct net_bridge_port_group *pg;
+
+	if (WARN_ON(br_multicast_is_star_g(&sg->key.addr)))
+		return;
+	if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
+		return;
+
+	br_multicast_sg_host_state(star_mp, sg);
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.addr = sg->key.addr;
+	/* we need to add all exclude ports to the S,G */
+	for (pg = mlock_dereference(star_mp->ports, br);
+	     pg;
+	     pg = mlock_dereference(pg->next, br)) {
+		struct net_bridge_port_group *src_pg;
+
+		if (pg == sg || pg->filter_mode == MCAST_INCLUDE)
+			continue;
+
+		sg_key.port = pg->key.port;
+		if (br_sg_port_find(br, &sg_key))
+			continue;
+
+		src_pg = __br_multicast_add_group(br, pg->key.port,
+						  &sg->key.addr,
+						  sg->eth_addr,
+						  MCAST_INCLUDE, false, false);
+		if (IS_ERR_OR_NULL(src_pg) ||
+		    src_pg->rt_protocol != RTPROT_KERNEL)
+			continue;
+		src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
+	}
+}
+
+static void br_multicast_fwd_src_add(struct net_bridge_group_src *src)
+{
+	struct net_bridge_mdb_entry *star_mp;
+	struct net_bridge_port_group *sg;
+	struct br_ip sg_ip;
+
+	if (src->flags & BR_SGRP_F_INSTALLED)
+		return;
+
+	memset(&sg_ip, 0, sizeof(sg_ip));
+	sg_ip = src->pg->key.addr;
+	sg_ip.src = src->addr.src;
+	sg = __br_multicast_add_group(src->br, src->pg->key.port, &sg_ip,
+				      src->pg->eth_addr, MCAST_INCLUDE, false,
+				      !timer_pending(&src->timer));
+	if (IS_ERR_OR_NULL(sg))
+		return;
+	src->flags |= BR_SGRP_F_INSTALLED;
+	sg->flags &= ~MDB_PG_FLAGS_STAR_EXCL;
+
+	/* if it was added by user-space as perm we can skip next steps */
+	if (sg->rt_protocol != RTPROT_KERNEL &&
+	    (sg->flags & MDB_PG_FLAGS_PERMANENT))
+		return;
+
+	/* the kernel is now responsible for removing this S,G */
+	del_timer(&sg->timer);
+	star_mp = br_mdb_ip_get(src->br, &src->pg->key.addr);
+	if (!star_mp)
+		return;
+
+	br_multicast_sg_add_exclude_ports(star_mp, sg);
+}
+
+static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src)
+{
+	struct net_bridge_port_group *p, *pg = src->pg;
+	struct net_bridge_port_group __rcu **pp;
+	struct net_bridge_mdb_entry *mp;
+	struct br_ip sg_ip;
+
+	memset(&sg_ip, 0, sizeof(sg_ip));
+	sg_ip = pg->key.addr;
+	sg_ip.src = src->addr.src;
+
+	mp = br_mdb_ip_get(src->br, &sg_ip);
+	if (!mp)
+		return;
+
+	for (pp = &mp->ports;
+	     (p = mlock_dereference(*pp, src->br)) != NULL;
+	     pp = &p->next) {
+		if (!br_port_group_equal(p, pg->key.port, pg->eth_addr))
+			continue;
+
+		if (p->rt_protocol != RTPROT_KERNEL &&
+		    (p->flags & MDB_PG_FLAGS_PERMANENT))
+			break;
+
+		br_multicast_del_pg(mp, p, pp);
+		break;
+	}
+	src->flags &= ~BR_SGRP_F_INSTALLED;
+}
+
+/* install S,G and based on src's timer enable or disable forwarding */
+static void br_multicast_fwd_src_handle(struct net_bridge_group_src *src)
+{
+	struct net_bridge_port_group_sg_key sg_key;
+	struct net_bridge_port_group *sg;
+	u8 old_flags;
+
+	br_multicast_fwd_src_add(src);
+
+	memset(&sg_key, 0, sizeof(sg_key));
+	sg_key.addr = src->pg->key.addr;
+	sg_key.addr.src = src->addr.src;
+	sg_key.port = src->pg->key.port;
+
+	sg = br_sg_port_find(src->br, &sg_key);
+	if (!sg || (sg->flags & MDB_PG_FLAGS_PERMANENT))
+		return;
+
+	old_flags = sg->flags;
+	if (timer_pending(&src->timer))
+		sg->flags &= ~MDB_PG_FLAGS_BLOCKED;
+	else
+		sg->flags |= MDB_PG_FLAGS_BLOCKED;
+
+	if (old_flags != sg->flags) {
+		struct net_bridge_mdb_entry *sg_mp;
+
+		sg_mp = br_mdb_ip_get(src->br, &sg_key.addr);
+		if (!sg_mp)
+			return;
+		br_mdb_notify(src->br->dev, sg_mp, sg, RTM_NEWMDB);
+	}
+}
+
+static void br_multicast_destroy_mdb_entry(struct net_bridge_mcast_gc *gc)
+{
+	struct net_bridge_mdb_entry *mp;
+
+	mp = container_of(gc, struct net_bridge_mdb_entry, mcast_gc);
+	WARN_ON(!hlist_unhashed(&mp->mdb_node));
+	WARN_ON(mp->ports);
+
+	del_timer_sync(&mp->timer);
+	kfree_rcu(mp, rcu);
+}
+
+static void br_multicast_del_mdb_entry(struct net_bridge_mdb_entry *mp)
+{
+	struct net_bridge *br = mp->br;
+
+	rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode,
+			       br_mdb_rht_params);
+	hlist_del_init_rcu(&mp->mdb_node);
+	hlist_add_head(&mp->mcast_gc.gc_node, &br->mcast_gc_list);
+	queue_work(system_long_wq, &br->mcast_gc_work);
+}
+
 static void br_multicast_group_expired(struct timer_list *t)
 {
 	struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer);
 	struct net_bridge *br = mp->br;
 
 	spin_lock(&br->multicast_lock);
-	if (!netif_running(br->dev) || timer_pending(&mp->timer))
+	if (hlist_unhashed(&mp->mdb_node) || !netif_running(br->dev) ||
+	    timer_pending(&mp->timer))
 		goto out;
 
 	br_multicast_host_leave(mp, true);
 
 	if (mp->ports)
 		goto out;
+	br_multicast_del_mdb_entry(mp);
+out:
+	spin_unlock(&br->multicast_lock);
+}
 
-	rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode,
-			       br_mdb_rht_params);
-	hlist_del_rcu(&mp->mdb_node);
+static void br_multicast_destroy_group_src(struct net_bridge_mcast_gc *gc)
+{
+	struct net_bridge_group_src *src;
 
-	kfree_rcu(mp, rcu);
+	src = container_of(gc, struct net_bridge_group_src, mcast_gc);
+	WARN_ON(!hlist_unhashed(&src->node));
 
-out:
-	spin_unlock(&br->multicast_lock);
+	del_timer_sync(&src->timer);
+	kfree_rcu(src, rcu);
+}
+
+static void br_multicast_del_group_src(struct net_bridge_group_src *src)
+{
+	struct net_bridge *br = src->pg->key.port->br;
+
+	br_multicast_fwd_src_remove(src);
+	hlist_del_init_rcu(&src->node);
+	src->pg->src_ents--;
+	hlist_add_head(&src->mcast_gc.gc_node, &br->mcast_gc_list);
+	queue_work(system_long_wq, &br->mcast_gc_work);
+}
+
+static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc)
+{
+	struct net_bridge_port_group *pg;
+
+	pg = container_of(gc, struct net_bridge_port_group, mcast_gc);
+	WARN_ON(!hlist_unhashed(&pg->mglist));
+	WARN_ON(!hlist_empty(&pg->src_list));
+
+	del_timer_sync(&pg->rexmit_timer);
+	del_timer_sync(&pg->timer);
+	kfree_rcu(pg, rcu);
 }
 
-static void br_multicast_del_pg(struct net_bridge *br,
-				struct net_bridge_port_group *pg)
+void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
+			 struct net_bridge_port_group *pg,
+			 struct net_bridge_port_group __rcu **pp)
 {
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_group_src *ent;
+	struct hlist_node *tmp;
+
+	rcu_assign_pointer(*pp, pg->next);
+	hlist_del_init(&pg->mglist);
+	hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node)
+		br_multicast_del_group_src(ent);
+	br_mdb_notify(br->dev, mp, pg, RTM_DELMDB);
+	if (!br_multicast_is_star_g(&mp->addr)) {
+		rhashtable_remove_fast(&br->sg_port_tbl, &pg->rhnode,
+				       br_sg_port_rht_params);
+		br_multicast_sg_del_exclude_ports(mp);
+	} else {
+		br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
+	}
+	hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list);
+	queue_work(system_long_wq, &br->mcast_gc_work);
+
+	if (!mp->ports && !mp->host_joined && netif_running(br->dev))
+		mod_timer(&mp->timer, jiffies);
+}
+
+static void br_multicast_find_del_pg(struct net_bridge *br,
+				     struct net_bridge_port_group *pg)
+{
+	struct net_bridge_port_group __rcu **pp;
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port_group *p;
-	struct net_bridge_port_group __rcu **pp;
 
-	mp = br_mdb_ip_get(br, &pg->addr);
+	mp = br_mdb_ip_get(br, &pg->key.addr);
 	if (WARN_ON(!mp))
 		return;
 
@@ -180,17 +627,7 @@ static void br_multicast_del_pg(struct net_bridge *br,
 		if (p != pg)
 			continue;
 
-		rcu_assign_pointer(*pp, p->next);
-		hlist_del_init(&p->mglist);
-		del_timer(&p->timer);
-		br_mdb_notify(br->dev, p->port, &pg->addr, RTM_DELMDB,
-			      p->flags);
-		kfree_rcu(p, rcu);
-
-		if (!mp->ports && !mp->host_joined &&
-		    netif_running(br->dev))
-			mod_timer(&mp->timer, jiffies);
-
+		br_multicast_del_pg(mp, pg, pp);
 		return;
 	}
 
@@ -200,35 +637,98 @@ static void br_multicast_del_pg(struct net_bridge *br,
 static void br_multicast_port_group_expired(struct timer_list *t)
 {
 	struct net_bridge_port_group *pg = from_timer(pg, t, timer);
-	struct net_bridge *br = pg->port->br;
+	struct net_bridge_group_src *src_ent;
+	struct net_bridge *br = pg->key.port->br;
+	struct hlist_node *tmp;
+	bool changed;
 
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) || timer_pending(&pg->timer) ||
 	    hlist_unhashed(&pg->mglist) || pg->flags & MDB_PG_FLAGS_PERMANENT)
 		goto out;
 
-	br_multicast_del_pg(br, pg);
+	changed = !!(pg->filter_mode == MCAST_EXCLUDE);
+	pg->filter_mode = MCAST_INCLUDE;
+	hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) {
+		if (!timer_pending(&src_ent->timer)) {
+			br_multicast_del_group_src(src_ent);
+			changed = true;
+		}
+	}
+
+	if (hlist_empty(&pg->src_list)) {
+		br_multicast_find_del_pg(br, pg);
+	} else if (changed) {
+		struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->key.addr);
 
+		if (changed && br_multicast_is_star_g(&pg->key.addr))
+			br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
+
+		if (WARN_ON(!mp))
+			goto out;
+		br_mdb_notify(br->dev, mp, pg, RTM_NEWMDB);
+	}
 out:
 	spin_unlock(&br->multicast_lock);
 }
 
-static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
-						    __be32 group,
-						    u8 *igmp_type)
+static void br_multicast_gc(struct hlist_head *head)
 {
+	struct net_bridge_mcast_gc *gcent;
+	struct hlist_node *tmp;
+
+	hlist_for_each_entry_safe(gcent, tmp, head, gc_node) {
+		hlist_del_init(&gcent->gc_node);
+		gcent->destroy(gcent);
+	}
+}
+
+static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
+						    struct net_bridge_port_group *pg,
+						    __be32 ip_dst, __be32 group,
+						    bool with_srcs, bool over_lmqt,
+						    u8 sflag, u8 *igmp_type,
+						    bool *need_rexmit)
+{
+	struct net_bridge_port *p = pg ? pg->key.port : NULL;
+	struct net_bridge_group_src *ent;
+	size_t pkt_size, igmp_hdr_size;
+	unsigned long now = jiffies;
 	struct igmpv3_query *ihv3;
-	size_t igmp_hdr_size;
+	void *csum_start = NULL;
+	__sum16 *csum = NULL;
 	struct sk_buff *skb;
 	struct igmphdr *ih;
 	struct ethhdr *eth;
+	unsigned long lmqt;
 	struct iphdr *iph;
+	u16 lmqt_srcs = 0;
 
 	igmp_hdr_size = sizeof(*ih);
-	if (br->multicast_igmp_version == 3)
+	if (br->multicast_igmp_version == 3) {
 		igmp_hdr_size = sizeof(*ihv3);
-	skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) +
-						 igmp_hdr_size + 4);
+		if (pg && with_srcs) {
+			lmqt = now + (br->multicast_last_member_interval *
+				      br->multicast_last_member_count);
+			hlist_for_each_entry(ent, &pg->src_list, node) {
+				if (over_lmqt == time_after(ent->timer.expires,
+							    lmqt) &&
+				    ent->src_query_rexmit_cnt > 0)
+					lmqt_srcs++;
+			}
+
+			if (!lmqt_srcs)
+				return NULL;
+			igmp_hdr_size += lmqt_srcs * sizeof(__be32);
+		}
+	}
+
+	pkt_size = sizeof(*eth) + sizeof(*iph) + 4 + igmp_hdr_size;
+	if ((p && pkt_size > p->dev->mtu) ||
+	    pkt_size > br->dev->mtu)
+		return NULL;
+
+	skb = netdev_alloc_skb_ip_align(br->dev, pkt_size);
 	if (!skb)
 		goto out;
 
@@ -238,29 +738,24 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 	eth = eth_hdr(skb);
 
 	ether_addr_copy(eth->h_source, br->dev->dev_addr);
-	eth->h_dest[0] = 1;
-	eth->h_dest[1] = 0;
-	eth->h_dest[2] = 0x5e;
-	eth->h_dest[3] = 0;
-	eth->h_dest[4] = 0;
-	eth->h_dest[5] = 1;
+	ip_eth_mc_map(ip_dst, eth->h_dest);
 	eth->h_proto = htons(ETH_P_IP);
 	skb_put(skb, sizeof(*eth));
 
 	skb_set_network_header(skb, skb->len);
 	iph = ip_hdr(skb);
+	iph->tot_len = htons(pkt_size - sizeof(*eth));
 
 	iph->version = 4;
 	iph->ihl = 6;
 	iph->tos = 0xc0;
-	iph->tot_len = htons(sizeof(*iph) + igmp_hdr_size + 4);
 	iph->id = 0;
 	iph->frag_off = htons(IP_DF);
 	iph->ttl = 1;
 	iph->protocol = IPPROTO_IGMP;
 	iph->saddr = br_opt_get(br, BROPT_MULTICAST_QUERY_USE_IFADDR) ?
 		     inet_select_addr(br->dev, 0, RT_SCOPE_LINK) : 0;
-	iph->daddr = htonl(INADDR_ALLHOSTS_GROUP);
+	iph->daddr = ip_dst;
 	((u8 *)&iph[1])[0] = IPOPT_RA;
 	((u8 *)&iph[1])[1] = 4;
 	((u8 *)&iph[1])[2] = 0;
@@ -280,7 +775,8 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 			   (HZ / IGMP_TIMER_SCALE);
 		ih->group = group;
 		ih->csum = 0;
-		ih->csum = ip_compute_csum((void *)ih, sizeof(*ih));
+		csum = &ih->csum;
+		csum_start = (void *)ih;
 		break;
 	case 3:
 		ihv3 = igmpv3_query_hdr(skb);
@@ -290,15 +786,40 @@ static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge *br,
 			     (HZ / IGMP_TIMER_SCALE);
 		ihv3->group = group;
 		ihv3->qqic = br->multicast_query_interval / HZ;
-		ihv3->nsrcs = 0;
+		ihv3->nsrcs = htons(lmqt_srcs);
 		ihv3->resv = 0;
-		ihv3->suppress = 0;
+		ihv3->suppress = sflag;
 		ihv3->qrv = 2;
 		ihv3->csum = 0;
-		ihv3->csum = ip_compute_csum((void *)ihv3, sizeof(*ihv3));
+		csum = &ihv3->csum;
+		csum_start = (void *)ihv3;
+		if (!pg || !with_srcs)
+			break;
+
+		lmqt_srcs = 0;
+		hlist_for_each_entry(ent, &pg->src_list, node) {
+			if (over_lmqt == time_after(ent->timer.expires,
+						    lmqt) &&
+			    ent->src_query_rexmit_cnt > 0) {
+				ihv3->srcs[lmqt_srcs++] = ent->addr.src.ip4;
+				ent->src_query_rexmit_cnt--;
+				if (need_rexmit && ent->src_query_rexmit_cnt)
+					*need_rexmit = true;
+			}
+		}
+		if (WARN_ON(lmqt_srcs != ntohs(ihv3->nsrcs))) {
+			kfree_skb(skb);
+			return NULL;
+		}
 		break;
 	}
 
+	if (WARN_ON(!csum || !csum_start)) {
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	*csum = ip_compute_csum(csum_start, igmp_hdr_size);
 	skb_put(skb, igmp_hdr_size);
 	__skb_pull(skb, sizeof(*eth));
 
@@ -308,23 +829,54 @@ out:
 
 #if IS_ENABLED(CONFIG_IPV6)
 static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
-						    const struct in6_addr *grp,
-						    u8 *igmp_type)
-{
+						    struct net_bridge_port_group *pg,
+						    const struct in6_addr *ip6_dst,
+						    const struct in6_addr *group,
+						    bool with_srcs, bool over_llqt,
+						    u8 sflag, u8 *igmp_type,
+						    bool *need_rexmit)
+{
+	struct net_bridge_port *p = pg ? pg->key.port : NULL;
+	struct net_bridge_group_src *ent;
+	size_t pkt_size, mld_hdr_size;
+	unsigned long now = jiffies;
 	struct mld2_query *mld2q;
+	void *csum_start = NULL;
 	unsigned long interval;
+	__sum16 *csum = NULL;
 	struct ipv6hdr *ip6h;
 	struct mld_msg *mldq;
-	size_t mld_hdr_size;
 	struct sk_buff *skb;
+	unsigned long llqt;
 	struct ethhdr *eth;
+	u16 llqt_srcs = 0;
 	u8 *hopopt;
 
 	mld_hdr_size = sizeof(*mldq);
-	if (br->multicast_mld_version == 2)
+	if (br->multicast_mld_version == 2) {
 		mld_hdr_size = sizeof(*mld2q);
-	skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*ip6h) +
-						 8 + mld_hdr_size);
+		if (pg && with_srcs) {
+			llqt = now + (br->multicast_last_member_interval *
+				      br->multicast_last_member_count);
+			hlist_for_each_entry(ent, &pg->src_list, node) {
+				if (over_llqt == time_after(ent->timer.expires,
+							    llqt) &&
+				    ent->src_query_rexmit_cnt > 0)
+					llqt_srcs++;
+			}
+
+			if (!llqt_srcs)
+				return NULL;
+			mld_hdr_size += llqt_srcs * sizeof(struct in6_addr);
+		}
+	}
+
+	pkt_size = sizeof(*eth) + sizeof(*ip6h) + 8 + mld_hdr_size;
+	if ((p && pkt_size > p->dev->mtu) ||
+	    pkt_size > br->dev->mtu)
+		return NULL;
+
+	skb = netdev_alloc_skb_ip_align(br->dev, pkt_size);
 	if (!skb)
 		goto out;
 
@@ -346,7 +898,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 	ip6h->payload_len = htons(8 + mld_hdr_size);
 	ip6h->nexthdr = IPPROTO_HOPOPTS;
 	ip6h->hop_limit = 1;
-	ipv6_addr_set(&ip6h->daddr, htonl(0xff020000), 0, 0, htonl(1));
+	ip6h->daddr = *ip6_dst;
 	if (ipv6_dev_get_saddr(dev_net(br->dev), br->dev, &ip6h->daddr, 0,
 			       &ip6h->saddr)) {
 		kfree_skb(skb);
@@ -371,7 +923,7 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 
 	/* ICMPv6 */
 	skb_set_transport_header(skb, skb->len);
-	interval = ipv6_addr_any(grp) ?
+	interval = ipv6_addr_any(group) ?
 			br->multicast_query_response_interval :
 			br->multicast_last_member_interval;
 	*igmp_type = ICMPV6_MGM_QUERY;
@@ -383,12 +935,9 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 		mldq->mld_cksum = 0;
 		mldq->mld_maxdelay = htons((u16)jiffies_to_msecs(interval));
 		mldq->mld_reserved = 0;
-		mldq->mld_mca = *grp;
-		mldq->mld_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
-						  sizeof(*mldq), IPPROTO_ICMPV6,
-						  csum_partial(mldq,
-							       sizeof(*mldq),
-							       0));
+		mldq->mld_mca = *group;
+		csum = &mldq->mld_cksum;
+		csum_start = (void *)mldq;
 		break;
 	case 2:
 		mld2q = (struct mld2_query *)icmp6_hdr(skb);
@@ -398,21 +947,43 @@ static struct sk_buff *br_ip6_multicast_alloc_query(struct net_bridge *br,
 		mld2q->mld2q_cksum = 0;
 		mld2q->mld2q_resv1 = 0;
 		mld2q->mld2q_resv2 = 0;
-		mld2q->mld2q_suppress = 0;
+		mld2q->mld2q_suppress = sflag;
 		mld2q->mld2q_qrv = 2;
-		mld2q->mld2q_nsrcs = 0;
+		mld2q->mld2q_nsrcs = htons(llqt_srcs);
 		mld2q->mld2q_qqic = br->multicast_query_interval / HZ;
-		mld2q->mld2q_mca = *grp;
-		mld2q->mld2q_cksum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
-						     sizeof(*mld2q),
-						     IPPROTO_ICMPV6,
-						     csum_partial(mld2q,
-								  sizeof(*mld2q),
-								  0));
+		mld2q->mld2q_mca = *group;
+		csum = &mld2q->mld2q_cksum;
+		csum_start = (void *)mld2q;
+		if (!pg || !with_srcs)
+			break;
+
+		llqt_srcs = 0;
+		hlist_for_each_entry(ent, &pg->src_list, node) {
+			if (over_llqt == time_after(ent->timer.expires,
+						    llqt) &&
+			    ent->src_query_rexmit_cnt > 0) {
+				mld2q->mld2q_srcs[llqt_srcs++] = ent->addr.src.ip6;
+				ent->src_query_rexmit_cnt--;
+				if (need_rexmit && ent->src_query_rexmit_cnt)
+					*need_rexmit = true;
+			}
+		}
+		if (WARN_ON(llqt_srcs != ntohs(mld2q->mld2q_nsrcs))) {
+			kfree_skb(skb);
+			return NULL;
+		}
 		break;
 	}
-	skb_put(skb, mld_hdr_size);
 
+	if (WARN_ON(!csum || !csum_start)) {
+		kfree_skb(skb);
+		return NULL;
+	}
+
+	*csum = csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr, mld_hdr_size,
+				IPPROTO_ICMPV6,
+				csum_partial(csum_start, mld_hdr_size, 0));
+	skb_put(skb, mld_hdr_size);
 	__skb_pull(skb, sizeof(*eth));
 
 out:
@@ -421,16 +992,39 @@ out:
 #endif
 
 static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br,
-						struct br_ip *addr,
-						u8 *igmp_type)
+						struct net_bridge_port_group *pg,
+						struct br_ip *ip_dst,
+						struct br_ip *group,
+						bool with_srcs, bool over_lmqt,
+						u8 sflag, u8 *igmp_type,
+						bool *need_rexmit)
 {
-	switch (addr->proto) {
+	__be32 ip4_dst;
+
+	switch (group->proto) {
 	case htons(ETH_P_IP):
-		return br_ip4_multicast_alloc_query(br, addr->u.ip4, igmp_type);
+		ip4_dst = ip_dst ? ip_dst->dst.ip4 : htonl(INADDR_ALLHOSTS_GROUP);
+		return br_ip4_multicast_alloc_query(br, pg,
+						    ip4_dst, group->dst.ip4,
+						    with_srcs, over_lmqt,
+						    sflag, igmp_type,
+						    need_rexmit);
 #if IS_ENABLED(CONFIG_IPV6)
-	case htons(ETH_P_IPV6):
-		return br_ip6_multicast_alloc_query(br, &addr->u.ip6,
-						    igmp_type);
+	case htons(ETH_P_IPV6): {
+		struct in6_addr ip6_dst;
+
+		if (ip_dst)
+			ip6_dst = ip_dst->dst.ip6;
+		else
+			ipv6_addr_set(&ip6_dst, htonl(0xff020000), 0, 0,
+				      htonl(1));
+
+		return br_ip6_multicast_alloc_query(br, pg,
+						    &ip6_dst, &group->dst.ip6,
+						    with_srcs, over_lmqt,
+						    sflag, igmp_type,
+						    need_rexmit);
+	}
 #endif
 	}
 	return NULL;
@@ -457,6 +1051,7 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
 
 	mp->br = br;
 	mp->addr = *group;
+	mp->mcast_gc.destroy = br_multicast_destroy_mdb_entry;
 	timer_setup(&mp->timer, br_multicast_group_expired, 0);
 	err = rhashtable_lookup_insert_fast(&br->mdb_hash_tbl, &mp->rhnode,
 					    br_mdb_rht_params);
@@ -470,12 +1065,101 @@ struct net_bridge_mdb_entry *br_multicast_new_group(struct net_bridge *br,
 	return mp;
 }
 
+static void br_multicast_group_src_expired(struct timer_list *t)
+{
+	struct net_bridge_group_src *src = from_timer(src, t, timer);
+	struct net_bridge_port_group *pg;
+	struct net_bridge *br = src->br;
+
+	spin_lock(&br->multicast_lock);
+	if (hlist_unhashed(&src->node) || !netif_running(br->dev) ||
+	    timer_pending(&src->timer))
+		goto out;
+
+	pg = src->pg;
+	if (pg->filter_mode == MCAST_INCLUDE) {
+		br_multicast_del_group_src(src);
+		if (!hlist_empty(&pg->src_list))
+			goto out;
+		br_multicast_find_del_pg(br, pg);
+	} else {
+		br_multicast_fwd_src_handle(src);
+	}
+
+out:
+	spin_unlock(&br->multicast_lock);
+}
+
+static struct net_bridge_group_src *
+br_multicast_find_group_src(struct net_bridge_port_group *pg, struct br_ip *ip)
+{
+	struct net_bridge_group_src *ent;
+
+	switch (ip->proto) {
+	case htons(ETH_P_IP):
+		hlist_for_each_entry(ent, &pg->src_list, node)
+			if (ip->src.ip4 == ent->addr.src.ip4)
+				return ent;
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		hlist_for_each_entry(ent, &pg->src_list, node)
+			if (!ipv6_addr_cmp(&ent->addr.src.ip6, &ip->src.ip6))
+				return ent;
+		break;
+#endif
+	}
+
+	return NULL;
+}
+
+static struct net_bridge_group_src *
+br_multicast_new_group_src(struct net_bridge_port_group *pg, struct br_ip *src_ip)
+{
+	struct net_bridge_group_src *grp_src;
+
+	if (unlikely(pg->src_ents >= PG_SRC_ENT_LIMIT))
+		return NULL;
+
+	switch (src_ip->proto) {
+	case htons(ETH_P_IP):
+		if (ipv4_is_zeronet(src_ip->src.ip4) ||
+		    ipv4_is_multicast(src_ip->src.ip4))
+			return NULL;
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		if (ipv6_addr_any(&src_ip->src.ip6) ||
+		    ipv6_addr_is_multicast(&src_ip->src.ip6))
+			return NULL;
+		break;
+#endif
+	}
+
+	grp_src = kzalloc(sizeof(*grp_src), GFP_ATOMIC);
+	if (unlikely(!grp_src))
+		return NULL;
+
+	grp_src->pg = pg;
+	grp_src->br = pg->key.port->br;
+	grp_src->addr = *src_ip;
+	grp_src->mcast_gc.destroy = br_multicast_destroy_group_src;
+	timer_setup(&grp_src->timer, br_multicast_group_src_expired, 0);
+
+	hlist_add_head_rcu(&grp_src->node, &pg->src_list);
+	pg->src_ents++;
+
+	return grp_src;
+}
+
 struct net_bridge_port_group *br_multicast_new_port_group(
 			struct net_bridge_port *port,
 			struct br_ip *group,
 			struct net_bridge_port_group __rcu *next,
 			unsigned char flags,
-			const unsigned char *src)
+			const unsigned char *src,
+			u8 filter_mode,
+			u8 rt_protocol)
 {
 	struct net_bridge_port_group *p;
 
@@ -483,12 +1167,25 @@ struct net_bridge_port_group *br_multicast_new_port_group(
 	if (unlikely(!p))
 		return NULL;
 
-	p->addr = *group;
-	p->port = port;
+	p->key.addr = *group;
+	p->key.port = port;
 	p->flags = flags;
+	p->filter_mode = filter_mode;
+	p->rt_protocol = rt_protocol;
+	p->mcast_gc.destroy = br_multicast_destroy_port_group;
+	INIT_HLIST_HEAD(&p->src_list);
+
+	if (!br_multicast_is_star_g(group) &&
+	    rhashtable_lookup_insert_fast(&port->br->sg_port_tbl, &p->rhnode,
+					  br_sg_port_rht_params)) {
+		kfree(p);
+		return NULL;
+	}
+
 	rcu_assign_pointer(p->next, next);
-	hlist_add_head(&p->mglist, &port->mglist);
 	timer_setup(&p->timer, br_multicast_port_group_expired, 0);
+	timer_setup(&p->rexmit_timer, br_multicast_port_group_rexmit, 0);
+	hlist_add_head(&p->mglist, &port->mglist);
 
 	if (src)
 		memcpy(p->eth_addr, src, ETH_ALEN);
@@ -498,27 +1195,19 @@ struct net_bridge_port_group *br_multicast_new_port_group(
 	return p;
 }
 
-static bool br_port_group_equal(struct net_bridge_port_group *p,
-				struct net_bridge_port *port,
-				const unsigned char *src)
-{
-	if (p->port != port)
-		return false;
-
-	if (!(port->flags & BR_MULTICAST_TO_UNICAST))
-		return true;
-
-	return ether_addr_equal(src, p->eth_addr);
-}
-
 void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify)
 {
 	if (!mp->host_joined) {
 		mp->host_joined = true;
+		if (br_multicast_is_star_g(&mp->addr))
+			br_multicast_star_g_host_state(mp);
 		if (notify)
-			br_mdb_notify(mp->br->dev, NULL, &mp->addr,
-				      RTM_NEWMDB, 0);
+			br_mdb_notify(mp->br->dev, mp, NULL, RTM_NEWMDB);
 	}
+
+	if (br_group_is_l2(&mp->addr))
+		return;
+
 	mod_timer(&mp->timer, jiffies + mp->br->multicast_membership_interval);
 }
 
@@ -528,30 +1217,33 @@ void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify)
 		return;
 
 	mp->host_joined = false;
+	if (br_multicast_is_star_g(&mp->addr))
+		br_multicast_star_g_host_state(mp);
 	if (notify)
-		br_mdb_notify(mp->br->dev, NULL, &mp->addr, RTM_DELMDB, 0);
+		br_mdb_notify(mp->br->dev, mp, NULL, RTM_DELMDB);
 }
 
-static int br_multicast_add_group(struct net_bridge *br,
-				  struct net_bridge_port *port,
-				  struct br_ip *group,
-				  const unsigned char *src)
+static struct net_bridge_port_group *
+__br_multicast_add_group(struct net_bridge *br,
+			 struct net_bridge_port *port,
+			 struct br_ip *group,
+			 const unsigned char *src,
+			 u8 filter_mode,
+			 bool igmpv2_mldv1,
+			 bool blocked)
 {
 	struct net_bridge_port_group __rcu **pp;
-	struct net_bridge_port_group *p;
+	struct net_bridge_port_group *p = NULL;
 	struct net_bridge_mdb_entry *mp;
 	unsigned long now = jiffies;
-	int err;
 
-	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) ||
 	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
 	mp = br_multicast_new_group(br, group);
-	err = PTR_ERR(mp);
 	if (IS_ERR(mp))
-		goto err;
+		return ERR_PTR(PTR_ERR(mp));
 
 	if (!port) {
 		br_multicast_host_join(mp, true);
@@ -563,23 +1255,46 @@ static int br_multicast_add_group(struct net_bridge *br,
 	     pp = &p->next) {
 		if (br_port_group_equal(p, port, src))
 			goto found;
-		if ((unsigned long)p->port < (unsigned long)port)
+		if ((unsigned long)p->key.port < (unsigned long)port)
 			break;
 	}
 
-	p = br_multicast_new_port_group(port, group, *pp, 0, src);
-	if (unlikely(!p))
-		goto err;
+	p = br_multicast_new_port_group(port, group, *pp, 0, src,
+					filter_mode, RTPROT_KERNEL);
+	if (unlikely(!p)) {
+		p = ERR_PTR(-ENOMEM);
+		goto out;
+	}
 	rcu_assign_pointer(*pp, p);
-	br_mdb_notify(br->dev, port, group, RTM_NEWMDB, 0);
+	if (blocked)
+		p->flags |= MDB_PG_FLAGS_BLOCKED;
+	br_mdb_notify(br->dev, mp, p, RTM_NEWMDB);
 
 found:
-	mod_timer(&p->timer, now + br->multicast_membership_interval);
+	if (igmpv2_mldv1)
+		mod_timer(&p->timer, now + br->multicast_membership_interval);
+
 out:
-	err = 0;
+	return p;
+}
 
-err:
+static int br_multicast_add_group(struct net_bridge *br,
+				  struct net_bridge_port *port,
+				  struct br_ip *group,
+				  const unsigned char *src,
+				  u8 filter_mode,
+				  bool igmpv2_mldv1)
+{
+	struct net_bridge_port_group *pg;
+	int err;
+
+	spin_lock(&br->multicast_lock);
+	pg = __br_multicast_add_group(br, port, group, src, filter_mode,
+				      igmpv2_mldv1, false);
+	/* NULL is considered valid for host joined groups */
+	err = IS_ERR(pg) ? PTR_ERR(pg) : 0;
 	spin_unlock(&br->multicast_lock);
+
 	return err;
 }
 
@@ -587,19 +1302,23 @@ static int br_ip4_multicast_add_group(struct net_bridge *br,
 				      struct net_bridge_port *port,
 				      __be32 group,
 				      __u16 vid,
-				      const unsigned char *src)
+				      const unsigned char *src,
+				      bool igmpv2)
 {
 	struct br_ip br_group;
+	u8 filter_mode;
 
 	if (ipv4_is_local_multicast(group))
 		return 0;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip4 = group;
+	br_group.dst.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
+	filter_mode = igmpv2 ? MCAST_EXCLUDE : MCAST_INCLUDE;
 
-	return br_multicast_add_group(br, port, &br_group, src);
+	return br_multicast_add_group(br, port, &br_group, src, filter_mode,
+				      igmpv2);
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -607,19 +1326,23 @@ static int br_ip6_multicast_add_group(struct net_bridge *br,
 				      struct net_bridge_port *port,
 				      const struct in6_addr *group,
 				      __u16 vid,
-				      const unsigned char *src)
+				      const unsigned char *src,
+				      bool mldv1)
 {
 	struct br_ip br_group;
+	u8 filter_mode;
 
 	if (ipv6_addr_is_ll_all_nodes(group))
 		return 0;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip6 = *group;
+	br_group.dst.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
+	filter_mode = mldv1 ? MCAST_EXCLUDE : MCAST_INCLUDE;
 
-	return br_multicast_add_group(br, port, &br_group, src);
+	return br_multicast_add_group(br, port, &br_group, src, filter_mode,
+				      mldv1);
 }
 #endif
 
@@ -702,21 +1425,30 @@ static void br_multicast_select_own_querier(struct net_bridge *br,
 					    struct sk_buff *skb)
 {
 	if (ip->proto == htons(ETH_P_IP))
-		br->ip4_querier.addr.u.ip4 = ip_hdr(skb)->saddr;
+		br->ip4_querier.addr.src.ip4 = ip_hdr(skb)->saddr;
 #if IS_ENABLED(CONFIG_IPV6)
 	else
-		br->ip6_querier.addr.u.ip6 = ipv6_hdr(skb)->saddr;
+		br->ip6_querier.addr.src.ip6 = ipv6_hdr(skb)->saddr;
 #endif
 }
 
 static void __br_multicast_send_query(struct net_bridge *br,
 				      struct net_bridge_port *port,
-				      struct br_ip *ip)
-{
+				      struct net_bridge_port_group *pg,
+				      struct br_ip *ip_dst,
+				      struct br_ip *group,
+				      bool with_srcs,
+				      u8 sflag,
+				      bool *need_rexmit)
+{
+	bool over_lmqt = !!sflag;
 	struct sk_buff *skb;
 	u8 igmp_type;
 
-	skb = br_multicast_alloc_query(br, ip, &igmp_type);
+again_under_lmqt:
+	skb = br_multicast_alloc_query(br, pg, ip_dst, group, with_srcs,
+				       over_lmqt, sflag, &igmp_type,
+				       need_rexmit);
 	if (!skb)
 		return;
 
@@ -727,8 +1459,13 @@ static void __br_multicast_send_query(struct net_bridge *br,
 		NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_OUT,
 			dev_net(port->dev), NULL, skb, NULL, skb->dev,
 			br_dev_queue_push_xmit);
+
+		if (over_lmqt && with_srcs && sflag) {
+			over_lmqt = false;
+			goto again_under_lmqt;
+		}
 	} else {
-		br_multicast_select_own_querier(br, ip, skb);
+		br_multicast_select_own_querier(br, group, skb);
 		br_multicast_count(br, port, skb, igmp_type,
 				   BR_MCAST_DIR_RX);
 		netif_rx(skb);
@@ -748,7 +1485,7 @@ static void br_multicast_send_query(struct net_bridge *br,
 	    !br_opt_get(br, BROPT_MULTICAST_QUERIER))
 		return;
 
-	memset(&br_group.u, 0, sizeof(br_group.u));
+	memset(&br_group.dst, 0, sizeof(br_group.dst));
 
 	if (port ? (own_query == &port->ip4_own_query) :
 		   (own_query == &br->ip4_own_query)) {
@@ -764,7 +1501,8 @@ static void br_multicast_send_query(struct net_bridge *br,
 	if (!other_query || timer_pending(&other_query->timer))
 		return;
 
-	__br_multicast_send_query(br, port, &br_group);
+	__br_multicast_send_query(br, port, NULL, NULL, &br_group, false, 0,
+				  NULL);
 
 	time = jiffies;
 	time += own_query->startup_sent < br->multicast_startup_query_count ?
@@ -809,6 +1547,44 @@ static void br_ip6_multicast_port_query_expired(struct timer_list *t)
 }
 #endif
 
+static void br_multicast_port_group_rexmit(struct timer_list *t)
+{
+	struct net_bridge_port_group *pg = from_timer(pg, t, rexmit_timer);
+	struct bridge_mcast_other_query *other_query = NULL;
+	struct net_bridge *br = pg->key.port->br;
+	bool need_rexmit = false;
+
+	spin_lock(&br->multicast_lock);
+	if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) ||
+	    !br_opt_get(br, BROPT_MULTICAST_ENABLED) ||
+	    !br_opt_get(br, BROPT_MULTICAST_QUERIER))
+		goto out;
+
+	if (pg->key.addr.proto == htons(ETH_P_IP))
+		other_query = &br->ip4_other_query;
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		other_query = &br->ip6_other_query;
+#endif
+
+	if (!other_query || timer_pending(&other_query->timer))
+		goto out;
+
+	if (pg->grp_query_rexmit_cnt) {
+		pg->grp_query_rexmit_cnt--;
+		__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
+					  &pg->key.addr, false, 1, NULL);
+	}
+	__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
+				  &pg->key.addr, true, 0, &need_rexmit);
+
+	if (pg->grp_query_rexmit_cnt || need_rexmit)
+		mod_timer(&pg->rexmit_timer, jiffies +
+					     br->multicast_last_member_interval);
+out:
+	spin_unlock(&br->multicast_lock);
+}
+
 static void br_mc_disabled_update(struct net_device *dev, bool value)
 {
 	struct switchdev_attr attr = {
@@ -847,13 +1623,16 @@ void br_multicast_del_port(struct net_bridge_port *port)
 {
 	struct net_bridge *br = port->br;
 	struct net_bridge_port_group *pg;
+	HLIST_HEAD(deleted_head);
 	struct hlist_node *n;
 
 	/* Take care of the remaining groups, only perm ones should be left */
 	spin_lock_bh(&br->multicast_lock);
 	hlist_for_each_entry_safe(pg, n, &port->mglist, mglist)
-		br_multicast_del_pg(br, pg);
+		br_multicast_find_del_pg(br, pg);
+	hlist_move_list(&br->mcast_gc_list, &deleted_head);
 	spin_unlock_bh(&br->multicast_lock);
+	br_multicast_gc(&deleted_head);
 	del_timer_sync(&port->multicast_router_timer);
 	free_percpu(port->mcast_stats);
 }
@@ -901,7 +1680,7 @@ void br_multicast_disable_port(struct net_bridge_port *port)
 	spin_lock(&br->multicast_lock);
 	hlist_for_each_entry_safe(pg, n, &port->mglist, mglist)
 		if (!(pg->flags & MDB_PG_FLAGS_PERMANENT))
-			br_multicast_del_pg(br, pg);
+			br_multicast_find_del_pg(br, pg);
 
 	__del_port_router(port);
 
@@ -913,20 +1692,574 @@ void br_multicast_disable_port(struct net_bridge_port *port)
 	spin_unlock(&br->multicast_lock);
 }
 
+static int __grp_src_delete_marked(struct net_bridge_port_group *pg)
+{
+	struct net_bridge_group_src *ent;
+	struct hlist_node *tmp;
+	int deleted = 0;
+
+	hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node)
+		if (ent->flags & BR_SGRP_F_DELETE) {
+			br_multicast_del_group_src(ent);
+			deleted++;
+		}
+
+	return deleted;
+}
+
+static void __grp_src_mod_timer(struct net_bridge_group_src *src,
+				unsigned long expires)
+{
+	mod_timer(&src->timer, expires);
+	br_multicast_fwd_src_handle(src);
+}
+
+static void __grp_src_query_marked_and_rexmit(struct net_bridge_port_group *pg)
+{
+	struct bridge_mcast_other_query *other_query = NULL;
+	struct net_bridge *br = pg->key.port->br;
+	u32 lmqc = br->multicast_last_member_count;
+	unsigned long lmqt, lmi, now = jiffies;
+	struct net_bridge_group_src *ent;
+
+	if (!netif_running(br->dev) ||
+	    !br_opt_get(br, BROPT_MULTICAST_ENABLED))
+		return;
+
+	if (pg->key.addr.proto == htons(ETH_P_IP))
+		other_query = &br->ip4_other_query;
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		other_query = &br->ip6_other_query;
+#endif
+
+	lmqt = now + br_multicast_lmqt(br);
+	hlist_for_each_entry(ent, &pg->src_list, node) {
+		if (ent->flags & BR_SGRP_F_SEND) {
+			ent->flags &= ~BR_SGRP_F_SEND;
+			if (ent->timer.expires > lmqt) {
+				if (br_opt_get(br, BROPT_MULTICAST_QUERIER) &&
+				    other_query &&
+				    !timer_pending(&other_query->timer))
+					ent->src_query_rexmit_cnt = lmqc;
+				__grp_src_mod_timer(ent, lmqt);
+			}
+		}
+	}
+
+	if (!br_opt_get(br, BROPT_MULTICAST_QUERIER) ||
+	    !other_query || timer_pending(&other_query->timer))
+		return;
+
+	__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
+				  &pg->key.addr, true, 1, NULL);
+
+	lmi = now + br->multicast_last_member_interval;
+	if (!timer_pending(&pg->rexmit_timer) ||
+	    time_after(pg->rexmit_timer.expires, lmi))
+		mod_timer(&pg->rexmit_timer, lmi);
+}
+
+static void __grp_send_query_and_rexmit(struct net_bridge_port_group *pg)
+{
+	struct bridge_mcast_other_query *other_query = NULL;
+	struct net_bridge *br = pg->key.port->br;
+	unsigned long now = jiffies, lmi;
+
+	if (!netif_running(br->dev) ||
+	    !br_opt_get(br, BROPT_MULTICAST_ENABLED))
+		return;
+
+	if (pg->key.addr.proto == htons(ETH_P_IP))
+		other_query = &br->ip4_other_query;
+#if IS_ENABLED(CONFIG_IPV6)
+	else
+		other_query = &br->ip6_other_query;
+#endif
+
+	if (br_opt_get(br, BROPT_MULTICAST_QUERIER) &&
+	    other_query && !timer_pending(&other_query->timer)) {
+		lmi = now + br->multicast_last_member_interval;
+		pg->grp_query_rexmit_cnt = br->multicast_last_member_count - 1;
+		__br_multicast_send_query(br, pg->key.port, pg, &pg->key.addr,
+					  &pg->key.addr, false, 0, NULL);
+		if (!timer_pending(&pg->rexmit_timer) ||
+		    time_after(pg->rexmit_timer.expires, lmi))
+			mod_timer(&pg->rexmit_timer, lmi);
+	}
+
+	if (pg->filter_mode == MCAST_EXCLUDE &&
+	    (!timer_pending(&pg->timer) ||
+	     time_after(pg->timer.expires, now + br_multicast_lmqt(br))))
+		mod_timer(&pg->timer, now + br_multicast_lmqt(br));
+}
+
+/* State          Msg type      New state                Actions
+ * INCLUDE (A)    IS_IN (B)     INCLUDE (A+B)            (B)=GMI
+ * INCLUDE (A)    ALLOW (B)     INCLUDE (A+B)            (B)=GMI
+ * EXCLUDE (X,Y)  ALLOW (A)     EXCLUDE (X+A,Y-A)        (A)=GMI
+ */
+static bool br_multicast_isinc_allow(struct net_bridge_port_group *pg,
+				     void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_group_src *ent;
+	unsigned long now = jiffies;
+	bool changed = false;
+	struct br_ip src_ip;
+	u32 src_idx;
+
+	memset(&src_ip, 0, sizeof(src_ip));
+	src_ip.proto = pg->key.addr.proto;
+	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
+		memcpy(&src_ip.src, srcs, src_size);
+		ent = br_multicast_find_group_src(pg, &src_ip);
+		if (!ent) {
+			ent = br_multicast_new_group_src(pg, &src_ip);
+			if (ent)
+				changed = true;
+		}
+
+		if (ent)
+			__grp_src_mod_timer(ent, now + br_multicast_gmi(br));
+		srcs += src_size;
+	}
+
+	return changed;
+}
+
+/* State          Msg type      New state                Actions
+ * INCLUDE (A)    IS_EX (B)     EXCLUDE (A*B,B-A)        (B-A)=0
+ *                                                       Delete (A-B)
+ *                                                       Group Timer=GMI
+ */
+static void __grp_src_isexc_incl(struct net_bridge_port_group *pg,
+				 void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge_group_src *ent;
+	struct br_ip src_ip;
+	u32 src_idx;
+
+	hlist_for_each_entry(ent, &pg->src_list, node)
+		ent->flags |= BR_SGRP_F_DELETE;
+
+	memset(&src_ip, 0, sizeof(src_ip));
+	src_ip.proto = pg->key.addr.proto;
+	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
+		memcpy(&src_ip.src, srcs, src_size);
+		ent = br_multicast_find_group_src(pg, &src_ip);
+		if (ent)
+			ent->flags &= ~BR_SGRP_F_DELETE;
+		else
+			ent = br_multicast_new_group_src(pg, &src_ip);
+		if (ent)
+			br_multicast_fwd_src_handle(ent);
+		srcs += src_size;
+	}
+
+	__grp_src_delete_marked(pg);
+}
+
+/* State          Msg type      New state                Actions
+ * EXCLUDE (X,Y)  IS_EX (A)     EXCLUDE (A-Y,Y*A)        (A-X-Y)=GMI
+ *                                                       Delete (X-A)
+ *                                                       Delete (Y-A)
+ *                                                       Group Timer=GMI
+ */
+static bool __grp_src_isexc_excl(struct net_bridge_port_group *pg,
+				 void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge *br = pg->key.port->br;
+	struct net_bridge_group_src *ent;
+	unsigned long now = jiffies;
+	bool changed = false;
+	struct br_ip src_ip;
+	u32 src_idx;
+
+	hlist_for_each_entry(ent, &pg->src_list, node)
+		ent->flags |= BR_SGRP_F_DELETE;
+
+	memset(&src_ip, 0, sizeof(src_ip));
+	src_ip.proto = pg->key.addr.proto;
+	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
+		memcpy(&src_ip.src, srcs, src_size);
+		ent = br_multicast_find_group_src(pg, &src_ip);
+		if (ent) {
+			ent->flags &= ~BR_SGRP_F_DELETE;
+		} else {
+			ent = br_multicast_new_group_src(pg, &src_ip);
+			if (ent) {
+				__grp_src_mod_timer(ent,
+						    now + br_multicast_gmi(br));
+				changed = true;
+			}
+		}
+		srcs += src_size;
+	}
+
+	if (__grp_src_delete_marked(pg))
+		changed = true;
+
+	return changed;
+}
+
+static bool br_multicast_isexc(struct net_bridge_port_group *pg,
+			       void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge *br = pg->key.port->br;
+	bool changed = false;
+
+	switch (pg->filter_mode) {
+	case MCAST_INCLUDE:
+		__grp_src_isexc_incl(pg, srcs, nsrcs, src_size);
+		br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE);
+		changed = true;
+		break;
+	case MCAST_EXCLUDE:
+		changed = __grp_src_isexc_excl(pg, srcs, nsrcs, src_size);
+		break;
+	}
+
+	pg->filter_mode = MCAST_EXCLUDE;
+	mod_timer(&pg->timer, jiffies + br_multicast_gmi(br));
+
+	return changed;
+}
+
+/* State          Msg type      New state                Actions
+ * INCLUDE (A)    TO_IN (B)     INCLUDE (A+B)            (B)=GMI
+ *                                                       Send Q(G,A-B)
+ */
+static bool __grp_src_toin_incl(struct net_bridge_port_group *pg,
+				void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge *br = pg->key.port->br;
+	u32 src_idx, to_send = pg->src_ents;
+	struct net_bridge_group_src *ent;
+	unsigned long now = jiffies;
+	bool changed = false;
+	struct br_ip src_ip;
+
+	hlist_for_each_entry(ent, &pg->src_list, node)
+		ent->flags |= BR_SGRP_F_SEND;
+
+	memset(&src_ip, 0, sizeof(src_ip));
+	src_ip.proto = pg->key.addr.proto;
+	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
+		memcpy(&src_ip.src, srcs, src_size);
+		ent = br_multicast_find_group_src(pg, &src_ip);
+		if (ent) {
+			ent->flags &= ~BR_SGRP_F_SEND;
+			to_send--;
+		} else {
+			ent = br_multicast_new_group_src(pg, &src_ip);
+			if (ent)
+				changed = true;
+		}
+		if (ent)
+			__grp_src_mod_timer(ent, now + br_multicast_gmi(br));
+		srcs += src_size;
+	}
+
+	if (to_send)
+		__grp_src_query_marked_and_rexmit(pg);
+
+	return changed;
+}
+
+/* State          Msg type      New state                Actions
+ * EXCLUDE (X,Y)  TO_IN (A)     EXCLUDE (X+A,Y-A)        (A)=GMI
+ *                                                       Send Q(G,X-A)
+ *                                                       Send Q(G)
+ */
+static bool __grp_src_toin_excl(struct net_bridge_port_group *pg,
+				void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge *br = pg->key.port->br;
+	u32 src_idx, to_send = pg->src_ents;
+	struct net_bridge_group_src *ent;
+	unsigned long now = jiffies;
+	bool changed = false;
+	struct br_ip src_ip;
+
+	hlist_for_each_entry(ent, &pg->src_list, node)
+		if (timer_pending(&ent->timer))
+			ent->flags |= BR_SGRP_F_SEND;
+
+	memset(&src_ip, 0, sizeof(src_ip));
+	src_ip.proto = pg->key.addr.proto;
+	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
+		memcpy(&src_ip.src, srcs, src_size);
+		ent = br_multicast_find_group_src(pg, &src_ip);
+		if (ent) {
+			if (timer_pending(&ent->timer)) {
+				ent->flags &= ~BR_SGRP_F_SEND;
+				to_send--;
+			}
+		} else {
+			ent = br_multicast_new_group_src(pg, &src_ip);
+			if (ent)
+				changed = true;
+		}
+		if (ent)
+			__grp_src_mod_timer(ent, now + br_multicast_gmi(br));
+		srcs += src_size;
+	}
+
+	if (to_send)
+		__grp_src_query_marked_and_rexmit(pg);
+
+	__grp_send_query_and_rexmit(pg);
+
+	return changed;
+}
+
+static bool br_multicast_toin(struct net_bridge_port_group *pg,
+			      void *srcs, u32 nsrcs, size_t src_size)
+{
+	bool changed = false;
+
+	switch (pg->filter_mode) {
+	case MCAST_INCLUDE:
+		changed = __grp_src_toin_incl(pg, srcs, nsrcs, src_size);
+		break;
+	case MCAST_EXCLUDE:
+		changed = __grp_src_toin_excl(pg, srcs, nsrcs, src_size);
+		break;
+	}
+
+	return changed;
+}
+
+/* State          Msg type      New state                Actions
+ * INCLUDE (A)    TO_EX (B)     EXCLUDE (A*B,B-A)        (B-A)=0
+ *                                                       Delete (A-B)
+ *                                                       Send Q(G,A*B)
+ *                                                       Group Timer=GMI
+ */
+static void __grp_src_toex_incl(struct net_bridge_port_group *pg,
+				void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge_group_src *ent;
+	u32 src_idx, to_send = 0;
+	struct br_ip src_ip;
+
+	hlist_for_each_entry(ent, &pg->src_list, node)
+		ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE;
+
+	memset(&src_ip, 0, sizeof(src_ip));
+	src_ip.proto = pg->key.addr.proto;
+	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
+		memcpy(&src_ip.src, srcs, src_size);
+		ent = br_multicast_find_group_src(pg, &src_ip);
+		if (ent) {
+			ent->flags = (ent->flags & ~BR_SGRP_F_DELETE) |
+				     BR_SGRP_F_SEND;
+			to_send++;
+		} else {
+			ent = br_multicast_new_group_src(pg, &src_ip);
+		}
+		if (ent)
+			br_multicast_fwd_src_handle(ent);
+		srcs += src_size;
+	}
+
+	__grp_src_delete_marked(pg);
+	if (to_send)
+		__grp_src_query_marked_and_rexmit(pg);
+}
+
+/* State          Msg type      New state                Actions
+ * EXCLUDE (X,Y)  TO_EX (A)     EXCLUDE (A-Y,Y*A)        (A-X-Y)=Group Timer
+ *                                                       Delete (X-A)
+ *                                                       Delete (Y-A)
+ *                                                       Send Q(G,A-Y)
+ *                                                       Group Timer=GMI
+ */
+static bool __grp_src_toex_excl(struct net_bridge_port_group *pg,
+				void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge_group_src *ent;
+	u32 src_idx, to_send = 0;
+	bool changed = false;
+	struct br_ip src_ip;
+
+	hlist_for_each_entry(ent, &pg->src_list, node)
+		ent->flags = (ent->flags & ~BR_SGRP_F_SEND) | BR_SGRP_F_DELETE;
+
+	memset(&src_ip, 0, sizeof(src_ip));
+	src_ip.proto = pg->key.addr.proto;
+	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
+		memcpy(&src_ip.src, srcs, src_size);
+		ent = br_multicast_find_group_src(pg, &src_ip);
+		if (ent) {
+			ent->flags &= ~BR_SGRP_F_DELETE;
+		} else {
+			ent = br_multicast_new_group_src(pg, &src_ip);
+			if (ent) {
+				__grp_src_mod_timer(ent, pg->timer.expires);
+				changed = true;
+			}
+		}
+		if (ent && timer_pending(&ent->timer)) {
+			ent->flags |= BR_SGRP_F_SEND;
+			to_send++;
+		}
+		srcs += src_size;
+	}
+
+	if (__grp_src_delete_marked(pg))
+		changed = true;
+	if (to_send)
+		__grp_src_query_marked_and_rexmit(pg);
+
+	return changed;
+}
+
+static bool br_multicast_toex(struct net_bridge_port_group *pg,
+			      void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge *br = pg->key.port->br;
+	bool changed = false;
+
+	switch (pg->filter_mode) {
+	case MCAST_INCLUDE:
+		__grp_src_toex_incl(pg, srcs, nsrcs, src_size);
+		br_multicast_star_g_handle_mode(pg, MCAST_EXCLUDE);
+		changed = true;
+		break;
+	case MCAST_EXCLUDE:
+		changed = __grp_src_toex_excl(pg, srcs, nsrcs, src_size);
+		break;
+	}
+
+	pg->filter_mode = MCAST_EXCLUDE;
+	mod_timer(&pg->timer, jiffies + br_multicast_gmi(br));
+
+	return changed;
+}
+
+/* State          Msg type      New state                Actions
+ * INCLUDE (A)    BLOCK (B)     INCLUDE (A)              Send Q(G,A*B)
+ */
+static void __grp_src_block_incl(struct net_bridge_port_group *pg,
+				 void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge_group_src *ent;
+	u32 src_idx, to_send = 0;
+	struct br_ip src_ip;
+
+	hlist_for_each_entry(ent, &pg->src_list, node)
+		ent->flags &= ~BR_SGRP_F_SEND;
+
+	memset(&src_ip, 0, sizeof(src_ip));
+	src_ip.proto = pg->key.addr.proto;
+	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
+		memcpy(&src_ip.src, srcs, src_size);
+		ent = br_multicast_find_group_src(pg, &src_ip);
+		if (ent) {
+			ent->flags |= BR_SGRP_F_SEND;
+			to_send++;
+		}
+		srcs += src_size;
+	}
+
+	if (to_send)
+		__grp_src_query_marked_and_rexmit(pg);
+
+	if (pg->filter_mode == MCAST_INCLUDE && hlist_empty(&pg->src_list))
+		br_multicast_find_del_pg(pg->key.port->br, pg);
+}
+
+/* State          Msg type      New state                Actions
+ * EXCLUDE (X,Y)  BLOCK (A)     EXCLUDE (X+(A-Y),Y)      (A-X-Y)=Group Timer
+ *                                                       Send Q(G,A-Y)
+ */
+static bool __grp_src_block_excl(struct net_bridge_port_group *pg,
+				 void *srcs, u32 nsrcs, size_t src_size)
+{
+	struct net_bridge_group_src *ent;
+	u32 src_idx, to_send = 0;
+	bool changed = false;
+	struct br_ip src_ip;
+
+	hlist_for_each_entry(ent, &pg->src_list, node)
+		ent->flags &= ~BR_SGRP_F_SEND;
+
+	memset(&src_ip, 0, sizeof(src_ip));
+	src_ip.proto = pg->key.addr.proto;
+	for (src_idx = 0; src_idx < nsrcs; src_idx++) {
+		memcpy(&src_ip.src, srcs, src_size);
+		ent = br_multicast_find_group_src(pg, &src_ip);
+		if (!ent) {
+			ent = br_multicast_new_group_src(pg, &src_ip);
+			if (ent) {
+				__grp_src_mod_timer(ent, pg->timer.expires);
+				changed = true;
+			}
+		}
+		if (ent && timer_pending(&ent->timer)) {
+			ent->flags |= BR_SGRP_F_SEND;
+			to_send++;
+		}
+		srcs += src_size;
+	}
+
+	if (to_send)
+		__grp_src_query_marked_and_rexmit(pg);
+
+	return changed;
+}
+
+static bool br_multicast_block(struct net_bridge_port_group *pg,
+			       void *srcs, u32 nsrcs, size_t src_size)
+{
+	bool changed = false;
+
+	switch (pg->filter_mode) {
+	case MCAST_INCLUDE:
+		__grp_src_block_incl(pg, srcs, nsrcs, src_size);
+		break;
+	case MCAST_EXCLUDE:
+		changed = __grp_src_block_excl(pg, srcs, nsrcs, src_size);
+		break;
+	}
+
+	return changed;
+}
+
+static struct net_bridge_port_group *
+br_multicast_find_port(struct net_bridge_mdb_entry *mp,
+		       struct net_bridge_port *p,
+		       const unsigned char *src)
+{
+	struct net_bridge *br __maybe_unused = mp->br;
+	struct net_bridge_port_group *pg;
+
+	for (pg = mlock_dereference(mp->ports, br);
+	     pg;
+	     pg = mlock_dereference(pg->next, br))
+		if (br_port_group_equal(pg, p, src))
+			return pg;
+
+	return NULL;
+}
+
 static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 					 struct net_bridge_port *port,
 					 struct sk_buff *skb,
 					 u16 vid)
 {
+	bool igmpv2 = br->multicast_igmp_version == 2;
+	struct net_bridge_mdb_entry *mdst;
+	struct net_bridge_port_group *pg;
 	const unsigned char *src;
 	struct igmpv3_report *ih;
 	struct igmpv3_grec *grec;
-	int i;
-	int len;
-	int num;
-	int type;
-	int err = 0;
+	int i, len, num, type;
+	bool changed = false;
 	__be32 group;
+	int err = 0;
 	u16 nsrcs;
 
 	ih = igmpv3_report_hdr(skb);
@@ -947,7 +2280,6 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 		if (!ip_mc_may_pull(skb, len))
 			return -EINVAL;
 
-		/* We treat this as an IGMPv2 report for now. */
 		switch (type) {
 		case IGMPV3_MODE_IS_INCLUDE:
 		case IGMPV3_MODE_IS_EXCLUDE:
@@ -962,16 +2294,62 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br,
 		}
 
 		src = eth_hdr(skb)->h_source;
-		if ((type == IGMPV3_CHANGE_TO_INCLUDE ||
-		     type == IGMPV3_MODE_IS_INCLUDE) &&
-		    nsrcs == 0) {
-			br_ip4_multicast_leave_group(br, port, group, vid, src);
+		if (nsrcs == 0 &&
+		    (type == IGMPV3_CHANGE_TO_INCLUDE ||
+		     type == IGMPV3_MODE_IS_INCLUDE)) {
+			if (!port || igmpv2) {
+				br_ip4_multicast_leave_group(br, port, group, vid, src);
+				continue;
+			}
 		} else {
 			err = br_ip4_multicast_add_group(br, port, group, vid,
-							 src);
+							 src, igmpv2);
 			if (err)
 				break;
 		}
+
+		if (!port || igmpv2)
+			continue;
+
+		spin_lock_bh(&br->multicast_lock);
+		mdst = br_mdb_ip4_get(br, group, vid);
+		if (!mdst)
+			goto unlock_continue;
+		pg = br_multicast_find_port(mdst, port, src);
+		if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT))
+			goto unlock_continue;
+		/* reload grec */
+		grec = (void *)(skb->data + len - sizeof(*grec) - (nsrcs * 4));
+		switch (type) {
+		case IGMPV3_ALLOW_NEW_SOURCES:
+			changed = br_multicast_isinc_allow(pg, grec->grec_src,
+							   nsrcs, sizeof(__be32));
+			break;
+		case IGMPV3_MODE_IS_INCLUDE:
+			changed = br_multicast_isinc_allow(pg, grec->grec_src, nsrcs,
+							   sizeof(__be32));
+			break;
+		case IGMPV3_MODE_IS_EXCLUDE:
+			changed = br_multicast_isexc(pg, grec->grec_src, nsrcs,
+						     sizeof(__be32));
+			break;
+		case IGMPV3_CHANGE_TO_INCLUDE:
+			changed = br_multicast_toin(pg, grec->grec_src, nsrcs,
+						    sizeof(__be32));
+			break;
+		case IGMPV3_CHANGE_TO_EXCLUDE:
+			changed = br_multicast_toex(pg, grec->grec_src, nsrcs,
+						    sizeof(__be32));
+			break;
+		case IGMPV3_BLOCK_OLD_SOURCES:
+			changed = br_multicast_block(pg, grec->grec_src, nsrcs,
+						     sizeof(__be32));
+			break;
+		}
+		if (changed)
+			br_mdb_notify(br->dev, mdst, pg, RTM_NEWMDB);
+unlock_continue:
+		spin_unlock_bh(&br->multicast_lock);
 	}
 
 	return err;
@@ -983,14 +2361,16 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 					struct sk_buff *skb,
 					u16 vid)
 {
+	bool mldv1 = br->multicast_mld_version == 1;
+	struct net_bridge_mdb_entry *mdst;
+	struct net_bridge_port_group *pg;
 	unsigned int nsrcs_offset;
 	const unsigned char *src;
 	struct icmp6hdr *icmp6h;
 	struct mld2_grec *grec;
 	unsigned int grec_len;
-	int i;
-	int len;
-	int num;
+	bool changed = false;
+	int i, len, num;
 	int err = 0;
 
 	if (!ipv6_mc_may_pull(skb, sizeof(*icmp6h)))
@@ -1024,7 +2404,6 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		grec = (struct mld2_grec *)(skb->data + len);
 		len += grec_len;
 
-		/* We treat these as MLDv1 reports for now. */
 		switch (grec->grec_type) {
 		case MLD2_MODE_IS_INCLUDE:
 		case MLD2_MODE_IS_EXCLUDE:
@@ -1042,15 +2421,61 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br,
 		if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE ||
 		     grec->grec_type == MLD2_MODE_IS_INCLUDE) &&
 		    nsrcs == 0) {
-			br_ip6_multicast_leave_group(br, port, &grec->grec_mca,
-						     vid, src);
+			if (!port || mldv1) {
+				br_ip6_multicast_leave_group(br, port,
+							     &grec->grec_mca,
+							     vid, src);
+				continue;
+			}
 		} else {
 			err = br_ip6_multicast_add_group(br, port,
 							 &grec->grec_mca, vid,
-							 src);
+							 src, mldv1);
 			if (err)
 				break;
 		}
+
+		if (!port || mldv1)
+			continue;
+
+		spin_lock_bh(&br->multicast_lock);
+		mdst = br_mdb_ip6_get(br, &grec->grec_mca, vid);
+		if (!mdst)
+			goto unlock_continue;
+		pg = br_multicast_find_port(mdst, port, src);
+		if (!pg || (pg->flags & MDB_PG_FLAGS_PERMANENT))
+			goto unlock_continue;
+		switch (grec->grec_type) {
+		case MLD2_ALLOW_NEW_SOURCES:
+			changed = br_multicast_isinc_allow(pg, grec->grec_src,
+							   nsrcs,
+							   sizeof(struct in6_addr));
+			break;
+		case MLD2_MODE_IS_INCLUDE:
+			changed = br_multicast_isinc_allow(pg, grec->grec_src, nsrcs,
+							   sizeof(struct in6_addr));
+			break;
+		case MLD2_MODE_IS_EXCLUDE:
+			changed = br_multicast_isexc(pg, grec->grec_src, nsrcs,
+						     sizeof(struct in6_addr));
+			break;
+		case MLD2_CHANGE_TO_INCLUDE:
+			changed = br_multicast_toin(pg, grec->grec_src, nsrcs,
+						    sizeof(struct in6_addr));
+			break;
+		case MLD2_CHANGE_TO_EXCLUDE:
+			changed = br_multicast_toex(pg, grec->grec_src, nsrcs,
+						    sizeof(struct in6_addr));
+			break;
+		case MLD2_BLOCK_OLD_SOURCES:
+			changed = br_multicast_block(pg, grec->grec_src, nsrcs,
+						     sizeof(struct in6_addr));
+			break;
+		}
+		if (changed)
+			br_mdb_notify(br->dev, mdst, pg, RTM_NEWMDB);
+unlock_continue:
+		spin_unlock_bh(&br->multicast_lock);
 	}
 
 	return err;
@@ -1065,16 +2490,16 @@ static bool br_ip4_multicast_select_querier(struct net_bridge *br,
 	    !timer_pending(&br->ip4_other_query.timer))
 		goto update;
 
-	if (!br->ip4_querier.addr.u.ip4)
+	if (!br->ip4_querier.addr.src.ip4)
 		goto update;
 
-	if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.u.ip4))
+	if (ntohl(saddr) <= ntohl(br->ip4_querier.addr.src.ip4))
 		goto update;
 
 	return false;
 
 update:
-	br->ip4_querier.addr.u.ip4 = saddr;
+	br->ip4_querier.addr.src.ip4 = saddr;
 
 	/* update protected by general multicast_lock by caller */
 	rcu_assign_pointer(br->ip4_querier.port, port);
@@ -1091,13 +2516,13 @@ static bool br_ip6_multicast_select_querier(struct net_bridge *br,
 	    !timer_pending(&br->ip6_other_query.timer))
 		goto update;
 
-	if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.u.ip6) <= 0)
+	if (ipv6_addr_cmp(saddr, &br->ip6_querier.addr.src.ip6) <= 0)
 		goto update;
 
 	return false;
 
 update:
-	br->ip6_querier.addr.u.ip6 = *saddr;
+	br->ip6_querier.addr.src.ip6 = *saddr;
 
 	/* update protected by general multicast_lock by caller */
 	rcu_assign_pointer(br->ip6_querier.port, port);
@@ -1112,10 +2537,10 @@ static bool br_multicast_select_querier(struct net_bridge *br,
 {
 	switch (saddr->proto) {
 	case htons(ETH_P_IP):
-		return br_ip4_multicast_select_querier(br, port, saddr->u.ip4);
+		return br_ip4_multicast_select_querier(br, port, saddr->src.ip4);
 #if IS_ENABLED(CONFIG_IPV6)
 	case htons(ETH_P_IPV6):
-		return br_ip6_multicast_select_querier(br, port, &saddr->u.ip6);
+		return br_ip6_multicast_select_querier(br, port, &saddr->src.ip6);
 #endif
 	}
 
@@ -1245,7 +2670,8 @@ static void br_ip4_multicast_query(struct net_bridge *br,
 		}
 	} else if (transport_len >= sizeof(*ih3)) {
 		ih3 = igmpv3_query_hdr(skb);
-		if (ih3->nsrcs)
+		if (ih3->nsrcs ||
+		    (br->multicast_igmp_version == 3 && group && ih3->suppress))
 			goto out;
 
 		max_delay = ih3->code ?
@@ -1256,7 +2682,7 @@ static void br_ip4_multicast_query(struct net_bridge *br,
 
 	if (!group) {
 		saddr.proto = htons(ETH_P_IP);
-		saddr.u.ip4 = iph->saddr;
+		saddr.src.ip4 = iph->saddr;
 
 		br_multicast_query_received(br, port, &br->ip4_other_query,
 					    &saddr, max_delay);
@@ -1280,7 +2706,9 @@ static void br_ip4_multicast_query(struct net_bridge *br,
 	     pp = &p->next) {
 		if (timer_pending(&p->timer) ?
 		    time_after(p->timer.expires, now + max_delay) :
-		    try_to_del_timer_sync(&p->timer) >= 0)
+		    try_to_del_timer_sync(&p->timer) >= 0 &&
+		    (br->multicast_igmp_version == 2 ||
+		     p->filter_mode == MCAST_EXCLUDE))
 			mod_timer(&p->timer, now + max_delay);
 	}
 
@@ -1330,6 +2758,10 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 		mld2q = (struct mld2_query *)icmp6_hdr(skb);
 		if (!mld2q->mld2q_nsrcs)
 			group = &mld2q->mld2q_mca;
+		if (br->multicast_mld_version == 2 &&
+		    !ipv6_addr_any(&mld2q->mld2q_mca) &&
+		    mld2q->mld2q_suppress)
+			goto out;
 
 		max_delay = max(msecs_to_jiffies(mldv2_mrc(mld2q)), 1UL);
 	}
@@ -1338,7 +2770,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 
 	if (is_general_query) {
 		saddr.proto = htons(ETH_P_IPV6);
-		saddr.u.ip6 = ipv6_hdr(skb)->saddr;
+		saddr.src.ip6 = ipv6_hdr(skb)->saddr;
 
 		br_multicast_query_received(br, port, &br->ip6_other_query,
 					    &saddr, max_delay);
@@ -1363,7 +2795,9 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 	     pp = &p->next) {
 		if (timer_pending(&p->timer) ?
 		    time_after(p->timer.expires, now + max_delay) :
-		    try_to_del_timer_sync(&p->timer) >= 0)
+		    try_to_del_timer_sync(&p->timer) >= 0 &&
+		    (br->multicast_mld_version == 1 ||
+		     p->filter_mode == MCAST_EXCLUDE))
 			mod_timer(&p->timer, now + max_delay);
 	}
 
@@ -1407,16 +2841,8 @@ br_multicast_leave_group(struct net_bridge *br,
 			if (p->flags & MDB_PG_FLAGS_PERMANENT)
 				break;
 
-			rcu_assign_pointer(*pp, p->next);
-			hlist_del_init(&p->mglist);
-			del_timer(&p->timer);
-			kfree_rcu(p, rcu);
-			br_mdb_notify(br->dev, port, group, RTM_DELMDB,
-				      p->flags | MDB_PG_FLAGS_FAST_LEAVE);
-
-			if (!mp->ports && !mp->host_joined &&
-			    netif_running(br->dev))
-				mod_timer(&mp->timer, jiffies);
+			p->flags |= MDB_PG_FLAGS_FAST_LEAVE;
+			br_multicast_del_pg(mp, p, pp);
 		}
 		goto out;
 	}
@@ -1425,7 +2851,8 @@ br_multicast_leave_group(struct net_bridge *br,
 		goto out;
 
 	if (br_opt_get(br, BROPT_MULTICAST_QUERIER)) {
-		__br_multicast_send_query(br, port, &mp->addr);
+		__br_multicast_send_query(br, port, NULL, NULL, &mp->addr,
+					  false, 0, NULL);
 
 		time = jiffies + br->multicast_last_member_count *
 				 br->multicast_last_member_interval;
@@ -1467,7 +2894,7 @@ br_multicast_leave_group(struct net_bridge *br,
 	for (p = mlock_dereference(mp->ports, br);
 	     p != NULL;
 	     p = mlock_dereference(p->next, br)) {
-		if (p->port != port)
+		if (p->key.port != port)
 			continue;
 
 		if (!hlist_unhashed(&p->mglist) &&
@@ -1498,7 +2925,7 @@ static void br_ip4_multicast_leave_group(struct net_bridge *br,
 	own_query = port ? &port->ip4_own_query : &br->ip4_own_query;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip4 = group;
+	br_group.dst.ip4 = group;
 	br_group.proto = htons(ETH_P_IP);
 	br_group.vid = vid;
 
@@ -1522,7 +2949,7 @@ static void br_ip6_multicast_leave_group(struct net_bridge *br,
 	own_query = port ? &port->ip6_own_query : &br->ip6_own_query;
 
 	memset(&br_group, 0, sizeof(br_group));
-	br_group.u.ip6 = *group;
+	br_group.dst.ip6 = *group;
 	br_group.proto = htons(ETH_P_IPV6);
 	br_group.vid = vid;
 
@@ -1627,7 +3054,8 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
 	case IGMP_HOST_MEMBERSHIP_REPORT:
 	case IGMPV2_HOST_MEMBERSHIP_REPORT:
 		BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
-		err = br_ip4_multicast_add_group(br, port, ih->group, vid, src);
+		err = br_ip4_multicast_add_group(br, port, ih->group, vid, src,
+						 true);
 		break;
 	case IGMPV3_HOST_MEMBERSHIP_REPORT:
 		err = br_ip4_multicast_igmp3_report(br, port, skb, vid);
@@ -1706,7 +3134,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br,
 		src = eth_hdr(skb)->h_source;
 		BR_INPUT_SKB_CB(skb)->mrouters_only = 1;
 		err = br_ip6_multicast_add_group(br, port, &mld->mld_mca, vid,
-						 src);
+						 src, true);
 		break;
 	case ICMPV6_MLD2_REPORT:
 		err = br_ip6_multicast_mld2_report(br, port, skb, vid);
@@ -1781,6 +3209,19 @@ static void br_ip6_multicast_query_expired(struct timer_list *t)
 }
 #endif
 
+static void br_multicast_gc_work(struct work_struct *work)
+{
+	struct net_bridge *br = container_of(work, struct net_bridge,
+					     mcast_gc_work);
+	HLIST_HEAD(deleted_head);
+
+	spin_lock_bh(&br->multicast_lock);
+	hlist_move_list(&br->mcast_gc_list, &deleted_head);
+	spin_unlock_bh(&br->multicast_lock);
+
+	br_multicast_gc(&deleted_head);
+}
+
 void br_multicast_init(struct net_bridge *br)
 {
 	br->hash_max = BR_MULTICAST_DEFAULT_HASH_MAX;
@@ -1821,6 +3262,8 @@ void br_multicast_init(struct net_bridge *br)
 		    br_ip6_multicast_query_expired, 0);
 #endif
 	INIT_HLIST_HEAD(&br->mdb_list);
+	INIT_HLIST_HEAD(&br->mcast_gc_list);
+	INIT_WORK(&br->mcast_gc_work, br_multicast_gc_work);
 }
 
 static void br_ip4_multicast_join_snoopers(struct net_bridge *br)
@@ -1848,7 +3291,7 @@ static inline void br_ip6_multicast_join_snoopers(struct net_bridge *br)
 }
 #endif
 
-static void br_multicast_join_snoopers(struct net_bridge *br)
+void br_multicast_join_snoopers(struct net_bridge *br)
 {
 	br_ip4_multicast_join_snoopers(br);
 	br_ip6_multicast_join_snoopers(br);
@@ -1879,7 +3322,7 @@ static inline void br_ip6_multicast_leave_snoopers(struct net_bridge *br)
 }
 #endif
 
-static void br_multicast_leave_snoopers(struct net_bridge *br)
+void br_multicast_leave_snoopers(struct net_bridge *br)
 {
 	br_ip4_multicast_leave_snoopers(br);
 	br_ip6_multicast_leave_snoopers(br);
@@ -1898,9 +3341,6 @@ static void __br_multicast_open(struct net_bridge *br,
 
 void br_multicast_open(struct net_bridge *br)
 {
-	if (br_opt_get(br, BROPT_MULTICAST_ENABLED))
-		br_multicast_join_snoopers(br);
-
 	__br_multicast_open(br, &br->ip4_own_query);
 #if IS_ENABLED(CONFIG_IPV6)
 	__br_multicast_open(br, &br->ip6_own_query);
@@ -1916,26 +3356,23 @@ void br_multicast_stop(struct net_bridge *br)
 	del_timer_sync(&br->ip6_other_query.timer);
 	del_timer_sync(&br->ip6_own_query.timer);
 #endif
-
-	if (br_opt_get(br, BROPT_MULTICAST_ENABLED))
-		br_multicast_leave_snoopers(br);
 }
 
 void br_multicast_dev_del(struct net_bridge *br)
 {
 	struct net_bridge_mdb_entry *mp;
+	HLIST_HEAD(deleted_head);
 	struct hlist_node *tmp;
 
 	spin_lock_bh(&br->multicast_lock);
-	hlist_for_each_entry_safe(mp, tmp, &br->mdb_list, mdb_node) {
-		del_timer(&mp->timer);
-		rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode,
-				       br_mdb_rht_params);
-		hlist_del_rcu(&mp->mdb_node);
-		kfree_rcu(mp, rcu);
-	}
+	hlist_for_each_entry_safe(mp, tmp, &br->mdb_list, mdb_node)
+		br_multicast_del_mdb_entry(mp);
+	hlist_move_list(&br->mcast_gc_list, &deleted_head);
 	spin_unlock_bh(&br->multicast_lock);
 
+	br_multicast_gc(&deleted_head);
+	cancel_work_sync(&br->mcast_gc_work);
+
 	rcu_barrier();
 }
 
@@ -2049,6 +3486,7 @@ static void br_multicast_start_querier(struct net_bridge *br,
 int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 {
 	struct net_bridge_port *port;
+	bool change_snoopers = false;
 
 	spin_lock_bh(&br->multicast_lock);
 	if (!!br_opt_get(br, BROPT_MULTICAST_ENABLED) == !!val)
@@ -2057,7 +3495,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 	br_mc_disabled_update(br->dev, val);
 	br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val);
 	if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) {
-		br_multicast_leave_snoopers(br);
+		change_snoopers = true;
 		goto unlock;
 	}
 
@@ -2068,9 +3506,30 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val)
 	list_for_each_entry(port, &br->port_list, list)
 		__br_multicast_enable_port(port);
 
+	change_snoopers = true;
+
 unlock:
 	spin_unlock_bh(&br->multicast_lock);
 
+	/* br_multicast_join_snoopers has the potential to cause
+	 * an MLD Report/Leave to be delivered to br_multicast_rcv,
+	 * which would in turn call br_multicast_add_group, which would
+	 * attempt to acquire multicast_lock. This function should be
+	 * called after the lock has been released to avoid deadlocks on
+	 * multicast_lock.
+	 *
+	 * br_multicast_leave_snoopers does not have the problem since
+	 * br_multicast_rcv first checks BROPT_MULTICAST_ENABLED, and
+	 * returns without calling br_multicast_ipv4/6_rcv if it's not
+	 * enabled. Moved both functions out just for symmetry.
+	 */
+	if (change_snoopers) {
+		if (br_opt_get(br, BROPT_MULTICAST_ENABLED))
+			br_multicast_join_snoopers(br);
+		else
+			br_multicast_leave_snoopers(br);
+	}
+
 	return 0;
 }
 
@@ -2211,7 +3670,7 @@ int br_multicast_list_adjacent(struct net_device *dev,
 			if (!entry)
 				goto unlock;
 
-			entry->addr = group->addr;
+			entry->addr = group->key.addr;
 			list_add(&entry->list, br_ip_list);
 			count++;
 		}
@@ -2252,7 +3711,7 @@ bool br_multicast_has_querier_anywhere(struct net_device *dev, int proto)
 	memset(&eth, 0, sizeof(eth));
 	eth.h_proto = htons(proto);
 
-	ret = br_multicast_querier_exists(br, &eth);
+	ret = br_multicast_querier_exists(br, &eth, NULL);
 
 unlock:
 	rcu_read_unlock();
@@ -2468,10 +3927,23 @@ void br_multicast_get_stats(const struct net_bridge *br,
 
 int br_mdb_hash_init(struct net_bridge *br)
 {
-	return rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params);
+	int err;
+
+	err = rhashtable_init(&br->sg_port_tbl, &br_sg_port_rht_params);
+	if (err)
+		return err;
+
+	err = rhashtable_init(&br->mdb_hash_tbl, &br_mdb_rht_params);
+	if (err) {
+		rhashtable_destroy(&br->sg_port_tbl);
+		return err;
+	}
+
+	return 0;
 }
 
 void br_mdb_hash_fini(struct net_bridge *br)
 {
+	rhashtable_destroy(&br->sg_port_tbl);
 	rhashtable_destroy(&br->mdb_hash_tbl);
 }
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 04c3f9a82650..8edfb98ae1d5 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -735,6 +735,11 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
 	mtu_reserved = nf_bridge_mtu_reduction(skb);
 	mtu = skb->dev->mtu;
 
+	if (nf_bridge->pkt_otherhost) {
+		skb->pkt_type = PACKET_OTHERHOST;
+		nf_bridge->pkt_otherhost = false;
+	}
+
 	if (nf_bridge->frag_max_size && nf_bridge->frag_max_size < mtu)
 		mtu = nf_bridge->frag_max_size;
 
@@ -835,8 +840,6 @@ static unsigned int br_nf_post_routing(void *priv,
 	else
 		return NF_ACCEPT;
 
-	/* We assume any code from br_dev_queue_push_xmit onwards doesn't care
-	 * about the value of skb->pkt_type. */
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		skb->pkt_type = PACKET_HOST;
 		nf_bridge->pkt_otherhost = true;
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index da310f0ca725..49700ce0e919 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -16,6 +16,7 @@
 
 #include "br_private.h"
 #include "br_private_stp.h"
+#include "br_private_cfm.h"
 #include "br_private_tunnel.h"
 
 static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg,
@@ -93,9 +94,11 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev,
 {
 	struct net_bridge_vlan_group *vg = NULL;
 	struct net_bridge_port *p = NULL;
-	struct net_bridge *br;
-	int num_vlan_infos;
+	struct net_bridge *br = NULL;
+	u32 num_cfm_peer_mep_infos;
+	u32 num_cfm_mep_infos;
 	size_t vinfo_sz = 0;
+	int num_vlan_infos;
 
 	rcu_read_lock();
 	if (netif_is_bridge_port(dev)) {
@@ -114,6 +117,49 @@ static size_t br_get_link_af_size_filtered(const struct net_device *dev,
 	/* Each VLAN is returned in bridge_vlan_info along with flags */
 	vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info));
 
+	if (!(filter_mask & RTEXT_FILTER_CFM_STATUS))
+		return vinfo_sz;
+
+	if (!br)
+		return vinfo_sz;
+
+	/* CFM status info must be added */
+	br_cfm_mep_count(br, &num_cfm_mep_infos);
+	br_cfm_peer_mep_count(br, &num_cfm_peer_mep_infos);
+
+	vinfo_sz += nla_total_size(0);	/* IFLA_BRIDGE_CFM */
+	/* For each status struct the MEP instance (u32) is added */
+	/* MEP instance (u32) + br_cfm_mep_status */
+	vinfo_sz += num_cfm_mep_infos *
+		     /*IFLA_BRIDGE_CFM_MEP_STATUS_INSTANCE */
+		    (nla_total_size(sizeof(u32))
+		     /* IFLA_BRIDGE_CFM_MEP_STATUS_OPCODE_UNEXP_SEEN */
+		     + nla_total_size(sizeof(u32))
+		     /* IFLA_BRIDGE_CFM_MEP_STATUS_VERSION_UNEXP_SEEN */
+		     + nla_total_size(sizeof(u32))
+		     /* IFLA_BRIDGE_CFM_MEP_STATUS_RX_LEVEL_LOW_SEEN */
+		     + nla_total_size(sizeof(u32)));
+	/* MEP instance (u32) + br_cfm_cc_peer_status */
+	vinfo_sz += num_cfm_peer_mep_infos *
+		     /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_INSTANCE */
+		    (nla_total_size(sizeof(u32))
+		     /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PEER_MEPID */
+		     + nla_total_size(sizeof(u32))
+		     /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_CCM_DEFECT */
+		     + nla_total_size(sizeof(u32))
+		     /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_RDI */
+		     + nla_total_size(sizeof(u32))
+		     /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_PORT_TLV_VALUE */
+		     + nla_total_size(sizeof(u8))
+		     /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_IF_TLV_VALUE */
+		     + nla_total_size(sizeof(u8))
+		     /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEEN */
+		     + nla_total_size(sizeof(u32))
+		     /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_TLV_SEEN */
+		     + nla_total_size(sizeof(u32))
+		     /* IFLA_BRIDGE_CFM_CC_PEER_STATUS_SEQ_UNEXP_SEEN */
+		     + nla_total_size(sizeof(u32)));
+
 	return vinfo_sz;
 }
 
@@ -377,7 +423,8 @@ nla_put_failure:
 static int br_fill_ifinfo(struct sk_buff *skb,
 			  const struct net_bridge_port *port,
 			  u32 pid, u32 seq, int event, unsigned int flags,
-			  u32 filter_mask, const struct net_device *dev)
+			  u32 filter_mask, const struct net_device *dev,
+			  bool getlink)
 {
 	u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN;
 	struct nlattr *af = NULL;
@@ -426,7 +473,9 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 
 	if (filter_mask & (RTEXT_FILTER_BRVLAN |
 			   RTEXT_FILTER_BRVLAN_COMPRESSED |
-			   RTEXT_FILTER_MRP)) {
+			   RTEXT_FILTER_MRP |
+			   RTEXT_FILTER_CFM_CONFIG |
+			   RTEXT_FILTER_CFM_STATUS)) {
 		af = nla_nest_start_noflag(skb, IFLA_AF_SPEC);
 		if (!af)
 			goto nla_put_failure;
@@ -475,6 +524,36 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 			goto nla_put_failure;
 	}
 
+	if (filter_mask & (RTEXT_FILTER_CFM_CONFIG | RTEXT_FILTER_CFM_STATUS)) {
+		struct nlattr *cfm_nest = NULL;
+		int err;
+
+		if (!br_cfm_created(br) || port)
+			goto done;
+
+		cfm_nest = nla_nest_start(skb, IFLA_BRIDGE_CFM);
+		if (!cfm_nest)
+			goto nla_put_failure;
+
+		if (filter_mask & RTEXT_FILTER_CFM_CONFIG) {
+			rcu_read_lock();
+			err = br_cfm_config_fill_info(skb, br);
+			rcu_read_unlock();
+			if (err)
+				goto nla_put_failure;
+		}
+
+		if (filter_mask & RTEXT_FILTER_CFM_STATUS) {
+			rcu_read_lock();
+			err = br_cfm_status_fill_info(skb, br, getlink);
+			rcu_read_unlock();
+			if (err)
+				goto nla_put_failure;
+		}
+
+		nla_nest_end(skb, cfm_nest);
+	}
+
 done:
 	if (af)
 		nla_nest_end(skb, af);
@@ -486,11 +565,9 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-/* Notify listeners of a change in bridge or port information */
-void br_ifinfo_notify(int event, const struct net_bridge *br,
-		      const struct net_bridge_port *port)
+void br_info_notify(int event, const struct net_bridge *br,
+		    const struct net_bridge_port *port, u32 filter)
 {
-	u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
 	struct net_device *dev;
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
@@ -515,7 +592,7 @@ void br_ifinfo_notify(int event, const struct net_bridge *br,
 	if (skb == NULL)
 		goto errout;
 
-	err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev);
+	err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev, false);
 	if (err < 0) {
 		/* -EMSGSIZE implies BUG in br_nlmsg_size() */
 		WARN_ON(err == -EMSGSIZE);
@@ -528,6 +605,15 @@ errout:
 	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
 }
 
+/* Notify listeners of a change in bridge or port information */
+void br_ifinfo_notify(int event, const struct net_bridge *br,
+		      const struct net_bridge_port *port)
+{
+	u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED;
+
+	return br_info_notify(event, br, port, filter);
+}
+
 /*
  * Dump information about all ports, in response to GETLINK
  */
@@ -538,11 +624,13 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 
 	if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) &&
 	    !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) &&
-	    !(filter_mask & RTEXT_FILTER_MRP))
+	    !(filter_mask & RTEXT_FILTER_MRP) &&
+	    !(filter_mask & RTEXT_FILTER_CFM_CONFIG) &&
+	    !(filter_mask & RTEXT_FILTER_CFM_STATUS))
 		return 0;
 
 	return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags,
-			      filter_mask, dev);
+			      filter_mask, dev, true);
 }
 
 static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p,
@@ -700,6 +788,11 @@ static int br_afspec(struct net_bridge *br,
 			if (err)
 				return err;
 			break;
+		case IFLA_BRIDGE_CFM:
+			err = br_cfm_parse(br, p, attr, cmd, extack);
+			if (err)
+				return err;
+			break;
 		}
 	}
 
@@ -1091,8 +1184,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
 	[IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 },
 	[IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 },
 	[IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 },
-	[IFLA_BR_MULTI_BOOLOPT] = { .type = NLA_EXACT_LEN,
-				    .len = sizeof(struct br_boolopt_multi) },
+	[IFLA_BR_MULTI_BOOLOPT] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)),
 };
 
 static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -1631,7 +1724,7 @@ static int br_fill_linkxstats(struct sk_buff *skb,
 		pvid = br_get_pvid(vg);
 		list_for_each_entry(v, &vg->vlan_list, vlist) {
 			struct bridge_vlan_xstats vxi;
-			struct br_vlan_stats stats;
+			struct pcpu_sw_netstats stats;
 
 			if (++vl_idx < *prividx)
 				continue;
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index baa1500f384f..d62c6e1af64a 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -89,14 +89,6 @@ struct bridge_mcast_stats {
 };
 #endif
 
-struct br_vlan_stats {
-	u64 rx_bytes;
-	u64 rx_packets;
-	u64 tx_bytes;
-	u64 tx_packets;
-	struct u64_stats_sync syncp;
-};
-
 struct br_tunnel_info {
 	__be64			tunnel_id;
 	struct metadata_dst	*tunnel_dst;
@@ -137,7 +129,7 @@ struct net_bridge_vlan {
 	u16				flags;
 	u16				priv_flags;
 	u8				state;
-	struct br_vlan_stats __percpu	*stats;
+	struct pcpu_sw_netstats __percpu *stats;
 	union {
 		struct net_bridge	*br;
 		struct net_bridge_port	*port;
@@ -213,27 +205,71 @@ struct net_bridge_fdb_entry {
 #define MDB_PG_FLAGS_PERMANENT	BIT(0)
 #define MDB_PG_FLAGS_OFFLOAD	BIT(1)
 #define MDB_PG_FLAGS_FAST_LEAVE	BIT(2)
+#define MDB_PG_FLAGS_STAR_EXCL	BIT(3)
+#define MDB_PG_FLAGS_BLOCKED	BIT(4)
 
-struct net_bridge_port_group {
-	struct net_bridge_port		*port;
-	struct net_bridge_port_group __rcu *next;
-	struct hlist_node		mglist;
-	struct rcu_head			rcu;
+#define PG_SRC_ENT_LIMIT	32
+
+#define BR_SGRP_F_DELETE	BIT(0)
+#define BR_SGRP_F_SEND		BIT(1)
+#define BR_SGRP_F_INSTALLED	BIT(2)
+
+struct net_bridge_mcast_gc {
+	struct hlist_node		gc_node;
+	void				(*destroy)(struct net_bridge_mcast_gc *gc);
+};
+
+struct net_bridge_group_src {
+	struct hlist_node		node;
+
+	struct br_ip			addr;
+	struct net_bridge_port_group	*pg;
+	u8				flags;
+	u8				src_query_rexmit_cnt;
 	struct timer_list		timer;
+
+	struct net_bridge		*br;
+	struct net_bridge_mcast_gc	mcast_gc;
+	struct rcu_head			rcu;
+};
+
+struct net_bridge_port_group_sg_key {
+	struct net_bridge_port		*port;
 	struct br_ip			addr;
+};
+
+struct net_bridge_port_group {
+	struct net_bridge_port_group __rcu *next;
+	struct net_bridge_port_group_sg_key key;
 	unsigned char			eth_addr[ETH_ALEN] __aligned(2);
 	unsigned char			flags;
+	unsigned char			filter_mode;
+	unsigned char			grp_query_rexmit_cnt;
+	unsigned char			rt_protocol;
+
+	struct hlist_head		src_list;
+	unsigned int			src_ents;
+	struct timer_list		timer;
+	struct timer_list		rexmit_timer;
+	struct hlist_node		mglist;
+
+	struct rhash_head		rhnode;
+	struct net_bridge_mcast_gc	mcast_gc;
+	struct rcu_head			rcu;
 };
 
 struct net_bridge_mdb_entry {
 	struct rhash_head		rhnode;
 	struct net_bridge		*br;
 	struct net_bridge_port_group __rcu *ports;
-	struct rcu_head			rcu;
-	struct timer_list		timer;
 	struct br_ip			addr;
 	bool				host_joined;
+
+	struct timer_list		timer;
 	struct hlist_node		mdb_node;
+
+	struct net_bridge_mcast_gc	mcast_gc;
+	struct rcu_head			rcu;
 };
 
 struct net_bridge_port {
@@ -339,9 +375,8 @@ enum net_bridge_opts {
 struct net_bridge {
 	spinlock_t			lock;
 	spinlock_t			hash_lock;
-	struct list_head		port_list;
+	struct hlist_head		frame_type_list;
 	struct net_device		*dev;
-	struct pcpu_sw_netstats		__percpu *stats;
 	unsigned long			options;
 	/* These fields are accessed on each packet */
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
@@ -351,6 +386,7 @@ struct net_bridge {
 #endif
 
 	struct rhashtable		fdb_hash_tbl;
+	struct list_head		port_list;
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	union {
 		struct rtable		fake_rtable;
@@ -405,7 +441,9 @@ struct net_bridge {
 	unsigned long			multicast_startup_query_interval;
 
 	struct rhashtable		mdb_hash_tbl;
+	struct rhashtable		sg_port_tbl;
 
+	struct hlist_head		mcast_gc_list;
 	struct hlist_head		mdb_list;
 	struct hlist_head		router_list;
 
@@ -419,6 +457,7 @@ struct net_bridge {
 	struct bridge_mcast_own_query	ip6_own_query;
 	struct bridge_mcast_querier	ip6_querier;
 #endif /* IS_ENABLED(CONFIG_IPV6) */
+	struct work_struct		mcast_gc_work;
 #endif
 
 	struct timer_list		hello_timer;
@@ -434,7 +473,10 @@ struct net_bridge {
 	struct hlist_head		fdb_list;
 
 #if IS_ENABLED(CONFIG_BRIDGE_MRP)
-	struct list_head		mrp_list;
+	struct hlist_head		mrp_list;
+#endif
+#if IS_ENABLED(CONFIG_BRIDGE_CFM)
+	struct hlist_head		mep_list;
 #endif
 };
 
@@ -708,6 +750,16 @@ int nbp_backup_change(struct net_bridge_port *p, struct net_device *backup_dev);
 int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
 rx_handler_func_t *br_get_rx_handler(const struct net_device *dev);
 
+struct br_frame_type {
+	__be16			type;
+	int			(*frame_handler)(struct net_bridge_port *port,
+						 struct sk_buff *skb);
+	struct hlist_node	list;
+};
+
+void br_add_frame(struct net_bridge *br, struct br_frame_type *ft);
+void br_del_frame(struct net_bridge *br, struct br_frame_type *ft);
+
 static inline bool br_rx_handler_check_rcu(const struct net_device *dev)
 {
 	return rcu_dereference(dev->rx_handler) == br_get_rx_handler(dev);
@@ -745,6 +797,8 @@ void br_multicast_del_port(struct net_bridge_port *port);
 void br_multicast_enable_port(struct net_bridge_port *port);
 void br_multicast_disable_port(struct net_bridge_port *port);
 void br_multicast_init(struct net_bridge *br);
+void br_multicast_join_snoopers(struct net_bridge *br);
+void br_multicast_leave_snoopers(struct net_bridge *br);
 void br_multicast_open(struct net_bridge *br);
 void br_multicast_stop(struct net_bridge *br);
 void br_multicast_dev_del(struct net_bridge *br);
@@ -766,13 +820,17 @@ br_multicast_new_group(struct net_bridge *br, struct br_ip *group);
 struct net_bridge_port_group *
 br_multicast_new_port_group(struct net_bridge_port *port, struct br_ip *group,
 			    struct net_bridge_port_group __rcu *next,
-			    unsigned char flags, const unsigned char *src);
+			    unsigned char flags, const unsigned char *src,
+			    u8 filter_mode, u8 rt_protocol);
 int br_mdb_hash_init(struct net_bridge *br);
 void br_mdb_hash_fini(struct net_bridge *br);
-void br_mdb_notify(struct net_device *dev, struct net_bridge_port *port,
-		   struct br_ip *group, int type, u8 flags);
+void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp,
+		   struct net_bridge_port_group *pg, int type);
 void br_rtr_notify(struct net_device *dev, struct net_bridge_port *port,
 		   int type);
+void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
+			 struct net_bridge_port_group *pg,
+			 struct net_bridge_port_group __rcu **pp);
 void br_multicast_count(struct net_bridge *br, const struct net_bridge_port *p,
 			const struct sk_buff *skb, u8 type, u8 dir);
 int br_multicast_init_stats(struct net_bridge *br);
@@ -784,6 +842,15 @@ void br_mdb_init(void);
 void br_mdb_uninit(void);
 void br_multicast_host_join(struct net_bridge_mdb_entry *mp, bool notify);
 void br_multicast_host_leave(struct net_bridge_mdb_entry *mp, bool notify);
+void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
+				     u8 filter_mode);
+void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
+				       struct net_bridge_port_group *sg);
+
+static inline bool br_group_is_l2(const struct br_ip *group)
+{
+	return group->proto == 0;
+}
 
 #define mlock_dereference(X, br) \
 	rcu_dereference_protected(X, lockdep_is_held(&br->multicast_lock))
@@ -816,7 +883,8 @@ __br_multicast_querier_exists(struct net_bridge *br,
 }
 
 static inline bool br_multicast_querier_exists(struct net_bridge *br,
-					       struct ethhdr *eth)
+					       struct ethhdr *eth,
+					       const struct net_bridge_mdb_entry *mdb)
 {
 	switch (eth->h_proto) {
 	case (htons(ETH_P_IP)):
@@ -828,6 +896,35 @@ static inline bool br_multicast_querier_exists(struct net_bridge *br,
 			&br->ip6_other_query, true);
 #endif
 	default:
+		return !!mdb && br_group_is_l2(&mdb->addr);
+	}
+}
+
+static inline bool br_multicast_is_star_g(const struct br_ip *ip)
+{
+	switch (ip->proto) {
+	case htons(ETH_P_IP):
+		return ipv4_is_zeronet(ip->src.ip4);
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		return ipv6_addr_any(&ip->src.ip6);
+#endif
+	default:
+		return false;
+	}
+}
+
+static inline bool br_multicast_should_handle_mode(const struct net_bridge *br,
+						   __be16 proto)
+{
+	switch (proto) {
+	case htons(ETH_P_IP):
+		return !!(br->multicast_igmp_version == 3);
+#if IS_ENABLED(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		return !!(br->multicast_mld_version == 2);
+#endif
+	default:
 		return false;
 	}
 }
@@ -836,6 +933,19 @@ static inline int br_multicast_igmp_type(const struct sk_buff *skb)
 {
 	return BR_INPUT_SKB_CB(skb)->igmp;
 }
+
+static inline unsigned long br_multicast_lmqt(const struct net_bridge *br)
+{
+	return br->multicast_last_member_interval *
+	       br->multicast_last_member_count;
+}
+
+static inline unsigned long br_multicast_gmi(const struct net_bridge *br)
+{
+	/* use the RFC default of 2 for QRV */
+	return 2 * br->multicast_query_interval +
+	       br->multicast_query_response_interval;
+}
 #else
 static inline int br_multicast_rcv(struct net_bridge *br,
 				   struct net_bridge_port *port,
@@ -872,6 +982,14 @@ static inline void br_multicast_init(struct net_bridge *br)
 {
 }
 
+static inline void br_multicast_join_snoopers(struct net_bridge *br)
+{
+}
+
+static inline void br_multicast_leave_snoopers(struct net_bridge *br)
+{
+}
+
 static inline void br_multicast_open(struct net_bridge *br)
 {
 }
@@ -896,7 +1014,8 @@ static inline bool br_multicast_is_router(struct net_bridge *br)
 }
 
 static inline bool br_multicast_querier_exists(struct net_bridge *br,
-					       struct ethhdr *eth)
+					       struct ethhdr *eth,
+					       const struct net_bridge_mdb_entry *mdb)
 {
 	return false;
 }
@@ -975,7 +1094,7 @@ void nbp_vlan_flush(struct net_bridge_port *port);
 int nbp_vlan_init(struct net_bridge_port *port, struct netlink_ext_ack *extack);
 int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask);
 void br_vlan_get_stats(const struct net_bridge_vlan *v,
-		       struct br_vlan_stats *stats);
+		       struct pcpu_sw_netstats *stats);
 void br_vlan_port_event(struct net_bridge_port *p, unsigned long event);
 int br_vlan_bridge_event(struct net_device *dev, unsigned long event,
 			 void *ptr);
@@ -1171,7 +1290,7 @@ static inline struct net_bridge_vlan_group *nbp_vlan_group_rcu(
 }
 
 static inline void br_vlan_get_stats(const struct net_bridge_vlan *v,
-				     struct br_vlan_stats *stats)
+				     struct pcpu_sw_netstats *stats)
 {
 }
 
@@ -1320,7 +1439,6 @@ extern int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr)
 #if IS_ENABLED(CONFIG_BRIDGE_MRP)
 int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p,
 		 struct nlattr *attr, int cmd, struct netlink_ext_ack *extack);
-int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb);
 bool br_mrp_enabled(struct net_bridge *br);
 void br_mrp_port_del(struct net_bridge *br, struct net_bridge_port *p);
 int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br);
@@ -1332,11 +1450,6 @@ static inline int br_mrp_parse(struct net_bridge *br, struct net_bridge_port *p,
 	return -EOPNOTSUPP;
 }
 
-static inline int br_mrp_process(struct net_bridge_port *p, struct sk_buff *skb)
-{
-	return 0;
-}
-
 static inline bool br_mrp_enabled(struct net_bridge *br)
 {
 	return false;
@@ -1354,12 +1467,67 @@ static inline int br_mrp_fill_info(struct sk_buff *skb, struct net_bridge *br)
 
 #endif
 
+/* br_cfm.c */
+#if IS_ENABLED(CONFIG_BRIDGE_CFM)
+int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p,
+		 struct nlattr *attr, int cmd, struct netlink_ext_ack *extack);
+bool br_cfm_created(struct net_bridge *br);
+void br_cfm_port_del(struct net_bridge *br, struct net_bridge_port *p);
+int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br);
+int br_cfm_status_fill_info(struct sk_buff *skb,
+			    struct net_bridge *br,
+			    bool getlink);
+int br_cfm_mep_count(struct net_bridge *br, u32 *count);
+int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count);
+#else
+static inline int br_cfm_parse(struct net_bridge *br, struct net_bridge_port *p,
+			       struct nlattr *attr, int cmd,
+			       struct netlink_ext_ack *extack)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool br_cfm_created(struct net_bridge *br)
+{
+	return false;
+}
+
+static inline void br_cfm_port_del(struct net_bridge *br,
+				   struct net_bridge_port *p)
+{
+}
+
+static inline int br_cfm_config_fill_info(struct sk_buff *skb, struct net_bridge *br)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int br_cfm_status_fill_info(struct sk_buff *skb,
+					  struct net_bridge *br,
+					  bool getlink)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int br_cfm_mep_count(struct net_bridge *br, u32 *count)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int br_cfm_peer_mep_count(struct net_bridge *br, u32 *count)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 /* br_netlink.c */
 extern struct rtnl_link_ops br_link_ops;
 int br_netlink_init(void);
 void br_netlink_fini(void);
 void br_ifinfo_notify(int event, const struct net_bridge *br,
 		      const struct net_bridge_port *port);
+void br_info_notify(int event, const struct net_bridge *br,
+		    const struct net_bridge_port *port, u32 filter);
 int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags,
 	       struct netlink_ext_ack *extack);
 int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags);
diff --git a/net/bridge/br_private_cfm.h b/net/bridge/br_private_cfm.h
new file mode 100644
index 000000000000..a43a5e7fa2c3
--- /dev/null
+++ b/net/bridge/br_private_cfm.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _BR_PRIVATE_CFM_H_
+#define _BR_PRIVATE_CFM_H_
+
+#include "br_private.h"
+#include <uapi/linux/cfm_bridge.h>
+
+struct br_cfm_mep_create {
+	enum br_cfm_domain domain; /* Domain for this MEP */
+	enum br_cfm_mep_direction direction; /* Up or Down MEP direction */
+	u32 ifindex; /* Residence port */
+};
+
+int br_cfm_mep_create(struct net_bridge *br,
+		      const u32 instance,
+		      struct br_cfm_mep_create *const create,
+		      struct netlink_ext_ack *extack);
+
+int br_cfm_mep_delete(struct net_bridge *br,
+		      const u32 instance,
+		      struct netlink_ext_ack *extack);
+
+struct br_cfm_mep_config {
+	u32 mdlevel;
+	u32 mepid; /* MEPID for this MEP */
+	struct mac_addr unicast_mac; /* The MEP unicast MAC */
+};
+
+int br_cfm_mep_config_set(struct net_bridge *br,
+			  const u32 instance,
+			  const struct br_cfm_mep_config *const config,
+			  struct netlink_ext_ack *extack);
+
+struct br_cfm_maid {
+	u8 data[CFM_MAID_LENGTH];
+};
+
+struct br_cfm_cc_config {
+	/* Expected received CCM PDU MAID. */
+	struct br_cfm_maid exp_maid;
+
+	/* Expected received CCM PDU interval. */
+	/* Transmitting CCM PDU interval when CCM tx is enabled. */
+	enum br_cfm_ccm_interval exp_interval;
+
+	bool enable; /* Enable/disable CCM PDU handling */
+};
+
+int br_cfm_cc_config_set(struct net_bridge *br,
+			 const u32 instance,
+			 const struct br_cfm_cc_config *const config,
+			 struct netlink_ext_ack *extack);
+
+int br_cfm_cc_peer_mep_add(struct net_bridge *br, const u32 instance,
+			   u32 peer_mep_id,
+			   struct netlink_ext_ack *extack);
+int br_cfm_cc_peer_mep_remove(struct net_bridge *br, const u32 instance,
+			      u32 peer_mep_id,
+			      struct netlink_ext_ack *extack);
+
+/* Transmitted CCM Remote Defect Indication status set.
+ * This RDI is inserted in transmitted CCM PDUs if CCM transmission is enabled.
+ * See br_cfm_cc_ccm_tx() with interval != BR_CFM_CCM_INTERVAL_NONE
+ */
+int br_cfm_cc_rdi_set(struct net_bridge *br, const u32 instance,
+		      const bool rdi, struct netlink_ext_ack *extack);
+
+/* OAM PDU Tx information */
+struct br_cfm_cc_ccm_tx_info {
+	struct mac_addr dmac;
+	/* The CCM will be transmitted for this period in seconds.
+	 * Call br_cfm_cc_ccm_tx before timeout to keep transmission alive.
+	 * When period is zero any ongoing transmission will be stopped.
+	 */
+	u32 period;
+
+	bool seq_no_update; /* Update Tx CCM sequence number */
+	bool if_tlv; /* Insert Interface Status TLV */
+	u8 if_tlv_value; /* Interface Status TLV value */
+	bool port_tlv; /* Insert Port Status TLV */
+	u8 port_tlv_value; /* Port Status TLV value */
+	/* Sender ID TLV ??
+	 * Organization-Specific TLV ??
+	 */
+};
+
+int br_cfm_cc_ccm_tx(struct net_bridge *br, const u32 instance,
+		     const struct br_cfm_cc_ccm_tx_info *const tx_info,
+		     struct netlink_ext_ack *extack);
+
+struct br_cfm_mep_status {
+	/* Indications that an OAM PDU has been seen. */
+	bool opcode_unexp_seen; /* RX of OAM PDU with unexpected opcode */
+	bool version_unexp_seen; /* RX of OAM PDU with unexpected version */
+	bool rx_level_low_seen; /* Rx of OAM PDU with level low */
+};
+
+struct br_cfm_cc_peer_status {
+	/* This CCM related status is based on the latest received CCM PDU. */
+	u8 port_tlv_value; /* Port Status TLV value */
+	u8 if_tlv_value; /* Interface Status TLV value */
+
+	/* CCM has not been received for 3.25 intervals */
+	u8 ccm_defect:1;
+
+	/* (RDI == 1) for last received CCM PDU */
+	u8 rdi:1;
+
+	/* Indications that a CCM PDU has been seen. */
+	u8 seen:1; /* CCM PDU received */
+	u8 tlv_seen:1; /* CCM PDU with TLV received */
+	/* CCM PDU with unexpected sequence number received */
+	u8 seq_unexp_seen:1;
+};
+
+struct br_cfm_mep {
+	/* list header of MEP instances */
+	struct hlist_node		head;
+	u32				instance;
+	struct br_cfm_mep_create	create;
+	struct br_cfm_mep_config	config;
+	struct br_cfm_cc_config		cc_config;
+	struct br_cfm_cc_ccm_tx_info	cc_ccm_tx_info;
+	/* List of multiple peer MEPs */
+	struct hlist_head		peer_mep_list;
+	struct net_bridge_port __rcu	*b_port;
+	unsigned long			ccm_tx_end;
+	struct delayed_work		ccm_tx_dwork;
+	u32				ccm_tx_snumber;
+	u32				ccm_rx_snumber;
+	struct br_cfm_mep_status	status;
+	bool				rdi;
+	struct rcu_head			rcu;
+};
+
+struct br_cfm_peer_mep {
+	struct hlist_node		head;
+	struct br_cfm_mep		*mep;
+	struct delayed_work		ccm_rx_dwork;
+	u32				mepid;
+	struct br_cfm_cc_peer_status	cc_status;
+	u32				ccm_rx_count_miss;
+	struct rcu_head			rcu;
+};
+
+#endif /* _BR_PRIVATE_CFM_H_ */
diff --git a/net/bridge/br_private_mrp.h b/net/bridge/br_private_mrp.h
index af0e9eff6549..2514954c1431 100644
--- a/net/bridge/br_private_mrp.h
+++ b/net/bridge/br_private_mrp.h
@@ -8,7 +8,7 @@
 
 struct br_mrp {
 	/* list of mrp instances */
-	struct list_head		list;
+	struct hlist_node		list;
 
 	struct net_bridge_port __rcu	*p_port;
 	struct net_bridge_port __rcu	*s_port;
@@ -72,8 +72,7 @@ int br_mrp_switchdev_set_ring_state(struct net_bridge *br, struct br_mrp *mrp,
 int br_mrp_switchdev_send_ring_test(struct net_bridge *br, struct br_mrp *mrp,
 				    u32 interval, u8 max_miss, u32 period,
 				    bool monitor);
-int br_mrp_port_switchdev_set_state(struct net_bridge_port *p,
-				    enum br_mrp_port_state_type state);
+int br_mrp_port_switchdev_set_state(struct net_bridge_port *p, u32 state);
 int br_mrp_port_switchdev_set_role(struct net_bridge_port *p,
 				   enum br_mrp_port_role_type role);
 int br_mrp_switchdev_set_in_role(struct net_bridge *br, struct br_mrp *mrp,
@@ -88,4 +87,33 @@ int br_mrp_switchdev_send_in_test(struct net_bridge *br, struct br_mrp *mrp,
 int br_mrp_ring_port_open(struct net_device *dev, u8 loc);
 int br_mrp_in_port_open(struct net_device *dev, u8 loc);
 
+/* MRP protocol data units */
+struct br_mrp_tlv_hdr {
+	__u8 type;
+	__u8 length;
+};
+
+struct br_mrp_common_hdr {
+	__be16 seq_id;
+	__u8 domain[MRP_DOMAIN_UUID_LENGTH];
+};
+
+struct br_mrp_ring_test_hdr {
+	__be16 prio;
+	__u8 sa[ETH_ALEN];
+	__be16 port_role;
+	__be16 state;
+	__be16 transitions;
+	__be32 timestamp;
+} __attribute__((__packed__));
+
+struct br_mrp_in_test_hdr {
+	__be16 id;
+	__u8 sa[ETH_ALEN];
+	__be16 port_role;
+	__be16 state;
+	__be16 transitions;
+	__be32 timestamp;
+} __attribute__((__packed__));
+
 #endif /* _BR_PRIVATE_MRP_H */
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index ee8780080be5..701cad646b20 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -140,7 +140,7 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br,
 	return err == -EOPNOTSUPP ? 0 : err;
 }
 
-/* Returns a master vlan, if it didn't exist it gets created. In all cases a
+/* Returns a master vlan, if it didn't exist it gets created. In all cases
  * a reference is taken to the master vlan before returning.
  */
 static struct net_bridge_vlan *
@@ -266,11 +266,14 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags,
 		}
 
 		masterv = br_vlan_get_master(br, v->vid, extack);
-		if (!masterv)
+		if (!masterv) {
+			err = -ENOMEM;
 			goto out_filt;
+		}
 		v->brvlan = masterv;
 		if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) {
-			v->stats = netdev_alloc_pcpu_stats(struct br_vlan_stats);
+			v->stats =
+			     netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 			if (!v->stats) {
 				err = -ENOMEM;
 				goto out_filt;
@@ -421,7 +424,7 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br,
 			       struct net_bridge_vlan_group *vg,
 			       struct sk_buff *skb)
 {
-	struct br_vlan_stats *stats;
+	struct pcpu_sw_netstats *stats;
 	struct net_bridge_vlan *v;
 	u16 vid;
 
@@ -474,7 +477,7 @@ static bool __allowed_ingress(const struct net_bridge *br,
 			      struct sk_buff *skb, u16 *vid,
 			      u8 *state)
 {
-	struct br_vlan_stats *stats;
+	struct pcpu_sw_netstats *stats;
 	struct net_bridge_vlan *v;
 	bool tagged;
 
@@ -708,7 +711,7 @@ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags, bool *changed,
 	if (!vlan)
 		return -ENOMEM;
 
-	vlan->stats = netdev_alloc_pcpu_stats(struct br_vlan_stats);
+	vlan->stats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
 	if (!vlan->stats) {
 		kfree(vlan);
 		return -ENOMEM;
@@ -853,15 +856,25 @@ EXPORT_SYMBOL_GPL(br_vlan_get_proto);
 
 int __br_vlan_set_proto(struct net_bridge *br, __be16 proto)
 {
+	struct switchdev_attr attr = {
+		.orig_dev = br->dev,
+		.id = SWITCHDEV_ATTR_ID_BRIDGE_VLAN_PROTOCOL,
+		.flags = SWITCHDEV_F_SKIP_EOPNOTSUPP,
+		.u.vlan_protocol = ntohs(proto),
+	};
 	int err = 0;
 	struct net_bridge_port *p;
 	struct net_bridge_vlan *vlan;
 	struct net_bridge_vlan_group *vg;
-	__be16 oldproto;
+	__be16 oldproto = br->vlan_proto;
 
 	if (br->vlan_proto == proto)
 		return 0;
 
+	err = switchdev_port_attr_set(br->dev, &attr);
+	if (err && err != -EOPNOTSUPP)
+		return err;
+
 	/* Add VLANs for the new proto to the device filter. */
 	list_for_each_entry(p, &br->port_list, list) {
 		vg = nbp_vlan_group(p);
@@ -872,7 +885,6 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto)
 		}
 	}
 
-	oldproto = br->vlan_proto;
 	br->vlan_proto = proto;
 
 	recalculate_group_addr(br);
@@ -888,6 +900,9 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto)
 	return 0;
 
 err_filt:
+	attr.u.vlan_protocol = ntohs(oldproto);
+	switchdev_port_attr_set(br->dev, &attr);
+
 	list_for_each_entry_continue_reverse(vlan, &vg->vlan_list, vlist)
 		vlan_vid_del(p->dev, proto, vlan->vid);
 
@@ -1262,14 +1277,14 @@ void nbp_vlan_flush(struct net_bridge_port *port)
 }
 
 void br_vlan_get_stats(const struct net_bridge_vlan *v,
-		       struct br_vlan_stats *stats)
+		       struct pcpu_sw_netstats *stats)
 {
 	int i;
 
 	memset(stats, 0, sizeof(*stats));
 	for_each_possible_cpu(i) {
 		u64 rxpackets, rxbytes, txpackets, txbytes;
-		struct br_vlan_stats *cpu_stats;
+		struct pcpu_sw_netstats *cpu_stats;
 		unsigned int start;
 
 		cpu_stats = per_cpu_ptr(v->stats, i);
@@ -1585,7 +1600,7 @@ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event)
 static bool br_vlan_stats_fill(struct sk_buff *skb,
 			       const struct net_bridge_vlan *v)
 {
-	struct br_vlan_stats stats;
+	struct pcpu_sw_netstats stats;
 	struct nlattr *nest;
 
 	nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY_STATS);
@@ -1897,8 +1912,8 @@ out_err:
 }
 
 static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = {
-	[BRIDGE_VLANDB_ENTRY_INFO]	= { .type = NLA_EXACT_LEN,
-					    .len = sizeof(struct bridge_vlan_info) },
+	[BRIDGE_VLANDB_ENTRY_INFO]	=
+		NLA_POLICY_EXACT_LEN(sizeof(struct bridge_vlan_info)),
 	[BRIDGE_VLANDB_ENTRY_RANGE]	= { .type = NLA_U16 },
 	[BRIDGE_VLANDB_ENTRY_STATE]	= { .type = NLA_U8 },
 	[BRIDGE_VLANDB_ENTRY_TUNNEL_INFO] = { .type = NLA_NESTED },
diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig
index 5040fe43f4b4..ac5372121e60 100644
--- a/net/bridge/netfilter/Kconfig
+++ b/net/bridge/netfilter/Kconfig
@@ -17,7 +17,9 @@ config NFT_BRIDGE_META
 
 config NFT_BRIDGE_REJECT
 	tristate "Netfilter nf_tables bridge reject support"
-	depends on NFT_REJECT && NFT_REJECT_IPV4 && NFT_REJECT_IPV6
+	depends on NFT_REJECT
+	depends on NF_REJECT_IPV4
+	depends on NF_REJECT_IPV6
 	help
 	  Add support to reject packets.
 
diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c
index 12a4f4d93681..3fda71a8579d 100644
--- a/net/bridge/netfilter/ebt_dnat.c
+++ b/net/bridge/netfilter/ebt_dnat.c
@@ -21,7 +21,7 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ebt_nat_info *info = par->targinfo;
 
-	if (skb_ensure_writable(skb, ETH_ALEN))
+	if (skb_ensure_writable(skb, 0))
 		return EBT_DROP;
 
 	ether_addr_copy(eth_hdr(skb)->h_dest, info->mac);
diff --git a/net/bridge/netfilter/ebt_redirect.c b/net/bridge/netfilter/ebt_redirect.c
index 0cad62a4052b..307790562b49 100644
--- a/net/bridge/netfilter/ebt_redirect.c
+++ b/net/bridge/netfilter/ebt_redirect.c
@@ -21,7 +21,7 @@ ebt_redirect_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ebt_redirect_info *info = par->targinfo;
 
-	if (skb_ensure_writable(skb, ETH_ALEN))
+	if (skb_ensure_writable(skb, 0))
 		return EBT_DROP;
 
 	if (xt_hooknum(par) != NF_BR_BROUTING)
diff --git a/net/bridge/netfilter/ebt_snat.c b/net/bridge/netfilter/ebt_snat.c
index 27443bf229a3..7dfbcdfc30e5 100644
--- a/net/bridge/netfilter/ebt_snat.c
+++ b/net/bridge/netfilter/ebt_snat.c
@@ -22,7 +22,7 @@ ebt_snat_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ebt_nat_info *info = par->targinfo;
 
-	if (skb_ensure_writable(skb, ETH_ALEN * 2))
+	if (skb_ensure_writable(skb, 0))
 		return EBT_DROP;
 
 	ether_addr_copy(eth_hdr(skb)->h_source, info->mac);
diff --git a/net/bridge/netfilter/ebt_stp.c b/net/bridge/netfilter/ebt_stp.c
index 0d6d20c9105e..8f68afda5f81 100644
--- a/net/bridge/netfilter/ebt_stp.c
+++ b/net/bridge/netfilter/ebt_stp.c
@@ -15,7 +15,6 @@
 #include <linux/netfilter_bridge/ebt_stp.h>
 
 #define BPDU_TYPE_CONFIG 0
-#define BPDU_TYPE_TCN 0x80
 
 struct stp_header {
 	u8 dsap;
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index deae2c9a0f69..eba0efe64d05 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -39,30 +39,6 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb,
 	}
 }
 
-static int nft_bridge_iphdr_validate(struct sk_buff *skb)
-{
-	struct iphdr *iph;
-	u32 len;
-
-	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
-		return 0;
-
-	iph = ip_hdr(skb);
-	if (iph->ihl < 5 || iph->version != 4)
-		return 0;
-
-	len = ntohs(iph->tot_len);
-	if (skb->len < len)
-		return 0;
-	else if (len < (iph->ihl*4))
-		return 0;
-
-	if (!pskb_may_pull(skb, iph->ihl*4))
-		return 0;
-
-	return 1;
-}
-
 /* We cannot use oldskb->dev, it can be either bridge device (NF_BRIDGE INPUT)
  * or the bridge port (NF_BRIDGE PREROUTING).
  */
@@ -72,29 +48,11 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
 					    int hook)
 {
 	struct sk_buff *nskb;
-	struct iphdr *niph;
-	const struct tcphdr *oth;
-	struct tcphdr _oth;
 
-	if (!nft_bridge_iphdr_validate(oldskb))
-		return;
-
-	oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
-	if (!oth)
-		return;
-
-	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
-			 LL_MAX_HEADER, GFP_ATOMIC);
+	nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
 	if (!nskb)
 		return;
 
-	skb_reserve(nskb, LL_MAX_HEADER);
-	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
-				   net->ipv4.sysctl_ip_default_ttl);
-	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
-	niph->tot_len = htons(nskb->len);
-	ip_send_check(niph);
-
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
 	br_forward(br_port_get_rcu(dev), nskb, false, true);
@@ -106,139 +64,32 @@ static void nft_reject_br_send_v4_unreach(struct net *net,
 					  int hook, u8 code)
 {
 	struct sk_buff *nskb;
-	struct iphdr *niph;
-	struct icmphdr *icmph;
-	unsigned int len;
-	__wsum csum;
-	u8 proto;
-
-	if (!nft_bridge_iphdr_validate(oldskb))
-		return;
-
-	/* IP header checks: fragment. */
-	if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
-		return;
-
-	/* RFC says return as much as we can without exceeding 576 bytes. */
-	len = min_t(unsigned int, 536, oldskb->len);
-
-	if (!pskb_may_pull(oldskb, len))
-		return;
-
-	if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len)))
-		return;
-
-	proto = ip_hdr(oldskb)->protocol;
-
-	if (!skb_csum_unnecessary(oldskb) &&
-	    nf_reject_verify_csum(proto) &&
-	    nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto))
-		return;
 
-	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) +
-			 LL_MAX_HEADER + len, GFP_ATOMIC);
+	nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
 	if (!nskb)
 		return;
 
-	skb_reserve(nskb, LL_MAX_HEADER);
-	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP,
-				   net->ipv4.sysctl_ip_default_ttl);
-
-	skb_reset_transport_header(nskb);
-	icmph = skb_put_zero(nskb, sizeof(struct icmphdr));
-	icmph->type     = ICMP_DEST_UNREACH;
-	icmph->code	= code;
-
-	skb_put_data(nskb, skb_network_header(oldskb), len);
-
-	csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0);
-	icmph->checksum = csum_fold(csum);
-
-	niph->tot_len	= htons(nskb->len);
-	ip_send_check(niph);
-
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
 	br_forward(br_port_get_rcu(dev), nskb, false, true);
 }
 
-static int nft_bridge_ip6hdr_validate(struct sk_buff *skb)
-{
-	struct ipv6hdr *hdr;
-	u32 pkt_len;
-
-	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
-		return 0;
-
-	hdr = ipv6_hdr(skb);
-	if (hdr->version != 6)
-		return 0;
-
-	pkt_len = ntohs(hdr->payload_len);
-	if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
-		return 0;
-
-	return 1;
-}
-
 static void nft_reject_br_send_v6_tcp_reset(struct net *net,
 					    struct sk_buff *oldskb,
 					    const struct net_device *dev,
 					    int hook)
 {
 	struct sk_buff *nskb;
-	const struct tcphdr *oth;
-	struct tcphdr _oth;
-	unsigned int otcplen;
-	struct ipv6hdr *nip6h;
 
-	if (!nft_bridge_ip6hdr_validate(oldskb))
-		return;
-
-	oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook);
-	if (!oth)
-		return;
-
-	nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct tcphdr) +
-			 LL_MAX_HEADER, GFP_ATOMIC);
+	nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
 	if (!nskb)
 		return;
 
-	skb_reserve(nskb, LL_MAX_HEADER);
-	nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
-				     net->ipv6.devconf_all->hop_limit);
-	nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen);
-	nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
-
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
 	br_forward(br_port_get_rcu(dev), nskb, false, true);
 }
 
-static bool reject6_br_csum_ok(struct sk_buff *skb, int hook)
-{
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	int thoff;
-	__be16 fo;
-	u8 proto = ip6h->nexthdr;
-
-	if (skb_csum_unnecessary(skb))
-		return true;
-
-	if (ip6h->payload_len &&
-	    pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
-		return false;
-
-	ip6h = ipv6_hdr(skb);
-	thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
-	if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
-		return false;
-
-	if (!nf_reject_verify_csum(proto))
-		return true;
-
-	return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
-}
 
 static void nft_reject_br_send_v6_unreach(struct net *net,
 					  struct sk_buff *oldskb,
@@ -246,49 +97,11 @@ static void nft_reject_br_send_v6_unreach(struct net *net,
 					  int hook, u8 code)
 {
 	struct sk_buff *nskb;
-	struct ipv6hdr *nip6h;
-	struct icmp6hdr *icmp6h;
-	unsigned int len;
-
-	if (!nft_bridge_ip6hdr_validate(oldskb))
-		return;
 
-	/* Include "As much of invoking packet as possible without the ICMPv6
-	 * packet exceeding the minimum IPv6 MTU" in the ICMP payload.
-	 */
-	len = min_t(unsigned int, 1220, oldskb->len);
-
-	if (!pskb_may_pull(oldskb, len))
-		return;
-
-	if (!reject6_br_csum_ok(oldskb, hook))
-		return;
-
-	nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) +
-			 LL_MAX_HEADER + len, GFP_ATOMIC);
+	nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
 	if (!nskb)
 		return;
 
-	skb_reserve(nskb, LL_MAX_HEADER);
-	nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6,
-				     net->ipv6.devconf_all->hop_limit);
-
-	skb_reset_transport_header(nskb);
-	icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr));
-	icmp6h->icmp6_type = ICMPV6_DEST_UNREACH;
-	icmp6h->icmp6_code = code;
-
-	skb_put_data(nskb, skb_network_header(oldskb), len);
-	nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
-
-	icmp6h->icmp6_cksum =
-		csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr,
-				nskb->len - sizeof(struct ipv6hdr),
-				IPPROTO_ICMPV6,
-				csum_partial(icmp6h,
-					     nskb->len - sizeof(struct ipv6hdr),
-					     0));
-
 	nft_reject_br_push_etherhdr(oldskb, nskb);
 
 	br_forward(br_port_get_rcu(dev), nskb, false, true);
@@ -364,69 +177,13 @@ static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
 						    (1 << NF_BR_LOCAL_IN));
 }
 
-static int nft_reject_bridge_init(const struct nft_ctx *ctx,
-				  const struct nft_expr *expr,
-				  const struct nlattr * const tb[])
-{
-	struct nft_reject *priv = nft_expr_priv(expr);
-	int icmp_code;
-
-	if (tb[NFTA_REJECT_TYPE] == NULL)
-		return -EINVAL;
-
-	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
-	switch (priv->type) {
-	case NFT_REJECT_ICMP_UNREACH:
-	case NFT_REJECT_ICMPX_UNREACH:
-		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
-			return -EINVAL;
-
-		icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
-		if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
-		    icmp_code > NFT_REJECT_ICMPX_MAX)
-			return -EINVAL;
-
-		priv->icmp_code = icmp_code;
-		break;
-	case NFT_REJECT_TCP_RST:
-		break;
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int nft_reject_bridge_dump(struct sk_buff *skb,
-				  const struct nft_expr *expr)
-{
-	const struct nft_reject *priv = nft_expr_priv(expr);
-
-	if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
-		goto nla_put_failure;
-
-	switch (priv->type) {
-	case NFT_REJECT_ICMP_UNREACH:
-	case NFT_REJECT_ICMPX_UNREACH:
-		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
-			goto nla_put_failure;
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
 static struct nft_expr_type nft_reject_bridge_type;
 static const struct nft_expr_ops nft_reject_bridge_ops = {
 	.type		= &nft_reject_bridge_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
 	.eval		= nft_reject_bridge_eval,
-	.init		= nft_reject_bridge_init,
-	.dump		= nft_reject_bridge_dump,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
 	.validate	= nft_reject_bridge_validate,
 };
 
diff --git a/net/caif/cfsrvl.c b/net/caif/cfsrvl.c
index d0a4d0ac7045..9cef9496a707 100644
--- a/net/caif/cfsrvl.c
+++ b/net/caif/cfsrvl.c
@@ -21,7 +21,6 @@
 #define SRVL_FLOW_OFF 0x81
 #define SRVL_FLOW_ON  0x80
 #define SRVL_SET_PIN  0x82
-#define SRVL_CTRL_PKT_SIZE 1
 
 #define container_obj(layr) container_of(layr, struct cfsrvl, layer)
 
diff --git a/net/can/Kconfig b/net/can/Kconfig
index 25436a715db3..7c9958df91d3 100644
--- a/net/can/Kconfig
+++ b/net/can/Kconfig
@@ -55,6 +55,21 @@ config CAN_GW
 
 source "net/can/j1939/Kconfig"
 
+config CAN_ISOTP
+	tristate "ISO 15765-2:2016 CAN transport protocol"
+	help
+	  CAN Transport Protocols offer support for segmented Point-to-Point
+	  communication between CAN nodes via two defined CAN Identifiers.
+	  As CAN frames can only transport a small amount of data bytes
+	  (max. 8 bytes for 'classic' CAN and max. 64 bytes for CAN FD) this
+	  segmentation is needed to transport longer Protocol Data Units (PDU)
+	  as needed e.g. for vehicle diagnosis (UDS, ISO 14229) or IP-over-CAN
+	  traffic.
+	  This protocol driver implements data transfers according to
+	  ISO 15765-2:2016 for 'classic' CAN and CAN FD frame types.
+	  If you want to perform automotive vehicle diagnostic services (UDS),
+	  say 'y'.
+
 source "drivers/net/can/Kconfig"
 
 endif
diff --git a/net/can/Makefile b/net/can/Makefile
index 08bd217fc051..58f2c31c1ef3 100644
--- a/net/can/Makefile
+++ b/net/can/Makefile
@@ -17,3 +17,6 @@ obj-$(CONFIG_CAN_GW)	+= can-gw.o
 can-gw-y		:= gw.o
 
 obj-$(CONFIG_CAN_J1939)	+= j1939/
+
+obj-$(CONFIG_CAN_ISOTP)	+= can-isotp.o
+can-isotp-y		:= isotp.o
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 5c06404bdf3e..837bb8af0ec3 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -338,7 +338,7 @@ static unsigned int effhash(canid_t can_id)
  * can_rcv_list_find - determine optimal filterlist inside device filter struct
  * @can_id: pointer to CAN identifier of a given can_filter
  * @mask: pointer to CAN mask of a given can_filter
- * @d: pointer to the device filter struct
+ * @dev_rcv_lists: pointer to the device filter struct
  *
  * Description:
  *  Returns the optimal filterlist to reduce the filter handling in the
@@ -358,7 +358,7 @@ static unsigned int effhash(canid_t can_id)
  *
  * Return:
  *  Pointer to optimal filterlist for the given can_id/mask pair.
- *  Constistency checked mask.
+ *  Consistency checked mask.
  *  Reduced can_id to have a preprocessed filter compare value.
  */
 static struct hlist_head *can_rcv_list_find(canid_t *can_id, canid_t *mask,
@@ -411,7 +411,7 @@ static struct hlist_head *can_rcv_list_find(canid_t *can_id, canid_t *mask,
 /**
  * can_rx_register - subscribe CAN frames from a specific interface
  * @net: the applicable net namespace
- * @dev: pointer to netdevice (NULL => subcribe from 'all' CAN devices list)
+ * @dev: pointer to netdevice (NULL => subscribe from 'all' CAN devices list)
  * @can_id: CAN identifier (see description)
  * @mask: CAN mask (see description)
  * @func: callback function on filter match
@@ -541,10 +541,13 @@ void can_rx_unregister(struct net *net, struct net_device *dev, canid_t can_id,
 
 	/* Check for bugs in CAN protocol implementations using af_can.c:
 	 * 'rcv' will be NULL if no matching list item was found for removal.
+	 * As this case may potentially happen when closing a socket while
+	 * the notifier for removing the CAN netdev is running we just print
+	 * a warning here.
 	 */
 	if (!rcv) {
-		WARN(1, "BUG: receive list entry not found for dev %s, id %03X, mask %03X\n",
-		     DNAME(dev), can_id, mask);
+		pr_warn("can: receive list entry not found for dev %s, id %03X, mask %03X\n",
+			DNAME(dev), can_id, mask);
 		goto out;
 	}
 
@@ -677,16 +680,25 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU ||
-		     cfd->len > CAN_MAX_DLEN)) {
-		pr_warn_once("PF_CAN: dropped non conform CAN skbuf: dev type %d, len %d, datalen %d\n",
+	if (unlikely(dev->type != ARPHRD_CAN || skb->len != CAN_MTU)) {
+		pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d\n",
+			     dev->type, skb->len);
+		goto free_skb;
+	}
+
+	/* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */
+	if (unlikely(cfd->len > CAN_MAX_DLEN)) {
+		pr_warn_once("PF_CAN: dropped non conform CAN skbuff: dev type %d, len %d, datalen %d\n",
 			     dev->type, skb->len, cfd->len);
-		kfree_skb(skb);
-		return NET_RX_DROP;
+		goto free_skb;
 	}
 
 	can_receive(skb, dev);
 	return NET_RX_SUCCESS;
+
+free_skb:
+	kfree_skb(skb);
+	return NET_RX_DROP;
 }
 
 static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
@@ -694,16 +706,25 @@ static int canfd_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct canfd_frame *cfd = (struct canfd_frame *)skb->data;
 
-	if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU ||
-		     cfd->len > CANFD_MAX_DLEN)) {
-		pr_warn_once("PF_CAN: dropped non conform CAN FD skbuf: dev type %d, len %d, datalen %d\n",
+	if (unlikely(dev->type != ARPHRD_CAN || skb->len != CANFD_MTU)) {
+		pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d\n",
+			     dev->type, skb->len);
+		goto free_skb;
+	}
+
+	/* This check is made separately since cfd->len would be uninitialized if skb->len = 0. */
+	if (unlikely(cfd->len > CANFD_MAX_DLEN)) {
+		pr_warn_once("PF_CAN: dropped non conform CAN FD skbuff: dev type %d, len %d, datalen %d\n",
 			     dev->type, skb->len, cfd->len);
-		kfree_skb(skb);
-		return NET_RX_DROP;
+		goto free_skb;
 	}
 
 	can_receive(skb, dev);
 	return NET_RX_SUCCESS;
+
+free_skb:
+	kfree_skb(skb);
+	return NET_RX_DROP;
 }
 
 /* af_can protocol functions */
@@ -870,12 +891,12 @@ static __init int can_init(void)
 	int err;
 
 	/* check for correct padding to be able to use the structs similarly */
-	BUILD_BUG_ON(offsetof(struct can_frame, can_dlc) !=
+	BUILD_BUG_ON(offsetof(struct can_frame, len) !=
 		     offsetof(struct canfd_frame, len) ||
 		     offsetof(struct can_frame, data) !=
 		     offsetof(struct canfd_frame, data));
 
-	pr_info("can: controller area network core (" CAN_VERSION_STRING ")\n");
+	pr_info("can: controller area network core\n");
 
 	rcv_cache = kmem_cache_create("can_receiver", sizeof(struct receiver),
 				      0, 0, NULL);
diff --git a/net/can/bcm.c b/net/can/bcm.c
index d14ea12affb1..0e5c37be4a2b 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 /*
  * bcm.c - Broadcast Manager to filter/send (cyclic) CAN content
  *
@@ -81,8 +81,6 @@
 		     (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
 		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
-#define CAN_BCM_VERSION "20170425"
-
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Oliver Hartkopp <oliver.hartkopp@volkswagen.de>");
@@ -1696,7 +1694,7 @@ static int __init bcm_module_init(void)
 {
 	int err;
 
-	pr_info("can: broadcast manager protocol (rev " CAN_BCM_VERSION " t)\n");
+	pr_info("can: broadcast manager protocol\n");
 
 	err = can_proto_register(&bcm_can_proto);
 	if (err < 0) {
diff --git a/net/can/gw.c b/net/can/gw.c
index 65d60c93af29..8598d9da0e5f 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 /* gw.c - CAN frame Gateway/Router/Bridge with netlink interface
  *
  * Copyright (c) 2019 Volkswagen Group Electronic Research
@@ -59,7 +59,6 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
-#define CAN_GW_VERSION "20190810"
 #define CAN_GW_NAME "can-gw"
 
 MODULE_DESCRIPTION("PF_CAN netlink gateway");
@@ -200,6 +199,68 @@ static void mod_set_fddata(struct canfd_frame *cf, struct cf_mod *mod)
 	memcpy(cf->data, mod->modframe.set.data, CANFD_MAX_DLEN);
 }
 
+/* retrieve valid CC DLC value and store it into 'len' */
+static void mod_retrieve_ccdlc(struct canfd_frame *cf)
+{
+	struct can_frame *ccf = (struct can_frame *)cf;
+
+	/* len8_dlc is only valid if len == CAN_MAX_DLEN */
+	if (ccf->len != CAN_MAX_DLEN)
+		return;
+
+	/* do we have a valid len8_dlc value from 9 .. 15 ? */
+	if (ccf->len8_dlc > CAN_MAX_DLEN && ccf->len8_dlc <= CAN_MAX_RAW_DLC)
+		ccf->len = ccf->len8_dlc;
+}
+
+/* convert valid CC DLC value in 'len' into struct can_frame elements */
+static void mod_store_ccdlc(struct canfd_frame *cf)
+{
+	struct can_frame *ccf = (struct can_frame *)cf;
+
+	/* clear potential leftovers */
+	ccf->len8_dlc = 0;
+
+	/* plain data length 0 .. 8 - that was easy */
+	if (ccf->len <= CAN_MAX_DLEN)
+		return;
+
+	/* potentially broken values are catched in can_can_gw_rcv() */
+	if (ccf->len > CAN_MAX_RAW_DLC)
+		return;
+
+	/* we have a valid dlc value from 9 .. 15 in ccf->len */
+	ccf->len8_dlc = ccf->len;
+	ccf->len = CAN_MAX_DLEN;
+}
+
+static void mod_and_ccdlc(struct canfd_frame *cf, struct cf_mod *mod)
+{
+	mod_retrieve_ccdlc(cf);
+	mod_and_len(cf, mod);
+	mod_store_ccdlc(cf);
+}
+
+static void mod_or_ccdlc(struct canfd_frame *cf, struct cf_mod *mod)
+{
+	mod_retrieve_ccdlc(cf);
+	mod_or_len(cf, mod);
+	mod_store_ccdlc(cf);
+}
+
+static void mod_xor_ccdlc(struct canfd_frame *cf, struct cf_mod *mod)
+{
+	mod_retrieve_ccdlc(cf);
+	mod_xor_len(cf, mod);
+	mod_store_ccdlc(cf);
+}
+
+static void mod_set_ccdlc(struct canfd_frame *cf, struct cf_mod *mod)
+{
+	mod_set_len(cf, mod);
+	mod_store_ccdlc(cf);
+}
+
 static void canframecpy(struct canfd_frame *dst, struct can_frame *src)
 {
 	/* Copy the struct members separately to ensure that no uninitialized
@@ -208,7 +269,7 @@ static void canframecpy(struct canfd_frame *dst, struct can_frame *src)
 	 */
 
 	dst->can_id = src->can_id;
-	dst->len = src->can_dlc;
+	dst->len = src->len;
 	*(u64 *)dst->data = *(u64 *)src->data;
 }
 
@@ -843,8 +904,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
 			if (mb.modtype & CGW_MOD_ID)
 				mod->modfunc[modidx++] = mod_and_id;
 
-			if (mb.modtype & CGW_MOD_LEN)
-				mod->modfunc[modidx++] = mod_and_len;
+			if (mb.modtype & CGW_MOD_DLC)
+				mod->modfunc[modidx++] = mod_and_ccdlc;
 
 			if (mb.modtype & CGW_MOD_DATA)
 				mod->modfunc[modidx++] = mod_and_data;
@@ -859,8 +920,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
 			if (mb.modtype & CGW_MOD_ID)
 				mod->modfunc[modidx++] = mod_or_id;
 
-			if (mb.modtype & CGW_MOD_LEN)
-				mod->modfunc[modidx++] = mod_or_len;
+			if (mb.modtype & CGW_MOD_DLC)
+				mod->modfunc[modidx++] = mod_or_ccdlc;
 
 			if (mb.modtype & CGW_MOD_DATA)
 				mod->modfunc[modidx++] = mod_or_data;
@@ -875,8 +936,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
 			if (mb.modtype & CGW_MOD_ID)
 				mod->modfunc[modidx++] = mod_xor_id;
 
-			if (mb.modtype & CGW_MOD_LEN)
-				mod->modfunc[modidx++] = mod_xor_len;
+			if (mb.modtype & CGW_MOD_DLC)
+				mod->modfunc[modidx++] = mod_xor_ccdlc;
 
 			if (mb.modtype & CGW_MOD_DATA)
 				mod->modfunc[modidx++] = mod_xor_data;
@@ -891,8 +952,8 @@ static int cgw_parse_attr(struct nlmsghdr *nlh, struct cf_mod *mod,
 			if (mb.modtype & CGW_MOD_ID)
 				mod->modfunc[modidx++] = mod_set_id;
 
-			if (mb.modtype & CGW_MOD_LEN)
-				mod->modfunc[modidx++] = mod_set_len;
+			if (mb.modtype & CGW_MOD_DLC)
+				mod->modfunc[modidx++] = mod_set_ccdlc;
 
 			if (mb.modtype & CGW_MOD_DATA)
 				mod->modfunc[modidx++] = mod_set_data;
@@ -1194,8 +1255,7 @@ static __init int cgw_module_init(void)
 	/* sanitize given module parameter */
 	max_hops = clamp_t(unsigned int, max_hops, CGW_MIN_HOPS, CGW_MAX_HOPS);
 
-	pr_info("can: netlink gateway (rev " CAN_GW_VERSION ") max_hops=%d\n",
-		max_hops);
+	pr_info("can: netlink gateway - max_hops=%d\n",	max_hops);
 
 	ret = register_pernet_subsys(&cangw_pernet_ops);
 	if (ret)
diff --git a/net/can/isotp.c b/net/can/isotp.c
new file mode 100644
index 000000000000..3ef7f78e553b
--- /dev/null
+++ b/net/can/isotp.c
@@ -0,0 +1,1446 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+/* isotp.c - ISO 15765-2 CAN transport protocol for protocol family CAN
+ *
+ * This implementation does not provide ISO-TP specific return values to the
+ * userspace.
+ *
+ * - RX path timeout of data reception leads to -ETIMEDOUT
+ * - RX path SN mismatch leads to -EILSEQ
+ * - RX path data reception with wrong padding leads to -EBADMSG
+ * - TX path flowcontrol reception timeout leads to -ECOMM
+ * - TX path flowcontrol reception overflow leads to -EMSGSIZE
+ * - TX path flowcontrol reception with wrong layout/padding leads to -EBADMSG
+ * - when a transfer (tx) is on the run the next write() blocks until it's done
+ * - use CAN_ISOTP_WAIT_TX_DONE flag to block the caller until the PDU is sent
+ * - as we have static buffers the check whether the PDU fits into the buffer
+ *   is done at FF reception time (no support for sending 'wait frames')
+ * - take care of the tx-queue-len as traffic shaping is still on the TODO list
+ *
+ * Copyright (c) 2020 Volkswagen Group Electronic Research
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. 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.
+ * 3. Neither the name of Volkswagen nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * Alternatively, provided that this notice is retained in full, this
+ * software may be distributed under the terms of the GNU General
+ * Public License ("GPL") version 2, in which case the provisions of the
+ * GPL apply INSTEAD OF those given above.
+ *
+ * The provided data structures and external interfaces from this code
+ * are not restricted to be used by modules with a GPL compatible license.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
+ * DAMAGE.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/hrtimer.h>
+#include <linux/wait.h>
+#include <linux/uio.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/socket.h>
+#include <linux/if_arp.h>
+#include <linux/skbuff.h>
+#include <linux/can.h>
+#include <linux/can/core.h>
+#include <linux/can/skb.h>
+#include <linux/can/isotp.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/net_namespace.h>
+
+MODULE_DESCRIPTION("PF_CAN isotp 15765-2:2016 protocol");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_AUTHOR("Oliver Hartkopp <socketcan@hartkopp.net>");
+MODULE_ALIAS("can-proto-6");
+
+#define SINGLE_MASK(id) (((id) & CAN_EFF_FLAG) ? \
+			 (CAN_EFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG) : \
+			 (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
+
+/* ISO 15765-2:2016 supports more than 4095 byte per ISO PDU as the FF_DL can
+ * take full 32 bit values (4 Gbyte). We would need some good concept to handle
+ * this between user space and kernel space. For now increase the static buffer
+ * to something about 8 kbyte to be able to test this new functionality.
+ */
+#define MAX_MSG_LENGTH 8200
+
+/* N_PCI type values in bits 7-4 of N_PCI bytes */
+#define N_PCI_SF 0x00	/* single frame */
+#define N_PCI_FF 0x10	/* first frame */
+#define N_PCI_CF 0x20	/* consecutive frame */
+#define N_PCI_FC 0x30	/* flow control */
+
+#define N_PCI_SZ 1	/* size of the PCI byte #1 */
+#define SF_PCI_SZ4 1	/* size of SingleFrame PCI including 4 bit SF_DL */
+#define SF_PCI_SZ8 2	/* size of SingleFrame PCI including 8 bit SF_DL */
+#define FF_PCI_SZ12 2	/* size of FirstFrame PCI including 12 bit FF_DL */
+#define FF_PCI_SZ32 6	/* size of FirstFrame PCI including 32 bit FF_DL */
+#define FC_CONTENT_SZ 3	/* flow control content size in byte (FS/BS/STmin) */
+
+#define ISOTP_CHECK_PADDING (CAN_ISOTP_CHK_PAD_LEN | CAN_ISOTP_CHK_PAD_DATA)
+
+/* Flow Status given in FC frame */
+#define ISOTP_FC_CTS 0		/* clear to send */
+#define ISOTP_FC_WT 1		/* wait */
+#define ISOTP_FC_OVFLW 2	/* overflow */
+
+enum {
+	ISOTP_IDLE = 0,
+	ISOTP_WAIT_FIRST_FC,
+	ISOTP_WAIT_FC,
+	ISOTP_WAIT_DATA,
+	ISOTP_SENDING
+};
+
+struct tpcon {
+	int idx;
+	int len;
+	u8 state;
+	u8 bs;
+	u8 sn;
+	u8 ll_dl;
+	u8 buf[MAX_MSG_LENGTH + 1];
+};
+
+struct isotp_sock {
+	struct sock sk;
+	int bound;
+	int ifindex;
+	canid_t txid;
+	canid_t rxid;
+	ktime_t tx_gap;
+	ktime_t lastrxcf_tstamp;
+	struct hrtimer rxtimer, txtimer;
+	struct can_isotp_options opt;
+	struct can_isotp_fc_options rxfc, txfc;
+	struct can_isotp_ll_options ll;
+	u32 force_tx_stmin;
+	u32 force_rx_stmin;
+	struct tpcon rx, tx;
+	struct notifier_block notifier;
+	wait_queue_head_t wait;
+};
+
+static inline struct isotp_sock *isotp_sk(const struct sock *sk)
+{
+	return (struct isotp_sock *)sk;
+}
+
+static enum hrtimer_restart isotp_rx_timer_handler(struct hrtimer *hrtimer)
+{
+	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
+					     rxtimer);
+	struct sock *sk = &so->sk;
+
+	if (so->rx.state == ISOTP_WAIT_DATA) {
+		/* we did not get new data frames in time */
+
+		/* report 'connection timed out' */
+		sk->sk_err = ETIMEDOUT;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+
+		/* reset rx state */
+		so->rx.state = ISOTP_IDLE;
+	}
+
+	return HRTIMER_NORESTART;
+}
+
+static int isotp_send_fc(struct sock *sk, int ae, u8 flowstatus)
+{
+	struct net_device *dev;
+	struct sk_buff *nskb;
+	struct canfd_frame *ncf;
+	struct isotp_sock *so = isotp_sk(sk);
+	int can_send_ret;
+
+	nskb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv), gfp_any());
+	if (!nskb)
+		return 1;
+
+	dev = dev_get_by_index(sock_net(sk), so->ifindex);
+	if (!dev) {
+		kfree_skb(nskb);
+		return 1;
+	}
+
+	can_skb_reserve(nskb);
+	can_skb_prv(nskb)->ifindex = dev->ifindex;
+	can_skb_prv(nskb)->skbcnt = 0;
+
+	nskb->dev = dev;
+	can_skb_set_owner(nskb, sk);
+	ncf = (struct canfd_frame *)nskb->data;
+	skb_put(nskb, so->ll.mtu);
+
+	/* create & send flow control reply */
+	ncf->can_id = so->txid;
+
+	if (so->opt.flags & CAN_ISOTP_TX_PADDING) {
+		memset(ncf->data, so->opt.txpad_content, CAN_MAX_DLEN);
+		ncf->len = CAN_MAX_DLEN;
+	} else {
+		ncf->len = ae + FC_CONTENT_SZ;
+	}
+
+	ncf->data[ae] = N_PCI_FC | flowstatus;
+	ncf->data[ae + 1] = so->rxfc.bs;
+	ncf->data[ae + 2] = so->rxfc.stmin;
+
+	if (ae)
+		ncf->data[0] = so->opt.ext_address;
+
+	if (so->ll.mtu == CANFD_MTU)
+		ncf->flags = so->ll.tx_flags;
+
+	can_send_ret = can_send(nskb, 1);
+	if (can_send_ret)
+		pr_notice_once("can-isotp: %s: can_send_ret %d\n",
+			       __func__, can_send_ret);
+
+	dev_put(dev);
+
+	/* reset blocksize counter */
+	so->rx.bs = 0;
+
+	/* reset last CF frame rx timestamp for rx stmin enforcement */
+	so->lastrxcf_tstamp = ktime_set(0, 0);
+
+	/* start rx timeout watchdog */
+	hrtimer_start(&so->rxtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
+	return 0;
+}
+
+static void isotp_rcv_skb(struct sk_buff *skb, struct sock *sk)
+{
+	struct sockaddr_can *addr = (struct sockaddr_can *)skb->cb;
+
+	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct sockaddr_can));
+
+	memset(addr, 0, sizeof(*addr));
+	addr->can_family = AF_CAN;
+	addr->can_ifindex = skb->dev->ifindex;
+
+	if (sock_queue_rcv_skb(sk, skb) < 0)
+		kfree_skb(skb);
+}
+
+static u8 padlen(u8 datalen)
+{
+	static const u8 plen[] = {
+		8, 8, 8, 8, 8, 8, 8, 8, 8,	/* 0 - 8 */
+		12, 12, 12, 12,			/* 9 - 12 */
+		16, 16, 16, 16,			/* 13 - 16 */
+		20, 20, 20, 20,			/* 17 - 20 */
+		24, 24, 24, 24,			/* 21 - 24 */
+		32, 32, 32, 32, 32, 32, 32, 32,	/* 25 - 32 */
+		48, 48, 48, 48, 48, 48, 48, 48,	/* 33 - 40 */
+		48, 48, 48, 48, 48, 48, 48, 48	/* 41 - 48 */
+	};
+
+	if (datalen > 48)
+		return 64;
+
+	return plen[datalen];
+}
+
+/* check for length optimization and return 1/true when the check fails */
+static int check_optimized(struct canfd_frame *cf, int start_index)
+{
+	/* for CAN_DL <= 8 the start_index is equal to the CAN_DL as the
+	 * padding would start at this point. E.g. if the padding would
+	 * start at cf.data[7] cf->len has to be 7 to be optimal.
+	 * Note: The data[] index starts with zero.
+	 */
+	if (cf->len <= CAN_MAX_DLEN)
+		return (cf->len != start_index);
+
+	/* This relation is also valid in the non-linear DLC range, where
+	 * we need to take care of the minimal next possible CAN_DL.
+	 * The correct check would be (padlen(cf->len) != padlen(start_index)).
+	 * But as cf->len can only take discrete values from 12, .., 64 at this
+	 * point the padlen(cf->len) is always equal to cf->len.
+	 */
+	return (cf->len != padlen(start_index));
+}
+
+/* check padding and return 1/true when the check fails */
+static int check_pad(struct isotp_sock *so, struct canfd_frame *cf,
+		     int start_index, u8 content)
+{
+	int i;
+
+	/* no RX_PADDING value => check length of optimized frame length */
+	if (!(so->opt.flags & CAN_ISOTP_RX_PADDING)) {
+		if (so->opt.flags & CAN_ISOTP_CHK_PAD_LEN)
+			return check_optimized(cf, start_index);
+
+		/* no valid test against empty value => ignore frame */
+		return 1;
+	}
+
+	/* check datalength of correctly padded CAN frame */
+	if ((so->opt.flags & CAN_ISOTP_CHK_PAD_LEN) &&
+	    cf->len != padlen(cf->len))
+		return 1;
+
+	/* check padding content */
+	if (so->opt.flags & CAN_ISOTP_CHK_PAD_DATA) {
+		for (i = start_index; i < cf->len; i++)
+			if (cf->data[i] != content)
+				return 1;
+	}
+	return 0;
+}
+
+static int isotp_rcv_fc(struct isotp_sock *so, struct canfd_frame *cf, int ae)
+{
+	struct sock *sk = &so->sk;
+
+	if (so->tx.state != ISOTP_WAIT_FC &&
+	    so->tx.state != ISOTP_WAIT_FIRST_FC)
+		return 0;
+
+	hrtimer_cancel(&so->txtimer);
+
+	if ((cf->len < ae + FC_CONTENT_SZ) ||
+	    ((so->opt.flags & ISOTP_CHECK_PADDING) &&
+	     check_pad(so, cf, ae + FC_CONTENT_SZ, so->opt.rxpad_content))) {
+		/* malformed PDU - report 'not a data message' */
+		sk->sk_err = EBADMSG;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+
+		so->tx.state = ISOTP_IDLE;
+		wake_up_interruptible(&so->wait);
+		return 1;
+	}
+
+	/* get communication parameters only from the first FC frame */
+	if (so->tx.state == ISOTP_WAIT_FIRST_FC) {
+		so->txfc.bs = cf->data[ae + 1];
+		so->txfc.stmin = cf->data[ae + 2];
+
+		/* fix wrong STmin values according spec */
+		if (so->txfc.stmin > 0x7F &&
+		    (so->txfc.stmin < 0xF1 || so->txfc.stmin > 0xF9))
+			so->txfc.stmin = 0x7F;
+
+		so->tx_gap = ktime_set(0, 0);
+		/* add transmission time for CAN frame N_As */
+		so->tx_gap = ktime_add_ns(so->tx_gap, so->opt.frame_txtime);
+		/* add waiting time for consecutive frames N_Cs */
+		if (so->opt.flags & CAN_ISOTP_FORCE_TXSTMIN)
+			so->tx_gap = ktime_add_ns(so->tx_gap,
+						  so->force_tx_stmin);
+		else if (so->txfc.stmin < 0x80)
+			so->tx_gap = ktime_add_ns(so->tx_gap,
+						  so->txfc.stmin * 1000000);
+		else
+			so->tx_gap = ktime_add_ns(so->tx_gap,
+						  (so->txfc.stmin - 0xF0)
+						  * 100000);
+		so->tx.state = ISOTP_WAIT_FC;
+	}
+
+	switch (cf->data[ae] & 0x0F) {
+	case ISOTP_FC_CTS:
+		so->tx.bs = 0;
+		so->tx.state = ISOTP_SENDING;
+		/* start cyclic timer for sending CF frame */
+		hrtimer_start(&so->txtimer, so->tx_gap,
+			      HRTIMER_MODE_REL_SOFT);
+		break;
+
+	case ISOTP_FC_WT:
+		/* start timer to wait for next FC frame */
+		hrtimer_start(&so->txtimer, ktime_set(1, 0),
+			      HRTIMER_MODE_REL_SOFT);
+		break;
+
+	case ISOTP_FC_OVFLW:
+		/* overflow on receiver side - report 'message too long' */
+		sk->sk_err = EMSGSIZE;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+		fallthrough;
+
+	default:
+		/* stop this tx job */
+		so->tx.state = ISOTP_IDLE;
+		wake_up_interruptible(&so->wait);
+	}
+	return 0;
+}
+
+static int isotp_rcv_sf(struct sock *sk, struct canfd_frame *cf, int pcilen,
+			struct sk_buff *skb, int len)
+{
+	struct isotp_sock *so = isotp_sk(sk);
+	struct sk_buff *nskb;
+
+	hrtimer_cancel(&so->rxtimer);
+	so->rx.state = ISOTP_IDLE;
+
+	if (!len || len > cf->len - pcilen)
+		return 1;
+
+	if ((so->opt.flags & ISOTP_CHECK_PADDING) &&
+	    check_pad(so, cf, pcilen + len, so->opt.rxpad_content)) {
+		/* malformed PDU - report 'not a data message' */
+		sk->sk_err = EBADMSG;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+		return 1;
+	}
+
+	nskb = alloc_skb(len, gfp_any());
+	if (!nskb)
+		return 1;
+
+	memcpy(skb_put(nskb, len), &cf->data[pcilen], len);
+
+	nskb->tstamp = skb->tstamp;
+	nskb->dev = skb->dev;
+	isotp_rcv_skb(nskb, sk);
+	return 0;
+}
+
+static int isotp_rcv_ff(struct sock *sk, struct canfd_frame *cf, int ae)
+{
+	struct isotp_sock *so = isotp_sk(sk);
+	int i;
+	int off;
+	int ff_pci_sz;
+
+	hrtimer_cancel(&so->rxtimer);
+	so->rx.state = ISOTP_IDLE;
+
+	/* get the used sender LL_DL from the (first) CAN frame data length */
+	so->rx.ll_dl = padlen(cf->len);
+
+	/* the first frame has to use the entire frame up to LL_DL length */
+	if (cf->len != so->rx.ll_dl)
+		return 1;
+
+	/* get the FF_DL */
+	so->rx.len = (cf->data[ae] & 0x0F) << 8;
+	so->rx.len += cf->data[ae + 1];
+
+	/* Check for FF_DL escape sequence supporting 32 bit PDU length */
+	if (so->rx.len) {
+		ff_pci_sz = FF_PCI_SZ12;
+	} else {
+		/* FF_DL = 0 => get real length from next 4 bytes */
+		so->rx.len = cf->data[ae + 2] << 24;
+		so->rx.len += cf->data[ae + 3] << 16;
+		so->rx.len += cf->data[ae + 4] << 8;
+		so->rx.len += cf->data[ae + 5];
+		ff_pci_sz = FF_PCI_SZ32;
+	}
+
+	/* take care of a potential SF_DL ESC offset for TX_DL > 8 */
+	off = (so->rx.ll_dl > CAN_MAX_DLEN) ? 1 : 0;
+
+	if (so->rx.len + ae + off + ff_pci_sz < so->rx.ll_dl)
+		return 1;
+
+	if (so->rx.len > MAX_MSG_LENGTH) {
+		/* send FC frame with overflow status */
+		isotp_send_fc(sk, ae, ISOTP_FC_OVFLW);
+		return 1;
+	}
+
+	/* copy the first received data bytes */
+	so->rx.idx = 0;
+	for (i = ae + ff_pci_sz; i < so->rx.ll_dl; i++)
+		so->rx.buf[so->rx.idx++] = cf->data[i];
+
+	/* initial setup for this pdu reception */
+	so->rx.sn = 1;
+	so->rx.state = ISOTP_WAIT_DATA;
+
+	/* no creation of flow control frames */
+	if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
+		return 0;
+
+	/* send our first FC frame */
+	isotp_send_fc(sk, ae, ISOTP_FC_CTS);
+	return 0;
+}
+
+static int isotp_rcv_cf(struct sock *sk, struct canfd_frame *cf, int ae,
+			struct sk_buff *skb)
+{
+	struct isotp_sock *so = isotp_sk(sk);
+	struct sk_buff *nskb;
+	int i;
+
+	if (so->rx.state != ISOTP_WAIT_DATA)
+		return 0;
+
+	/* drop if timestamp gap is less than force_rx_stmin nano secs */
+	if (so->opt.flags & CAN_ISOTP_FORCE_RXSTMIN) {
+		if (ktime_to_ns(ktime_sub(skb->tstamp, so->lastrxcf_tstamp)) <
+		    so->force_rx_stmin)
+			return 0;
+
+		so->lastrxcf_tstamp = skb->tstamp;
+	}
+
+	hrtimer_cancel(&so->rxtimer);
+
+	/* CFs are never longer than the FF */
+	if (cf->len > so->rx.ll_dl)
+		return 1;
+
+	/* CFs have usually the LL_DL length */
+	if (cf->len < so->rx.ll_dl) {
+		/* this is only allowed for the last CF */
+		if (so->rx.len - so->rx.idx > so->rx.ll_dl - ae - N_PCI_SZ)
+			return 1;
+	}
+
+	if ((cf->data[ae] & 0x0F) != so->rx.sn) {
+		/* wrong sn detected - report 'illegal byte sequence' */
+		sk->sk_err = EILSEQ;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+
+		/* reset rx state */
+		so->rx.state = ISOTP_IDLE;
+		return 1;
+	}
+	so->rx.sn++;
+	so->rx.sn %= 16;
+
+	for (i = ae + N_PCI_SZ; i < cf->len; i++) {
+		so->rx.buf[so->rx.idx++] = cf->data[i];
+		if (so->rx.idx >= so->rx.len)
+			break;
+	}
+
+	if (so->rx.idx >= so->rx.len) {
+		/* we are done */
+		so->rx.state = ISOTP_IDLE;
+
+		if ((so->opt.flags & ISOTP_CHECK_PADDING) &&
+		    check_pad(so, cf, i + 1, so->opt.rxpad_content)) {
+			/* malformed PDU - report 'not a data message' */
+			sk->sk_err = EBADMSG;
+			if (!sock_flag(sk, SOCK_DEAD))
+				sk->sk_error_report(sk);
+			return 1;
+		}
+
+		nskb = alloc_skb(so->rx.len, gfp_any());
+		if (!nskb)
+			return 1;
+
+		memcpy(skb_put(nskb, so->rx.len), so->rx.buf,
+		       so->rx.len);
+
+		nskb->tstamp = skb->tstamp;
+		nskb->dev = skb->dev;
+		isotp_rcv_skb(nskb, sk);
+		return 0;
+	}
+
+	/* perform blocksize handling, if enabled */
+	if (!so->rxfc.bs || ++so->rx.bs < so->rxfc.bs) {
+		/* start rx timeout watchdog */
+		hrtimer_start(&so->rxtimer, ktime_set(1, 0),
+			      HRTIMER_MODE_REL_SOFT);
+		return 0;
+	}
+
+	/* no creation of flow control frames */
+	if (so->opt.flags & CAN_ISOTP_LISTEN_MODE)
+		return 0;
+
+	/* we reached the specified blocksize so->rxfc.bs */
+	isotp_send_fc(sk, ae, ISOTP_FC_CTS);
+	return 0;
+}
+
+static void isotp_rcv(struct sk_buff *skb, void *data)
+{
+	struct sock *sk = (struct sock *)data;
+	struct isotp_sock *so = isotp_sk(sk);
+	struct canfd_frame *cf;
+	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
+	u8 n_pci_type, sf_dl;
+
+	/* Strictly receive only frames with the configured MTU size
+	 * => clear separation of CAN2.0 / CAN FD transport channels
+	 */
+	if (skb->len != so->ll.mtu)
+		return;
+
+	cf = (struct canfd_frame *)skb->data;
+
+	/* if enabled: check reception of my configured extended address */
+	if (ae && cf->data[0] != so->opt.rx_ext_address)
+		return;
+
+	n_pci_type = cf->data[ae] & 0xF0;
+
+	if (so->opt.flags & CAN_ISOTP_HALF_DUPLEX) {
+		/* check rx/tx path half duplex expectations */
+		if ((so->tx.state != ISOTP_IDLE && n_pci_type != N_PCI_FC) ||
+		    (so->rx.state != ISOTP_IDLE && n_pci_type == N_PCI_FC))
+			return;
+	}
+
+	switch (n_pci_type) {
+	case N_PCI_FC:
+		/* tx path: flow control frame containing the FC parameters */
+		isotp_rcv_fc(so, cf, ae);
+		break;
+
+	case N_PCI_SF:
+		/* rx path: single frame
+		 *
+		 * As we do not have a rx.ll_dl configuration, we can only test
+		 * if the CAN frames payload length matches the LL_DL == 8
+		 * requirements - no matter if it's CAN 2.0 or CAN FD
+		 */
+
+		/* get the SF_DL from the N_PCI byte */
+		sf_dl = cf->data[ae] & 0x0F;
+
+		if (cf->len <= CAN_MAX_DLEN) {
+			isotp_rcv_sf(sk, cf, SF_PCI_SZ4 + ae, skb, sf_dl);
+		} else {
+			if (skb->len == CANFD_MTU) {
+				/* We have a CAN FD frame and CAN_DL is greater than 8:
+				 * Only frames with the SF_DL == 0 ESC value are valid.
+				 *
+				 * If so take care of the increased SF PCI size
+				 * (SF_PCI_SZ8) to point to the message content behind
+				 * the extended SF PCI info and get the real SF_DL
+				 * length value from the formerly first data byte.
+				 */
+				if (sf_dl == 0)
+					isotp_rcv_sf(sk, cf, SF_PCI_SZ8 + ae, skb,
+						     cf->data[SF_PCI_SZ4 + ae]);
+			}
+		}
+		break;
+
+	case N_PCI_FF:
+		/* rx path: first frame */
+		isotp_rcv_ff(sk, cf, ae);
+		break;
+
+	case N_PCI_CF:
+		/* rx path: consecutive frame */
+		isotp_rcv_cf(sk, cf, ae, skb);
+		break;
+	}
+}
+
+static void isotp_fill_dataframe(struct canfd_frame *cf, struct isotp_sock *so,
+				 int ae, int off)
+{
+	int pcilen = N_PCI_SZ + ae + off;
+	int space = so->tx.ll_dl - pcilen;
+	int num = min_t(int, so->tx.len - so->tx.idx, space);
+	int i;
+
+	cf->can_id = so->txid;
+	cf->len = num + pcilen;
+
+	if (num < space) {
+		if (so->opt.flags & CAN_ISOTP_TX_PADDING) {
+			/* user requested padding */
+			cf->len = padlen(cf->len);
+			memset(cf->data, so->opt.txpad_content, cf->len);
+		} else if (cf->len > CAN_MAX_DLEN) {
+			/* mandatory padding for CAN FD frames */
+			cf->len = padlen(cf->len);
+			memset(cf->data, CAN_ISOTP_DEFAULT_PAD_CONTENT,
+			       cf->len);
+		}
+	}
+
+	for (i = 0; i < num; i++)
+		cf->data[pcilen + i] = so->tx.buf[so->tx.idx++];
+
+	if (ae)
+		cf->data[0] = so->opt.ext_address;
+}
+
+static void isotp_create_fframe(struct canfd_frame *cf, struct isotp_sock *so,
+				int ae)
+{
+	int i;
+	int ff_pci_sz;
+
+	cf->can_id = so->txid;
+	cf->len = so->tx.ll_dl;
+	if (ae)
+		cf->data[0] = so->opt.ext_address;
+
+	/* create N_PCI bytes with 12/32 bit FF_DL data length */
+	if (so->tx.len > 4095) {
+		/* use 32 bit FF_DL notation */
+		cf->data[ae] = N_PCI_FF;
+		cf->data[ae + 1] = 0;
+		cf->data[ae + 2] = (u8)(so->tx.len >> 24) & 0xFFU;
+		cf->data[ae + 3] = (u8)(so->tx.len >> 16) & 0xFFU;
+		cf->data[ae + 4] = (u8)(so->tx.len >> 8) & 0xFFU;
+		cf->data[ae + 5] = (u8)so->tx.len & 0xFFU;
+		ff_pci_sz = FF_PCI_SZ32;
+	} else {
+		/* use 12 bit FF_DL notation */
+		cf->data[ae] = (u8)(so->tx.len >> 8) | N_PCI_FF;
+		cf->data[ae + 1] = (u8)so->tx.len & 0xFFU;
+		ff_pci_sz = FF_PCI_SZ12;
+	}
+
+	/* add first data bytes depending on ae */
+	for (i = ae + ff_pci_sz; i < so->tx.ll_dl; i++)
+		cf->data[i] = so->tx.buf[so->tx.idx++];
+
+	so->tx.sn = 1;
+	so->tx.state = ISOTP_WAIT_FIRST_FC;
+}
+
+static enum hrtimer_restart isotp_tx_timer_handler(struct hrtimer *hrtimer)
+{
+	struct isotp_sock *so = container_of(hrtimer, struct isotp_sock,
+					     txtimer);
+	struct sock *sk = &so->sk;
+	struct sk_buff *skb;
+	struct net_device *dev;
+	struct canfd_frame *cf;
+	enum hrtimer_restart restart = HRTIMER_NORESTART;
+	int can_send_ret;
+	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
+
+	switch (so->tx.state) {
+	case ISOTP_WAIT_FC:
+	case ISOTP_WAIT_FIRST_FC:
+
+		/* we did not get any flow control frame in time */
+
+		/* report 'communication error on send' */
+		sk->sk_err = ECOMM;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+
+		/* reset tx state */
+		so->tx.state = ISOTP_IDLE;
+		wake_up_interruptible(&so->wait);
+		break;
+
+	case ISOTP_SENDING:
+
+		/* push out the next segmented pdu */
+		dev = dev_get_by_index(sock_net(sk), so->ifindex);
+		if (!dev)
+			break;
+
+isotp_tx_burst:
+		skb = alloc_skb(so->ll.mtu + sizeof(struct can_skb_priv),
+				GFP_ATOMIC);
+		if (!skb) {
+			dev_put(dev);
+			break;
+		}
+
+		can_skb_reserve(skb);
+		can_skb_prv(skb)->ifindex = dev->ifindex;
+		can_skb_prv(skb)->skbcnt = 0;
+
+		cf = (struct canfd_frame *)skb->data;
+		skb_put(skb, so->ll.mtu);
+
+		/* create consecutive frame */
+		isotp_fill_dataframe(cf, so, ae, 0);
+
+		/* place consecutive frame N_PCI in appropriate index */
+		cf->data[ae] = N_PCI_CF | so->tx.sn++;
+		so->tx.sn %= 16;
+		so->tx.bs++;
+
+		if (so->ll.mtu == CANFD_MTU)
+			cf->flags = so->ll.tx_flags;
+
+		skb->dev = dev;
+		can_skb_set_owner(skb, sk);
+
+		can_send_ret = can_send(skb, 1);
+		if (can_send_ret)
+			pr_notice_once("can-isotp: %s: can_send_ret %d\n",
+				       __func__, can_send_ret);
+
+		if (so->tx.idx >= so->tx.len) {
+			/* we are done */
+			so->tx.state = ISOTP_IDLE;
+			dev_put(dev);
+			wake_up_interruptible(&so->wait);
+			break;
+		}
+
+		if (so->txfc.bs && so->tx.bs >= so->txfc.bs) {
+			/* stop and wait for FC */
+			so->tx.state = ISOTP_WAIT_FC;
+			dev_put(dev);
+			hrtimer_set_expires(&so->txtimer,
+					    ktime_add(ktime_get(),
+						      ktime_set(1, 0)));
+			restart = HRTIMER_RESTART;
+			break;
+		}
+
+		/* no gap between data frames needed => use burst mode */
+		if (!so->tx_gap)
+			goto isotp_tx_burst;
+
+		/* start timer to send next data frame with correct delay */
+		dev_put(dev);
+		hrtimer_set_expires(&so->txtimer,
+				    ktime_add(ktime_get(), so->tx_gap));
+		restart = HRTIMER_RESTART;
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+	}
+
+	return restart;
+}
+
+static int isotp_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
+{
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+	struct sk_buff *skb;
+	struct net_device *dev;
+	struct canfd_frame *cf;
+	int ae = (so->opt.flags & CAN_ISOTP_EXTEND_ADDR) ? 1 : 0;
+	int wait_tx_done = (so->opt.flags & CAN_ISOTP_WAIT_TX_DONE) ? 1 : 0;
+	int off;
+	int err;
+
+	if (!so->bound)
+		return -EADDRNOTAVAIL;
+
+	/* we do not support multiple buffers - for now */
+	if (so->tx.state != ISOTP_IDLE || wq_has_sleeper(&so->wait)) {
+		if (msg->msg_flags & MSG_DONTWAIT)
+			return -EAGAIN;
+
+		/* wait for complete transmission of current pdu */
+		wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+	}
+
+	if (!size || size > MAX_MSG_LENGTH)
+		return -EINVAL;
+
+	/* take care of a potential SF_DL ESC offset for TX_DL > 8 */
+	off = (so->tx.ll_dl > CAN_MAX_DLEN) ? 1 : 0;
+
+	/* does the given data fit into a single frame for SF_BROADCAST? */
+	if ((so->opt.flags & CAN_ISOTP_SF_BROADCAST) &&
+	    (size > so->tx.ll_dl - SF_PCI_SZ4 - ae - off))
+		return -EINVAL;
+
+	err = memcpy_from_msg(so->tx.buf, msg, size);
+	if (err < 0)
+		return err;
+
+	dev = dev_get_by_index(sock_net(sk), so->ifindex);
+	if (!dev)
+		return -ENXIO;
+
+	skb = sock_alloc_send_skb(sk, so->ll.mtu + sizeof(struct can_skb_priv),
+				  msg->msg_flags & MSG_DONTWAIT, &err);
+	if (!skb) {
+		dev_put(dev);
+		return err;
+	}
+
+	can_skb_reserve(skb);
+	can_skb_prv(skb)->ifindex = dev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
+
+	so->tx.state = ISOTP_SENDING;
+	so->tx.len = size;
+	so->tx.idx = 0;
+
+	cf = (struct canfd_frame *)skb->data;
+	skb_put(skb, so->ll.mtu);
+
+	/* check for single frame transmission depending on TX_DL */
+	if (size <= so->tx.ll_dl - SF_PCI_SZ4 - ae - off) {
+		/* The message size generally fits into a SingleFrame - good.
+		 *
+		 * SF_DL ESC offset optimization:
+		 *
+		 * When TX_DL is greater 8 but the message would still fit
+		 * into a 8 byte CAN frame, we can omit the offset.
+		 * This prevents a protocol caused length extension from
+		 * CAN_DL = 8 to CAN_DL = 12 due to the SF_SL ESC handling.
+		 */
+		if (size <= CAN_MAX_DLEN - SF_PCI_SZ4 - ae)
+			off = 0;
+
+		isotp_fill_dataframe(cf, so, ae, off);
+
+		/* place single frame N_PCI w/o length in appropriate index */
+		cf->data[ae] = N_PCI_SF;
+
+		/* place SF_DL size value depending on the SF_DL ESC offset */
+		if (off)
+			cf->data[SF_PCI_SZ4 + ae] = size;
+		else
+			cf->data[ae] |= size;
+
+		so->tx.state = ISOTP_IDLE;
+		wake_up_interruptible(&so->wait);
+
+		/* don't enable wait queue for a single frame transmission */
+		wait_tx_done = 0;
+	} else {
+		/* send first frame and wait for FC */
+
+		isotp_create_fframe(cf, so, ae);
+
+		/* start timeout for FC */
+		hrtimer_start(&so->txtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT);
+	}
+
+	/* send the first or only CAN frame */
+	if (so->ll.mtu == CANFD_MTU)
+		cf->flags = so->ll.tx_flags;
+
+	skb->dev = dev;
+	skb->sk = sk;
+	err = can_send(skb, 1);
+	dev_put(dev);
+	if (err) {
+		pr_notice_once("can-isotp: %s: can_send_ret %d\n",
+			       __func__, err);
+		return err;
+	}
+
+	if (wait_tx_done) {
+		/* wait for complete transmission of current pdu */
+		wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+	}
+
+	return size;
+}
+
+static int isotp_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
+			 int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sk_buff *skb;
+	int err = 0;
+	int noblock;
+
+	noblock = flags & MSG_DONTWAIT;
+	flags &= ~MSG_DONTWAIT;
+
+	skb = skb_recv_datagram(sk, flags, noblock, &err);
+	if (!skb)
+		return err;
+
+	if (size < skb->len)
+		msg->msg_flags |= MSG_TRUNC;
+	else
+		size = skb->len;
+
+	err = memcpy_to_msg(msg, skb->data, size);
+	if (err < 0) {
+		skb_free_datagram(sk, skb);
+		return err;
+	}
+
+	sock_recv_timestamp(msg, sk, skb);
+
+	if (msg->msg_name) {
+		msg->msg_namelen = sizeof(struct sockaddr_can);
+		memcpy(msg->msg_name, skb->cb, msg->msg_namelen);
+	}
+
+	skb_free_datagram(sk, skb);
+
+	return size;
+}
+
+static int isotp_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so;
+	struct net *net;
+
+	if (!sk)
+		return 0;
+
+	so = isotp_sk(sk);
+	net = sock_net(sk);
+
+	/* wait for complete transmission of current pdu */
+	wait_event_interruptible(so->wait, so->tx.state == ISOTP_IDLE);
+
+	unregister_netdevice_notifier(&so->notifier);
+
+	lock_sock(sk);
+
+	hrtimer_cancel(&so->txtimer);
+	hrtimer_cancel(&so->rxtimer);
+
+	/* remove current filters & unregister */
+	if (so->bound && (!(so->opt.flags & CAN_ISOTP_SF_BROADCAST))) {
+		if (so->ifindex) {
+			struct net_device *dev;
+
+			dev = dev_get_by_index(net, so->ifindex);
+			if (dev) {
+				can_rx_unregister(net, dev, so->rxid,
+						  SINGLE_MASK(so->rxid),
+						  isotp_rcv, sk);
+				dev_put(dev);
+			}
+		}
+	}
+
+	so->ifindex = 0;
+	so->bound = 0;
+
+	sock_orphan(sk);
+	sock->sk = NULL;
+
+	release_sock(sk);
+	sock_put(sk);
+
+	return 0;
+}
+
+static int isotp_bind(struct socket *sock, struct sockaddr *uaddr, int len)
+{
+	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+	struct net *net = sock_net(sk);
+	int ifindex;
+	struct net_device *dev;
+	int err = 0;
+	int notify_enetdown = 0;
+	int do_rx_reg = 1;
+
+	if (len < CAN_REQUIRED_SIZE(struct sockaddr_can, can_addr.tp))
+		return -EINVAL;
+
+	/* do not register frame reception for functional addressing */
+	if (so->opt.flags & CAN_ISOTP_SF_BROADCAST)
+		do_rx_reg = 0;
+
+	/* do not validate rx address for functional addressing */
+	if (do_rx_reg) {
+		if (addr->can_addr.tp.rx_id == addr->can_addr.tp.tx_id)
+			return -EADDRNOTAVAIL;
+
+		if (addr->can_addr.tp.rx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG))
+			return -EADDRNOTAVAIL;
+	}
+
+	if (addr->can_addr.tp.tx_id & (CAN_ERR_FLAG | CAN_RTR_FLAG))
+		return -EADDRNOTAVAIL;
+
+	if (!addr->can_ifindex)
+		return -ENODEV;
+
+	lock_sock(sk);
+
+	if (so->bound && addr->can_ifindex == so->ifindex &&
+	    addr->can_addr.tp.rx_id == so->rxid &&
+	    addr->can_addr.tp.tx_id == so->txid)
+		goto out;
+
+	dev = dev_get_by_index(net, addr->can_ifindex);
+	if (!dev) {
+		err = -ENODEV;
+		goto out;
+	}
+	if (dev->type != ARPHRD_CAN) {
+		dev_put(dev);
+		err = -ENODEV;
+		goto out;
+	}
+	if (dev->mtu < so->ll.mtu) {
+		dev_put(dev);
+		err = -EINVAL;
+		goto out;
+	}
+	if (!(dev->flags & IFF_UP))
+		notify_enetdown = 1;
+
+	ifindex = dev->ifindex;
+
+	if (do_rx_reg)
+		can_rx_register(net, dev, addr->can_addr.tp.rx_id,
+				SINGLE_MASK(addr->can_addr.tp.rx_id),
+				isotp_rcv, sk, "isotp", sk);
+
+	dev_put(dev);
+
+	if (so->bound && do_rx_reg) {
+		/* unregister old filter */
+		if (so->ifindex) {
+			dev = dev_get_by_index(net, so->ifindex);
+			if (dev) {
+				can_rx_unregister(net, dev, so->rxid,
+						  SINGLE_MASK(so->rxid),
+						  isotp_rcv, sk);
+				dev_put(dev);
+			}
+		}
+	}
+
+	/* switch to new settings */
+	so->ifindex = ifindex;
+	so->rxid = addr->can_addr.tp.rx_id;
+	so->txid = addr->can_addr.tp.tx_id;
+	so->bound = 1;
+
+out:
+	release_sock(sk);
+
+	if (notify_enetdown) {
+		sk->sk_err = ENETDOWN;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+	}
+
+	return err;
+}
+
+static int isotp_getname(struct socket *sock, struct sockaddr *uaddr, int peer)
+{
+	struct sockaddr_can *addr = (struct sockaddr_can *)uaddr;
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+
+	if (peer)
+		return -EOPNOTSUPP;
+
+	memset(addr, 0, sizeof(*addr));
+	addr->can_family = AF_CAN;
+	addr->can_ifindex = so->ifindex;
+	addr->can_addr.tp.rx_id = so->rxid;
+	addr->can_addr.tp.tx_id = so->txid;
+
+	return sizeof(*addr);
+}
+
+static int isotp_setsockopt(struct socket *sock, int level, int optname,
+			    sockptr_t optval, unsigned int optlen)
+{
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+	int ret = 0;
+
+	if (level != SOL_CAN_ISOTP)
+		return -EINVAL;
+
+	if (so->bound)
+		return -EISCONN;
+
+	switch (optname) {
+	case CAN_ISOTP_OPTS:
+		if (optlen != sizeof(struct can_isotp_options))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&so->opt, optval, optlen))
+			return -EFAULT;
+
+		/* no separate rx_ext_address is given => use ext_address */
+		if (!(so->opt.flags & CAN_ISOTP_RX_EXT_ADDR))
+			so->opt.rx_ext_address = so->opt.ext_address;
+		break;
+
+	case CAN_ISOTP_RECV_FC:
+		if (optlen != sizeof(struct can_isotp_fc_options))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&so->rxfc, optval, optlen))
+			return -EFAULT;
+		break;
+
+	case CAN_ISOTP_TX_STMIN:
+		if (optlen != sizeof(u32))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&so->force_tx_stmin, optval, optlen))
+			return -EFAULT;
+		break;
+
+	case CAN_ISOTP_RX_STMIN:
+		if (optlen != sizeof(u32))
+			return -EINVAL;
+
+		if (copy_from_sockptr(&so->force_rx_stmin, optval, optlen))
+			return -EFAULT;
+		break;
+
+	case CAN_ISOTP_LL_OPTS:
+		if (optlen == sizeof(struct can_isotp_ll_options)) {
+			struct can_isotp_ll_options ll;
+
+			if (copy_from_sockptr(&ll, optval, optlen))
+				return -EFAULT;
+
+			/* check for correct ISO 11898-1 DLC data length */
+			if (ll.tx_dl != padlen(ll.tx_dl))
+				return -EINVAL;
+
+			if (ll.mtu != CAN_MTU && ll.mtu != CANFD_MTU)
+				return -EINVAL;
+
+			if (ll.mtu == CAN_MTU && ll.tx_dl > CAN_MAX_DLEN)
+				return -EINVAL;
+
+			memcpy(&so->ll, &ll, sizeof(ll));
+
+			/* set ll_dl for tx path to similar place as for rx */
+			so->tx.ll_dl = ll.tx_dl;
+		} else {
+			return -EINVAL;
+		}
+		break;
+
+	default:
+		ret = -ENOPROTOOPT;
+	}
+
+	return ret;
+}
+
+static int isotp_getsockopt(struct socket *sock, int level, int optname,
+			    char __user *optval, int __user *optlen)
+{
+	struct sock *sk = sock->sk;
+	struct isotp_sock *so = isotp_sk(sk);
+	int len;
+	void *val;
+
+	if (level != SOL_CAN_ISOTP)
+		return -EINVAL;
+	if (get_user(len, optlen))
+		return -EFAULT;
+	if (len < 0)
+		return -EINVAL;
+
+	switch (optname) {
+	case CAN_ISOTP_OPTS:
+		len = min_t(int, len, sizeof(struct can_isotp_options));
+		val = &so->opt;
+		break;
+
+	case CAN_ISOTP_RECV_FC:
+		len = min_t(int, len, sizeof(struct can_isotp_fc_options));
+		val = &so->rxfc;
+		break;
+
+	case CAN_ISOTP_TX_STMIN:
+		len = min_t(int, len, sizeof(u32));
+		val = &so->force_tx_stmin;
+		break;
+
+	case CAN_ISOTP_RX_STMIN:
+		len = min_t(int, len, sizeof(u32));
+		val = &so->force_rx_stmin;
+		break;
+
+	case CAN_ISOTP_LL_OPTS:
+		len = min_t(int, len, sizeof(struct can_isotp_ll_options));
+		val = &so->ll;
+		break;
+
+	default:
+		return -ENOPROTOOPT;
+	}
+
+	if (put_user(len, optlen))
+		return -EFAULT;
+	if (copy_to_user(optval, val, len))
+		return -EFAULT;
+	return 0;
+}
+
+static int isotp_notifier(struct notifier_block *nb, unsigned long msg,
+			  void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct isotp_sock *so = container_of(nb, struct isotp_sock, notifier);
+	struct sock *sk = &so->sk;
+
+	if (!net_eq(dev_net(dev), sock_net(sk)))
+		return NOTIFY_DONE;
+
+	if (dev->type != ARPHRD_CAN)
+		return NOTIFY_DONE;
+
+	if (so->ifindex != dev->ifindex)
+		return NOTIFY_DONE;
+
+	switch (msg) {
+	case NETDEV_UNREGISTER:
+		lock_sock(sk);
+		/* remove current filters & unregister */
+		if (so->bound && (!(so->opt.flags & CAN_ISOTP_SF_BROADCAST)))
+			can_rx_unregister(dev_net(dev), dev, so->rxid,
+					  SINGLE_MASK(so->rxid),
+					  isotp_rcv, sk);
+
+		so->ifindex = 0;
+		so->bound  = 0;
+		release_sock(sk);
+
+		sk->sk_err = ENODEV;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+		break;
+
+	case NETDEV_DOWN:
+		sk->sk_err = ENETDOWN;
+		if (!sock_flag(sk, SOCK_DEAD))
+			sk->sk_error_report(sk);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int isotp_init(struct sock *sk)
+{
+	struct isotp_sock *so = isotp_sk(sk);
+
+	so->ifindex = 0;
+	so->bound = 0;
+
+	so->opt.flags = CAN_ISOTP_DEFAULT_FLAGS;
+	so->opt.ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS;
+	so->opt.rx_ext_address = CAN_ISOTP_DEFAULT_EXT_ADDRESS;
+	so->opt.rxpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT;
+	so->opt.txpad_content = CAN_ISOTP_DEFAULT_PAD_CONTENT;
+	so->opt.frame_txtime = CAN_ISOTP_DEFAULT_FRAME_TXTIME;
+	so->rxfc.bs = CAN_ISOTP_DEFAULT_RECV_BS;
+	so->rxfc.stmin = CAN_ISOTP_DEFAULT_RECV_STMIN;
+	so->rxfc.wftmax = CAN_ISOTP_DEFAULT_RECV_WFTMAX;
+	so->ll.mtu = CAN_ISOTP_DEFAULT_LL_MTU;
+	so->ll.tx_dl = CAN_ISOTP_DEFAULT_LL_TX_DL;
+	so->ll.tx_flags = CAN_ISOTP_DEFAULT_LL_TX_FLAGS;
+
+	/* set ll_dl for tx path to similar place as for rx */
+	so->tx.ll_dl = so->ll.tx_dl;
+
+	so->rx.state = ISOTP_IDLE;
+	so->tx.state = ISOTP_IDLE;
+
+	hrtimer_init(&so->rxtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	so->rxtimer.function = isotp_rx_timer_handler;
+	hrtimer_init(&so->txtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+	so->txtimer.function = isotp_tx_timer_handler;
+
+	init_waitqueue_head(&so->wait);
+
+	so->notifier.notifier_call = isotp_notifier;
+	register_netdevice_notifier(&so->notifier);
+
+	return 0;
+}
+
+static int isotp_sock_no_ioctlcmd(struct socket *sock, unsigned int cmd,
+				  unsigned long arg)
+{
+	/* no ioctls for socket layer -> hand it down to NIC layer */
+	return -ENOIOCTLCMD;
+}
+
+static const struct proto_ops isotp_ops = {
+	.family = PF_CAN,
+	.release = isotp_release,
+	.bind = isotp_bind,
+	.connect = sock_no_connect,
+	.socketpair = sock_no_socketpair,
+	.accept = sock_no_accept,
+	.getname = isotp_getname,
+	.poll = datagram_poll,
+	.ioctl = isotp_sock_no_ioctlcmd,
+	.gettstamp = sock_gettstamp,
+	.listen = sock_no_listen,
+	.shutdown = sock_no_shutdown,
+	.setsockopt = isotp_setsockopt,
+	.getsockopt = isotp_getsockopt,
+	.sendmsg = isotp_sendmsg,
+	.recvmsg = isotp_recvmsg,
+	.mmap = sock_no_mmap,
+	.sendpage = sock_no_sendpage,
+};
+
+static struct proto isotp_proto __read_mostly = {
+	.name = "CAN_ISOTP",
+	.owner = THIS_MODULE,
+	.obj_size = sizeof(struct isotp_sock),
+	.init = isotp_init,
+};
+
+static const struct can_proto isotp_can_proto = {
+	.type = SOCK_DGRAM,
+	.protocol = CAN_ISOTP,
+	.ops = &isotp_ops,
+	.prot = &isotp_proto,
+};
+
+static __init int isotp_module_init(void)
+{
+	int err;
+
+	pr_info("can: isotp protocol\n");
+
+	err = can_proto_register(&isotp_can_proto);
+	if (err < 0)
+		pr_err("can: registration of isotp protocol failed\n");
+
+	return err;
+}
+
+static __exit void isotp_module_exit(void)
+{
+	can_proto_unregister(&isotp_can_proto);
+}
+
+module_init(isotp_module_init);
+module_exit(isotp_module_exit);
diff --git a/net/can/j1939/main.c b/net/can/j1939/main.c
index 137054bff9ec..bb914d8b4216 100644
--- a/net/can/j1939/main.c
+++ b/net/can/j1939/main.c
@@ -62,7 +62,7 @@ static void j1939_can_recv(struct sk_buff *iskb, void *data)
 	skb_pull(skb, J1939_CAN_HDR);
 
 	/* fix length, set to dlc, with 8 maximum */
-	skb_trim(skb, min_t(uint8_t, cf->can_dlc, 8));
+	skb_trim(skb, min_t(uint8_t, cf->len, 8));
 
 	/* set addr */
 	skcb = j1939_skb_to_cb(skb);
@@ -335,7 +335,7 @@ int j1939_send_one(struct j1939_priv *priv, struct sk_buff *skb)
 		canid |= skcb->addr.da << 8;
 
 	cf->can_id = canid;
-	cf->can_dlc = dlc;
+	cf->len = dlc;
 
 	return can_send(skb, 1);
 
diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c
index 1be4c898b2fa..f23966526a88 100644
--- a/net/can/j1939/socket.c
+++ b/net/can/j1939/socket.c
@@ -475,6 +475,12 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len)
 			goto out_release_sock;
 		}
 
+		if (!(ndev->flags & IFF_UP)) {
+			dev_put(ndev);
+			ret = -ENETDOWN;
+			goto out_release_sock;
+		}
+
 		priv = j1939_netdev_start(ndev);
 		dev_put(ndev);
 		if (IS_ERR(priv)) {
diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
index 0cec4152f979..e09d087ba240 100644
--- a/net/can/j1939/transport.c
+++ b/net/can/j1939/transport.c
@@ -580,6 +580,7 @@ sk_buff *j1939_tp_tx_dat_new(struct j1939_priv *priv,
 	skb->dev = priv->ndev;
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = priv->ndev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
 	/* reserve CAN header */
 	skb_reserve(skb, offsetof(struct can_frame, data));
 
@@ -1487,6 +1488,7 @@ j1939_session *j1939_session_fresh_new(struct j1939_priv *priv,
 	skb->dev = priv->ndev;
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = priv->ndev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
 	skcb = j1939_skb_to_cb(skb);
 	memcpy(skcb, rel_skcb, sizeof(*skcb));
 
diff --git a/net/can/proc.c b/net/can/proc.c
index e6881bfc3ed1..5ea8695f507e 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 /*
  * proc.c - procfs support for Protocol family CAN core module
  *
@@ -54,7 +54,6 @@
  * proc filenames for the PF_CAN core
  */
 
-#define CAN_PROC_VERSION     "version"
 #define CAN_PROC_STATS       "stats"
 #define CAN_PROC_RESET_STATS "reset_stats"
 #define CAN_PROC_RCVLIST_ALL "rcvlist_all"
@@ -293,12 +292,6 @@ static int can_reset_stats_proc_show(struct seq_file *m, void *v)
 	return 0;
 }
 
-static int can_version_proc_show(struct seq_file *m, void *v)
-{
-	seq_printf(m, "%s\n", CAN_VERSION_STRING);
-	return 0;
-}
-
 static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx,
 					     struct net_device *dev,
 					     struct can_dev_rcv_lists *dev_rcv_lists)
@@ -441,8 +434,6 @@ void can_init_proc(struct net *net)
 	}
 
 	/* own procfs entries from the AF_CAN core */
-	net->can.pde_version = proc_create_net_single(CAN_PROC_VERSION, 0644,
-			net->can.proc_dir, can_version_proc_show, NULL);
 	net->can.pde_stats = proc_create_net_single(CAN_PROC_STATS, 0644,
 			net->can.proc_dir, can_stats_proc_show, NULL);
 	net->can.pde_reset_stats = proc_create_net_single(CAN_PROC_RESET_STATS,
@@ -471,8 +462,8 @@ void can_init_proc(struct net *net)
  */
 void can_remove_proc(struct net *net)
 {
-	if (net->can.pde_version)
-		remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir);
+	if (!net->can.proc_dir)
+		return;
 
 	if (net->can.pde_stats)
 		remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir);
@@ -498,6 +489,5 @@ void can_remove_proc(struct net *net)
 	if (net->can.pde_rcvlist_sff)
 		remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir);
 
-	if (net->can.proc_dir)
-		remove_proc_entry("can", net->proc_net);
+	remove_proc_entry("can", net->proc_net);
 }
diff --git a/net/can/raw.c b/net/can/raw.c
index 94a9405658dc..6ec8aa1d0da4 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
 /* raw.c - Raw sockets for protocol family CAN
  *
  * Copyright (c) 2002-2007 Volkswagen Group Electronic Research
@@ -55,8 +55,6 @@
 #include <net/sock.h>
 #include <net/net_namespace.h>
 
-#define CAN_RAW_VERSION CAN_VERSION
-
 MODULE_DESCRIPTION("PF_CAN raw protocol");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Urs Thuermann <urs.thuermann@volkswagen.de>");
@@ -154,16 +152,16 @@ static void raw_rcv(struct sk_buff *oskb, void *data)
 	if (!skb)
 		return;
 
-	/*  Put the datagram to the queue so that raw_recvmsg() can
-	 *  get it from there.  We need to pass the interface index to
-	 *  raw_recvmsg().  We pass a whole struct sockaddr_can in skb->cb
-	 *  containing the interface index.
+	/* Put the datagram to the queue so that raw_recvmsg() can get
+	 * it from there. We need to pass the interface index to
+	 * raw_recvmsg(). We pass a whole struct sockaddr_can in
+	 * skb->cb containing the interface index.
 	 */
 
 	sock_skb_cb_check_size(sizeof(struct sockaddr_can));
 	addr = (struct sockaddr_can *)skb->cb;
 	memset(addr, 0, sizeof(*addr));
-	addr->can_family  = AF_CAN;
+	addr->can_family = AF_CAN;
 	addr->can_ifindex = skb->dev->ifindex;
 
 	/* add CAN specific message flags for raw_recvmsg() */
@@ -290,8 +288,8 @@ static int raw_notifier(struct notifier_block *nb,
 			kfree(ro->filter);
 
 		ro->ifindex = 0;
-		ro->bound   = 0;
-		ro->count   = 0;
+		ro->bound = 0;
+		ro->count = 0;
 		release_sock(sk);
 
 		sk->sk_err = ENODEV;
@@ -374,8 +372,8 @@ static int raw_release(struct socket *sock)
 		kfree(ro->filter);
 
 	ro->ifindex = 0;
-	ro->bound   = 0;
-	ro->count   = 0;
+	ro->bound = 0;
+	ro->count = 0;
 	free_percpu(ro->uniq);
 
 	sock_orphan(sk);
@@ -773,7 +771,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	skb_setup_tx_timestamp(skb, sk->sk_tsflags);
 
 	skb->dev = dev;
-	skb->sk  = sk;
+	skb->sk = sk;
 	skb->priority = sk->sk_priority;
 
 	err = can_send(skb, ro->loopback);
@@ -801,8 +799,12 @@ static int raw_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	int err = 0;
 	int noblock;
 
-	noblock =  flags & MSG_DONTWAIT;
-	flags   &= ~MSG_DONTWAIT;
+	noblock = flags & MSG_DONTWAIT;
+	flags &= ~MSG_DONTWAIT;
+
+	if (flags & MSG_ERRQUEUE)
+		return sock_recv_errqueue(sk, msg, size,
+					  SOL_CAN_RAW, SCM_CAN_RAW_ERRQUEUE);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
 	if (!skb)
@@ -881,7 +883,7 @@ static __init int raw_module_init(void)
 {
 	int err;
 
-	pr_info("can: raw protocol (rev " CAN_RAW_VERSION ")\n");
+	pr_info("can: raw protocol\n");
 
 	err = can_proto_register(&raw_can_proto);
 	if (err < 0)
diff --git a/net/ceph/Kconfig b/net/ceph/Kconfig
index f36f9a3a4e20..c5c4eef3a9ff 100644
--- a/net/ceph/Kconfig
+++ b/net/ceph/Kconfig
@@ -5,6 +5,9 @@ config CEPH_LIB
 	select LIBCRC32C
 	select CRYPTO_AES
 	select CRYPTO_CBC
+	select CRYPTO_GCM
+	select CRYPTO_HMAC
+	select CRYPTO_SHA256
 	select CRYPTO
 	select KEYS
 	default n
diff --git a/net/ceph/Makefile b/net/ceph/Makefile
index ce09bb4fb249..8802a0c0155d 100644
--- a/net/ceph/Makefile
+++ b/net/ceph/Makefile
@@ -14,4 +14,5 @@ libceph-y := ceph_common.o messenger.o msgpool.o buffer.o pagelist.o \
 	crypto.o armor.o \
 	auth_x.o \
 	ceph_strings.o ceph_hash.o \
-	pagevec.o snapshot.o string_table.o
+	pagevec.o snapshot.o string_table.o \
+	messenger_v1.o messenger_v2.o
diff --git a/net/ceph/auth.c b/net/ceph/auth.c
index fbeee068ea14..eb261aa5fe18 100644
--- a/net/ceph/auth.c
+++ b/net/ceph/auth.c
@@ -21,28 +21,31 @@ static u32 supported_protocols[] = {
 	CEPH_AUTH_CEPHX
 };
 
-static int ceph_auth_init_protocol(struct ceph_auth_client *ac, int protocol)
+static int init_protocol(struct ceph_auth_client *ac, int proto)
 {
-	switch (protocol) {
+	dout("%s proto %d\n", __func__, proto);
+
+	switch (proto) {
 	case CEPH_AUTH_NONE:
 		return ceph_auth_none_init(ac);
 	case CEPH_AUTH_CEPHX:
 		return ceph_x_init(ac);
 	default:
-		return -ENOENT;
+		pr_err("bad auth protocol %d\n", proto);
+		return -EINVAL;
 	}
 }
 
 /*
  * setup, teardown.
  */
-struct ceph_auth_client *ceph_auth_init(const char *name, const struct ceph_crypto_key *key)
+struct ceph_auth_client *ceph_auth_init(const char *name,
+					const struct ceph_crypto_key *key,
+					const int *con_modes)
 {
 	struct ceph_auth_client *ac;
 	int ret;
 
-	dout("auth_init name '%s'\n", name);
-
 	ret = -ENOMEM;
 	ac = kzalloc(sizeof(*ac), GFP_NOFS);
 	if (!ac)
@@ -54,8 +57,12 @@ struct ceph_auth_client *ceph_auth_init(const char *name, const struct ceph_cryp
 		ac->name = name;
 	else
 		ac->name = CEPH_AUTH_NAME_DEFAULT;
-	dout("auth_init name %s\n", ac->name);
 	ac->key = key;
+	ac->preferred_mode = con_modes[0];
+	ac->fallback_mode = con_modes[1];
+
+	dout("%s name '%s' preferred_mode %d fallback_mode %d\n", __func__,
+	     ac->name, ac->preferred_mode, ac->fallback_mode);
 	return ac;
 
 out:
@@ -145,31 +152,35 @@ bad:
 	goto out;
 }
 
-static int ceph_build_auth_request(struct ceph_auth_client *ac,
-				   void *msg_buf, size_t msg_len)
+static int build_request(struct ceph_auth_client *ac, bool add_header,
+			 void *buf, int buf_len)
 {
-	struct ceph_mon_request_header *monhdr = msg_buf;
-	void *p = monhdr + 1;
-	void *end = msg_buf + msg_len;
+	void *end = buf + buf_len;
+	void *p;
 	int ret;
 
-	monhdr->have_version = 0;
-	monhdr->session_mon = cpu_to_le16(-1);
-	monhdr->session_mon_tid = 0;
-
-	ceph_encode_32(&p, ac->protocol);
+	p = buf;
+	if (add_header) {
+		/* struct ceph_mon_request_header + protocol */
+		ceph_encode_64_safe(&p, end, 0, e_range);
+		ceph_encode_16_safe(&p, end, -1, e_range);
+		ceph_encode_64_safe(&p, end, 0, e_range);
+		ceph_encode_32_safe(&p, end, ac->protocol, e_range);
+	}
 
+	ceph_encode_need(&p, end, sizeof(u32), e_range);
 	ret = ac->ops->build_request(ac, p + sizeof(u32), end);
 	if (ret < 0) {
-		pr_err("error %d building auth method %s request\n", ret,
-		       ac->ops->name);
-		goto out;
+		pr_err("auth protocol '%s' building request failed: %d\n",
+		       ceph_auth_proto_name(ac->protocol), ret);
+		return ret;
 	}
 	dout(" built request %d bytes\n", ret);
 	ceph_encode_32(&p, ret);
-	ret = p + ret - msg_buf;
-out:
-	return ret;
+	return p + ret - buf;
+
+e_range:
+	return -ERANGE;
 }
 
 /*
@@ -229,10 +240,10 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 			ac->ops = NULL;
 		}
 		if (ac->protocol != protocol) {
-			ret = ceph_auth_init_protocol(ac, protocol);
+			ret = init_protocol(ac, protocol);
 			if (ret) {
-				pr_err("error %d on auth protocol %d init\n",
-				       ret, protocol);
+				pr_err("auth protocol '%s' init failed: %d\n",
+				       ceph_auth_proto_name(protocol), ret);
 				goto out;
 			}
 		}
@@ -240,12 +251,13 @@ int ceph_handle_auth_reply(struct ceph_auth_client *ac,
 		ac->negotiating = false;
 	}
 
-	ret = ac->ops->handle_reply(ac, result, payload, payload_end);
-	if (ret == -EAGAIN) {
-		ret = ceph_build_auth_request(ac, reply_buf, reply_len);
-	} else if (ret) {
-		pr_err("auth method '%s' error %d\n", ac->ops->name, ret);
-	}
+	ret = ac->ops->handle_reply(ac, result, payload, payload_end,
+				    NULL, NULL, NULL, NULL);
+	if (ret == -EAGAIN)
+		ret = build_request(ac, true, reply_buf, reply_len);
+	else if (ret)
+		pr_err("auth protocol '%s' mauth authentication failed: %d\n",
+		       ceph_auth_proto_name(ac->protocol), result);
 
 out:
 	mutex_unlock(&ac->mutex);
@@ -264,7 +276,7 @@ int ceph_build_auth(struct ceph_auth_client *ac,
 
 	mutex_lock(&ac->mutex);
 	if (ac->ops->should_authenticate(ac))
-		ret = ceph_build_auth_request(ac, msg_buf, msg_len);
+		ret = build_request(ac, true, msg_buf, msg_len);
 	mutex_unlock(&ac->mutex);
 	return ret;
 }
@@ -281,19 +293,38 @@ int ceph_auth_is_authenticated(struct ceph_auth_client *ac)
 }
 EXPORT_SYMBOL(ceph_auth_is_authenticated);
 
-int ceph_auth_create_authorizer(struct ceph_auth_client *ac,
-				int peer_type,
-				struct ceph_auth_handshake *auth)
+int __ceph_auth_get_authorizer(struct ceph_auth_client *ac,
+			       struct ceph_auth_handshake *auth,
+			       int peer_type, bool force_new,
+			       int *proto, int *pref_mode, int *fallb_mode)
 {
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&ac->mutex);
-	if (ac->ops && ac->ops->create_authorizer)
+	if (force_new && auth->authorizer) {
+		ceph_auth_destroy_authorizer(auth->authorizer);
+		auth->authorizer = NULL;
+	}
+	if (!auth->authorizer)
 		ret = ac->ops->create_authorizer(ac, peer_type, auth);
+	else if (ac->ops->update_authorizer)
+		ret = ac->ops->update_authorizer(ac, peer_type, auth);
+	else
+		ret = 0;
+	if (ret)
+		goto out;
+
+	*proto = ac->protocol;
+	if (pref_mode && fallb_mode) {
+		*pref_mode = ac->preferred_mode;
+		*fallb_mode = ac->fallback_mode;
+	}
+
+out:
 	mutex_unlock(&ac->mutex);
 	return ret;
 }
-EXPORT_SYMBOL(ceph_auth_create_authorizer);
+EXPORT_SYMBOL(__ceph_auth_get_authorizer);
 
 void ceph_auth_destroy_authorizer(struct ceph_authorizer *a)
 {
@@ -301,20 +332,6 @@ void ceph_auth_destroy_authorizer(struct ceph_authorizer *a)
 }
 EXPORT_SYMBOL(ceph_auth_destroy_authorizer);
 
-int ceph_auth_update_authorizer(struct ceph_auth_client *ac,
-				int peer_type,
-				struct ceph_auth_handshake *a)
-{
-	int ret = 0;
-
-	mutex_lock(&ac->mutex);
-	if (ac->ops && ac->ops->update_authorizer)
-		ret = ac->ops->update_authorizer(ac, peer_type, a);
-	mutex_unlock(&ac->mutex);
-	return ret;
-}
-EXPORT_SYMBOL(ceph_auth_update_authorizer);
-
 int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac,
 				       struct ceph_authorizer *a,
 				       void *challenge_buf,
@@ -332,13 +349,18 @@ int ceph_auth_add_authorizer_challenge(struct ceph_auth_client *ac,
 EXPORT_SYMBOL(ceph_auth_add_authorizer_challenge);
 
 int ceph_auth_verify_authorizer_reply(struct ceph_auth_client *ac,
-				      struct ceph_authorizer *a)
+				      struct ceph_authorizer *a,
+				      void *reply, int reply_len,
+				      u8 *session_key, int *session_key_len,
+				      u8 *con_secret, int *con_secret_len)
 {
 	int ret = 0;
 
 	mutex_lock(&ac->mutex);
 	if (ac->ops && ac->ops->verify_authorizer_reply)
-		ret = ac->ops->verify_authorizer_reply(ac, a);
+		ret = ac->ops->verify_authorizer_reply(ac, a,
+			reply, reply_len, session_key, session_key_len,
+			con_secret, con_secret_len);
 	mutex_unlock(&ac->mutex);
 	return ret;
 }
@@ -352,3 +374,279 @@ void ceph_auth_invalidate_authorizer(struct ceph_auth_client *ac, int peer_type)
 	mutex_unlock(&ac->mutex);
 }
 EXPORT_SYMBOL(ceph_auth_invalidate_authorizer);
+
+/*
+ * msgr2 authentication
+ */
+
+static bool contains(const int *arr, int cnt, int val)
+{
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		if (arr[i] == val)
+			return true;
+	}
+
+	return false;
+}
+
+static int encode_con_modes(void **p, void *end, int pref_mode, int fallb_mode)
+{
+	WARN_ON(pref_mode == CEPH_CON_MODE_UNKNOWN);
+	if (fallb_mode != CEPH_CON_MODE_UNKNOWN) {
+		ceph_encode_32_safe(p, end, 2, e_range);
+		ceph_encode_32_safe(p, end, pref_mode, e_range);
+		ceph_encode_32_safe(p, end, fallb_mode, e_range);
+	} else {
+		ceph_encode_32_safe(p, end, 1, e_range);
+		ceph_encode_32_safe(p, end, pref_mode, e_range);
+	}
+
+	return 0;
+
+e_range:
+	return -ERANGE;
+}
+
+/*
+ * Similar to ceph_auth_build_hello().
+ */
+int ceph_auth_get_request(struct ceph_auth_client *ac, void *buf, int buf_len)
+{
+	int proto = ac->key ? CEPH_AUTH_CEPHX : CEPH_AUTH_NONE;
+	void *end = buf + buf_len;
+	void *lenp;
+	void *p;
+	int ret;
+
+	mutex_lock(&ac->mutex);
+	if (ac->protocol == CEPH_AUTH_UNKNOWN) {
+		ret = init_protocol(ac, proto);
+		if (ret) {
+			pr_err("auth protocol '%s' init failed: %d\n",
+			       ceph_auth_proto_name(proto), ret);
+			goto out;
+		}
+	} else {
+		WARN_ON(ac->protocol != proto);
+		ac->ops->reset(ac);
+	}
+
+	p = buf;
+	ceph_encode_32_safe(&p, end, ac->protocol, e_range);
+	ret = encode_con_modes(&p, end, ac->preferred_mode, ac->fallback_mode);
+	if (ret)
+		goto out;
+
+	lenp = p;
+	p += 4;  /* space for len */
+
+	ceph_encode_8_safe(&p, end, CEPH_AUTH_MODE_MON, e_range);
+	ret = ceph_auth_entity_name_encode(ac->name, &p, end);
+	if (ret)
+		goto out;
+
+	ceph_encode_64_safe(&p, end, ac->global_id, e_range);
+	ceph_encode_32(&lenp, p - lenp - 4);
+	ret = p - buf;
+
+out:
+	mutex_unlock(&ac->mutex);
+	return ret;
+
+e_range:
+	ret = -ERANGE;
+	goto out;
+}
+
+int ceph_auth_handle_reply_more(struct ceph_auth_client *ac, void *reply,
+				int reply_len, void *buf, int buf_len)
+{
+	int ret;
+
+	mutex_lock(&ac->mutex);
+	ret = ac->ops->handle_reply(ac, 0, reply, reply + reply_len,
+				    NULL, NULL, NULL, NULL);
+	if (ret == -EAGAIN)
+		ret = build_request(ac, false, buf, buf_len);
+	else
+		WARN_ON(ret >= 0);
+	mutex_unlock(&ac->mutex);
+	return ret;
+}
+
+int ceph_auth_handle_reply_done(struct ceph_auth_client *ac,
+				u64 global_id, void *reply, int reply_len,
+				u8 *session_key, int *session_key_len,
+				u8 *con_secret, int *con_secret_len)
+{
+	int ret;
+
+	mutex_lock(&ac->mutex);
+	if (global_id && ac->global_id != global_id) {
+		dout("%s global_id %llu -> %llu\n", __func__, ac->global_id,
+		     global_id);
+		ac->global_id = global_id;
+	}
+
+	ret = ac->ops->handle_reply(ac, 0, reply, reply + reply_len,
+				    session_key, session_key_len,
+				    con_secret, con_secret_len);
+	mutex_unlock(&ac->mutex);
+	return ret;
+}
+
+bool ceph_auth_handle_bad_method(struct ceph_auth_client *ac,
+				 int used_proto, int result,
+				 const int *allowed_protos, int proto_cnt,
+				 const int *allowed_modes, int mode_cnt)
+{
+	mutex_lock(&ac->mutex);
+	WARN_ON(used_proto != ac->protocol);
+
+	if (result == -EOPNOTSUPP) {
+		if (!contains(allowed_protos, proto_cnt, ac->protocol)) {
+			pr_err("auth protocol '%s' not allowed\n",
+			       ceph_auth_proto_name(ac->protocol));
+			goto not_allowed;
+		}
+		if (!contains(allowed_modes, mode_cnt, ac->preferred_mode) &&
+		    (ac->fallback_mode == CEPH_CON_MODE_UNKNOWN ||
+		     !contains(allowed_modes, mode_cnt, ac->fallback_mode))) {
+			pr_err("preferred mode '%s' not allowed\n",
+			       ceph_con_mode_name(ac->preferred_mode));
+			if (ac->fallback_mode == CEPH_CON_MODE_UNKNOWN)
+				pr_err("no fallback mode\n");
+			else
+				pr_err("fallback mode '%s' not allowed\n",
+				       ceph_con_mode_name(ac->fallback_mode));
+			goto not_allowed;
+		}
+	}
+
+	WARN_ON(result == -EOPNOTSUPP || result >= 0);
+	pr_err("auth protocol '%s' msgr authentication failed: %d\n",
+	       ceph_auth_proto_name(ac->protocol), result);
+
+	mutex_unlock(&ac->mutex);
+	return true;
+
+not_allowed:
+	mutex_unlock(&ac->mutex);
+	return false;
+}
+
+int ceph_auth_get_authorizer(struct ceph_auth_client *ac,
+			     struct ceph_auth_handshake *auth,
+			     int peer_type, void *buf, int *buf_len)
+{
+	void *end = buf + *buf_len;
+	int pref_mode, fallb_mode;
+	int proto;
+	void *p;
+	int ret;
+
+	ret = __ceph_auth_get_authorizer(ac, auth, peer_type, true, &proto,
+					 &pref_mode, &fallb_mode);
+	if (ret)
+		return ret;
+
+	p = buf;
+	ceph_encode_32_safe(&p, end, proto, e_range);
+	ret = encode_con_modes(&p, end, pref_mode, fallb_mode);
+	if (ret)
+		return ret;
+
+	ceph_encode_32_safe(&p, end, auth->authorizer_buf_len, e_range);
+	*buf_len = p - buf;
+	return 0;
+
+e_range:
+	return -ERANGE;
+}
+EXPORT_SYMBOL(ceph_auth_get_authorizer);
+
+int ceph_auth_handle_svc_reply_more(struct ceph_auth_client *ac,
+				    struct ceph_auth_handshake *auth,
+				    void *reply, int reply_len,
+				    void *buf, int *buf_len)
+{
+	void *end = buf + *buf_len;
+	void *p;
+	int ret;
+
+	ret = ceph_auth_add_authorizer_challenge(ac, auth->authorizer,
+						 reply, reply_len);
+	if (ret)
+		return ret;
+
+	p = buf;
+	ceph_encode_32_safe(&p, end, auth->authorizer_buf_len, e_range);
+	*buf_len = p - buf;
+	return 0;
+
+e_range:
+	return -ERANGE;
+}
+EXPORT_SYMBOL(ceph_auth_handle_svc_reply_more);
+
+int ceph_auth_handle_svc_reply_done(struct ceph_auth_client *ac,
+				    struct ceph_auth_handshake *auth,
+				    void *reply, int reply_len,
+				    u8 *session_key, int *session_key_len,
+				    u8 *con_secret, int *con_secret_len)
+{
+	return ceph_auth_verify_authorizer_reply(ac, auth->authorizer,
+		reply, reply_len, session_key, session_key_len,
+		con_secret, con_secret_len);
+}
+EXPORT_SYMBOL(ceph_auth_handle_svc_reply_done);
+
+bool ceph_auth_handle_bad_authorizer(struct ceph_auth_client *ac,
+				     int peer_type, int used_proto, int result,
+				     const int *allowed_protos, int proto_cnt,
+				     const int *allowed_modes, int mode_cnt)
+{
+	mutex_lock(&ac->mutex);
+	WARN_ON(used_proto != ac->protocol);
+
+	if (result == -EOPNOTSUPP) {
+		if (!contains(allowed_protos, proto_cnt, ac->protocol)) {
+			pr_err("auth protocol '%s' not allowed by %s\n",
+			       ceph_auth_proto_name(ac->protocol),
+			       ceph_entity_type_name(peer_type));
+			goto not_allowed;
+		}
+		if (!contains(allowed_modes, mode_cnt, ac->preferred_mode) &&
+		    (ac->fallback_mode == CEPH_CON_MODE_UNKNOWN ||
+		     !contains(allowed_modes, mode_cnt, ac->fallback_mode))) {
+			pr_err("preferred mode '%s' not allowed by %s\n",
+			       ceph_con_mode_name(ac->preferred_mode),
+			       ceph_entity_type_name(peer_type));
+			if (ac->fallback_mode == CEPH_CON_MODE_UNKNOWN)
+				pr_err("no fallback mode\n");
+			else
+				pr_err("fallback mode '%s' not allowed by %s\n",
+				       ceph_con_mode_name(ac->fallback_mode),
+				       ceph_entity_type_name(peer_type));
+			goto not_allowed;
+		}
+	}
+
+	WARN_ON(result == -EOPNOTSUPP || result >= 0);
+	pr_err("auth protocol '%s' authorization to %s failed: %d\n",
+	       ceph_auth_proto_name(ac->protocol),
+	       ceph_entity_type_name(peer_type), result);
+
+	if (ac->ops->invalidate_authorizer)
+		ac->ops->invalidate_authorizer(ac, peer_type);
+
+	mutex_unlock(&ac->mutex);
+	return true;
+
+not_allowed:
+	mutex_unlock(&ac->mutex);
+	return false;
+}
+EXPORT_SYMBOL(ceph_auth_handle_bad_authorizer);
diff --git a/net/ceph/auth_none.c b/net/ceph/auth_none.c
index edb7042479ed..70e86e462250 100644
--- a/net/ceph/auth_none.c
+++ b/net/ceph/auth_none.c
@@ -70,7 +70,9 @@ static int build_request(struct ceph_auth_client *ac, void *buf, void *end)
  * authenticate state, so nothing happens here.
  */
 static int handle_reply(struct ceph_auth_client *ac, int result,
-			void *buf, void *end)
+			void *buf, void *end, u8 *session_key,
+			int *session_key_len, u8 *con_secret,
+			int *con_secret_len)
 {
 	struct ceph_auth_none_info *xi = ac->private;
 
@@ -116,7 +118,6 @@ static int ceph_auth_none_create_authorizer(
 }
 
 static const struct ceph_auth_client_ops ceph_auth_none_ops = {
-	.name = "none",
 	.reset = reset,
 	.destroy = destroy,
 	.is_authenticated = is_authenticated,
diff --git a/net/ceph/auth_x.c b/net/ceph/auth_x.c
index b52732337ca6..ca44c327bace 100644
--- a/net/ceph/auth_x.c
+++ b/net/ceph/auth_x.c
@@ -22,12 +22,15 @@ static void ceph_x_validate_tickets(struct ceph_auth_client *ac, int *pneed);
 static int ceph_x_is_authenticated(struct ceph_auth_client *ac)
 {
 	struct ceph_x_info *xi = ac->private;
-	int need;
+	int missing;
+	int need;  /* missing + need renewal */
 
 	ceph_x_validate_tickets(ac, &need);
-	dout("ceph_x_is_authenticated want=%d need=%d have=%d\n",
-	     ac->want_keys, need, xi->have_keys);
-	return (ac->want_keys & xi->have_keys) == ac->want_keys;
+	missing = ac->want_keys & ~xi->have_keys;
+	WARN_ON((need & missing) != missing);
+	dout("%s want 0x%x have 0x%x missing 0x%x -> %d\n", __func__,
+	     ac->want_keys, xi->have_keys, missing, !missing);
+	return !missing;
 }
 
 static int ceph_x_should_authenticate(struct ceph_auth_client *ac)
@@ -36,9 +39,9 @@ static int ceph_x_should_authenticate(struct ceph_auth_client *ac)
 	int need;
 
 	ceph_x_validate_tickets(ac, &need);
-	dout("ceph_x_should_authenticate want=%d need=%d have=%d\n",
-	     ac->want_keys, need, xi->have_keys);
-	return need != 0;
+	dout("%s want 0x%x have 0x%x need 0x%x -> %d\n", __func__,
+	     ac->want_keys, xi->have_keys, need, !!need);
+	return !!need;
 }
 
 static int ceph_x_encrypt_offset(void)
@@ -197,7 +200,7 @@ static int process_one_ticket(struct ceph_auth_client *ac,
 	dout(" decrypted %d bytes\n", ret);
 	dend = dp + ret;
 
-	tkt_struct_v = ceph_decode_8(&dp);
+	ceph_decode_8_safe(&dp, dend, tkt_struct_v, bad);
 	if (tkt_struct_v != 1)
 		goto bad;
 
@@ -205,6 +208,7 @@ static int process_one_ticket(struct ceph_auth_client *ac,
 	if (ret)
 		goto out;
 
+	ceph_decode_need(&dp, dend, sizeof(struct ceph_timespec), bad);
 	ceph_decode_timespec64(&validity, dp);
 	dp += sizeof(struct ceph_timespec);
 	new_expires = ktime_get_real_seconds() + validity.tv_sec;
@@ -265,22 +269,21 @@ out:
 
 static int ceph_x_proc_ticket_reply(struct ceph_auth_client *ac,
 				    struct ceph_crypto_key *secret,
-				    void *buf, void *end)
+				    void **p, void *end)
 {
-	void *p = buf;
 	u8 reply_struct_v;
 	u32 num;
 	int ret;
 
-	ceph_decode_8_safe(&p, end, reply_struct_v, bad);
+	ceph_decode_8_safe(p, end, reply_struct_v, bad);
 	if (reply_struct_v != 1)
 		return -EINVAL;
 
-	ceph_decode_32_safe(&p, end, num, bad);
+	ceph_decode_32_safe(p, end, num, bad);
 	dout("%d tickets\n", num);
 
 	while (num--) {
-		ret = process_one_ticket(ac, secret, &p, end);
+		ret = process_one_ticket(ac, secret, p, end);
 		if (ret)
 			return ret;
 	}
@@ -379,6 +382,7 @@ static int ceph_x_build_authorizer(struct ceph_auth_client *ac,
 		}
 	}
 	au->service = th->service;
+	WARN_ON(!th->secret_id);
 	au->secret_id = th->secret_id;
 
 	msg_a = au->buf->vec.iov_base;
@@ -442,9 +446,10 @@ static bool need_key(struct ceph_x_ticket_handler *th)
 
 static bool have_key(struct ceph_x_ticket_handler *th)
 {
-	if (th->have_key) {
-		if (ktime_get_real_seconds() >= th->expires)
-			th->have_key = false;
+	if (th->have_key && ktime_get_real_seconds() >= th->expires) {
+		dout("ticket %d (%s) secret_id %llu expired\n", th->service,
+		     ceph_entity_type_name(th->service), th->secret_id);
+		th->have_key = false;
 	}
 
 	return th->have_key;
@@ -486,6 +491,7 @@ static int ceph_x_build_request(struct ceph_auth_client *ac,
 	struct ceph_x_info *xi = ac->private;
 	int need;
 	struct ceph_x_request_header *head = buf;
+	void *p;
 	int ret;
 	struct ceph_x_ticket_handler *th =
 		get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH);
@@ -494,18 +500,17 @@ static int ceph_x_build_request(struct ceph_auth_client *ac,
 		return PTR_ERR(th);
 
 	ceph_x_validate_tickets(ac, &need);
-
-	dout("build_request want %x have %x need %x\n",
-	     ac->want_keys, xi->have_keys, need);
+	dout("%s want 0x%x have 0x%x need 0x%x\n", __func__, ac->want_keys,
+	     xi->have_keys, need);
 
 	if (need & CEPH_ENTITY_TYPE_AUTH) {
 		struct ceph_x_authenticate *auth = (void *)(head + 1);
-		void *p = auth + 1;
 		void *enc_buf = xi->auth_authorizer.enc_buf;
 		struct ceph_x_challenge_blob *blob = enc_buf +
 							ceph_x_encrypt_offset();
 		u64 *u;
 
+		p = auth + 1;
 		if (p > end)
 			return -ERANGE;
 
@@ -521,7 +526,7 @@ static int ceph_x_build_request(struct ceph_auth_client *ac,
 		if (ret < 0)
 			return ret;
 
-		auth->struct_v = 1;
+		auth->struct_v = 2;  /* nautilus+ */
 		auth->key = 0;
 		for (u = (u64 *)enc_buf; u + 1 <= (u64 *)(enc_buf + ret); u++)
 			auth->key ^= *(__le64 *)u;
@@ -534,39 +539,137 @@ static int ceph_x_build_request(struct ceph_auth_client *ac,
 		if (ret < 0)
 			return ret;
 
+		/* nautilus+: request service tickets at the same time */
+		need = ac->want_keys & ~CEPH_ENTITY_TYPE_AUTH;
+		WARN_ON(!need);
+		ceph_encode_32_safe(&p, end, need, e_range);
 		return p - buf;
 	}
 
 	if (need) {
-		void *p = head + 1;
-		struct ceph_x_service_ticket_request *req;
-
-		if (p > end)
-			return -ERANGE;
-		head->op = cpu_to_le16(CEPHX_GET_PRINCIPAL_SESSION_KEY);
-
+		dout(" get_principal_session_key\n");
 		ret = ceph_x_build_authorizer(ac, th, &xi->auth_authorizer);
 		if (ret)
 			return ret;
-		ceph_encode_copy(&p, xi->auth_authorizer.buf->vec.iov_base,
-				 xi->auth_authorizer.buf->vec.iov_len);
 
-		req = p;
-		req->keys = cpu_to_le32(need);
-		p += sizeof(*req);
+		p = buf;
+		ceph_encode_16_safe(&p, end, CEPHX_GET_PRINCIPAL_SESSION_KEY,
+				    e_range);
+		ceph_encode_copy_safe(&p, end,
+			xi->auth_authorizer.buf->vec.iov_base,
+			xi->auth_authorizer.buf->vec.iov_len, e_range);
+		ceph_encode_8_safe(&p, end, 1, e_range);
+		ceph_encode_32_safe(&p, end, need, e_range);
 		return p - buf;
 	}
 
 	return 0;
+
+e_range:
+	return -ERANGE;
+}
+
+static int decode_con_secret(void **p, void *end, u8 *con_secret,
+			     int *con_secret_len)
+{
+	int len;
+
+	ceph_decode_32_safe(p, end, len, bad);
+	ceph_decode_need(p, end, len, bad);
+
+	dout("%s len %d\n", __func__, len);
+	if (con_secret) {
+		if (len > CEPH_MAX_CON_SECRET_LEN) {
+			pr_err("connection secret too big %d\n", len);
+			goto bad_memzero;
+		}
+		memcpy(con_secret, *p, len);
+		*con_secret_len = len;
+	}
+	memzero_explicit(*p, len);
+	*p += len;
+	return 0;
+
+bad_memzero:
+	memzero_explicit(*p, len);
+bad:
+	pr_err("failed to decode connection secret\n");
+	return -EINVAL;
+}
+
+static int handle_auth_session_key(struct ceph_auth_client *ac,
+				   void **p, void *end,
+				   u8 *session_key, int *session_key_len,
+				   u8 *con_secret, int *con_secret_len)
+{
+	struct ceph_x_info *xi = ac->private;
+	struct ceph_x_ticket_handler *th;
+	void *dp, *dend;
+	int len;
+	int ret;
+
+	/* AUTH ticket */
+	ret = ceph_x_proc_ticket_reply(ac, &xi->secret, p, end);
+	if (ret)
+		return ret;
+
+	if (*p == end) {
+		/* pre-nautilus (or didn't request service tickets!) */
+		WARN_ON(session_key || con_secret);
+		return 0;
+	}
+
+	th = get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH);
+	if (IS_ERR(th))
+		return PTR_ERR(th);
+
+	if (session_key) {
+		memcpy(session_key, th->session_key.key, th->session_key.len);
+		*session_key_len = th->session_key.len;
+	}
+
+	/* connection secret */
+	ceph_decode_32_safe(p, end, len, e_inval);
+	dout("%s connection secret blob len %d\n", __func__, len);
+	if (len > 0) {
+		dp = *p + ceph_x_encrypt_offset();
+		ret = ceph_x_decrypt(&th->session_key, p, *p + len);
+		if (ret < 0)
+			return ret;
+
+		dout("%s decrypted %d bytes\n", __func__, ret);
+		dend = dp + ret;
+
+		ret = decode_con_secret(&dp, dend, con_secret, con_secret_len);
+		if (ret)
+			return ret;
+	}
+
+	/* service tickets */
+	ceph_decode_32_safe(p, end, len, e_inval);
+	dout("%s service tickets blob len %d\n", __func__, len);
+	if (len > 0) {
+		ret = ceph_x_proc_ticket_reply(ac, &th->session_key,
+					       p, *p + len);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
 }
 
 static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result,
-			       void *buf, void *end)
+			       void *buf, void *end,
+			       u8 *session_key, int *session_key_len,
+			       u8 *con_secret, int *con_secret_len)
 {
 	struct ceph_x_info *xi = ac->private;
-	struct ceph_x_reply_header *head = buf;
 	struct ceph_x_ticket_handler *th;
 	int len = end - buf;
+	void *p;
 	int op;
 	int ret;
 
@@ -587,22 +690,25 @@ static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result,
 		return -EAGAIN;
 	}
 
-	op = le16_to_cpu(head->op);
-	result = le32_to_cpu(head->result);
+	p = buf;
+	ceph_decode_16_safe(&p, end, op, e_inval);
+	ceph_decode_32_safe(&p, end, result, e_inval);
 	dout("handle_reply op %d result %d\n", op, result);
 	switch (op) {
 	case CEPHX_GET_AUTH_SESSION_KEY:
-		/* verify auth key */
-		ret = ceph_x_proc_ticket_reply(ac, &xi->secret,
-					       buf + sizeof(*head), end);
+		/* AUTH ticket + [connection secret] + service tickets */
+		ret = handle_auth_session_key(ac, &p, end, session_key,
+					      session_key_len, con_secret,
+					      con_secret_len);
 		break;
 
 	case CEPHX_GET_PRINCIPAL_SESSION_KEY:
 		th = get_ticket_handler(ac, CEPH_ENTITY_TYPE_AUTH);
 		if (IS_ERR(th))
 			return PTR_ERR(th);
-		ret = ceph_x_proc_ticket_reply(ac, &th->session_key,
-					       buf + sizeof(*head), end);
+
+		/* service tickets */
+		ret = ceph_x_proc_ticket_reply(ac, &th->session_key, &p, end);
 		break;
 
 	default:
@@ -613,6 +719,9 @@ static int ceph_x_handle_reply(struct ceph_auth_client *ac, int result,
 	if (ac->want_keys == xi->have_keys)
 		return 0;
 	return -EAGAIN;
+
+e_inval:
+	return -EINVAL;
 }
 
 static void ceph_x_destroy_authorizer(struct ceph_authorizer *a)
@@ -678,40 +787,44 @@ static int ceph_x_update_authorizer(
 	return 0;
 }
 
-static int decrypt_authorize_challenge(struct ceph_x_authorizer *au,
-				       void *challenge_buf,
-				       int challenge_buf_len,
-				       u64 *server_challenge)
+/*
+ * CephXAuthorizeChallenge
+ */
+static int decrypt_authorizer_challenge(struct ceph_crypto_key *secret,
+					void *challenge, int challenge_len,
+					u64 *server_challenge)
 {
-	struct ceph_x_authorize_challenge *ch =
-	    challenge_buf + sizeof(struct ceph_x_encrypt_header);
+	void *dp, *dend;
 	int ret;
 
 	/* no leading len */
-	ret = __ceph_x_decrypt(&au->session_key, challenge_buf,
-			       challenge_buf_len);
+	ret = __ceph_x_decrypt(secret, challenge, challenge_len);
 	if (ret < 0)
 		return ret;
-	if (ret < sizeof(*ch)) {
-		pr_err("bad size %d for ceph_x_authorize_challenge\n", ret);
-		return -EINVAL;
-	}
 
-	*server_challenge = le64_to_cpu(ch->server_challenge);
+	dout("%s decrypted %d bytes\n", __func__, ret);
+	dp = challenge + sizeof(struct ceph_x_encrypt_header);
+	dend = dp + ret;
+
+	ceph_decode_skip_8(&dp, dend, e_inval);  /* struct_v */
+	ceph_decode_64_safe(&dp, dend, *server_challenge, e_inval);
+	dout("%s server_challenge %llu\n", __func__, *server_challenge);
 	return 0;
+
+e_inval:
+	return -EINVAL;
 }
 
 static int ceph_x_add_authorizer_challenge(struct ceph_auth_client *ac,
 					   struct ceph_authorizer *a,
-					   void *challenge_buf,
-					   int challenge_buf_len)
+					   void *challenge, int challenge_len)
 {
 	struct ceph_x_authorizer *au = (void *)a;
 	u64 server_challenge;
 	int ret;
 
-	ret = decrypt_authorize_challenge(au, challenge_buf, challenge_buf_len,
-					  &server_challenge);
+	ret = decrypt_authorizer_challenge(&au->session_key, challenge,
+					   challenge_len, &server_challenge);
 	if (ret) {
 		pr_err("failed to decrypt authorize challenge: %d", ret);
 		return ret;
@@ -726,29 +839,67 @@ static int ceph_x_add_authorizer_challenge(struct ceph_auth_client *ac,
 	return 0;
 }
 
+/*
+ * CephXAuthorizeReply
+ */
+static int decrypt_authorizer_reply(struct ceph_crypto_key *secret,
+				    void **p, void *end, u64 *nonce_plus_one,
+				    u8 *con_secret, int *con_secret_len)
+{
+	void *dp, *dend;
+	u8 struct_v;
+	int ret;
+
+	dp = *p + ceph_x_encrypt_offset();
+	ret = ceph_x_decrypt(secret, p, end);
+	if (ret < 0)
+		return ret;
+
+	dout("%s decrypted %d bytes\n", __func__, ret);
+	dend = dp + ret;
+
+	ceph_decode_8_safe(&dp, dend, struct_v, e_inval);
+	ceph_decode_64_safe(&dp, dend, *nonce_plus_one, e_inval);
+	dout("%s nonce_plus_one %llu\n", __func__, *nonce_plus_one);
+	if (struct_v >= 2) {
+		ret = decode_con_secret(&dp, dend, con_secret, con_secret_len);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
 static int ceph_x_verify_authorizer_reply(struct ceph_auth_client *ac,
-					  struct ceph_authorizer *a)
+					  struct ceph_authorizer *a,
+					  void *reply, int reply_len,
+					  u8 *session_key, int *session_key_len,
+					  u8 *con_secret, int *con_secret_len)
 {
 	struct ceph_x_authorizer *au = (void *)a;
-	void *p = au->enc_buf;
-	struct ceph_x_authorize_reply *reply = p + ceph_x_encrypt_offset();
+	u64 nonce_plus_one;
 	int ret;
 
-	ret = ceph_x_decrypt(&au->session_key, &p, p + CEPHX_AU_ENC_BUF_LEN);
-	if (ret < 0)
+	if (session_key) {
+		memcpy(session_key, au->session_key.key, au->session_key.len);
+		*session_key_len = au->session_key.len;
+	}
+
+	ret = decrypt_authorizer_reply(&au->session_key, &reply,
+				       reply + reply_len, &nonce_plus_one,
+				       con_secret, con_secret_len);
+	if (ret)
 		return ret;
-	if (ret < sizeof(*reply)) {
-		pr_err("bad size %d for ceph_x_authorize_reply\n", ret);
-		return -EINVAL;
+
+	if (nonce_plus_one != au->nonce + 1) {
+		pr_err("failed to authenticate server\n");
+		return -EPERM;
 	}
 
-	if (au->nonce + 1 != le64_to_cpu(reply->nonce_plus_one))
-		ret = -EPERM;
-	else
-		ret = 0;
-	dout("verify_authorizer_reply nonce %llx got %llx ret %d\n",
-	     au->nonce, le64_to_cpu(reply->nonce_plus_one), ret);
-	return ret;
+	return 0;
 }
 
 static void ceph_x_reset(struct ceph_auth_client *ac)
@@ -785,8 +936,15 @@ static void invalidate_ticket(struct ceph_auth_client *ac, int peer_type)
 	struct ceph_x_ticket_handler *th;
 
 	th = get_ticket_handler(ac, peer_type);
-	if (!IS_ERR(th))
+	if (IS_ERR(th))
+		return;
+
+	if (th->have_key) {
+		dout("ticket %d (%s) secret_id %llu invalidated\n",
+		     th->service, ceph_entity_type_name(th->service),
+		     th->secret_id);
 		th->have_key = false;
+	}
 }
 
 static void ceph_x_invalidate_authorizer(struct ceph_auth_client *ac,
@@ -911,7 +1069,6 @@ static int ceph_x_check_message_signature(struct ceph_auth_handshake *auth,
 }
 
 static const struct ceph_auth_client_ops ceph_x_ops = {
-	.name = "x",
 	.is_authenticated = ceph_x_is_authenticated,
 	.should_authenticate = ceph_x_should_authenticate,
 	.build_request = ceph_x_build_request,
diff --git a/net/ceph/auth_x_protocol.h b/net/ceph/auth_x_protocol.h
index 24b0b74564d0..792fcb974dc3 100644
--- a/net/ceph/auth_x_protocol.h
+++ b/net/ceph/auth_x_protocol.h
@@ -38,7 +38,8 @@ struct ceph_x_authenticate {
 	__u8 struct_v;
 	__le64 client_challenge;
 	__le64 key;
-	/* ticket blob */
+	/* old_ticket blob */
+	/* nautilus+: other_keys */
 } __attribute__ ((packed));
 
 struct ceph_x_service_ticket_request {
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 4e7edd707a14..271287c5ec12 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -265,6 +265,7 @@ enum {
 	Opt_ip,
 	Opt_crush_location,
 	Opt_read_from_replica,
+	Opt_ms_mode,
 	/* string args above */
 	Opt_share,
 	Opt_crc,
@@ -287,6 +288,23 @@ static const struct constant_table ceph_param_read_from_replica[] = {
 	{}
 };
 
+enum ceph_ms_mode {
+	Opt_ms_mode_legacy,
+	Opt_ms_mode_crc,
+	Opt_ms_mode_secure,
+	Opt_ms_mode_prefer_crc,
+	Opt_ms_mode_prefer_secure
+};
+
+static const struct constant_table ceph_param_ms_mode[] = {
+	{"legacy",		Opt_ms_mode_legacy},
+	{"crc",			Opt_ms_mode_crc},
+	{"secure",		Opt_ms_mode_secure},
+	{"prefer-crc",		Opt_ms_mode_prefer_crc},
+	{"prefer-secure",	Opt_ms_mode_prefer_secure},
+	{}
+};
+
 static const struct fs_parameter_spec ceph_parameters[] = {
 	fsparam_flag	("abort_on_full",		Opt_abort_on_full),
 	fsparam_flag_no ("cephx_require_signatures",	Opt_cephx_require_signatures),
@@ -305,6 +323,8 @@ static const struct fs_parameter_spec ceph_parameters[] = {
 			 fs_param_deprecated, NULL),
 	fsparam_enum	("read_from_replica",		Opt_read_from_replica,
 			 ceph_param_read_from_replica),
+	fsparam_enum	("ms_mode",			Opt_ms_mode,
+			 ceph_param_ms_mode),
 	fsparam_string	("secret",			Opt_secret),
 	fsparam_flag_no ("share",			Opt_share),
 	fsparam_flag_no ("tcp_nodelay",			Opt_tcp_nodelay),
@@ -333,6 +353,8 @@ struct ceph_options *ceph_alloc_options(void)
 	opt->osd_idle_ttl = CEPH_OSD_IDLE_TTL_DEFAULT;
 	opt->osd_request_timeout = CEPH_OSD_REQUEST_TIMEOUT_DEFAULT;
 	opt->read_from_replica = CEPH_READ_FROM_REPLICA_DEFAULT;
+	opt->con_modes[0] = CEPH_CON_MODE_UNKNOWN;
+	opt->con_modes[1] = CEPH_CON_MODE_UNKNOWN;
 	return opt;
 }
 EXPORT_SYMBOL(ceph_alloc_options);
@@ -503,6 +525,32 @@ int ceph_parse_param(struct fs_parameter *param, struct ceph_options *opt,
 			BUG();
 		}
 		break;
+	case Opt_ms_mode:
+		switch (result.uint_32) {
+		case Opt_ms_mode_legacy:
+			opt->con_modes[0] = CEPH_CON_MODE_UNKNOWN;
+			opt->con_modes[1] = CEPH_CON_MODE_UNKNOWN;
+			break;
+		case Opt_ms_mode_crc:
+			opt->con_modes[0] = CEPH_CON_MODE_CRC;
+			opt->con_modes[1] = CEPH_CON_MODE_UNKNOWN;
+			break;
+		case Opt_ms_mode_secure:
+			opt->con_modes[0] = CEPH_CON_MODE_SECURE;
+			opt->con_modes[1] = CEPH_CON_MODE_UNKNOWN;
+			break;
+		case Opt_ms_mode_prefer_crc:
+			opt->con_modes[0] = CEPH_CON_MODE_CRC;
+			opt->con_modes[1] = CEPH_CON_MODE_SECURE;
+			break;
+		case Opt_ms_mode_prefer_secure:
+			opt->con_modes[0] = CEPH_CON_MODE_SECURE;
+			opt->con_modes[1] = CEPH_CON_MODE_CRC;
+			break;
+		default:
+			BUG();
+		}
+		break;
 
 	case Opt_osdtimeout:
 		warn_plog(&log, "Ignoring osdtimeout");
@@ -616,6 +664,21 @@ int ceph_print_client_options(struct seq_file *m, struct ceph_client *client,
 	} else if (opt->read_from_replica == CEPH_OSD_FLAG_LOCALIZE_READS) {
 		seq_puts(m, "read_from_replica=localize,");
 	}
+	if (opt->con_modes[0] != CEPH_CON_MODE_UNKNOWN) {
+		if (opt->con_modes[0] == CEPH_CON_MODE_CRC &&
+		    opt->con_modes[1] == CEPH_CON_MODE_UNKNOWN) {
+			seq_puts(m, "ms_mode=crc,");
+		} else if (opt->con_modes[0] == CEPH_CON_MODE_SECURE &&
+			   opt->con_modes[1] == CEPH_CON_MODE_UNKNOWN) {
+			seq_puts(m, "ms_mode=secure,");
+		} else if (opt->con_modes[0] == CEPH_CON_MODE_CRC &&
+			   opt->con_modes[1] == CEPH_CON_MODE_SECURE) {
+			seq_puts(m, "ms_mode=prefer-crc,");
+		} else if (opt->con_modes[0] == CEPH_CON_MODE_SECURE &&
+			   opt->con_modes[1] == CEPH_CON_MODE_CRC) {
+			seq_puts(m, "ms_mode=prefer-secure,");
+		}
+	}
 
 	if (opt->flags & CEPH_OPT_FSID)
 		seq_printf(m, "fsid=%pU,", &opt->fsid);
diff --git a/net/ceph/ceph_strings.c b/net/ceph/ceph_strings.c
index 10e01494993c..355fea272120 100644
--- a/net/ceph/ceph_strings.c
+++ b/net/ceph/ceph_strings.c
@@ -18,6 +18,34 @@ const char *ceph_entity_type_name(int type)
 }
 EXPORT_SYMBOL(ceph_entity_type_name);
 
+const char *ceph_auth_proto_name(int proto)
+{
+	switch (proto) {
+	case CEPH_AUTH_UNKNOWN:
+		return "unknown";
+	case CEPH_AUTH_NONE:
+		return "none";
+	case CEPH_AUTH_CEPHX:
+		return "cephx";
+	default:
+		return "???";
+	}
+}
+
+const char *ceph_con_mode_name(int mode)
+{
+	switch (mode) {
+	case CEPH_CON_MODE_UNKNOWN:
+		return "unknown";
+	case CEPH_CON_MODE_CRC:
+		return "crc";
+	case CEPH_CON_MODE_SECURE:
+		return "secure";
+	default:
+		return "???";
+	}
+}
+
 const char *ceph_osd_op_name(int op)
 {
 	switch (op) {
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 4f75df40fb12..92d89b331645 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -96,6 +96,7 @@ int ceph_crypto_key_decode(struct ceph_crypto_key *key, void **p, void *end)
 	key->len = ceph_decode_16(p);
 	ceph_decode_need(p, end, key->len, bad);
 	ret = set_secret(key, *p);
+	memzero_explicit(*p, key->len);
 	*p += key->len;
 	return ret;
 
@@ -134,7 +135,7 @@ int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *inkey)
 void ceph_crypto_key_destroy(struct ceph_crypto_key *key)
 {
 	if (key) {
-		kfree(key->key);
+		kfree_sensitive(key->key);
 		key->key = NULL;
 		if (key->tfm) {
 			crypto_free_sync_skcipher(key->tfm);
diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h
index 96ef4d860bc9..13bd526349fa 100644
--- a/net/ceph/crypto.h
+++ b/net/ceph/crypto.h
@@ -5,6 +5,9 @@
 #include <linux/ceph/types.h>
 #include <linux/ceph/buffer.h>
 
+#define CEPH_KEY_LEN			16
+#define CEPH_MAX_CON_SECRET_LEN		64
+
 /*
  * cryptographic secret
  */
diff --git a/net/ceph/decode.c b/net/ceph/decode.c
index eea529595a7a..b44f7651be04 100644
--- a/net/ceph/decode.c
+++ b/net/ceph/decode.c
@@ -1,4 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/inet.h>
 
 #include <linux/ceph/decode.h>
 
@@ -82,3 +85,101 @@ bad:
 }
 EXPORT_SYMBOL(ceph_decode_entity_addr);
 
+/*
+ * Return addr of desired type (MSGR2 or LEGACY) or error.
+ * Make sure there is only one match.
+ *
+ * Assume encoding with MSG_ADDR2.
+ */
+int ceph_decode_entity_addrvec(void **p, void *end, bool msgr2,
+			       struct ceph_entity_addr *addr)
+{
+	__le32 my_type = msgr2 ? CEPH_ENTITY_ADDR_TYPE_MSGR2 :
+				 CEPH_ENTITY_ADDR_TYPE_LEGACY;
+	struct ceph_entity_addr tmp_addr;
+	int addr_cnt;
+	bool found;
+	u8 marker;
+	int ret;
+	int i;
+
+	ceph_decode_8_safe(p, end, marker, e_inval);
+	if (marker != 2) {
+		pr_err("bad addrvec marker %d\n", marker);
+		return -EINVAL;
+	}
+
+	ceph_decode_32_safe(p, end, addr_cnt, e_inval);
+
+	found = false;
+	for (i = 0; i < addr_cnt; i++) {
+		ret = ceph_decode_entity_addr(p, end, &tmp_addr);
+		if (ret)
+			return ret;
+
+		if (tmp_addr.type == my_type) {
+			if (found) {
+				pr_err("another match of type %d in addrvec\n",
+				       le32_to_cpu(my_type));
+				return -EINVAL;
+			}
+
+			memcpy(addr, &tmp_addr, sizeof(*addr));
+			found = true;
+		}
+	}
+	if (!found && addr_cnt != 0) {
+		pr_err("no match of type %d in addrvec\n",
+		       le32_to_cpu(my_type));
+		return -ENOENT;
+	}
+
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+EXPORT_SYMBOL(ceph_decode_entity_addrvec);
+
+static int get_sockaddr_encoding_len(sa_family_t family)
+{
+	union {
+		struct sockaddr sa;
+		struct sockaddr_in sin;
+		struct sockaddr_in6 sin6;
+	} u;
+
+	switch (family) {
+	case AF_INET:
+		return sizeof(u.sin);
+	case AF_INET6:
+		return sizeof(u.sin6);
+	default:
+		return sizeof(u);
+	}
+}
+
+int ceph_entity_addr_encoding_len(const struct ceph_entity_addr *addr)
+{
+	sa_family_t family = get_unaligned(&addr->in_addr.ss_family);
+	int addr_len = get_sockaddr_encoding_len(family);
+
+	return 1 + CEPH_ENCODING_START_BLK_LEN + 4 + 4 + 4 + addr_len;
+}
+
+void ceph_encode_entity_addr(void **p, const struct ceph_entity_addr *addr)
+{
+	sa_family_t family = get_unaligned(&addr->in_addr.ss_family);
+	int addr_len = get_sockaddr_encoding_len(family);
+
+	ceph_encode_8(p, 1);  /* marker */
+	ceph_start_encoding(p, 1, 1, sizeof(addr->type) +
+				     sizeof(addr->nonce) +
+				     sizeof(u32) + addr_len);
+	ceph_encode_copy(p, &addr->type, sizeof(addr->type));
+	ceph_encode_copy(p, &addr->nonce, sizeof(addr->nonce));
+
+	ceph_encode_32(p, addr_len);
+	ceph_encode_16(p, family);
+	ceph_encode_copy(p, addr->in_addr.__data, addr_len - sizeof(family));
+}
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index d4d7a0e52491..57d043b382ed 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -82,71 +82,51 @@
 #define CON_SOCK_STATE_CONNECTED	3	/* -> CLOSING or -> CLOSED */
 #define CON_SOCK_STATE_CLOSING		4	/* -> CLOSED */
 
-/*
- * connection states
- */
-#define CON_STATE_CLOSED        1  /* -> PREOPEN */
-#define CON_STATE_PREOPEN       2  /* -> CONNECTING, CLOSED */
-#define CON_STATE_CONNECTING    3  /* -> NEGOTIATING, CLOSED */
-#define CON_STATE_NEGOTIATING   4  /* -> OPEN, CLOSED */
-#define CON_STATE_OPEN          5  /* -> STANDBY, CLOSED */
-#define CON_STATE_STANDBY       6  /* -> PREOPEN, CLOSED */
-
-/*
- * ceph_connection flag bits
- */
-#define CON_FLAG_LOSSYTX           0  /* we can close channel or drop
-				       * messages on errors */
-#define CON_FLAG_KEEPALIVE_PENDING 1  /* we need to send a keepalive */
-#define CON_FLAG_WRITE_PENDING	   2  /* we have data ready to send */
-#define CON_FLAG_SOCK_CLOSED	   3  /* socket state changed to closed */
-#define CON_FLAG_BACKOFF           4  /* need to retry queuing delayed work */
-
 static bool con_flag_valid(unsigned long con_flag)
 {
 	switch (con_flag) {
-	case CON_FLAG_LOSSYTX:
-	case CON_FLAG_KEEPALIVE_PENDING:
-	case CON_FLAG_WRITE_PENDING:
-	case CON_FLAG_SOCK_CLOSED:
-	case CON_FLAG_BACKOFF:
+	case CEPH_CON_F_LOSSYTX:
+	case CEPH_CON_F_KEEPALIVE_PENDING:
+	case CEPH_CON_F_WRITE_PENDING:
+	case CEPH_CON_F_SOCK_CLOSED:
+	case CEPH_CON_F_BACKOFF:
 		return true;
 	default:
 		return false;
 	}
 }
 
-static void con_flag_clear(struct ceph_connection *con, unsigned long con_flag)
+void ceph_con_flag_clear(struct ceph_connection *con, unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
 	clear_bit(con_flag, &con->flags);
 }
 
-static void con_flag_set(struct ceph_connection *con, unsigned long con_flag)
+void ceph_con_flag_set(struct ceph_connection *con, unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
 	set_bit(con_flag, &con->flags);
 }
 
-static bool con_flag_test(struct ceph_connection *con, unsigned long con_flag)
+bool ceph_con_flag_test(struct ceph_connection *con, unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
 	return test_bit(con_flag, &con->flags);
 }
 
-static bool con_flag_test_and_clear(struct ceph_connection *con,
-					unsigned long con_flag)
+bool ceph_con_flag_test_and_clear(struct ceph_connection *con,
+				  unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
 	return test_and_clear_bit(con_flag, &con->flags);
 }
 
-static bool con_flag_test_and_set(struct ceph_connection *con,
-					unsigned long con_flag)
+bool ceph_con_flag_test_and_set(struct ceph_connection *con,
+				unsigned long con_flag)
 {
 	BUG_ON(!con_flag_valid(con_flag));
 
@@ -157,12 +137,6 @@ static bool con_flag_test_and_set(struct ceph_connection *con,
 
 static struct kmem_cache	*ceph_msg_cache;
 
-/* static tag bytes (protocol control messages) */
-static char tag_msg = CEPH_MSGR_TAG_MSG;
-static char tag_ack = CEPH_MSGR_TAG_ACK;
-static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
-static char tag_keepalive2 = CEPH_MSGR_TAG_KEEPALIVE2;
-
 #ifdef CONFIG_LOCKDEP
 static struct lock_class_key socket_class;
 #endif
@@ -184,7 +158,7 @@ static void con_fault(struct ceph_connection *con);
 static char addr_str[ADDR_STR_COUNT][MAX_ADDR_STR_LEN];
 static atomic_t addr_str_seq = ATOMIC_INIT(0);
 
-static struct page *zero_page;		/* used in certain error cases */
+struct page *ceph_zero_page;		/* used in certain error cases */
 
 const char *ceph_pr_addr(const struct ceph_entity_addr *addr)
 {
@@ -219,10 +193,13 @@ const char *ceph_pr_addr(const struct ceph_entity_addr *addr)
 }
 EXPORT_SYMBOL(ceph_pr_addr);
 
-static void encode_my_addr(struct ceph_messenger *msgr)
+void ceph_encode_my_addr(struct ceph_messenger *msgr)
 {
-	memcpy(&msgr->my_enc_addr, &msgr->inst.addr, sizeof(msgr->my_enc_addr));
-	ceph_encode_banner_addr(&msgr->my_enc_addr);
+	if (!ceph_msgr2(from_msgr(msgr))) {
+		memcpy(&msgr->my_enc_addr, &msgr->inst.addr,
+		       sizeof(msgr->my_enc_addr));
+		ceph_encode_banner_addr(&msgr->my_enc_addr);
+	}
 }
 
 /*
@@ -254,9 +231,9 @@ static void _ceph_msgr_exit(void)
 		ceph_msgr_wq = NULL;
 	}
 
-	BUG_ON(zero_page == NULL);
-	put_page(zero_page);
-	zero_page = NULL;
+	BUG_ON(!ceph_zero_page);
+	put_page(ceph_zero_page);
+	ceph_zero_page = NULL;
 
 	ceph_msgr_slab_exit();
 }
@@ -266,9 +243,9 @@ int __init ceph_msgr_init(void)
 	if (ceph_msgr_slab_init())
 		return -ENOMEM;
 
-	BUG_ON(zero_page != NULL);
-	zero_page = ZERO_PAGE(0);
-	get_page(zero_page);
+	BUG_ON(ceph_zero_page);
+	ceph_zero_page = ZERO_PAGE(0);
+	get_page(ceph_zero_page);
 
 	/*
 	 * The number of active work items is limited by the number of
@@ -372,7 +349,7 @@ static void ceph_sock_data_ready(struct sock *sk)
 	}
 
 	if (sk->sk_state != TCP_CLOSE_WAIT) {
-		dout("%s on %p state = %lu, queueing work\n", __func__,
+		dout("%s %p state = %d, queueing work\n", __func__,
 		     con, con->state);
 		queue_con(con);
 	}
@@ -390,7 +367,7 @@ static void ceph_sock_write_space(struct sock *sk)
 	 * buffer. See net/ipv4/tcp_input.c:tcp_check_space()
 	 * and net/core/stream.c:sk_stream_write_space().
 	 */
-	if (con_flag_test(con, CON_FLAG_WRITE_PENDING)) {
+	if (ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING)) {
 		if (sk_stream_is_writeable(sk)) {
 			dout("%s %p queueing write work\n", __func__, con);
 			clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
@@ -406,7 +383,7 @@ static void ceph_sock_state_change(struct sock *sk)
 {
 	struct ceph_connection *con = sk->sk_user_data;
 
-	dout("%s %p state = %lu sk_state = %u\n", __func__,
+	dout("%s %p state = %d sk_state = %u\n", __func__,
 	     con, con->state, sk->sk_state);
 
 	switch (sk->sk_state) {
@@ -416,7 +393,7 @@ static void ceph_sock_state_change(struct sock *sk)
 	case TCP_CLOSE_WAIT:
 		dout("%s TCP_CLOSE_WAIT\n", __func__);
 		con_sock_state_closing(con);
-		con_flag_set(con, CON_FLAG_SOCK_CLOSED);
+		ceph_con_flag_set(con, CEPH_CON_F_SOCK_CLOSED);
 		queue_con(con);
 		break;
 	case TCP_ESTABLISHED:
@@ -450,13 +427,15 @@ static void set_sock_callbacks(struct socket *sock,
 /*
  * initiate connection to a remote socket.
  */
-static int ceph_tcp_connect(struct ceph_connection *con)
+int ceph_tcp_connect(struct ceph_connection *con)
 {
 	struct sockaddr_storage ss = con->peer_addr.in_addr; /* align */
 	struct socket *sock;
 	unsigned int noio_flag;
 	int ret;
 
+	dout("%s con %p peer_addr %s\n", __func__, con,
+	     ceph_pr_addr(&con->peer_addr));
 	BUG_ON(con->sock);
 
 	/* sock_create_kern() allocates with GFP_KERNEL */
@@ -474,8 +453,6 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 
 	set_sock_callbacks(sock, con);
 
-	dout("connect %s\n", ceph_pr_addr(&con->peer_addr));
-
 	con_sock_state_connecting(con);
 	ret = sock->ops->connect(sock, (struct sockaddr *)&ss, sizeof(ss),
 				 O_NONBLOCK);
@@ -498,103 +475,13 @@ static int ceph_tcp_connect(struct ceph_connection *con)
 }
 
 /*
- * If @buf is NULL, discard up to @len bytes.
- */
-static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
-{
-	struct kvec iov = {buf, len};
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
-	int r;
-
-	if (!buf)
-		msg.msg_flags |= MSG_TRUNC;
-
-	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len);
-	r = sock_recvmsg(sock, &msg, msg.msg_flags);
-	if (r == -EAGAIN)
-		r = 0;
-	return r;
-}
-
-static int ceph_tcp_recvpage(struct socket *sock, struct page *page,
-		     int page_offset, size_t length)
-{
-	struct bio_vec bvec = {
-		.bv_page = page,
-		.bv_offset = page_offset,
-		.bv_len = length
-	};
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
-	int r;
-
-	BUG_ON(page_offset + length > PAGE_SIZE);
-	iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length);
-	r = sock_recvmsg(sock, &msg, msg.msg_flags);
-	if (r == -EAGAIN)
-		r = 0;
-	return r;
-}
-
-/*
- * write something.  @more is true if caller will be sending more data
- * shortly.
- */
-static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
-			    size_t kvlen, size_t len, bool more)
-{
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
-	int r;
-
-	if (more)
-		msg.msg_flags |= MSG_MORE;
-	else
-		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */
-
-	r = kernel_sendmsg(sock, &msg, iov, kvlen, len);
-	if (r == -EAGAIN)
-		r = 0;
-	return r;
-}
-
-/*
- * @more: either or both of MSG_MORE and MSG_SENDPAGE_NOTLAST
- */
-static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
-			     int offset, size_t size, int more)
-{
-	ssize_t (*sendpage)(struct socket *sock, struct page *page,
-			    int offset, size_t size, int flags);
-	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
-	int ret;
-
-	/*
-	 * sendpage cannot properly handle pages with page_count == 0,
-	 * we need to fall back to sendmsg if that's the case.
-	 *
-	 * Same goes for slab pages: skb_can_coalesce() allows
-	 * coalescing neighboring slab objects into a single frag which
-	 * triggers one of hardened usercopy checks.
-	 */
-	if (sendpage_ok(page))
-		sendpage = sock->ops->sendpage;
-	else
-		sendpage = sock_no_sendpage;
-
-	ret = sendpage(sock, page, offset, size, flags);
-	if (ret == -EAGAIN)
-		ret = 0;
-
-	return ret;
-}
-
-/*
  * Shutdown/close the socket for the given connection.
  */
-static int con_close_socket(struct ceph_connection *con)
+int ceph_con_close_socket(struct ceph_connection *con)
 {
 	int rc = 0;
 
-	dout("con_close_socket on %p sock %p\n", con, con->sock);
+	dout("%s con %p sock %p\n", __func__, con, con->sock);
 	if (con->sock) {
 		rc = con->sock->ops->shutdown(con->sock, SHUT_RDWR);
 		sock_release(con->sock);
@@ -607,12 +494,34 @@ static int con_close_socket(struct ceph_connection *con)
 	 * received a socket close event before we had the chance to
 	 * shut the socket down.
 	 */
-	con_flag_clear(con, CON_FLAG_SOCK_CLOSED);
+	ceph_con_flag_clear(con, CEPH_CON_F_SOCK_CLOSED);
 
 	con_sock_state_closed(con);
 	return rc;
 }
 
+static void ceph_con_reset_protocol(struct ceph_connection *con)
+{
+	dout("%s con %p\n", __func__, con);
+
+	ceph_con_close_socket(con);
+	if (con->in_msg) {
+		WARN_ON(con->in_msg->con != con);
+		ceph_msg_put(con->in_msg);
+		con->in_msg = NULL;
+	}
+	if (con->out_msg) {
+		WARN_ON(con->out_msg->con != con);
+		ceph_msg_put(con->out_msg);
+		con->out_msg = NULL;
+	}
+
+	if (ceph_msgr2(from_msgr(con->msgr)))
+		ceph_con_v2_reset_protocol(con);
+	else
+		ceph_con_v1_reset_protocol(con);
+}
+
 /*
  * Reset a connection.  Discard all incoming and outgoing messages
  * and clear *_seq state.
@@ -623,6 +532,7 @@ static void ceph_msg_remove(struct ceph_msg *msg)
 
 	ceph_msg_put(msg);
 }
+
 static void ceph_msg_remove_list(struct list_head *head)
 {
 	while (!list_empty(head)) {
@@ -632,31 +542,22 @@ static void ceph_msg_remove_list(struct list_head *head)
 	}
 }
 
-static void reset_connection(struct ceph_connection *con)
+void ceph_con_reset_session(struct ceph_connection *con)
 {
-	/* reset connection, out_queue, msg_ and connect_seq */
-	/* discard existing out_queue and msg_seq */
-	dout("reset_connection %p\n", con);
+	dout("%s con %p\n", __func__, con);
+
+	WARN_ON(con->in_msg);
+	WARN_ON(con->out_msg);
 	ceph_msg_remove_list(&con->out_queue);
 	ceph_msg_remove_list(&con->out_sent);
-
-	if (con->in_msg) {
-		BUG_ON(con->in_msg->con != con);
-		ceph_msg_put(con->in_msg);
-		con->in_msg = NULL;
-	}
-
-	con->connect_seq = 0;
 	con->out_seq = 0;
-	if (con->out_msg) {
-		BUG_ON(con->out_msg->con != con);
-		ceph_msg_put(con->out_msg);
-		con->out_msg = NULL;
-	}
 	con->in_seq = 0;
 	con->in_seq_acked = 0;
 
-	con->out_skip = 0;
+	if (ceph_msgr2(from_msgr(con->msgr)))
+		ceph_con_v2_reset_session(con);
+	else
+		ceph_con_v1_reset_session(con);
 }
 
 /*
@@ -666,17 +567,17 @@ void ceph_con_close(struct ceph_connection *con)
 {
 	mutex_lock(&con->mutex);
 	dout("con_close %p peer %s\n", con, ceph_pr_addr(&con->peer_addr));
-	con->state = CON_STATE_CLOSED;
+	con->state = CEPH_CON_S_CLOSED;
 
-	con_flag_clear(con, CON_FLAG_LOSSYTX);	/* so we retry next connect */
-	con_flag_clear(con, CON_FLAG_KEEPALIVE_PENDING);
-	con_flag_clear(con, CON_FLAG_WRITE_PENDING);
-	con_flag_clear(con, CON_FLAG_BACKOFF);
+	ceph_con_flag_clear(con, CEPH_CON_F_LOSSYTX);  /* so we retry next
+							  connect */
+	ceph_con_flag_clear(con, CEPH_CON_F_KEEPALIVE_PENDING);
+	ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+	ceph_con_flag_clear(con, CEPH_CON_F_BACKOFF);
 
-	reset_connection(con);
-	con->peer_global_seq = 0;
+	ceph_con_reset_protocol(con);
+	ceph_con_reset_session(con);
 	cancel_con(con);
-	con_close_socket(con);
 	mutex_unlock(&con->mutex);
 }
 EXPORT_SYMBOL(ceph_con_close);
@@ -691,8 +592,8 @@ void ceph_con_open(struct ceph_connection *con,
 	mutex_lock(&con->mutex);
 	dout("con_open %p %s\n", con, ceph_pr_addr(addr));
 
-	WARN_ON(con->state != CON_STATE_CLOSED);
-	con->state = CON_STATE_PREOPEN;
+	WARN_ON(con->state != CEPH_CON_S_CLOSED);
+	con->state = CEPH_CON_S_PREOPEN;
 
 	con->peer_name.type = (__u8) entity_type;
 	con->peer_name.num = cpu_to_le64(entity_num);
@@ -709,7 +610,10 @@ EXPORT_SYMBOL(ceph_con_open);
  */
 bool ceph_con_opened(struct ceph_connection *con)
 {
-	return con->connect_seq > 0;
+	if (ceph_msgr2(from_msgr(con->msgr)))
+		return ceph_con_v2_opened(con);
+
+	return ceph_con_v1_opened(con);
 }
 
 /*
@@ -732,16 +636,15 @@ void ceph_con_init(struct ceph_connection *con, void *private,
 	INIT_LIST_HEAD(&con->out_sent);
 	INIT_DELAYED_WORK(&con->work, ceph_con_workfn);
 
-	con->state = CON_STATE_CLOSED;
+	con->state = CEPH_CON_S_CLOSED;
 }
 EXPORT_SYMBOL(ceph_con_init);
 
-
 /*
  * We maintain a global counter to order connection attempts.  Get
  * a unique seq greater than @gt.
  */
-static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
+u32 ceph_get_global_seq(struct ceph_messenger *msgr, u32 gt)
 {
 	u32 ret;
 
@@ -753,48 +656,53 @@ static u32 get_global_seq(struct ceph_messenger *msgr, u32 gt)
 	return ret;
 }
 
-static void con_out_kvec_reset(struct ceph_connection *con)
-{
-	BUG_ON(con->out_skip);
-
-	con->out_kvec_left = 0;
-	con->out_kvec_bytes = 0;
-	con->out_kvec_cur = &con->out_kvec[0];
-}
-
-static void con_out_kvec_add(struct ceph_connection *con,
-				size_t size, void *data)
+/*
+ * Discard messages that have been acked by the server.
+ */
+void ceph_con_discard_sent(struct ceph_connection *con, u64 ack_seq)
 {
-	int index = con->out_kvec_left;
+	struct ceph_msg *msg;
+	u64 seq;
 
-	BUG_ON(con->out_skip);
-	BUG_ON(index >= ARRAY_SIZE(con->out_kvec));
+	dout("%s con %p ack_seq %llu\n", __func__, con, ack_seq);
+	while (!list_empty(&con->out_sent)) {
+		msg = list_first_entry(&con->out_sent, struct ceph_msg,
+				       list_head);
+		WARN_ON(msg->needs_out_seq);
+		seq = le64_to_cpu(msg->hdr.seq);
+		if (seq > ack_seq)
+			break;
 
-	con->out_kvec[index].iov_len = size;
-	con->out_kvec[index].iov_base = data;
-	con->out_kvec_left++;
-	con->out_kvec_bytes += size;
+		dout("%s con %p discarding msg %p seq %llu\n", __func__, con,
+		     msg, seq);
+		ceph_msg_remove(msg);
+	}
 }
 
 /*
- * Chop off a kvec from the end.  Return residual number of bytes for
- * that kvec, i.e. how many bytes would have been written if the kvec
- * hadn't been nuked.
+ * Discard messages that have been requeued in con_fault(), up to
+ * reconnect_seq.  This avoids gratuitously resending messages that
+ * the server had received and handled prior to reconnect.
  */
-static int con_out_kvec_skip(struct ceph_connection *con)
+void ceph_con_discard_requeued(struct ceph_connection *con, u64 reconnect_seq)
 {
-	int off = con->out_kvec_cur - con->out_kvec;
-	int skip = 0;
+	struct ceph_msg *msg;
+	u64 seq;
 
-	if (con->out_kvec_bytes > 0) {
-		skip = con->out_kvec[off + con->out_kvec_left - 1].iov_len;
-		BUG_ON(con->out_kvec_bytes < skip);
-		BUG_ON(!con->out_kvec_left);
-		con->out_kvec_bytes -= skip;
-		con->out_kvec_left--;
-	}
+	dout("%s con %p reconnect_seq %llu\n", __func__, con, reconnect_seq);
+	while (!list_empty(&con->out_queue)) {
+		msg = list_first_entry(&con->out_queue, struct ceph_msg,
+				       list_head);
+		if (msg->needs_out_seq)
+			break;
+		seq = le64_to_cpu(msg->hdr.seq);
+		if (seq > reconnect_seq)
+			break;
 
-	return skip;
+		dout("%s con %p discarding msg %p seq %llu\n", __func__, con,
+		     msg, seq);
+		ceph_msg_remove(msg);
+	}
 }
 
 #ifdef CONFIG_BLOCK
@@ -1113,10 +1021,9 @@ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor)
 	cursor->need_crc = true;
 }
 
-static void ceph_msg_data_cursor_init(struct ceph_msg *msg, size_t length)
+void ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor,
+			       struct ceph_msg *msg, size_t length)
 {
-	struct ceph_msg_data_cursor *cursor = &msg->cursor;
-
 	BUG_ON(!length);
 	BUG_ON(length > msg->data_length);
 	BUG_ON(!msg->num_data_items);
@@ -1132,9 +1039,9 @@ static void ceph_msg_data_cursor_init(struct ceph_msg *msg, size_t length)
  * data item, and supply the page offset and length of that piece.
  * Indicate whether this is the last piece in this data item.
  */
-static struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
-					size_t *page_offset, size_t *length,
-					bool *last_piece)
+struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
+				size_t *page_offset, size_t *length,
+				bool *last_piece)
 {
 	struct page *page;
 
@@ -1173,8 +1080,7 @@ static struct page *ceph_msg_data_next(struct ceph_msg_data_cursor *cursor,
  * Returns true if the result moves the cursor on to the next piece
  * of the data item.
  */
-static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
-				  size_t bytes)
+void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor, size_t bytes)
 {
 	bool new_piece;
 
@@ -1210,328 +1116,8 @@ static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
 	cursor->need_crc = new_piece;
 }
 
-static size_t sizeof_footer(struct ceph_connection *con)
-{
-	return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ?
-	    sizeof(struct ceph_msg_footer) :
-	    sizeof(struct ceph_msg_footer_old);
-}
-
-static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
-{
-	/* Initialize data cursor */
-
-	ceph_msg_data_cursor_init(msg, (size_t)data_len);
-}
-
-/*
- * Prepare footer for currently outgoing message, and finish things
- * off.  Assumes out_kvec* are already valid.. we just add on to the end.
- */
-static void prepare_write_message_footer(struct ceph_connection *con)
-{
-	struct ceph_msg *m = con->out_msg;
-
-	m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE;
-
-	dout("prepare_write_message_footer %p\n", con);
-	con_out_kvec_add(con, sizeof_footer(con), &m->footer);
-	if (con->peer_features & CEPH_FEATURE_MSG_AUTH) {
-		if (con->ops->sign_message)
-			con->ops->sign_message(m);
-		else
-			m->footer.sig = 0;
-	} else {
-		m->old_footer.flags = m->footer.flags;
-	}
-	con->out_more = m->more_to_follow;
-	con->out_msg_done = true;
-}
-
-/*
- * Prepare headers for the next outgoing message.
- */
-static void prepare_write_message(struct ceph_connection *con)
-{
-	struct ceph_msg *m;
-	u32 crc;
-
-	con_out_kvec_reset(con);
-	con->out_msg_done = false;
-
-	/* Sneak an ack in there first?  If we can get it into the same
-	 * TCP packet that's a good thing. */
-	if (con->in_seq > con->in_seq_acked) {
-		con->in_seq_acked = con->in_seq;
-		con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
-		con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-		con_out_kvec_add(con, sizeof (con->out_temp_ack),
-			&con->out_temp_ack);
-	}
-
-	BUG_ON(list_empty(&con->out_queue));
-	m = list_first_entry(&con->out_queue, struct ceph_msg, list_head);
-	con->out_msg = m;
-	BUG_ON(m->con != con);
-
-	/* put message on sent list */
-	ceph_msg_get(m);
-	list_move_tail(&m->list_head, &con->out_sent);
-
-	/*
-	 * only assign outgoing seq # if we haven't sent this message
-	 * yet.  if it is requeued, resend with it's original seq.
-	 */
-	if (m->needs_out_seq) {
-		m->hdr.seq = cpu_to_le64(++con->out_seq);
-		m->needs_out_seq = false;
-
-		if (con->ops->reencode_message)
-			con->ops->reencode_message(m);
-	}
-
-	dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n",
-	     m, con->out_seq, le16_to_cpu(m->hdr.type),
-	     le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len),
-	     m->data_length);
-	WARN_ON(m->front.iov_len != le32_to_cpu(m->hdr.front_len));
-	WARN_ON(m->data_length != le32_to_cpu(m->hdr.data_len));
-
-	/* tag + hdr + front + middle */
-	con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
-	con_out_kvec_add(con, sizeof(con->out_hdr), &con->out_hdr);
-	con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
-
-	if (m->middle)
-		con_out_kvec_add(con, m->middle->vec.iov_len,
-			m->middle->vec.iov_base);
-
-	/* fill in hdr crc and finalize hdr */
-	crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
-	con->out_msg->hdr.crc = cpu_to_le32(crc);
-	memcpy(&con->out_hdr, &con->out_msg->hdr, sizeof(con->out_hdr));
-
-	/* fill in front and middle crc, footer */
-	crc = crc32c(0, m->front.iov_base, m->front.iov_len);
-	con->out_msg->footer.front_crc = cpu_to_le32(crc);
-	if (m->middle) {
-		crc = crc32c(0, m->middle->vec.iov_base,
-				m->middle->vec.iov_len);
-		con->out_msg->footer.middle_crc = cpu_to_le32(crc);
-	} else
-		con->out_msg->footer.middle_crc = 0;
-	dout("%s front_crc %u middle_crc %u\n", __func__,
-	     le32_to_cpu(con->out_msg->footer.front_crc),
-	     le32_to_cpu(con->out_msg->footer.middle_crc));
-	con->out_msg->footer.flags = 0;
-
-	/* is there a data payload? */
-	con->out_msg->footer.data_crc = 0;
-	if (m->data_length) {
-		prepare_message_data(con->out_msg, m->data_length);
-		con->out_more = 1;  /* data + footer will follow */
-	} else {
-		/* no, queue up footer too and be done */
-		prepare_write_message_footer(con);
-	}
-
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
-}
-
-/*
- * Prepare an ack.
- */
-static void prepare_write_ack(struct ceph_connection *con)
-{
-	dout("prepare_write_ack %p %llu -> %llu\n", con,
-	     con->in_seq_acked, con->in_seq);
-	con->in_seq_acked = con->in_seq;
-
-	con_out_kvec_reset(con);
-
-	con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
-
-	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-	con_out_kvec_add(con, sizeof (con->out_temp_ack),
-				&con->out_temp_ack);
-
-	con->out_more = 1;  /* more will follow.. eventually.. */
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
-}
-
-/*
- * Prepare to share the seq during handshake
- */
-static void prepare_write_seq(struct ceph_connection *con)
-{
-	dout("prepare_write_seq %p %llu -> %llu\n", con,
-	     con->in_seq_acked, con->in_seq);
-	con->in_seq_acked = con->in_seq;
-
-	con_out_kvec_reset(con);
-
-	con->out_temp_ack = cpu_to_le64(con->in_seq_acked);
-	con_out_kvec_add(con, sizeof (con->out_temp_ack),
-			 &con->out_temp_ack);
-
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
-}
-
-/*
- * Prepare to write keepalive byte.
- */
-static void prepare_write_keepalive(struct ceph_connection *con)
-{
-	dout("prepare_write_keepalive %p\n", con);
-	con_out_kvec_reset(con);
-	if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) {
-		struct timespec64 now;
-
-		ktime_get_real_ts64(&now);
-		con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2);
-		ceph_encode_timespec64(&con->out_temp_keepalive2, &now);
-		con_out_kvec_add(con, sizeof(con->out_temp_keepalive2),
-				 &con->out_temp_keepalive2);
-	} else {
-		con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive);
-	}
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
-}
-
-/*
- * Connection negotiation.
- */
-
-static int get_connect_authorizer(struct ceph_connection *con)
-{
-	struct ceph_auth_handshake *auth;
-	int auth_proto;
-
-	if (!con->ops->get_authorizer) {
-		con->auth = NULL;
-		con->out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
-		con->out_connect.authorizer_len = 0;
-		return 0;
-	}
-
-	auth = con->ops->get_authorizer(con, &auth_proto, con->auth_retry);
-	if (IS_ERR(auth))
-		return PTR_ERR(auth);
-
-	con->auth = auth;
-	con->out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
-	con->out_connect.authorizer_len = cpu_to_le32(auth->authorizer_buf_len);
-	return 0;
-}
-
-/*
- * We connected to a peer and are saying hello.
- */
-static void prepare_write_banner(struct ceph_connection *con)
-{
-	con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
-	con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr),
-					&con->msgr->my_enc_addr);
-
-	con->out_more = 0;
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
-}
-
-static void __prepare_write_connect(struct ceph_connection *con)
-{
-	con_out_kvec_add(con, sizeof(con->out_connect), &con->out_connect);
-	if (con->auth)
-		con_out_kvec_add(con, con->auth->authorizer_buf_len,
-				 con->auth->authorizer_buf);
-
-	con->out_more = 0;
-	con_flag_set(con, CON_FLAG_WRITE_PENDING);
-}
-
-static int prepare_write_connect(struct ceph_connection *con)
-{
-	unsigned int global_seq = get_global_seq(con->msgr, 0);
-	int proto;
-	int ret;
-
-	switch (con->peer_name.type) {
-	case CEPH_ENTITY_TYPE_MON:
-		proto = CEPH_MONC_PROTOCOL;
-		break;
-	case CEPH_ENTITY_TYPE_OSD:
-		proto = CEPH_OSDC_PROTOCOL;
-		break;
-	case CEPH_ENTITY_TYPE_MDS:
-		proto = CEPH_MDSC_PROTOCOL;
-		break;
-	default:
-		BUG();
-	}
-
-	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
-	     con->connect_seq, global_seq, proto);
-
-	con->out_connect.features =
-	    cpu_to_le64(from_msgr(con->msgr)->supported_features);
-	con->out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
-	con->out_connect.connect_seq = cpu_to_le32(con->connect_seq);
-	con->out_connect.global_seq = cpu_to_le32(global_seq);
-	con->out_connect.protocol_version = cpu_to_le32(proto);
-	con->out_connect.flags = 0;
-
-	ret = get_connect_authorizer(con);
-	if (ret)
-		return ret;
-
-	__prepare_write_connect(con);
-	return 0;
-}
-
-/*
- * write as much of pending kvecs to the socket as we can.
- *  1 -> done
- *  0 -> socket full, but more to do
- * <0 -> error
- */
-static int write_partial_kvec(struct ceph_connection *con)
-{
-	int ret;
-
-	dout("write_partial_kvec %p %d left\n", con, con->out_kvec_bytes);
-	while (con->out_kvec_bytes > 0) {
-		ret = ceph_tcp_sendmsg(con->sock, con->out_kvec_cur,
-				       con->out_kvec_left, con->out_kvec_bytes,
-				       con->out_more);
-		if (ret <= 0)
-			goto out;
-		con->out_kvec_bytes -= ret;
-		if (con->out_kvec_bytes == 0)
-			break;            /* done */
-
-		/* account for full iov entries consumed */
-		while (ret >= con->out_kvec_cur->iov_len) {
-			BUG_ON(!con->out_kvec_left);
-			ret -= con->out_kvec_cur->iov_len;
-			con->out_kvec_cur++;
-			con->out_kvec_left--;
-		}
-		/* and for a partially-consumed entry */
-		if (ret) {
-			con->out_kvec_cur->iov_len -= ret;
-			con->out_kvec_cur->iov_base += ret;
-		}
-	}
-	con->out_kvec_left = 0;
-	ret = 1;
-out:
-	dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con,
-	     con->out_kvec_bytes, con->out_kvec_left, ret);
-	return ret;  /* done! */
-}
-
-static u32 ceph_crc32c_page(u32 crc, struct page *page,
-				unsigned int page_offset,
-				unsigned int length)
+u32 ceph_crc32c_page(u32 crc, struct page *page, unsigned int page_offset,
+		     unsigned int length)
 {
 	char *kaddr;
 
@@ -1542,257 +1128,8 @@ static u32 ceph_crc32c_page(u32 crc, struct page *page,
 
 	return crc;
 }
-/*
- * Write as much message data payload as we can.  If we finish, queue
- * up the footer.
- *  1 -> done, footer is now queued in out_kvec[].
- *  0 -> socket full, but more to do
- * <0 -> error
- */
-static int write_partial_message_data(struct ceph_connection *con)
-{
-	struct ceph_msg *msg = con->out_msg;
-	struct ceph_msg_data_cursor *cursor = &msg->cursor;
-	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
-	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
-	u32 crc;
-
-	dout("%s %p msg %p\n", __func__, con, msg);
-
-	if (!msg->num_data_items)
-		return -EINVAL;
-
-	/*
-	 * Iterate through each page that contains data to be
-	 * written, and send as much as possible for each.
-	 *
-	 * If we are calculating the data crc (the default), we will
-	 * need to map the page.  If we have no pages, they have
-	 * been revoked, so use the zero page.
-	 */
-	crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0;
-	while (cursor->total_resid) {
-		struct page *page;
-		size_t page_offset;
-		size_t length;
-		int ret;
-
-		if (!cursor->resid) {
-			ceph_msg_data_advance(cursor, 0);
-			continue;
-		}
-
-		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
-		if (length == cursor->total_resid)
-			more = MSG_MORE;
-		ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
-					more);
-		if (ret <= 0) {
-			if (do_datacrc)
-				msg->footer.data_crc = cpu_to_le32(crc);
-
-			return ret;
-		}
-		if (do_datacrc && cursor->need_crc)
-			crc = ceph_crc32c_page(crc, page, page_offset, length);
-		ceph_msg_data_advance(cursor, (size_t)ret);
-	}
-
-	dout("%s %p msg %p done\n", __func__, con, msg);
-
-	/* prepare and queue up footer, too */
-	if (do_datacrc)
-		msg->footer.data_crc = cpu_to_le32(crc);
-	else
-		msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
-	con_out_kvec_reset(con);
-	prepare_write_message_footer(con);
-
-	return 1;	/* must return > 0 to indicate success */
-}
-
-/*
- * write some zeros
- */
-static int write_partial_skip(struct ceph_connection *con)
-{
-	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
-	int ret;
-
-	dout("%s %p %d left\n", __func__, con, con->out_skip);
-	while (con->out_skip > 0) {
-		size_t size = min(con->out_skip, (int) PAGE_SIZE);
-
-		if (size == con->out_skip)
-			more = MSG_MORE;
-		ret = ceph_tcp_sendpage(con->sock, zero_page, 0, size, more);
-		if (ret <= 0)
-			goto out;
-		con->out_skip -= ret;
-	}
-	ret = 1;
-out:
-	return ret;
-}
-
-/*
- * Prepare to read connection handshake, or an ack.
- */
-static void prepare_read_banner(struct ceph_connection *con)
-{
-	dout("prepare_read_banner %p\n", con);
-	con->in_base_pos = 0;
-}
-
-static void prepare_read_connect(struct ceph_connection *con)
-{
-	dout("prepare_read_connect %p\n", con);
-	con->in_base_pos = 0;
-}
-
-static void prepare_read_ack(struct ceph_connection *con)
-{
-	dout("prepare_read_ack %p\n", con);
-	con->in_base_pos = 0;
-}
-
-static void prepare_read_seq(struct ceph_connection *con)
-{
-	dout("prepare_read_seq %p\n", con);
-	con->in_base_pos = 0;
-	con->in_tag = CEPH_MSGR_TAG_SEQ;
-}
-
-static void prepare_read_tag(struct ceph_connection *con)
-{
-	dout("prepare_read_tag %p\n", con);
-	con->in_base_pos = 0;
-	con->in_tag = CEPH_MSGR_TAG_READY;
-}
-
-static void prepare_read_keepalive_ack(struct ceph_connection *con)
-{
-	dout("prepare_read_keepalive_ack %p\n", con);
-	con->in_base_pos = 0;
-}
-
-/*
- * Prepare to read a message.
- */
-static int prepare_read_message(struct ceph_connection *con)
-{
-	dout("prepare_read_message %p\n", con);
-	BUG_ON(con->in_msg != NULL);
-	con->in_base_pos = 0;
-	con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0;
-	return 0;
-}
-
-
-static int read_partial(struct ceph_connection *con,
-			int end, int size, void *object)
-{
-	while (con->in_base_pos < end) {
-		int left = end - con->in_base_pos;
-		int have = size - left;
-		int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
-		if (ret <= 0)
-			return ret;
-		con->in_base_pos += ret;
-	}
-	return 1;
-}
-
-
-/*
- * Read all or part of the connect-side handshake on a new connection
- */
-static int read_partial_banner(struct ceph_connection *con)
-{
-	int size;
-	int end;
-	int ret;
-
-	dout("read_partial_banner %p at %d\n", con, con->in_base_pos);
-
-	/* peer's banner */
-	size = strlen(CEPH_BANNER);
-	end = size;
-	ret = read_partial(con, end, size, con->in_banner);
-	if (ret <= 0)
-		goto out;
-
-	size = sizeof (con->actual_peer_addr);
-	end += size;
-	ret = read_partial(con, end, size, &con->actual_peer_addr);
-	if (ret <= 0)
-		goto out;
-	ceph_decode_banner_addr(&con->actual_peer_addr);
-
-	size = sizeof (con->peer_addr_for_me);
-	end += size;
-	ret = read_partial(con, end, size, &con->peer_addr_for_me);
-	if (ret <= 0)
-		goto out;
-	ceph_decode_banner_addr(&con->peer_addr_for_me);
-
-out:
-	return ret;
-}
-
-static int read_partial_connect(struct ceph_connection *con)
-{
-	int size;
-	int end;
-	int ret;
-
-	dout("read_partial_connect %p at %d\n", con, con->in_base_pos);
-
-	size = sizeof (con->in_reply);
-	end = size;
-	ret = read_partial(con, end, size, &con->in_reply);
-	if (ret <= 0)
-		goto out;
-
-	if (con->auth) {
-		size = le32_to_cpu(con->in_reply.authorizer_len);
-		if (size > con->auth->authorizer_reply_buf_len) {
-			pr_err("authorizer reply too big: %d > %zu\n", size,
-			       con->auth->authorizer_reply_buf_len);
-			ret = -EINVAL;
-			goto out;
-		}
-
-		end += size;
-		ret = read_partial(con, end, size,
-				   con->auth->authorizer_reply_buf);
-		if (ret <= 0)
-			goto out;
-	}
-
-	dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n",
-	     con, (int)con->in_reply.tag,
-	     le32_to_cpu(con->in_reply.connect_seq),
-	     le32_to_cpu(con->in_reply.global_seq));
-out:
-	return ret;
-}
 
-/*
- * Verify the hello banner looks okay.
- */
-static int verify_hello(struct ceph_connection *con)
-{
-	if (memcmp(con->in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
-		pr_err("connect to %s got bad banner\n",
-		       ceph_pr_addr(&con->peer_addr));
-		con->error_msg = "protocol error, bad banner";
-		return -1;
-	}
-	return 0;
-}
-
-static bool addr_is_blank(struct ceph_entity_addr *addr)
+bool ceph_addr_is_blank(const struct ceph_entity_addr *addr)
 {
 	struct sockaddr_storage ss = addr->in_addr; /* align */
 	struct in_addr *addr4 = &((struct sockaddr_in *)&ss)->sin_addr;
@@ -1808,7 +1145,7 @@ static bool addr_is_blank(struct ceph_entity_addr *addr)
 	}
 }
 
-static int addr_port(struct ceph_entity_addr *addr)
+int ceph_addr_port(const struct ceph_entity_addr *addr)
 {
 	switch (get_unaligned(&addr->in_addr.ss_family)) {
 	case AF_INET:
@@ -1819,7 +1156,7 @@ static int addr_port(struct ceph_entity_addr *addr)
 	return 0;
 }
 
-static void addr_set_port(struct ceph_entity_addr *addr, int p)
+void ceph_addr_set_port(struct ceph_entity_addr *addr, int p)
 {
 	switch (get_unaligned(&addr->in_addr.ss_family)) {
 	case AF_INET:
@@ -1977,8 +1314,17 @@ int ceph_parse_ips(const char *c, const char *end,
 			port = CEPH_MON_PORT;
 		}
 
-		addr_set_port(&addr[i], port);
+		ceph_addr_set_port(&addr[i], port);
+		/*
+		 * We want the type to be set according to ms_mode
+		 * option, but options are normally parsed after mon
+		 * addresses.  Rather than complicating parsing, set
+		 * to LEGACY and override in build_initial_monmap()
+		 * for mon addresses and ceph_messenger_init() for
+		 * ip option.
+		 */
 		addr[i].type = CEPH_ENTITY_ADDR_TYPE_LEGACY;
+		addr[i].nonce = 0;
 
 		dout("parse_ips got %s\n", ceph_pr_addr(&addr[i]));
 
@@ -2000,521 +1346,12 @@ bad:
 	return ret;
 }
 
-static int process_banner(struct ceph_connection *con)
-{
-	dout("process_banner on %p\n", con);
-
-	if (verify_hello(con) < 0)
-		return -1;
-
-	/*
-	 * Make sure the other end is who we wanted.  note that the other
-	 * end may not yet know their ip address, so if it's 0.0.0.0, give
-	 * them the benefit of the doubt.
-	 */
-	if (memcmp(&con->peer_addr, &con->actual_peer_addr,
-		   sizeof(con->peer_addr)) != 0 &&
-	    !(addr_is_blank(&con->actual_peer_addr) &&
-	      con->actual_peer_addr.nonce == con->peer_addr.nonce)) {
-		pr_warn("wrong peer, want %s/%d, got %s/%d\n",
-			ceph_pr_addr(&con->peer_addr),
-			(int)le32_to_cpu(con->peer_addr.nonce),
-			ceph_pr_addr(&con->actual_peer_addr),
-			(int)le32_to_cpu(con->actual_peer_addr.nonce));
-		con->error_msg = "wrong peer at address";
-		return -1;
-	}
-
-	/*
-	 * did we learn our address?
-	 */
-	if (addr_is_blank(&con->msgr->inst.addr)) {
-		int port = addr_port(&con->msgr->inst.addr);
-
-		memcpy(&con->msgr->inst.addr.in_addr,
-		       &con->peer_addr_for_me.in_addr,
-		       sizeof(con->peer_addr_for_me.in_addr));
-		addr_set_port(&con->msgr->inst.addr, port);
-		encode_my_addr(con->msgr);
-		dout("process_banner learned my addr is %s\n",
-		     ceph_pr_addr(&con->msgr->inst.addr));
-	}
-
-	return 0;
-}
-
-static int process_connect(struct ceph_connection *con)
-{
-	u64 sup_feat = from_msgr(con->msgr)->supported_features;
-	u64 req_feat = from_msgr(con->msgr)->required_features;
-	u64 server_feat = le64_to_cpu(con->in_reply.features);
-	int ret;
-
-	dout("process_connect on %p tag %d\n", con, (int)con->in_tag);
-
-	if (con->auth) {
-		int len = le32_to_cpu(con->in_reply.authorizer_len);
-
-		/*
-		 * Any connection that defines ->get_authorizer()
-		 * should also define ->add_authorizer_challenge() and
-		 * ->verify_authorizer_reply().
-		 *
-		 * See get_connect_authorizer().
-		 */
-		if (con->in_reply.tag == CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) {
-			ret = con->ops->add_authorizer_challenge(
-				    con, con->auth->authorizer_reply_buf, len);
-			if (ret < 0)
-				return ret;
-
-			con_out_kvec_reset(con);
-			__prepare_write_connect(con);
-			prepare_read_connect(con);
-			return 0;
-		}
-
-		if (len) {
-			ret = con->ops->verify_authorizer_reply(con);
-			if (ret < 0) {
-				con->error_msg = "bad authorize reply";
-				return ret;
-			}
-		}
-	}
-
-	switch (con->in_reply.tag) {
-	case CEPH_MSGR_TAG_FEATURES:
-		pr_err("%s%lld %s feature set mismatch,"
-		       " my %llx < server's %llx, missing %llx\n",
-		       ENTITY_NAME(con->peer_name),
-		       ceph_pr_addr(&con->peer_addr),
-		       sup_feat, server_feat, server_feat & ~sup_feat);
-		con->error_msg = "missing required protocol features";
-		reset_connection(con);
-		return -1;
-
-	case CEPH_MSGR_TAG_BADPROTOVER:
-		pr_err("%s%lld %s protocol version mismatch,"
-		       " my %d != server's %d\n",
-		       ENTITY_NAME(con->peer_name),
-		       ceph_pr_addr(&con->peer_addr),
-		       le32_to_cpu(con->out_connect.protocol_version),
-		       le32_to_cpu(con->in_reply.protocol_version));
-		con->error_msg = "protocol version mismatch";
-		reset_connection(con);
-		return -1;
-
-	case CEPH_MSGR_TAG_BADAUTHORIZER:
-		con->auth_retry++;
-		dout("process_connect %p got BADAUTHORIZER attempt %d\n", con,
-		     con->auth_retry);
-		if (con->auth_retry == 2) {
-			con->error_msg = "connect authorization failure";
-			return -1;
-		}
-		con_out_kvec_reset(con);
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			return ret;
-		prepare_read_connect(con);
-		break;
-
-	case CEPH_MSGR_TAG_RESETSESSION:
-		/*
-		 * If we connected with a large connect_seq but the peer
-		 * has no record of a session with us (no connection, or
-		 * connect_seq == 0), they will send RESETSESION to indicate
-		 * that they must have reset their session, and may have
-		 * dropped messages.
-		 */
-		dout("process_connect got RESET peer seq %u\n",
-		     le32_to_cpu(con->in_reply.connect_seq));
-		pr_err("%s%lld %s connection reset\n",
-		       ENTITY_NAME(con->peer_name),
-		       ceph_pr_addr(&con->peer_addr));
-		reset_connection(con);
-		con_out_kvec_reset(con);
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			return ret;
-		prepare_read_connect(con);
-
-		/* Tell ceph about it. */
-		mutex_unlock(&con->mutex);
-		pr_info("reset on %s%lld\n", ENTITY_NAME(con->peer_name));
-		if (con->ops->peer_reset)
-			con->ops->peer_reset(con);
-		mutex_lock(&con->mutex);
-		if (con->state != CON_STATE_NEGOTIATING)
-			return -EAGAIN;
-		break;
-
-	case CEPH_MSGR_TAG_RETRY_SESSION:
-		/*
-		 * If we sent a smaller connect_seq than the peer has, try
-		 * again with a larger value.
-		 */
-		dout("process_connect got RETRY_SESSION my seq %u, peer %u\n",
-		     le32_to_cpu(con->out_connect.connect_seq),
-		     le32_to_cpu(con->in_reply.connect_seq));
-		con->connect_seq = le32_to_cpu(con->in_reply.connect_seq);
-		con_out_kvec_reset(con);
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			return ret;
-		prepare_read_connect(con);
-		break;
-
-	case CEPH_MSGR_TAG_RETRY_GLOBAL:
-		/*
-		 * If we sent a smaller global_seq than the peer has, try
-		 * again with a larger value.
-		 */
-		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
-		     con->peer_global_seq,
-		     le32_to_cpu(con->in_reply.global_seq));
-		get_global_seq(con->msgr,
-			       le32_to_cpu(con->in_reply.global_seq));
-		con_out_kvec_reset(con);
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			return ret;
-		prepare_read_connect(con);
-		break;
-
-	case CEPH_MSGR_TAG_SEQ:
-	case CEPH_MSGR_TAG_READY:
-		if (req_feat & ~server_feat) {
-			pr_err("%s%lld %s protocol feature mismatch,"
-			       " my required %llx > server's %llx, need %llx\n",
-			       ENTITY_NAME(con->peer_name),
-			       ceph_pr_addr(&con->peer_addr),
-			       req_feat, server_feat, req_feat & ~server_feat);
-			con->error_msg = "missing required protocol features";
-			reset_connection(con);
-			return -1;
-		}
-
-		WARN_ON(con->state != CON_STATE_NEGOTIATING);
-		con->state = CON_STATE_OPEN;
-		con->auth_retry = 0;    /* we authenticated; clear flag */
-		con->peer_global_seq = le32_to_cpu(con->in_reply.global_seq);
-		con->connect_seq++;
-		con->peer_features = server_feat;
-		dout("process_connect got READY gseq %d cseq %d (%d)\n",
-		     con->peer_global_seq,
-		     le32_to_cpu(con->in_reply.connect_seq),
-		     con->connect_seq);
-		WARN_ON(con->connect_seq !=
-			le32_to_cpu(con->in_reply.connect_seq));
-
-		if (con->in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
-			con_flag_set(con, CON_FLAG_LOSSYTX);
-
-		con->delay = 0;      /* reset backoff memory */
-
-		if (con->in_reply.tag == CEPH_MSGR_TAG_SEQ) {
-			prepare_write_seq(con);
-			prepare_read_seq(con);
-		} else {
-			prepare_read_tag(con);
-		}
-		break;
-
-	case CEPH_MSGR_TAG_WAIT:
-		/*
-		 * If there is a connection race (we are opening
-		 * connections to each other), one of us may just have
-		 * to WAIT.  This shouldn't happen if we are the
-		 * client.
-		 */
-		con->error_msg = "protocol error, got WAIT as client";
-		return -1;
-
-	default:
-		con->error_msg = "protocol error, garbage tag during connect";
-		return -1;
-	}
-	return 0;
-}
-
-
-/*
- * read (part of) an ack
- */
-static int read_partial_ack(struct ceph_connection *con)
-{
-	int size = sizeof (con->in_temp_ack);
-	int end = size;
-
-	return read_partial(con, end, size, &con->in_temp_ack);
-}
-
-/*
- * We can finally discard anything that's been acked.
- */
-static void process_ack(struct ceph_connection *con)
-{
-	struct ceph_msg *m;
-	u64 ack = le64_to_cpu(con->in_temp_ack);
-	u64 seq;
-	bool reconnect = (con->in_tag == CEPH_MSGR_TAG_SEQ);
-	struct list_head *list = reconnect ? &con->out_queue : &con->out_sent;
-
-	/*
-	 * In the reconnect case, con_fault() has requeued messages
-	 * in out_sent. We should cleanup old messages according to
-	 * the reconnect seq.
-	 */
-	while (!list_empty(list)) {
-		m = list_first_entry(list, struct ceph_msg, list_head);
-		if (reconnect && m->needs_out_seq)
-			break;
-		seq = le64_to_cpu(m->hdr.seq);
-		if (seq > ack)
-			break;
-		dout("got ack for seq %llu type %d at %p\n", seq,
-		     le16_to_cpu(m->hdr.type), m);
-		m->ack_stamp = jiffies;
-		ceph_msg_remove(m);
-	}
-
-	prepare_read_tag(con);
-}
-
-
-static int read_partial_message_section(struct ceph_connection *con,
-					struct kvec *section,
-					unsigned int sec_len, u32 *crc)
-{
-	int ret, left;
-
-	BUG_ON(!section);
-
-	while (section->iov_len < sec_len) {
-		BUG_ON(section->iov_base == NULL);
-		left = sec_len - section->iov_len;
-		ret = ceph_tcp_recvmsg(con->sock, (char *)section->iov_base +
-				       section->iov_len, left);
-		if (ret <= 0)
-			return ret;
-		section->iov_len += ret;
-	}
-	if (section->iov_len == sec_len)
-		*crc = crc32c(0, section->iov_base, section->iov_len);
-
-	return 1;
-}
-
-static int read_partial_msg_data(struct ceph_connection *con)
-{
-	struct ceph_msg *msg = con->in_msg;
-	struct ceph_msg_data_cursor *cursor = &msg->cursor;
-	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
-	struct page *page;
-	size_t page_offset;
-	size_t length;
-	u32 crc = 0;
-	int ret;
-
-	if (!msg->num_data_items)
-		return -EIO;
-
-	if (do_datacrc)
-		crc = con->in_data_crc;
-	while (cursor->total_resid) {
-		if (!cursor->resid) {
-			ceph_msg_data_advance(cursor, 0);
-			continue;
-		}
-
-		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
-		ret = ceph_tcp_recvpage(con->sock, page, page_offset, length);
-		if (ret <= 0) {
-			if (do_datacrc)
-				con->in_data_crc = crc;
-
-			return ret;
-		}
-
-		if (do_datacrc)
-			crc = ceph_crc32c_page(crc, page, page_offset, ret);
-		ceph_msg_data_advance(cursor, (size_t)ret);
-	}
-	if (do_datacrc)
-		con->in_data_crc = crc;
-
-	return 1;	/* must return > 0 to indicate success */
-}
-
-/*
- * read (part of) a message.
- */
-static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip);
-
-static int read_partial_message(struct ceph_connection *con)
-{
-	struct ceph_msg *m = con->in_msg;
-	int size;
-	int end;
-	int ret;
-	unsigned int front_len, middle_len, data_len;
-	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
-	bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH);
-	u64 seq;
-	u32 crc;
-
-	dout("read_partial_message con %p msg %p\n", con, m);
-
-	/* header */
-	size = sizeof (con->in_hdr);
-	end = size;
-	ret = read_partial(con, end, size, &con->in_hdr);
-	if (ret <= 0)
-		return ret;
-
-	crc = crc32c(0, &con->in_hdr, offsetof(struct ceph_msg_header, crc));
-	if (cpu_to_le32(crc) != con->in_hdr.crc) {
-		pr_err("read_partial_message bad hdr crc %u != expected %u\n",
-		       crc, con->in_hdr.crc);
-		return -EBADMSG;
-	}
-
-	front_len = le32_to_cpu(con->in_hdr.front_len);
-	if (front_len > CEPH_MSG_MAX_FRONT_LEN)
-		return -EIO;
-	middle_len = le32_to_cpu(con->in_hdr.middle_len);
-	if (middle_len > CEPH_MSG_MAX_MIDDLE_LEN)
-		return -EIO;
-	data_len = le32_to_cpu(con->in_hdr.data_len);
-	if (data_len > CEPH_MSG_MAX_DATA_LEN)
-		return -EIO;
-
-	/* verify seq# */
-	seq = le64_to_cpu(con->in_hdr.seq);
-	if ((s64)seq - (s64)con->in_seq < 1) {
-		pr_info("skipping %s%lld %s seq %lld expected %lld\n",
-			ENTITY_NAME(con->peer_name),
-			ceph_pr_addr(&con->peer_addr),
-			seq, con->in_seq + 1);
-		con->in_base_pos = -front_len - middle_len - data_len -
-			sizeof_footer(con);
-		con->in_tag = CEPH_MSGR_TAG_READY;
-		return 1;
-	} else if ((s64)seq - (s64)con->in_seq > 1) {
-		pr_err("read_partial_message bad seq %lld expected %lld\n",
-		       seq, con->in_seq + 1);
-		con->error_msg = "bad message sequence # for incoming message";
-		return -EBADE;
-	}
-
-	/* allocate message? */
-	if (!con->in_msg) {
-		int skip = 0;
-
-		dout("got hdr type %d front %d data %d\n", con->in_hdr.type,
-		     front_len, data_len);
-		ret = ceph_con_in_msg_alloc(con, &skip);
-		if (ret < 0)
-			return ret;
-
-		BUG_ON(!con->in_msg ^ skip);
-		if (skip) {
-			/* skip this message */
-			dout("alloc_msg said skip message\n");
-			con->in_base_pos = -front_len - middle_len - data_len -
-				sizeof_footer(con);
-			con->in_tag = CEPH_MSGR_TAG_READY;
-			con->in_seq++;
-			return 1;
-		}
-
-		BUG_ON(!con->in_msg);
-		BUG_ON(con->in_msg->con != con);
-		m = con->in_msg;
-		m->front.iov_len = 0;    /* haven't read it yet */
-		if (m->middle)
-			m->middle->vec.iov_len = 0;
-
-		/* prepare for data payload, if any */
-
-		if (data_len)
-			prepare_message_data(con->in_msg, data_len);
-	}
-
-	/* front */
-	ret = read_partial_message_section(con, &m->front, front_len,
-					   &con->in_front_crc);
-	if (ret <= 0)
-		return ret;
-
-	/* middle */
-	if (m->middle) {
-		ret = read_partial_message_section(con, &m->middle->vec,
-						   middle_len,
-						   &con->in_middle_crc);
-		if (ret <= 0)
-			return ret;
-	}
-
-	/* (page) data */
-	if (data_len) {
-		ret = read_partial_msg_data(con);
-		if (ret <= 0)
-			return ret;
-	}
-
-	/* footer */
-	size = sizeof_footer(con);
-	end += size;
-	ret = read_partial(con, end, size, &m->footer);
-	if (ret <= 0)
-		return ret;
-
-	if (!need_sign) {
-		m->footer.flags = m->old_footer.flags;
-		m->footer.sig = 0;
-	}
-
-	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
-	     m, front_len, m->footer.front_crc, middle_len,
-	     m->footer.middle_crc, data_len, m->footer.data_crc);
-
-	/* crc ok? */
-	if (con->in_front_crc != le32_to_cpu(m->footer.front_crc)) {
-		pr_err("read_partial_message %p front crc %u != exp. %u\n",
-		       m, con->in_front_crc, m->footer.front_crc);
-		return -EBADMSG;
-	}
-	if (con->in_middle_crc != le32_to_cpu(m->footer.middle_crc)) {
-		pr_err("read_partial_message %p middle crc %u != exp %u\n",
-		       m, con->in_middle_crc, m->footer.middle_crc);
-		return -EBADMSG;
-	}
-	if (do_datacrc &&
-	    (m->footer.flags & CEPH_MSG_FOOTER_NOCRC) == 0 &&
-	    con->in_data_crc != le32_to_cpu(m->footer.data_crc)) {
-		pr_err("read_partial_message %p data crc %u != exp. %u\n", m,
-		       con->in_data_crc, le32_to_cpu(m->footer.data_crc));
-		return -EBADMSG;
-	}
-
-	if (need_sign && con->ops->check_message_signature &&
-	    con->ops->check_message_signature(m)) {
-		pr_err("read_partial_message %p signature check failed\n", m);
-		return -EBADMSG;
-	}
-
-	return 1; /* done! */
-}
-
 /*
  * Process message.  This happens in the worker thread.  The callback should
  * be careful not to do anything that waits on other incoming messages or it
  * may deadlock.
  */
-static void process_message(struct ceph_connection *con)
+void ceph_con_process_message(struct ceph_connection *con)
 {
 	struct ceph_msg *msg = con->in_msg;
 
@@ -2528,12 +1365,13 @@ static void process_message(struct ceph_connection *con)
 	con->in_seq++;
 	mutex_unlock(&con->mutex);
 
-	dout("===== %p %llu from %s%lld %d=%s len %d+%d (%u %u %u) =====\n",
+	dout("===== %p %llu from %s%lld %d=%s len %d+%d+%d (%u %u %u) =====\n",
 	     msg, le64_to_cpu(msg->hdr.seq),
 	     ENTITY_NAME(msg->hdr.src),
 	     le16_to_cpu(msg->hdr.type),
 	     ceph_msg_type_name(le16_to_cpu(msg->hdr.type)),
 	     le32_to_cpu(msg->hdr.front_len),
+	     le32_to_cpu(msg->hdr.middle_len),
 	     le32_to_cpu(msg->hdr.data_len),
 	     con->in_front_crc, con->in_middle_crc, con->in_data_crc);
 	con->ops->dispatch(con, msg);
@@ -2541,264 +1379,6 @@ static void process_message(struct ceph_connection *con)
 	mutex_lock(&con->mutex);
 }
 
-static int read_keepalive_ack(struct ceph_connection *con)
-{
-	struct ceph_timespec ceph_ts;
-	size_t size = sizeof(ceph_ts);
-	int ret = read_partial(con, size, size, &ceph_ts);
-	if (ret <= 0)
-		return ret;
-	ceph_decode_timespec64(&con->last_keepalive_ack, &ceph_ts);
-	prepare_read_tag(con);
-	return 1;
-}
-
-/*
- * Write something to the socket.  Called in a worker thread when the
- * socket appears to be writeable and we have something ready to send.
- */
-static int try_write(struct ceph_connection *con)
-{
-	int ret = 1;
-
-	dout("try_write start %p state %lu\n", con, con->state);
-	if (con->state != CON_STATE_PREOPEN &&
-	    con->state != CON_STATE_CONNECTING &&
-	    con->state != CON_STATE_NEGOTIATING &&
-	    con->state != CON_STATE_OPEN)
-		return 0;
-
-	/* open the socket first? */
-	if (con->state == CON_STATE_PREOPEN) {
-		BUG_ON(con->sock);
-		con->state = CON_STATE_CONNECTING;
-
-		con_out_kvec_reset(con);
-		prepare_write_banner(con);
-		prepare_read_banner(con);
-
-		BUG_ON(con->in_msg);
-		con->in_tag = CEPH_MSGR_TAG_READY;
-		dout("try_write initiating connect on %p new state %lu\n",
-		     con, con->state);
-		ret = ceph_tcp_connect(con);
-		if (ret < 0) {
-			con->error_msg = "connect error";
-			goto out;
-		}
-	}
-
-more:
-	dout("try_write out_kvec_bytes %d\n", con->out_kvec_bytes);
-	BUG_ON(!con->sock);
-
-	/* kvec data queued? */
-	if (con->out_kvec_left) {
-		ret = write_partial_kvec(con);
-		if (ret <= 0)
-			goto out;
-	}
-	if (con->out_skip) {
-		ret = write_partial_skip(con);
-		if (ret <= 0)
-			goto out;
-	}
-
-	/* msg pages? */
-	if (con->out_msg) {
-		if (con->out_msg_done) {
-			ceph_msg_put(con->out_msg);
-			con->out_msg = NULL;   /* we're done with this one */
-			goto do_next;
-		}
-
-		ret = write_partial_message_data(con);
-		if (ret == 1)
-			goto more;  /* we need to send the footer, too! */
-		if (ret == 0)
-			goto out;
-		if (ret < 0) {
-			dout("try_write write_partial_message_data err %d\n",
-			     ret);
-			goto out;
-		}
-	}
-
-do_next:
-	if (con->state == CON_STATE_OPEN) {
-		if (con_flag_test_and_clear(con, CON_FLAG_KEEPALIVE_PENDING)) {
-			prepare_write_keepalive(con);
-			goto more;
-		}
-		/* is anything else pending? */
-		if (!list_empty(&con->out_queue)) {
-			prepare_write_message(con);
-			goto more;
-		}
-		if (con->in_seq > con->in_seq_acked) {
-			prepare_write_ack(con);
-			goto more;
-		}
-	}
-
-	/* Nothing to do! */
-	con_flag_clear(con, CON_FLAG_WRITE_PENDING);
-	dout("try_write nothing else to write.\n");
-	ret = 0;
-out:
-	dout("try_write done on %p ret %d\n", con, ret);
-	return ret;
-}
-
-/*
- * Read what we can from the socket.
- */
-static int try_read(struct ceph_connection *con)
-{
-	int ret = -1;
-
-more:
-	dout("try_read start on %p state %lu\n", con, con->state);
-	if (con->state != CON_STATE_CONNECTING &&
-	    con->state != CON_STATE_NEGOTIATING &&
-	    con->state != CON_STATE_OPEN)
-		return 0;
-
-	BUG_ON(!con->sock);
-
-	dout("try_read tag %d in_base_pos %d\n", (int)con->in_tag,
-	     con->in_base_pos);
-
-	if (con->state == CON_STATE_CONNECTING) {
-		dout("try_read connecting\n");
-		ret = read_partial_banner(con);
-		if (ret <= 0)
-			goto out;
-		ret = process_banner(con);
-		if (ret < 0)
-			goto out;
-
-		con->state = CON_STATE_NEGOTIATING;
-
-		/*
-		 * Received banner is good, exchange connection info.
-		 * Do not reset out_kvec, as sending our banner raced
-		 * with receiving peer banner after connect completed.
-		 */
-		ret = prepare_write_connect(con);
-		if (ret < 0)
-			goto out;
-		prepare_read_connect(con);
-
-		/* Send connection info before awaiting response */
-		goto out;
-	}
-
-	if (con->state == CON_STATE_NEGOTIATING) {
-		dout("try_read negotiating\n");
-		ret = read_partial_connect(con);
-		if (ret <= 0)
-			goto out;
-		ret = process_connect(con);
-		if (ret < 0)
-			goto out;
-		goto more;
-	}
-
-	WARN_ON(con->state != CON_STATE_OPEN);
-
-	if (con->in_base_pos < 0) {
-		/*
-		 * skipping + discarding content.
-		 */
-		ret = ceph_tcp_recvmsg(con->sock, NULL, -con->in_base_pos);
-		if (ret <= 0)
-			goto out;
-		dout("skipped %d / %d bytes\n", ret, -con->in_base_pos);
-		con->in_base_pos += ret;
-		if (con->in_base_pos)
-			goto more;
-	}
-	if (con->in_tag == CEPH_MSGR_TAG_READY) {
-		/*
-		 * what's next?
-		 */
-		ret = ceph_tcp_recvmsg(con->sock, &con->in_tag, 1);
-		if (ret <= 0)
-			goto out;
-		dout("try_read got tag %d\n", (int)con->in_tag);
-		switch (con->in_tag) {
-		case CEPH_MSGR_TAG_MSG:
-			prepare_read_message(con);
-			break;
-		case CEPH_MSGR_TAG_ACK:
-			prepare_read_ack(con);
-			break;
-		case CEPH_MSGR_TAG_KEEPALIVE2_ACK:
-			prepare_read_keepalive_ack(con);
-			break;
-		case CEPH_MSGR_TAG_CLOSE:
-			con_close_socket(con);
-			con->state = CON_STATE_CLOSED;
-			goto out;
-		default:
-			goto bad_tag;
-		}
-	}
-	if (con->in_tag == CEPH_MSGR_TAG_MSG) {
-		ret = read_partial_message(con);
-		if (ret <= 0) {
-			switch (ret) {
-			case -EBADMSG:
-				con->error_msg = "bad crc/signature";
-				fallthrough;
-			case -EBADE:
-				ret = -EIO;
-				break;
-			case -EIO:
-				con->error_msg = "io error";
-				break;
-			}
-			goto out;
-		}
-		if (con->in_tag == CEPH_MSGR_TAG_READY)
-			goto more;
-		process_message(con);
-		if (con->state == CON_STATE_OPEN)
-			prepare_read_tag(con);
-		goto more;
-	}
-	if (con->in_tag == CEPH_MSGR_TAG_ACK ||
-	    con->in_tag == CEPH_MSGR_TAG_SEQ) {
-		/*
-		 * the final handshake seq exchange is semantically
-		 * equivalent to an ACK
-		 */
-		ret = read_partial_ack(con);
-		if (ret <= 0)
-			goto out;
-		process_ack(con);
-		goto more;
-	}
-	if (con->in_tag == CEPH_MSGR_TAG_KEEPALIVE2_ACK) {
-		ret = read_keepalive_ack(con);
-		if (ret <= 0)
-			goto out;
-		goto more;
-	}
-
-out:
-	dout("try_read done on %p ret %d\n", con, ret);
-	return ret;
-
-bad_tag:
-	pr_err("try_read bad con->in_tag = %d\n", (int)con->in_tag);
-	con->error_msg = "protocol error, garbage tag";
-	ret = -1;
-	goto out;
-}
-
-
 /*
  * Atomically queue work on a connection after the specified delay.
  * Bump @con reference to avoid races with connection teardown.
@@ -2811,13 +1391,16 @@ static int queue_con_delay(struct ceph_connection *con, unsigned long delay)
 		return -ENOENT;
 	}
 
+	if (delay >= HZ)
+		delay = round_jiffies_relative(delay);
+
+	dout("%s %p %lu\n", __func__, con, delay);
 	if (!queue_delayed_work(ceph_msgr_wq, &con->work, delay)) {
 		dout("%s %p - already queued\n", __func__, con);
 		con->ops->put(con);
 		return -EBUSY;
 	}
 
-	dout("%s %p %lu\n", __func__, con, delay);
 	return 0;
 }
 
@@ -2836,27 +1419,30 @@ static void cancel_con(struct ceph_connection *con)
 
 static bool con_sock_closed(struct ceph_connection *con)
 {
-	if (!con_flag_test_and_clear(con, CON_FLAG_SOCK_CLOSED))
+	if (!ceph_con_flag_test_and_clear(con, CEPH_CON_F_SOCK_CLOSED))
 		return false;
 
 #define CASE(x)								\
-	case CON_STATE_ ## x:						\
+	case CEPH_CON_S_ ## x:						\
 		con->error_msg = "socket closed (con state " #x ")";	\
 		break;
 
 	switch (con->state) {
 	CASE(CLOSED);
 	CASE(PREOPEN);
-	CASE(CONNECTING);
-	CASE(NEGOTIATING);
+	CASE(V1_BANNER);
+	CASE(V1_CONNECT_MSG);
+	CASE(V2_BANNER_PREFIX);
+	CASE(V2_BANNER_PAYLOAD);
+	CASE(V2_HELLO);
+	CASE(V2_AUTH);
+	CASE(V2_AUTH_SIGNATURE);
+	CASE(V2_SESSION_CONNECT);
+	CASE(V2_SESSION_RECONNECT);
 	CASE(OPEN);
 	CASE(STANDBY);
 	default:
-		pr_warn("%s con %p unrecognized state %lu\n",
-			__func__, con, con->state);
-		con->error_msg = "unrecognized con state";
 		BUG();
-		break;
 	}
 #undef CASE
 
@@ -2867,15 +1453,15 @@ static bool con_backoff(struct ceph_connection *con)
 {
 	int ret;
 
-	if (!con_flag_test_and_clear(con, CON_FLAG_BACKOFF))
+	if (!ceph_con_flag_test_and_clear(con, CEPH_CON_F_BACKOFF))
 		return false;
 
-	ret = queue_con_delay(con, round_jiffies_relative(con->delay));
+	ret = queue_con_delay(con, con->delay);
 	if (ret) {
 		dout("%s: con %p FAILED to back off %lu\n", __func__,
 			con, con->delay);
 		BUG_ON(ret == -ENOENT);
-		con_flag_set(con, CON_FLAG_BACKOFF);
+		ceph_con_flag_set(con, CEPH_CON_F_BACKOFF);
 	}
 
 	return true;
@@ -2891,11 +1477,11 @@ static void con_fault_finish(struct ceph_connection *con)
 	 * in case we faulted due to authentication, invalidate our
 	 * current tickets so that we can get new ones.
 	 */
-	if (con->auth_retry) {
-		dout("auth_retry %d, invalidating\n", con->auth_retry);
+	if (con->v1.auth_retry) {
+		dout("auth_retry %d, invalidating\n", con->v1.auth_retry);
 		if (con->ops->invalidate_authorizer)
 			con->ops->invalidate_authorizer(con);
-		con->auth_retry = 0;
+		con->v1.auth_retry = 0;
 	}
 
 	if (con->ops->fault)
@@ -2923,21 +1509,24 @@ static void ceph_con_workfn(struct work_struct *work)
 			dout("%s: con %p BACKOFF\n", __func__, con);
 			break;
 		}
-		if (con->state == CON_STATE_STANDBY) {
+		if (con->state == CEPH_CON_S_STANDBY) {
 			dout("%s: con %p STANDBY\n", __func__, con);
 			break;
 		}
-		if (con->state == CON_STATE_CLOSED) {
+		if (con->state == CEPH_CON_S_CLOSED) {
 			dout("%s: con %p CLOSED\n", __func__, con);
 			BUG_ON(con->sock);
 			break;
 		}
-		if (con->state == CON_STATE_PREOPEN) {
+		if (con->state == CEPH_CON_S_PREOPEN) {
 			dout("%s: con %p PREOPEN\n", __func__, con);
 			BUG_ON(con->sock);
 		}
 
-		ret = try_read(con);
+		if (ceph_msgr2(from_msgr(con->msgr)))
+			ret = ceph_con_v2_try_read(con);
+		else
+			ret = ceph_con_v1_try_read(con);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				continue;
@@ -2947,7 +1536,10 @@ static void ceph_con_workfn(struct work_struct *work)
 			break;
 		}
 
-		ret = try_write(con);
+		if (ceph_msgr2(from_msgr(con->msgr)))
+			ret = ceph_con_v2_try_write(con);
+		else
+			ret = ceph_con_v1_try_write(con);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				continue;
@@ -2974,59 +1566,54 @@ static void ceph_con_workfn(struct work_struct *work)
  */
 static void con_fault(struct ceph_connection *con)
 {
-	dout("fault %p state %lu to peer %s\n",
+	dout("fault %p state %d to peer %s\n",
 	     con, con->state, ceph_pr_addr(&con->peer_addr));
 
 	pr_warn("%s%lld %s %s\n", ENTITY_NAME(con->peer_name),
 		ceph_pr_addr(&con->peer_addr), con->error_msg);
 	con->error_msg = NULL;
 
-	WARN_ON(con->state != CON_STATE_CONNECTING &&
-	       con->state != CON_STATE_NEGOTIATING &&
-	       con->state != CON_STATE_OPEN);
+	WARN_ON(con->state == CEPH_CON_S_STANDBY ||
+		con->state == CEPH_CON_S_CLOSED);
 
-	con_close_socket(con);
+	ceph_con_reset_protocol(con);
 
-	if (con_flag_test(con, CON_FLAG_LOSSYTX)) {
+	if (ceph_con_flag_test(con, CEPH_CON_F_LOSSYTX)) {
 		dout("fault on LOSSYTX channel, marking CLOSED\n");
-		con->state = CON_STATE_CLOSED;
+		con->state = CEPH_CON_S_CLOSED;
 		return;
 	}
 
-	if (con->in_msg) {
-		BUG_ON(con->in_msg->con != con);
-		ceph_msg_put(con->in_msg);
-		con->in_msg = NULL;
-	}
-
 	/* Requeue anything that hasn't been acked */
 	list_splice_init(&con->out_sent, &con->out_queue);
 
 	/* If there are no messages queued or keepalive pending, place
 	 * the connection in a STANDBY state */
 	if (list_empty(&con->out_queue) &&
-	    !con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING)) {
+	    !ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)) {
 		dout("fault %p setting STANDBY clearing WRITE_PENDING\n", con);
-		con_flag_clear(con, CON_FLAG_WRITE_PENDING);
-		con->state = CON_STATE_STANDBY;
+		ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+		con->state = CEPH_CON_S_STANDBY;
 	} else {
 		/* retry after a delay. */
-		con->state = CON_STATE_PREOPEN;
-		if (con->delay == 0)
+		con->state = CEPH_CON_S_PREOPEN;
+		if (!con->delay) {
 			con->delay = BASE_DELAY_INTERVAL;
-		else if (con->delay < MAX_DELAY_INTERVAL)
+		} else if (con->delay < MAX_DELAY_INTERVAL) {
 			con->delay *= 2;
-		con_flag_set(con, CON_FLAG_BACKOFF);
+			if (con->delay > MAX_DELAY_INTERVAL)
+				con->delay = MAX_DELAY_INTERVAL;
+		}
+		ceph_con_flag_set(con, CEPH_CON_F_BACKOFF);
 		queue_con(con);
 	}
 }
 
-
 void ceph_messenger_reset_nonce(struct ceph_messenger *msgr)
 {
 	u32 nonce = le32_to_cpu(msgr->inst.addr.nonce) + 1000000;
 	msgr->inst.addr.nonce = cpu_to_le32(nonce);
-	encode_my_addr(msgr);
+	ceph_encode_my_addr(msgr);
 }
 
 /*
@@ -3037,26 +1624,35 @@ void ceph_messenger_init(struct ceph_messenger *msgr,
 {
 	spin_lock_init(&msgr->global_seq_lock);
 
-	if (myaddr)
-		msgr->inst.addr = *myaddr;
+	if (myaddr) {
+		memcpy(&msgr->inst.addr.in_addr, &myaddr->in_addr,
+		       sizeof(msgr->inst.addr.in_addr));
+		ceph_addr_set_port(&msgr->inst.addr, 0);
+	}
 
-	/* select a random nonce */
-	msgr->inst.addr.type = 0;
-	get_random_bytes(&msgr->inst.addr.nonce, sizeof(msgr->inst.addr.nonce));
-	encode_my_addr(msgr);
+	/*
+	 * Since nautilus, clients are identified using type ANY.
+	 * For msgr1, ceph_encode_banner_addr() munges it to NONE.
+	 */
+	msgr->inst.addr.type = CEPH_ENTITY_ADDR_TYPE_ANY;
+
+	/* generate a random non-zero nonce */
+	do {
+		get_random_bytes(&msgr->inst.addr.nonce,
+				 sizeof(msgr->inst.addr.nonce));
+	} while (!msgr->inst.addr.nonce);
+	ceph_encode_my_addr(msgr);
 
 	atomic_set(&msgr->stopping, 0);
 	write_pnet(&msgr->net, get_net(current->nsproxy->net_ns));
 
 	dout("%s %p\n", __func__, msgr);
 }
-EXPORT_SYMBOL(ceph_messenger_init);
 
 void ceph_messenger_fini(struct ceph_messenger *msgr)
 {
 	put_net(read_pnet(&msgr->net));
 }
-EXPORT_SYMBOL(ceph_messenger_fini);
 
 static void msg_con_set(struct ceph_msg *msg, struct ceph_connection *con)
 {
@@ -3070,17 +1666,19 @@ static void msg_con_set(struct ceph_msg *msg, struct ceph_connection *con)
 static void clear_standby(struct ceph_connection *con)
 {
 	/* come back from STANDBY? */
-	if (con->state == CON_STATE_STANDBY) {
+	if (con->state == CEPH_CON_S_STANDBY) {
 		dout("clear_standby %p and ++connect_seq\n", con);
-		con->state = CON_STATE_PREOPEN;
-		con->connect_seq++;
-		WARN_ON(con_flag_test(con, CON_FLAG_WRITE_PENDING));
-		WARN_ON(con_flag_test(con, CON_FLAG_KEEPALIVE_PENDING));
+		con->state = CEPH_CON_S_PREOPEN;
+		con->v1.connect_seq++;
+		WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING));
+		WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING));
 	}
 }
 
 /*
  * Queue up an outgoing message on the given connection.
+ *
+ * Consumes a ref on @msg.
  */
 void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 {
@@ -3091,7 +1689,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 
 	mutex_lock(&con->mutex);
 
-	if (con->state == CON_STATE_CLOSED) {
+	if (con->state == CEPH_CON_S_CLOSED) {
 		dout("con_send %p closed, dropping %p\n", con, msg);
 		ceph_msg_put(msg);
 		mutex_unlock(&con->mutex);
@@ -3114,7 +1712,7 @@ void ceph_con_send(struct ceph_connection *con, struct ceph_msg *msg)
 
 	/* if there wasn't anything waiting to send before, queue
 	 * new work */
-	if (con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0)
+	if (!ceph_con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING))
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_send);
@@ -3132,36 +1730,30 @@ void ceph_msg_revoke(struct ceph_msg *msg)
 	}
 
 	mutex_lock(&con->mutex);
-	if (!list_empty(&msg->list_head)) {
-		dout("%s %p msg %p - was on queue\n", __func__, con, msg);
-		list_del_init(&msg->list_head);
-		msg->hdr.seq = 0;
-
-		ceph_msg_put(msg);
+	if (list_empty(&msg->list_head)) {
+		WARN_ON(con->out_msg == msg);
+		dout("%s con %p msg %p not linked\n", __func__, con, msg);
+		mutex_unlock(&con->mutex);
+		return;
 	}
+
+	dout("%s con %p msg %p was linked\n", __func__, con, msg);
+	msg->hdr.seq = 0;
+	ceph_msg_remove(msg);
+
 	if (con->out_msg == msg) {
-		BUG_ON(con->out_skip);
-		/* footer */
-		if (con->out_msg_done) {
-			con->out_skip += con_out_kvec_skip(con);
-		} else {
-			BUG_ON(!msg->data_length);
-			con->out_skip += sizeof_footer(con);
-		}
-		/* data, middle, front */
-		if (msg->data_length)
-			con->out_skip += msg->cursor.total_resid;
-		if (msg->middle)
-			con->out_skip += con_out_kvec_skip(con);
-		con->out_skip += con_out_kvec_skip(con);
-
-		dout("%s %p msg %p - was sending, will write %d skip %d\n",
-		     __func__, con, msg, con->out_kvec_bytes, con->out_skip);
-		msg->hdr.seq = 0;
+		WARN_ON(con->state != CEPH_CON_S_OPEN);
+		dout("%s con %p msg %p was sending\n", __func__, con, msg);
+		if (ceph_msgr2(from_msgr(con->msgr)))
+			ceph_con_v2_revoke(con);
+		else
+			ceph_con_v1_revoke(con);
+		ceph_msg_put(con->out_msg);
 		con->out_msg = NULL;
-		ceph_msg_put(msg);
+	} else {
+		dout("%s con %p msg %p not current, out_msg %p\n", __func__,
+		     con, msg, con->out_msg);
 	}
-
 	mutex_unlock(&con->mutex);
 }
 
@@ -3179,25 +1771,17 @@ void ceph_msg_revoke_incoming(struct ceph_msg *msg)
 
 	mutex_lock(&con->mutex);
 	if (con->in_msg == msg) {
-		unsigned int front_len = le32_to_cpu(con->in_hdr.front_len);
-		unsigned int middle_len = le32_to_cpu(con->in_hdr.middle_len);
-		unsigned int data_len = le32_to_cpu(con->in_hdr.data_len);
-
-		/* skip rest of message */
-		dout("%s %p msg %p revoked\n", __func__, con, msg);
-		con->in_base_pos = con->in_base_pos -
-				sizeof(struct ceph_msg_header) -
-				front_len -
-				middle_len -
-				data_len -
-				sizeof(struct ceph_msg_footer);
+		WARN_ON(con->state != CEPH_CON_S_OPEN);
+		dout("%s con %p msg %p was recving\n", __func__, con, msg);
+		if (ceph_msgr2(from_msgr(con->msgr)))
+			ceph_con_v2_revoke_incoming(con);
+		else
+			ceph_con_v1_revoke_incoming(con);
 		ceph_msg_put(con->in_msg);
 		con->in_msg = NULL;
-		con->in_tag = CEPH_MSGR_TAG_READY;
-		con->in_seq++;
 	} else {
-		dout("%s %p in_msg %p msg %p no-op\n",
-		     __func__, con, con->in_msg, msg);
+		dout("%s con %p msg %p not current, in_msg %p\n", __func__,
+		     con, msg, con->in_msg);
 	}
 	mutex_unlock(&con->mutex);
 }
@@ -3210,10 +1794,10 @@ void ceph_con_keepalive(struct ceph_connection *con)
 	dout("con_keepalive %p\n", con);
 	mutex_lock(&con->mutex);
 	clear_standby(con);
-	con_flag_set(con, CON_FLAG_KEEPALIVE_PENDING);
+	ceph_con_flag_set(con, CEPH_CON_F_KEEPALIVE_PENDING);
 	mutex_unlock(&con->mutex);
 
-	if (con_flag_test_and_set(con, CON_FLAG_WRITE_PENDING) == 0)
+	if (!ceph_con_flag_test_and_set(con, CEPH_CON_F_WRITE_PENDING))
 		queue_con(con);
 }
 EXPORT_SYMBOL(ceph_con_keepalive);
@@ -3419,9 +2003,9 @@ static int ceph_alloc_middle(struct ceph_connection *con, struct ceph_msg *msg)
  * On error (ENOMEM, EAGAIN, ...),
  *  - con->in_msg == NULL
  */
-static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
+int ceph_con_in_msg_alloc(struct ceph_connection *con,
+			  struct ceph_msg_header *hdr, int *skip)
 {
-	struct ceph_msg_header *hdr = &con->in_hdr;
 	int middle_len = le32_to_cpu(hdr->middle_len);
 	struct ceph_msg *msg;
 	int ret = 0;
@@ -3432,7 +2016,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 	mutex_unlock(&con->mutex);
 	msg = con->ops->alloc_msg(con, hdr, skip);
 	mutex_lock(&con->mutex);
-	if (con->state != CON_STATE_OPEN) {
+	if (con->state != CEPH_CON_S_OPEN) {
 		if (msg)
 			ceph_msg_put(msg);
 		return -EAGAIN;
@@ -3453,7 +2037,7 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 		con->error_msg = "error allocating memory for incoming message";
 		return -ENOMEM;
 	}
-	memcpy(&con->in_msg->hdr, &con->in_hdr, sizeof(con->in_hdr));
+	memcpy(&con->in_msg->hdr, hdr, sizeof(*hdr));
 
 	if (middle_len && !con->in_msg->middle) {
 		ret = ceph_alloc_middle(con, con->in_msg);
@@ -3466,6 +2050,39 @@ static int ceph_con_in_msg_alloc(struct ceph_connection *con, int *skip)
 	return ret;
 }
 
+void ceph_con_get_out_msg(struct ceph_connection *con)
+{
+	struct ceph_msg *msg;
+
+	BUG_ON(list_empty(&con->out_queue));
+	msg = list_first_entry(&con->out_queue, struct ceph_msg, list_head);
+	WARN_ON(msg->con != con);
+
+	/*
+	 * Put the message on "sent" list using a ref from ceph_con_send().
+	 * It is put when the message is acked or revoked.
+	 */
+	list_move_tail(&msg->list_head, &con->out_sent);
+
+	/*
+	 * Only assign outgoing seq # if we haven't sent this message
+	 * yet.  If it is requeued, resend with it's original seq.
+	 */
+	if (msg->needs_out_seq) {
+		msg->hdr.seq = cpu_to_le64(++con->out_seq);
+		msg->needs_out_seq = false;
+
+		if (con->ops->reencode_message)
+			con->ops->reencode_message(msg);
+	}
+
+	/*
+	 * Get a ref for out_msg.  It is put when we are done sending the
+	 * message or in case of a fault.
+	 */
+	WARN_ON(con->out_msg);
+	con->out_msg = ceph_msg_get(msg);
+}
 
 /*
  * Free a generically kmalloc'd message.
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c
new file mode 100644
index 000000000000..2cb5ffdf071a
--- /dev/null
+++ b/net/ceph/messenger_v1.c
@@ -0,0 +1,1506 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ceph/ceph_debug.h>
+
+#include <linux/bvec.h>
+#include <linux/crc32c.h>
+#include <linux/net.h>
+#include <linux/socket.h>
+#include <net/sock.h>
+
+#include <linux/ceph/ceph_features.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+
+/* static tag bytes (protocol control messages) */
+static char tag_msg = CEPH_MSGR_TAG_MSG;
+static char tag_ack = CEPH_MSGR_TAG_ACK;
+static char tag_keepalive = CEPH_MSGR_TAG_KEEPALIVE;
+static char tag_keepalive2 = CEPH_MSGR_TAG_KEEPALIVE2;
+
+/*
+ * If @buf is NULL, discard up to @len bytes.
+ */
+static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
+{
+	struct kvec iov = {buf, len};
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+	int r;
+
+	if (!buf)
+		msg.msg_flags |= MSG_TRUNC;
+
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len);
+	r = sock_recvmsg(sock, &msg, msg.msg_flags);
+	if (r == -EAGAIN)
+		r = 0;
+	return r;
+}
+
+static int ceph_tcp_recvpage(struct socket *sock, struct page *page,
+		     int page_offset, size_t length)
+{
+	struct bio_vec bvec = {
+		.bv_page = page,
+		.bv_offset = page_offset,
+		.bv_len = length
+	};
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+	int r;
+
+	BUG_ON(page_offset + length > PAGE_SIZE);
+	iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length);
+	r = sock_recvmsg(sock, &msg, msg.msg_flags);
+	if (r == -EAGAIN)
+		r = 0;
+	return r;
+}
+
+/*
+ * write something.  @more is true if caller will be sending more data
+ * shortly.
+ */
+static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov,
+			    size_t kvlen, size_t len, bool more)
+{
+	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL };
+	int r;
+
+	if (more)
+		msg.msg_flags |= MSG_MORE;
+	else
+		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */
+
+	r = kernel_sendmsg(sock, &msg, iov, kvlen, len);
+	if (r == -EAGAIN)
+		r = 0;
+	return r;
+}
+
+/*
+ * @more: either or both of MSG_MORE and MSG_SENDPAGE_NOTLAST
+ */
+static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
+			     int offset, size_t size, int more)
+{
+	ssize_t (*sendpage)(struct socket *sock, struct page *page,
+			    int offset, size_t size, int flags);
+	int flags = MSG_DONTWAIT | MSG_NOSIGNAL | more;
+	int ret;
+
+	/*
+	 * sendpage cannot properly handle pages with page_count == 0,
+	 * we need to fall back to sendmsg if that's the case.
+	 *
+	 * Same goes for slab pages: skb_can_coalesce() allows
+	 * coalescing neighboring slab objects into a single frag which
+	 * triggers one of hardened usercopy checks.
+	 */
+	if (sendpage_ok(page))
+		sendpage = sock->ops->sendpage;
+	else
+		sendpage = sock_no_sendpage;
+
+	ret = sendpage(sock, page, offset, size, flags);
+	if (ret == -EAGAIN)
+		ret = 0;
+
+	return ret;
+}
+
+static void con_out_kvec_reset(struct ceph_connection *con)
+{
+	BUG_ON(con->v1.out_skip);
+
+	con->v1.out_kvec_left = 0;
+	con->v1.out_kvec_bytes = 0;
+	con->v1.out_kvec_cur = &con->v1.out_kvec[0];
+}
+
+static void con_out_kvec_add(struct ceph_connection *con,
+				size_t size, void *data)
+{
+	int index = con->v1.out_kvec_left;
+
+	BUG_ON(con->v1.out_skip);
+	BUG_ON(index >= ARRAY_SIZE(con->v1.out_kvec));
+
+	con->v1.out_kvec[index].iov_len = size;
+	con->v1.out_kvec[index].iov_base = data;
+	con->v1.out_kvec_left++;
+	con->v1.out_kvec_bytes += size;
+}
+
+/*
+ * Chop off a kvec from the end.  Return residual number of bytes for
+ * that kvec, i.e. how many bytes would have been written if the kvec
+ * hadn't been nuked.
+ */
+static int con_out_kvec_skip(struct ceph_connection *con)
+{
+	int skip = 0;
+
+	if (con->v1.out_kvec_bytes > 0) {
+		skip = con->v1.out_kvec_cur[con->v1.out_kvec_left - 1].iov_len;
+		BUG_ON(con->v1.out_kvec_bytes < skip);
+		BUG_ON(!con->v1.out_kvec_left);
+		con->v1.out_kvec_bytes -= skip;
+		con->v1.out_kvec_left--;
+	}
+
+	return skip;
+}
+
+static size_t sizeof_footer(struct ceph_connection *con)
+{
+	return (con->peer_features & CEPH_FEATURE_MSG_AUTH) ?
+	    sizeof(struct ceph_msg_footer) :
+	    sizeof(struct ceph_msg_footer_old);
+}
+
+static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
+{
+	/* Initialize data cursor */
+
+	ceph_msg_data_cursor_init(&msg->cursor, msg, data_len);
+}
+
+/*
+ * Prepare footer for currently outgoing message, and finish things
+ * off.  Assumes out_kvec* are already valid.. we just add on to the end.
+ */
+static void prepare_write_message_footer(struct ceph_connection *con)
+{
+	struct ceph_msg *m = con->out_msg;
+
+	m->footer.flags |= CEPH_MSG_FOOTER_COMPLETE;
+
+	dout("prepare_write_message_footer %p\n", con);
+	con_out_kvec_add(con, sizeof_footer(con), &m->footer);
+	if (con->peer_features & CEPH_FEATURE_MSG_AUTH) {
+		if (con->ops->sign_message)
+			con->ops->sign_message(m);
+		else
+			m->footer.sig = 0;
+	} else {
+		m->old_footer.flags = m->footer.flags;
+	}
+	con->v1.out_more = m->more_to_follow;
+	con->v1.out_msg_done = true;
+}
+
+/*
+ * Prepare headers for the next outgoing message.
+ */
+static void prepare_write_message(struct ceph_connection *con)
+{
+	struct ceph_msg *m;
+	u32 crc;
+
+	con_out_kvec_reset(con);
+	con->v1.out_msg_done = false;
+
+	/* Sneak an ack in there first?  If we can get it into the same
+	 * TCP packet that's a good thing. */
+	if (con->in_seq > con->in_seq_acked) {
+		con->in_seq_acked = con->in_seq;
+		con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+		con->v1.out_temp_ack = cpu_to_le64(con->in_seq_acked);
+		con_out_kvec_add(con, sizeof(con->v1.out_temp_ack),
+			&con->v1.out_temp_ack);
+	}
+
+	ceph_con_get_out_msg(con);
+	m = con->out_msg;
+
+	dout("prepare_write_message %p seq %lld type %d len %d+%d+%zd\n",
+	     m, con->out_seq, le16_to_cpu(m->hdr.type),
+	     le32_to_cpu(m->hdr.front_len), le32_to_cpu(m->hdr.middle_len),
+	     m->data_length);
+	WARN_ON(m->front.iov_len != le32_to_cpu(m->hdr.front_len));
+	WARN_ON(m->data_length != le32_to_cpu(m->hdr.data_len));
+
+	/* tag + hdr + front + middle */
+	con_out_kvec_add(con, sizeof (tag_msg), &tag_msg);
+	con_out_kvec_add(con, sizeof(con->v1.out_hdr), &con->v1.out_hdr);
+	con_out_kvec_add(con, m->front.iov_len, m->front.iov_base);
+
+	if (m->middle)
+		con_out_kvec_add(con, m->middle->vec.iov_len,
+			m->middle->vec.iov_base);
+
+	/* fill in hdr crc and finalize hdr */
+	crc = crc32c(0, &m->hdr, offsetof(struct ceph_msg_header, crc));
+	con->out_msg->hdr.crc = cpu_to_le32(crc);
+	memcpy(&con->v1.out_hdr, &con->out_msg->hdr, sizeof(con->v1.out_hdr));
+
+	/* fill in front and middle crc, footer */
+	crc = crc32c(0, m->front.iov_base, m->front.iov_len);
+	con->out_msg->footer.front_crc = cpu_to_le32(crc);
+	if (m->middle) {
+		crc = crc32c(0, m->middle->vec.iov_base,
+				m->middle->vec.iov_len);
+		con->out_msg->footer.middle_crc = cpu_to_le32(crc);
+	} else
+		con->out_msg->footer.middle_crc = 0;
+	dout("%s front_crc %u middle_crc %u\n", __func__,
+	     le32_to_cpu(con->out_msg->footer.front_crc),
+	     le32_to_cpu(con->out_msg->footer.middle_crc));
+	con->out_msg->footer.flags = 0;
+
+	/* is there a data payload? */
+	con->out_msg->footer.data_crc = 0;
+	if (m->data_length) {
+		prepare_message_data(con->out_msg, m->data_length);
+		con->v1.out_more = 1;  /* data + footer will follow */
+	} else {
+		/* no, queue up footer too and be done */
+		prepare_write_message_footer(con);
+	}
+
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+/*
+ * Prepare an ack.
+ */
+static void prepare_write_ack(struct ceph_connection *con)
+{
+	dout("prepare_write_ack %p %llu -> %llu\n", con,
+	     con->in_seq_acked, con->in_seq);
+	con->in_seq_acked = con->in_seq;
+
+	con_out_kvec_reset(con);
+
+	con_out_kvec_add(con, sizeof (tag_ack), &tag_ack);
+
+	con->v1.out_temp_ack = cpu_to_le64(con->in_seq_acked);
+	con_out_kvec_add(con, sizeof(con->v1.out_temp_ack),
+			 &con->v1.out_temp_ack);
+
+	con->v1.out_more = 1;  /* more will follow.. eventually.. */
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+/*
+ * Prepare to share the seq during handshake
+ */
+static void prepare_write_seq(struct ceph_connection *con)
+{
+	dout("prepare_write_seq %p %llu -> %llu\n", con,
+	     con->in_seq_acked, con->in_seq);
+	con->in_seq_acked = con->in_seq;
+
+	con_out_kvec_reset(con);
+
+	con->v1.out_temp_ack = cpu_to_le64(con->in_seq_acked);
+	con_out_kvec_add(con, sizeof(con->v1.out_temp_ack),
+			 &con->v1.out_temp_ack);
+
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+/*
+ * Prepare to write keepalive byte.
+ */
+static void prepare_write_keepalive(struct ceph_connection *con)
+{
+	dout("prepare_write_keepalive %p\n", con);
+	con_out_kvec_reset(con);
+	if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) {
+		struct timespec64 now;
+
+		ktime_get_real_ts64(&now);
+		con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2);
+		ceph_encode_timespec64(&con->v1.out_temp_keepalive2, &now);
+		con_out_kvec_add(con, sizeof(con->v1.out_temp_keepalive2),
+				 &con->v1.out_temp_keepalive2);
+	} else {
+		con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive);
+	}
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+/*
+ * Connection negotiation.
+ */
+
+static int get_connect_authorizer(struct ceph_connection *con)
+{
+	struct ceph_auth_handshake *auth;
+	int auth_proto;
+
+	if (!con->ops->get_authorizer) {
+		con->v1.auth = NULL;
+		con->v1.out_connect.authorizer_protocol = CEPH_AUTH_UNKNOWN;
+		con->v1.out_connect.authorizer_len = 0;
+		return 0;
+	}
+
+	auth = con->ops->get_authorizer(con, &auth_proto, con->v1.auth_retry);
+	if (IS_ERR(auth))
+		return PTR_ERR(auth);
+
+	con->v1.auth = auth;
+	con->v1.out_connect.authorizer_protocol = cpu_to_le32(auth_proto);
+	con->v1.out_connect.authorizer_len =
+		cpu_to_le32(auth->authorizer_buf_len);
+	return 0;
+}
+
+/*
+ * We connected to a peer and are saying hello.
+ */
+static void prepare_write_banner(struct ceph_connection *con)
+{
+	con_out_kvec_add(con, strlen(CEPH_BANNER), CEPH_BANNER);
+	con_out_kvec_add(con, sizeof (con->msgr->my_enc_addr),
+					&con->msgr->my_enc_addr);
+
+	con->v1.out_more = 0;
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+static void __prepare_write_connect(struct ceph_connection *con)
+{
+	con_out_kvec_add(con, sizeof(con->v1.out_connect),
+			 &con->v1.out_connect);
+	if (con->v1.auth)
+		con_out_kvec_add(con, con->v1.auth->authorizer_buf_len,
+				 con->v1.auth->authorizer_buf);
+
+	con->v1.out_more = 0;
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+}
+
+static int prepare_write_connect(struct ceph_connection *con)
+{
+	unsigned int global_seq = ceph_get_global_seq(con->msgr, 0);
+	int proto;
+	int ret;
+
+	switch (con->peer_name.type) {
+	case CEPH_ENTITY_TYPE_MON:
+		proto = CEPH_MONC_PROTOCOL;
+		break;
+	case CEPH_ENTITY_TYPE_OSD:
+		proto = CEPH_OSDC_PROTOCOL;
+		break;
+	case CEPH_ENTITY_TYPE_MDS:
+		proto = CEPH_MDSC_PROTOCOL;
+		break;
+	default:
+		BUG();
+	}
+
+	dout("prepare_write_connect %p cseq=%d gseq=%d proto=%d\n", con,
+	     con->v1.connect_seq, global_seq, proto);
+
+	con->v1.out_connect.features =
+		cpu_to_le64(from_msgr(con->msgr)->supported_features);
+	con->v1.out_connect.host_type = cpu_to_le32(CEPH_ENTITY_TYPE_CLIENT);
+	con->v1.out_connect.connect_seq = cpu_to_le32(con->v1.connect_seq);
+	con->v1.out_connect.global_seq = cpu_to_le32(global_seq);
+	con->v1.out_connect.protocol_version = cpu_to_le32(proto);
+	con->v1.out_connect.flags = 0;
+
+	ret = get_connect_authorizer(con);
+	if (ret)
+		return ret;
+
+	__prepare_write_connect(con);
+	return 0;
+}
+
+/*
+ * write as much of pending kvecs to the socket as we can.
+ *  1 -> done
+ *  0 -> socket full, but more to do
+ * <0 -> error
+ */
+static int write_partial_kvec(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("write_partial_kvec %p %d left\n", con, con->v1.out_kvec_bytes);
+	while (con->v1.out_kvec_bytes > 0) {
+		ret = ceph_tcp_sendmsg(con->sock, con->v1.out_kvec_cur,
+				       con->v1.out_kvec_left,
+				       con->v1.out_kvec_bytes,
+				       con->v1.out_more);
+		if (ret <= 0)
+			goto out;
+		con->v1.out_kvec_bytes -= ret;
+		if (!con->v1.out_kvec_bytes)
+			break;            /* done */
+
+		/* account for full iov entries consumed */
+		while (ret >= con->v1.out_kvec_cur->iov_len) {
+			BUG_ON(!con->v1.out_kvec_left);
+			ret -= con->v1.out_kvec_cur->iov_len;
+			con->v1.out_kvec_cur++;
+			con->v1.out_kvec_left--;
+		}
+		/* and for a partially-consumed entry */
+		if (ret) {
+			con->v1.out_kvec_cur->iov_len -= ret;
+			con->v1.out_kvec_cur->iov_base += ret;
+		}
+	}
+	con->v1.out_kvec_left = 0;
+	ret = 1;
+out:
+	dout("write_partial_kvec %p %d left in %d kvecs ret = %d\n", con,
+	     con->v1.out_kvec_bytes, con->v1.out_kvec_left, ret);
+	return ret;  /* done! */
+}
+
+/*
+ * Write as much message data payload as we can.  If we finish, queue
+ * up the footer.
+ *  1 -> done, footer is now queued in out_kvec[].
+ *  0 -> socket full, but more to do
+ * <0 -> error
+ */
+static int write_partial_message_data(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+	struct ceph_msg_data_cursor *cursor = &msg->cursor;
+	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
+	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+	u32 crc;
+
+	dout("%s %p msg %p\n", __func__, con, msg);
+
+	if (!msg->num_data_items)
+		return -EINVAL;
+
+	/*
+	 * Iterate through each page that contains data to be
+	 * written, and send as much as possible for each.
+	 *
+	 * If we are calculating the data crc (the default), we will
+	 * need to map the page.  If we have no pages, they have
+	 * been revoked, so use the zero page.
+	 */
+	crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0;
+	while (cursor->total_resid) {
+		struct page *page;
+		size_t page_offset;
+		size_t length;
+		int ret;
+
+		if (!cursor->resid) {
+			ceph_msg_data_advance(cursor, 0);
+			continue;
+		}
+
+		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
+		if (length == cursor->total_resid)
+			more = MSG_MORE;
+		ret = ceph_tcp_sendpage(con->sock, page, page_offset, length,
+					more);
+		if (ret <= 0) {
+			if (do_datacrc)
+				msg->footer.data_crc = cpu_to_le32(crc);
+
+			return ret;
+		}
+		if (do_datacrc && cursor->need_crc)
+			crc = ceph_crc32c_page(crc, page, page_offset, length);
+		ceph_msg_data_advance(cursor, (size_t)ret);
+	}
+
+	dout("%s %p msg %p done\n", __func__, con, msg);
+
+	/* prepare and queue up footer, too */
+	if (do_datacrc)
+		msg->footer.data_crc = cpu_to_le32(crc);
+	else
+		msg->footer.flags |= CEPH_MSG_FOOTER_NOCRC;
+	con_out_kvec_reset(con);
+	prepare_write_message_footer(con);
+
+	return 1;	/* must return > 0 to indicate success */
+}
+
+/*
+ * write some zeros
+ */
+static int write_partial_skip(struct ceph_connection *con)
+{
+	int more = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+	int ret;
+
+	dout("%s %p %d left\n", __func__, con, con->v1.out_skip);
+	while (con->v1.out_skip > 0) {
+		size_t size = min(con->v1.out_skip, (int)PAGE_SIZE);
+
+		if (size == con->v1.out_skip)
+			more = MSG_MORE;
+		ret = ceph_tcp_sendpage(con->sock, ceph_zero_page, 0, size,
+					more);
+		if (ret <= 0)
+			goto out;
+		con->v1.out_skip -= ret;
+	}
+	ret = 1;
+out:
+	return ret;
+}
+
+/*
+ * Prepare to read connection handshake, or an ack.
+ */
+static void prepare_read_banner(struct ceph_connection *con)
+{
+	dout("prepare_read_banner %p\n", con);
+	con->v1.in_base_pos = 0;
+}
+
+static void prepare_read_connect(struct ceph_connection *con)
+{
+	dout("prepare_read_connect %p\n", con);
+	con->v1.in_base_pos = 0;
+}
+
+static void prepare_read_ack(struct ceph_connection *con)
+{
+	dout("prepare_read_ack %p\n", con);
+	con->v1.in_base_pos = 0;
+}
+
+static void prepare_read_seq(struct ceph_connection *con)
+{
+	dout("prepare_read_seq %p\n", con);
+	con->v1.in_base_pos = 0;
+	con->v1.in_tag = CEPH_MSGR_TAG_SEQ;
+}
+
+static void prepare_read_tag(struct ceph_connection *con)
+{
+	dout("prepare_read_tag %p\n", con);
+	con->v1.in_base_pos = 0;
+	con->v1.in_tag = CEPH_MSGR_TAG_READY;
+}
+
+static void prepare_read_keepalive_ack(struct ceph_connection *con)
+{
+	dout("prepare_read_keepalive_ack %p\n", con);
+	con->v1.in_base_pos = 0;
+}
+
+/*
+ * Prepare to read a message.
+ */
+static int prepare_read_message(struct ceph_connection *con)
+{
+	dout("prepare_read_message %p\n", con);
+	BUG_ON(con->in_msg != NULL);
+	con->v1.in_base_pos = 0;
+	con->in_front_crc = con->in_middle_crc = con->in_data_crc = 0;
+	return 0;
+}
+
+static int read_partial(struct ceph_connection *con,
+			int end, int size, void *object)
+{
+	while (con->v1.in_base_pos < end) {
+		int left = end - con->v1.in_base_pos;
+		int have = size - left;
+		int ret = ceph_tcp_recvmsg(con->sock, object + have, left);
+		if (ret <= 0)
+			return ret;
+		con->v1.in_base_pos += ret;
+	}
+	return 1;
+}
+
+/*
+ * Read all or part of the connect-side handshake on a new connection
+ */
+static int read_partial_banner(struct ceph_connection *con)
+{
+	int size;
+	int end;
+	int ret;
+
+	dout("read_partial_banner %p at %d\n", con, con->v1.in_base_pos);
+
+	/* peer's banner */
+	size = strlen(CEPH_BANNER);
+	end = size;
+	ret = read_partial(con, end, size, con->v1.in_banner);
+	if (ret <= 0)
+		goto out;
+
+	size = sizeof(con->v1.actual_peer_addr);
+	end += size;
+	ret = read_partial(con, end, size, &con->v1.actual_peer_addr);
+	if (ret <= 0)
+		goto out;
+	ceph_decode_banner_addr(&con->v1.actual_peer_addr);
+
+	size = sizeof(con->v1.peer_addr_for_me);
+	end += size;
+	ret = read_partial(con, end, size, &con->v1.peer_addr_for_me);
+	if (ret <= 0)
+		goto out;
+	ceph_decode_banner_addr(&con->v1.peer_addr_for_me);
+
+out:
+	return ret;
+}
+
+static int read_partial_connect(struct ceph_connection *con)
+{
+	int size;
+	int end;
+	int ret;
+
+	dout("read_partial_connect %p at %d\n", con, con->v1.in_base_pos);
+
+	size = sizeof(con->v1.in_reply);
+	end = size;
+	ret = read_partial(con, end, size, &con->v1.in_reply);
+	if (ret <= 0)
+		goto out;
+
+	if (con->v1.auth) {
+		size = le32_to_cpu(con->v1.in_reply.authorizer_len);
+		if (size > con->v1.auth->authorizer_reply_buf_len) {
+			pr_err("authorizer reply too big: %d > %zu\n", size,
+			       con->v1.auth->authorizer_reply_buf_len);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		end += size;
+		ret = read_partial(con, end, size,
+				   con->v1.auth->authorizer_reply_buf);
+		if (ret <= 0)
+			goto out;
+	}
+
+	dout("read_partial_connect %p tag %d, con_seq = %u, g_seq = %u\n",
+	     con, con->v1.in_reply.tag,
+	     le32_to_cpu(con->v1.in_reply.connect_seq),
+	     le32_to_cpu(con->v1.in_reply.global_seq));
+out:
+	return ret;
+}
+
+/*
+ * Verify the hello banner looks okay.
+ */
+static int verify_hello(struct ceph_connection *con)
+{
+	if (memcmp(con->v1.in_banner, CEPH_BANNER, strlen(CEPH_BANNER))) {
+		pr_err("connect to %s got bad banner\n",
+		       ceph_pr_addr(&con->peer_addr));
+		con->error_msg = "protocol error, bad banner";
+		return -1;
+	}
+	return 0;
+}
+
+static int process_banner(struct ceph_connection *con)
+{
+	struct ceph_entity_addr *my_addr = &con->msgr->inst.addr;
+
+	dout("process_banner on %p\n", con);
+
+	if (verify_hello(con) < 0)
+		return -1;
+
+	/*
+	 * Make sure the other end is who we wanted.  note that the other
+	 * end may not yet know their ip address, so if it's 0.0.0.0, give
+	 * them the benefit of the doubt.
+	 */
+	if (memcmp(&con->peer_addr, &con->v1.actual_peer_addr,
+		   sizeof(con->peer_addr)) != 0 &&
+	    !(ceph_addr_is_blank(&con->v1.actual_peer_addr) &&
+	      con->v1.actual_peer_addr.nonce == con->peer_addr.nonce)) {
+		pr_warn("wrong peer, want %s/%u, got %s/%u\n",
+			ceph_pr_addr(&con->peer_addr),
+			le32_to_cpu(con->peer_addr.nonce),
+			ceph_pr_addr(&con->v1.actual_peer_addr),
+			le32_to_cpu(con->v1.actual_peer_addr.nonce));
+		con->error_msg = "wrong peer at address";
+		return -1;
+	}
+
+	/*
+	 * did we learn our address?
+	 */
+	if (ceph_addr_is_blank(my_addr)) {
+		memcpy(&my_addr->in_addr,
+		       &con->v1.peer_addr_for_me.in_addr,
+		       sizeof(con->v1.peer_addr_for_me.in_addr));
+		ceph_addr_set_port(my_addr, 0);
+		ceph_encode_my_addr(con->msgr);
+		dout("process_banner learned my addr is %s\n",
+		     ceph_pr_addr(my_addr));
+	}
+
+	return 0;
+}
+
+static int process_connect(struct ceph_connection *con)
+{
+	u64 sup_feat = from_msgr(con->msgr)->supported_features;
+	u64 req_feat = from_msgr(con->msgr)->required_features;
+	u64 server_feat = le64_to_cpu(con->v1.in_reply.features);
+	int ret;
+
+	dout("process_connect on %p tag %d\n", con, con->v1.in_tag);
+
+	if (con->v1.auth) {
+		int len = le32_to_cpu(con->v1.in_reply.authorizer_len);
+
+		/*
+		 * Any connection that defines ->get_authorizer()
+		 * should also define ->add_authorizer_challenge() and
+		 * ->verify_authorizer_reply().
+		 *
+		 * See get_connect_authorizer().
+		 */
+		if (con->v1.in_reply.tag ==
+				CEPH_MSGR_TAG_CHALLENGE_AUTHORIZER) {
+			ret = con->ops->add_authorizer_challenge(
+				con, con->v1.auth->authorizer_reply_buf, len);
+			if (ret < 0)
+				return ret;
+
+			con_out_kvec_reset(con);
+			__prepare_write_connect(con);
+			prepare_read_connect(con);
+			return 0;
+		}
+
+		if (len) {
+			ret = con->ops->verify_authorizer_reply(con);
+			if (ret < 0) {
+				con->error_msg = "bad authorize reply";
+				return ret;
+			}
+		}
+	}
+
+	switch (con->v1.in_reply.tag) {
+	case CEPH_MSGR_TAG_FEATURES:
+		pr_err("%s%lld %s feature set mismatch,"
+		       " my %llx < server's %llx, missing %llx\n",
+		       ENTITY_NAME(con->peer_name),
+		       ceph_pr_addr(&con->peer_addr),
+		       sup_feat, server_feat, server_feat & ~sup_feat);
+		con->error_msg = "missing required protocol features";
+		return -1;
+
+	case CEPH_MSGR_TAG_BADPROTOVER:
+		pr_err("%s%lld %s protocol version mismatch,"
+		       " my %d != server's %d\n",
+		       ENTITY_NAME(con->peer_name),
+		       ceph_pr_addr(&con->peer_addr),
+		       le32_to_cpu(con->v1.out_connect.protocol_version),
+		       le32_to_cpu(con->v1.in_reply.protocol_version));
+		con->error_msg = "protocol version mismatch";
+		return -1;
+
+	case CEPH_MSGR_TAG_BADAUTHORIZER:
+		con->v1.auth_retry++;
+		dout("process_connect %p got BADAUTHORIZER attempt %d\n", con,
+		     con->v1.auth_retry);
+		if (con->v1.auth_retry == 2) {
+			con->error_msg = "connect authorization failure";
+			return -1;
+		}
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
+		prepare_read_connect(con);
+		break;
+
+	case CEPH_MSGR_TAG_RESETSESSION:
+		/*
+		 * If we connected with a large connect_seq but the peer
+		 * has no record of a session with us (no connection, or
+		 * connect_seq == 0), they will send RESETSESION to indicate
+		 * that they must have reset their session, and may have
+		 * dropped messages.
+		 */
+		dout("process_connect got RESET peer seq %u\n",
+		     le32_to_cpu(con->v1.in_reply.connect_seq));
+		pr_info("%s%lld %s session reset\n",
+			ENTITY_NAME(con->peer_name),
+			ceph_pr_addr(&con->peer_addr));
+		ceph_con_reset_session(con);
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
+		prepare_read_connect(con);
+
+		/* Tell ceph about it. */
+		mutex_unlock(&con->mutex);
+		if (con->ops->peer_reset)
+			con->ops->peer_reset(con);
+		mutex_lock(&con->mutex);
+		if (con->state != CEPH_CON_S_V1_CONNECT_MSG)
+			return -EAGAIN;
+		break;
+
+	case CEPH_MSGR_TAG_RETRY_SESSION:
+		/*
+		 * If we sent a smaller connect_seq than the peer has, try
+		 * again with a larger value.
+		 */
+		dout("process_connect got RETRY_SESSION my seq %u, peer %u\n",
+		     le32_to_cpu(con->v1.out_connect.connect_seq),
+		     le32_to_cpu(con->v1.in_reply.connect_seq));
+		con->v1.connect_seq = le32_to_cpu(con->v1.in_reply.connect_seq);
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
+		prepare_read_connect(con);
+		break;
+
+	case CEPH_MSGR_TAG_RETRY_GLOBAL:
+		/*
+		 * If we sent a smaller global_seq than the peer has, try
+		 * again with a larger value.
+		 */
+		dout("process_connect got RETRY_GLOBAL my %u peer_gseq %u\n",
+		     con->v1.peer_global_seq,
+		     le32_to_cpu(con->v1.in_reply.global_seq));
+		ceph_get_global_seq(con->msgr,
+				    le32_to_cpu(con->v1.in_reply.global_seq));
+		con_out_kvec_reset(con);
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			return ret;
+		prepare_read_connect(con);
+		break;
+
+	case CEPH_MSGR_TAG_SEQ:
+	case CEPH_MSGR_TAG_READY:
+		if (req_feat & ~server_feat) {
+			pr_err("%s%lld %s protocol feature mismatch,"
+			       " my required %llx > server's %llx, need %llx\n",
+			       ENTITY_NAME(con->peer_name),
+			       ceph_pr_addr(&con->peer_addr),
+			       req_feat, server_feat, req_feat & ~server_feat);
+			con->error_msg = "missing required protocol features";
+			return -1;
+		}
+
+		WARN_ON(con->state != CEPH_CON_S_V1_CONNECT_MSG);
+		con->state = CEPH_CON_S_OPEN;
+		con->v1.auth_retry = 0;    /* we authenticated; clear flag */
+		con->v1.peer_global_seq =
+			le32_to_cpu(con->v1.in_reply.global_seq);
+		con->v1.connect_seq++;
+		con->peer_features = server_feat;
+		dout("process_connect got READY gseq %d cseq %d (%d)\n",
+		     con->v1.peer_global_seq,
+		     le32_to_cpu(con->v1.in_reply.connect_seq),
+		     con->v1.connect_seq);
+		WARN_ON(con->v1.connect_seq !=
+			le32_to_cpu(con->v1.in_reply.connect_seq));
+
+		if (con->v1.in_reply.flags & CEPH_MSG_CONNECT_LOSSY)
+			ceph_con_flag_set(con, CEPH_CON_F_LOSSYTX);
+
+		con->delay = 0;      /* reset backoff memory */
+
+		if (con->v1.in_reply.tag == CEPH_MSGR_TAG_SEQ) {
+			prepare_write_seq(con);
+			prepare_read_seq(con);
+		} else {
+			prepare_read_tag(con);
+		}
+		break;
+
+	case CEPH_MSGR_TAG_WAIT:
+		/*
+		 * If there is a connection race (we are opening
+		 * connections to each other), one of us may just have
+		 * to WAIT.  This shouldn't happen if we are the
+		 * client.
+		 */
+		con->error_msg = "protocol error, got WAIT as client";
+		return -1;
+
+	default:
+		con->error_msg = "protocol error, garbage tag during connect";
+		return -1;
+	}
+	return 0;
+}
+
+/*
+ * read (part of) an ack
+ */
+static int read_partial_ack(struct ceph_connection *con)
+{
+	int size = sizeof(con->v1.in_temp_ack);
+	int end = size;
+
+	return read_partial(con, end, size, &con->v1.in_temp_ack);
+}
+
+/*
+ * We can finally discard anything that's been acked.
+ */
+static void process_ack(struct ceph_connection *con)
+{
+	u64 ack = le64_to_cpu(con->v1.in_temp_ack);
+
+	if (con->v1.in_tag == CEPH_MSGR_TAG_ACK)
+		ceph_con_discard_sent(con, ack);
+	else
+		ceph_con_discard_requeued(con, ack);
+
+	prepare_read_tag(con);
+}
+
+static int read_partial_message_section(struct ceph_connection *con,
+					struct kvec *section,
+					unsigned int sec_len, u32 *crc)
+{
+	int ret, left;
+
+	BUG_ON(!section);
+
+	while (section->iov_len < sec_len) {
+		BUG_ON(section->iov_base == NULL);
+		left = sec_len - section->iov_len;
+		ret = ceph_tcp_recvmsg(con->sock, (char *)section->iov_base +
+				       section->iov_len, left);
+		if (ret <= 0)
+			return ret;
+		section->iov_len += ret;
+	}
+	if (section->iov_len == sec_len)
+		*crc = crc32c(0, section->iov_base, section->iov_len);
+
+	return 1;
+}
+
+static int read_partial_msg_data(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->in_msg;
+	struct ceph_msg_data_cursor *cursor = &msg->cursor;
+	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
+	struct page *page;
+	size_t page_offset;
+	size_t length;
+	u32 crc = 0;
+	int ret;
+
+	if (!msg->num_data_items)
+		return -EIO;
+
+	if (do_datacrc)
+		crc = con->in_data_crc;
+	while (cursor->total_resid) {
+		if (!cursor->resid) {
+			ceph_msg_data_advance(cursor, 0);
+			continue;
+		}
+
+		page = ceph_msg_data_next(cursor, &page_offset, &length, NULL);
+		ret = ceph_tcp_recvpage(con->sock, page, page_offset, length);
+		if (ret <= 0) {
+			if (do_datacrc)
+				con->in_data_crc = crc;
+
+			return ret;
+		}
+
+		if (do_datacrc)
+			crc = ceph_crc32c_page(crc, page, page_offset, ret);
+		ceph_msg_data_advance(cursor, (size_t)ret);
+	}
+	if (do_datacrc)
+		con->in_data_crc = crc;
+
+	return 1;	/* must return > 0 to indicate success */
+}
+
+/*
+ * read (part of) a message.
+ */
+static int read_partial_message(struct ceph_connection *con)
+{
+	struct ceph_msg *m = con->in_msg;
+	int size;
+	int end;
+	int ret;
+	unsigned int front_len, middle_len, data_len;
+	bool do_datacrc = !ceph_test_opt(from_msgr(con->msgr), NOCRC);
+	bool need_sign = (con->peer_features & CEPH_FEATURE_MSG_AUTH);
+	u64 seq;
+	u32 crc;
+
+	dout("read_partial_message con %p msg %p\n", con, m);
+
+	/* header */
+	size = sizeof(con->v1.in_hdr);
+	end = size;
+	ret = read_partial(con, end, size, &con->v1.in_hdr);
+	if (ret <= 0)
+		return ret;
+
+	crc = crc32c(0, &con->v1.in_hdr, offsetof(struct ceph_msg_header, crc));
+	if (cpu_to_le32(crc) != con->v1.in_hdr.crc) {
+		pr_err("read_partial_message bad hdr crc %u != expected %u\n",
+		       crc, con->v1.in_hdr.crc);
+		return -EBADMSG;
+	}
+
+	front_len = le32_to_cpu(con->v1.in_hdr.front_len);
+	if (front_len > CEPH_MSG_MAX_FRONT_LEN)
+		return -EIO;
+	middle_len = le32_to_cpu(con->v1.in_hdr.middle_len);
+	if (middle_len > CEPH_MSG_MAX_MIDDLE_LEN)
+		return -EIO;
+	data_len = le32_to_cpu(con->v1.in_hdr.data_len);
+	if (data_len > CEPH_MSG_MAX_DATA_LEN)
+		return -EIO;
+
+	/* verify seq# */
+	seq = le64_to_cpu(con->v1.in_hdr.seq);
+	if ((s64)seq - (s64)con->in_seq < 1) {
+		pr_info("skipping %s%lld %s seq %lld expected %lld\n",
+			ENTITY_NAME(con->peer_name),
+			ceph_pr_addr(&con->peer_addr),
+			seq, con->in_seq + 1);
+		con->v1.in_base_pos = -front_len - middle_len - data_len -
+				      sizeof_footer(con);
+		con->v1.in_tag = CEPH_MSGR_TAG_READY;
+		return 1;
+	} else if ((s64)seq - (s64)con->in_seq > 1) {
+		pr_err("read_partial_message bad seq %lld expected %lld\n",
+		       seq, con->in_seq + 1);
+		con->error_msg = "bad message sequence # for incoming message";
+		return -EBADE;
+	}
+
+	/* allocate message? */
+	if (!con->in_msg) {
+		int skip = 0;
+
+		dout("got hdr type %d front %d data %d\n", con->v1.in_hdr.type,
+		     front_len, data_len);
+		ret = ceph_con_in_msg_alloc(con, &con->v1.in_hdr, &skip);
+		if (ret < 0)
+			return ret;
+
+		BUG_ON((!con->in_msg) ^ skip);
+		if (skip) {
+			/* skip this message */
+			dout("alloc_msg said skip message\n");
+			con->v1.in_base_pos = -front_len - middle_len -
+					      data_len - sizeof_footer(con);
+			con->v1.in_tag = CEPH_MSGR_TAG_READY;
+			con->in_seq++;
+			return 1;
+		}
+
+		BUG_ON(!con->in_msg);
+		BUG_ON(con->in_msg->con != con);
+		m = con->in_msg;
+		m->front.iov_len = 0;    /* haven't read it yet */
+		if (m->middle)
+			m->middle->vec.iov_len = 0;
+
+		/* prepare for data payload, if any */
+
+		if (data_len)
+			prepare_message_data(con->in_msg, data_len);
+	}
+
+	/* front */
+	ret = read_partial_message_section(con, &m->front, front_len,
+					   &con->in_front_crc);
+	if (ret <= 0)
+		return ret;
+
+	/* middle */
+	if (m->middle) {
+		ret = read_partial_message_section(con, &m->middle->vec,
+						   middle_len,
+						   &con->in_middle_crc);
+		if (ret <= 0)
+			return ret;
+	}
+
+	/* (page) data */
+	if (data_len) {
+		ret = read_partial_msg_data(con);
+		if (ret <= 0)
+			return ret;
+	}
+
+	/* footer */
+	size = sizeof_footer(con);
+	end += size;
+	ret = read_partial(con, end, size, &m->footer);
+	if (ret <= 0)
+		return ret;
+
+	if (!need_sign) {
+		m->footer.flags = m->old_footer.flags;
+		m->footer.sig = 0;
+	}
+
+	dout("read_partial_message got msg %p %d (%u) + %d (%u) + %d (%u)\n",
+	     m, front_len, m->footer.front_crc, middle_len,
+	     m->footer.middle_crc, data_len, m->footer.data_crc);
+
+	/* crc ok? */
+	if (con->in_front_crc != le32_to_cpu(m->footer.front_crc)) {
+		pr_err("read_partial_message %p front crc %u != exp. %u\n",
+		       m, con->in_front_crc, m->footer.front_crc);
+		return -EBADMSG;
+	}
+	if (con->in_middle_crc != le32_to_cpu(m->footer.middle_crc)) {
+		pr_err("read_partial_message %p middle crc %u != exp %u\n",
+		       m, con->in_middle_crc, m->footer.middle_crc);
+		return -EBADMSG;
+	}
+	if (do_datacrc &&
+	    (m->footer.flags & CEPH_MSG_FOOTER_NOCRC) == 0 &&
+	    con->in_data_crc != le32_to_cpu(m->footer.data_crc)) {
+		pr_err("read_partial_message %p data crc %u != exp. %u\n", m,
+		       con->in_data_crc, le32_to_cpu(m->footer.data_crc));
+		return -EBADMSG;
+	}
+
+	if (need_sign && con->ops->check_message_signature &&
+	    con->ops->check_message_signature(m)) {
+		pr_err("read_partial_message %p signature check failed\n", m);
+		return -EBADMSG;
+	}
+
+	return 1; /* done! */
+}
+
+static int read_keepalive_ack(struct ceph_connection *con)
+{
+	struct ceph_timespec ceph_ts;
+	size_t size = sizeof(ceph_ts);
+	int ret = read_partial(con, size, size, &ceph_ts);
+	if (ret <= 0)
+		return ret;
+	ceph_decode_timespec64(&con->last_keepalive_ack, &ceph_ts);
+	prepare_read_tag(con);
+	return 1;
+}
+
+/*
+ * Read what we can from the socket.
+ */
+int ceph_con_v1_try_read(struct ceph_connection *con)
+{
+	int ret = -1;
+
+more:
+	dout("try_read start %p state %d\n", con, con->state);
+	if (con->state != CEPH_CON_S_V1_BANNER &&
+	    con->state != CEPH_CON_S_V1_CONNECT_MSG &&
+	    con->state != CEPH_CON_S_OPEN)
+		return 0;
+
+	BUG_ON(!con->sock);
+
+	dout("try_read tag %d in_base_pos %d\n", con->v1.in_tag,
+	     con->v1.in_base_pos);
+
+	if (con->state == CEPH_CON_S_V1_BANNER) {
+		ret = read_partial_banner(con);
+		if (ret <= 0)
+			goto out;
+		ret = process_banner(con);
+		if (ret < 0)
+			goto out;
+
+		con->state = CEPH_CON_S_V1_CONNECT_MSG;
+
+		/*
+		 * Received banner is good, exchange connection info.
+		 * Do not reset out_kvec, as sending our banner raced
+		 * with receiving peer banner after connect completed.
+		 */
+		ret = prepare_write_connect(con);
+		if (ret < 0)
+			goto out;
+		prepare_read_connect(con);
+
+		/* Send connection info before awaiting response */
+		goto out;
+	}
+
+	if (con->state == CEPH_CON_S_V1_CONNECT_MSG) {
+		ret = read_partial_connect(con);
+		if (ret <= 0)
+			goto out;
+		ret = process_connect(con);
+		if (ret < 0)
+			goto out;
+		goto more;
+	}
+
+	WARN_ON(con->state != CEPH_CON_S_OPEN);
+
+	if (con->v1.in_base_pos < 0) {
+		/*
+		 * skipping + discarding content.
+		 */
+		ret = ceph_tcp_recvmsg(con->sock, NULL, -con->v1.in_base_pos);
+		if (ret <= 0)
+			goto out;
+		dout("skipped %d / %d bytes\n", ret, -con->v1.in_base_pos);
+		con->v1.in_base_pos += ret;
+		if (con->v1.in_base_pos)
+			goto more;
+	}
+	if (con->v1.in_tag == CEPH_MSGR_TAG_READY) {
+		/*
+		 * what's next?
+		 */
+		ret = ceph_tcp_recvmsg(con->sock, &con->v1.in_tag, 1);
+		if (ret <= 0)
+			goto out;
+		dout("try_read got tag %d\n", con->v1.in_tag);
+		switch (con->v1.in_tag) {
+		case CEPH_MSGR_TAG_MSG:
+			prepare_read_message(con);
+			break;
+		case CEPH_MSGR_TAG_ACK:
+			prepare_read_ack(con);
+			break;
+		case CEPH_MSGR_TAG_KEEPALIVE2_ACK:
+			prepare_read_keepalive_ack(con);
+			break;
+		case CEPH_MSGR_TAG_CLOSE:
+			ceph_con_close_socket(con);
+			con->state = CEPH_CON_S_CLOSED;
+			goto out;
+		default:
+			goto bad_tag;
+		}
+	}
+	if (con->v1.in_tag == CEPH_MSGR_TAG_MSG) {
+		ret = read_partial_message(con);
+		if (ret <= 0) {
+			switch (ret) {
+			case -EBADMSG:
+				con->error_msg = "bad crc/signature";
+				fallthrough;
+			case -EBADE:
+				ret = -EIO;
+				break;
+			case -EIO:
+				con->error_msg = "io error";
+				break;
+			}
+			goto out;
+		}
+		if (con->v1.in_tag == CEPH_MSGR_TAG_READY)
+			goto more;
+		ceph_con_process_message(con);
+		if (con->state == CEPH_CON_S_OPEN)
+			prepare_read_tag(con);
+		goto more;
+	}
+	if (con->v1.in_tag == CEPH_MSGR_TAG_ACK ||
+	    con->v1.in_tag == CEPH_MSGR_TAG_SEQ) {
+		/*
+		 * the final handshake seq exchange is semantically
+		 * equivalent to an ACK
+		 */
+		ret = read_partial_ack(con);
+		if (ret <= 0)
+			goto out;
+		process_ack(con);
+		goto more;
+	}
+	if (con->v1.in_tag == CEPH_MSGR_TAG_KEEPALIVE2_ACK) {
+		ret = read_keepalive_ack(con);
+		if (ret <= 0)
+			goto out;
+		goto more;
+	}
+
+out:
+	dout("try_read done on %p ret %d\n", con, ret);
+	return ret;
+
+bad_tag:
+	pr_err("try_read bad tag %d\n", con->v1.in_tag);
+	con->error_msg = "protocol error, garbage tag";
+	ret = -1;
+	goto out;
+}
+
+/*
+ * Write something to the socket.  Called in a worker thread when the
+ * socket appears to be writeable and we have something ready to send.
+ */
+int ceph_con_v1_try_write(struct ceph_connection *con)
+{
+	int ret = 1;
+
+	dout("try_write start %p state %d\n", con, con->state);
+	if (con->state != CEPH_CON_S_PREOPEN &&
+	    con->state != CEPH_CON_S_V1_BANNER &&
+	    con->state != CEPH_CON_S_V1_CONNECT_MSG &&
+	    con->state != CEPH_CON_S_OPEN)
+		return 0;
+
+	/* open the socket first? */
+	if (con->state == CEPH_CON_S_PREOPEN) {
+		BUG_ON(con->sock);
+		con->state = CEPH_CON_S_V1_BANNER;
+
+		con_out_kvec_reset(con);
+		prepare_write_banner(con);
+		prepare_read_banner(con);
+
+		BUG_ON(con->in_msg);
+		con->v1.in_tag = CEPH_MSGR_TAG_READY;
+		dout("try_write initiating connect on %p new state %d\n",
+		     con, con->state);
+		ret = ceph_tcp_connect(con);
+		if (ret < 0) {
+			con->error_msg = "connect error";
+			goto out;
+		}
+	}
+
+more:
+	dout("try_write out_kvec_bytes %d\n", con->v1.out_kvec_bytes);
+	BUG_ON(!con->sock);
+
+	/* kvec data queued? */
+	if (con->v1.out_kvec_left) {
+		ret = write_partial_kvec(con);
+		if (ret <= 0)
+			goto out;
+	}
+	if (con->v1.out_skip) {
+		ret = write_partial_skip(con);
+		if (ret <= 0)
+			goto out;
+	}
+
+	/* msg pages? */
+	if (con->out_msg) {
+		if (con->v1.out_msg_done) {
+			ceph_msg_put(con->out_msg);
+			con->out_msg = NULL;   /* we're done with this one */
+			goto do_next;
+		}
+
+		ret = write_partial_message_data(con);
+		if (ret == 1)
+			goto more;  /* we need to send the footer, too! */
+		if (ret == 0)
+			goto out;
+		if (ret < 0) {
+			dout("try_write write_partial_message_data err %d\n",
+			     ret);
+			goto out;
+		}
+	}
+
+do_next:
+	if (con->state == CEPH_CON_S_OPEN) {
+		if (ceph_con_flag_test_and_clear(con,
+				CEPH_CON_F_KEEPALIVE_PENDING)) {
+			prepare_write_keepalive(con);
+			goto more;
+		}
+		/* is anything else pending? */
+		if (!list_empty(&con->out_queue)) {
+			prepare_write_message(con);
+			goto more;
+		}
+		if (con->in_seq > con->in_seq_acked) {
+			prepare_write_ack(con);
+			goto more;
+		}
+	}
+
+	/* Nothing to do! */
+	ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+	dout("try_write nothing else to write.\n");
+	ret = 0;
+out:
+	dout("try_write done on %p ret %d\n", con, ret);
+	return ret;
+}
+
+void ceph_con_v1_revoke(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+
+	WARN_ON(con->v1.out_skip);
+	/* footer */
+	if (con->v1.out_msg_done) {
+		con->v1.out_skip += con_out_kvec_skip(con);
+	} else {
+		WARN_ON(!msg->data_length);
+		con->v1.out_skip += sizeof_footer(con);
+	}
+	/* data, middle, front */
+	if (msg->data_length)
+		con->v1.out_skip += msg->cursor.total_resid;
+	if (msg->middle)
+		con->v1.out_skip += con_out_kvec_skip(con);
+	con->v1.out_skip += con_out_kvec_skip(con);
+
+	dout("%s con %p out_kvec_bytes %d out_skip %d\n", __func__, con,
+	     con->v1.out_kvec_bytes, con->v1.out_skip);
+}
+
+void ceph_con_v1_revoke_incoming(struct ceph_connection *con)
+{
+	unsigned int front_len = le32_to_cpu(con->v1.in_hdr.front_len);
+	unsigned int middle_len = le32_to_cpu(con->v1.in_hdr.middle_len);
+	unsigned int data_len = le32_to_cpu(con->v1.in_hdr.data_len);
+
+	/* skip rest of message */
+	con->v1.in_base_pos = con->v1.in_base_pos -
+			sizeof(struct ceph_msg_header) -
+			front_len -
+			middle_len -
+			data_len -
+			sizeof(struct ceph_msg_footer);
+
+	con->v1.in_tag = CEPH_MSGR_TAG_READY;
+	con->in_seq++;
+
+	dout("%s con %p in_base_pos %d\n", __func__, con, con->v1.in_base_pos);
+}
+
+bool ceph_con_v1_opened(struct ceph_connection *con)
+{
+	return con->v1.connect_seq;
+}
+
+void ceph_con_v1_reset_session(struct ceph_connection *con)
+{
+	con->v1.connect_seq = 0;
+	con->v1.peer_global_seq = 0;
+}
+
+void ceph_con_v1_reset_protocol(struct ceph_connection *con)
+{
+	con->v1.out_skip = 0;
+}
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c
new file mode 100644
index 000000000000..cc40ce4e02fb
--- /dev/null
+++ b/net/ceph/messenger_v2.c
@@ -0,0 +1,3459 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Ceph msgr2 protocol implementation
+ *
+ * Copyright (C) 2020 Ilya Dryomov <idryomov@gmail.com>
+ */
+
+#include <linux/ceph/ceph_debug.h>
+
+#include <crypto/aead.h>
+#include <crypto/algapi.h>  /* for crypto_memneq() */
+#include <crypto/hash.h>
+#include <crypto/sha2.h>
+#include <linux/bvec.h>
+#include <linux/crc32c.h>
+#include <linux/net.h>
+#include <linux/scatterlist.h>
+#include <linux/socket.h>
+#include <linux/sched/mm.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+
+#include <linux/ceph/ceph_features.h>
+#include <linux/ceph/decode.h>
+#include <linux/ceph/libceph.h>
+#include <linux/ceph/messenger.h>
+
+#include "crypto.h"  /* for CEPH_KEY_LEN and CEPH_MAX_CON_SECRET_LEN */
+
+#define FRAME_TAG_HELLO			1
+#define FRAME_TAG_AUTH_REQUEST		2
+#define FRAME_TAG_AUTH_BAD_METHOD	3
+#define FRAME_TAG_AUTH_REPLY_MORE	4
+#define FRAME_TAG_AUTH_REQUEST_MORE	5
+#define FRAME_TAG_AUTH_DONE		6
+#define FRAME_TAG_AUTH_SIGNATURE	7
+#define FRAME_TAG_CLIENT_IDENT		8
+#define FRAME_TAG_SERVER_IDENT		9
+#define FRAME_TAG_IDENT_MISSING_FEATURES 10
+#define FRAME_TAG_SESSION_RECONNECT	11
+#define FRAME_TAG_SESSION_RESET		12
+#define FRAME_TAG_SESSION_RETRY		13
+#define FRAME_TAG_SESSION_RETRY_GLOBAL	14
+#define FRAME_TAG_SESSION_RECONNECT_OK	15
+#define FRAME_TAG_WAIT			16
+#define FRAME_TAG_MESSAGE		17
+#define FRAME_TAG_KEEPALIVE2		18
+#define FRAME_TAG_KEEPALIVE2_ACK	19
+#define FRAME_TAG_ACK			20
+
+#define FRAME_LATE_STATUS_ABORTED	0x1
+#define FRAME_LATE_STATUS_COMPLETE	0xe
+#define FRAME_LATE_STATUS_ABORTED_MASK	0xf
+
+#define IN_S_HANDLE_PREAMBLE		1
+#define IN_S_HANDLE_CONTROL		2
+#define IN_S_HANDLE_CONTROL_REMAINDER	3
+#define IN_S_PREPARE_READ_DATA		4
+#define IN_S_PREPARE_READ_DATA_CONT	5
+#define IN_S_HANDLE_EPILOGUE		6
+#define IN_S_FINISH_SKIP		7
+
+#define OUT_S_QUEUE_DATA		1
+#define OUT_S_QUEUE_DATA_CONT		2
+#define OUT_S_QUEUE_ENC_PAGE		3
+#define OUT_S_QUEUE_ZEROS		4
+#define OUT_S_FINISH_MESSAGE		5
+#define OUT_S_GET_NEXT			6
+
+#define CTRL_BODY(p)	((void *)(p) + CEPH_PREAMBLE_LEN)
+#define FRONT_PAD(p)	((void *)(p) + CEPH_EPILOGUE_SECURE_LEN)
+#define MIDDLE_PAD(p)	(FRONT_PAD(p) + CEPH_GCM_BLOCK_LEN)
+#define DATA_PAD(p)	(MIDDLE_PAD(p) + CEPH_GCM_BLOCK_LEN)
+
+#define CEPH_MSG_FLAGS (MSG_DONTWAIT | MSG_NOSIGNAL)
+
+static int do_recvmsg(struct socket *sock, struct iov_iter *it)
+{
+	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
+	int ret;
+
+	msg.msg_iter = *it;
+	while (iov_iter_count(it)) {
+		ret = sock_recvmsg(sock, &msg, msg.msg_flags);
+		if (ret <= 0) {
+			if (ret == -EAGAIN)
+				ret = 0;
+			return ret;
+		}
+
+		iov_iter_advance(it, ret);
+	}
+
+	WARN_ON(msg_data_left(&msg));
+	return 1;
+}
+
+/*
+ * Read as much as possible.
+ *
+ * Return:
+ *   1 - done, nothing (else) to read
+ *   0 - socket is empty, need to wait
+ *  <0 - error
+ */
+static int ceph_tcp_recv(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p %s %zu\n", __func__, con,
+	     iov_iter_is_discard(&con->v2.in_iter) ? "discard" : "need",
+	     iov_iter_count(&con->v2.in_iter));
+	ret = do_recvmsg(con->sock, &con->v2.in_iter);
+	dout("%s con %p ret %d left %zu\n", __func__, con, ret,
+	     iov_iter_count(&con->v2.in_iter));
+	return ret;
+}
+
+static int do_sendmsg(struct socket *sock, struct iov_iter *it)
+{
+	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
+	int ret;
+
+	msg.msg_iter = *it;
+	while (iov_iter_count(it)) {
+		ret = sock_sendmsg(sock, &msg);
+		if (ret <= 0) {
+			if (ret == -EAGAIN)
+				ret = 0;
+			return ret;
+		}
+
+		iov_iter_advance(it, ret);
+	}
+
+	WARN_ON(msg_data_left(&msg));
+	return 1;
+}
+
+static int do_try_sendpage(struct socket *sock, struct iov_iter *it)
+{
+	struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS };
+	struct bio_vec bv;
+	int ret;
+
+	if (WARN_ON(!iov_iter_is_bvec(it)))
+		return -EINVAL;
+
+	while (iov_iter_count(it)) {
+		/* iov_iter_iovec() for ITER_BVEC */
+		bv.bv_page = it->bvec->bv_page;
+		bv.bv_offset = it->bvec->bv_offset + it->iov_offset;
+		bv.bv_len = min(iov_iter_count(it),
+				it->bvec->bv_len - it->iov_offset);
+
+		/*
+		 * sendpage cannot properly handle pages with
+		 * page_count == 0, we need to fall back to sendmsg if
+		 * that's the case.
+		 *
+		 * Same goes for slab pages: skb_can_coalesce() allows
+		 * coalescing neighboring slab objects into a single frag
+		 * which triggers one of hardened usercopy checks.
+		 */
+		if (sendpage_ok(bv.bv_page)) {
+			ret = sock->ops->sendpage(sock, bv.bv_page,
+						  bv.bv_offset, bv.bv_len,
+						  CEPH_MSG_FLAGS);
+		} else {
+			iov_iter_bvec(&msg.msg_iter, WRITE, &bv, 1, bv.bv_len);
+			ret = sock_sendmsg(sock, &msg);
+		}
+		if (ret <= 0) {
+			if (ret == -EAGAIN)
+				ret = 0;
+			return ret;
+		}
+
+		iov_iter_advance(it, ret);
+	}
+
+	return 1;
+}
+
+/*
+ * Write as much as possible.  The socket is expected to be corked,
+ * so we don't bother with MSG_MORE/MSG_SENDPAGE_NOTLAST here.
+ *
+ * Return:
+ *   1 - done, nothing (else) to write
+ *   0 - socket is full, need to wait
+ *  <0 - error
+ */
+static int ceph_tcp_send(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p have %zu try_sendpage %d\n", __func__, con,
+	     iov_iter_count(&con->v2.out_iter), con->v2.out_iter_sendpage);
+	if (con->v2.out_iter_sendpage)
+		ret = do_try_sendpage(con->sock, &con->v2.out_iter);
+	else
+		ret = do_sendmsg(con->sock, &con->v2.out_iter);
+	dout("%s con %p ret %d left %zu\n", __func__, con, ret,
+	     iov_iter_count(&con->v2.out_iter));
+	return ret;
+}
+
+static void add_in_kvec(struct ceph_connection *con, void *buf, int len)
+{
+	BUG_ON(con->v2.in_kvec_cnt >= ARRAY_SIZE(con->v2.in_kvecs));
+	WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
+
+	con->v2.in_kvecs[con->v2.in_kvec_cnt].iov_base = buf;
+	con->v2.in_kvecs[con->v2.in_kvec_cnt].iov_len = len;
+	con->v2.in_kvec_cnt++;
+
+	con->v2.in_iter.nr_segs++;
+	con->v2.in_iter.count += len;
+}
+
+static void reset_in_kvecs(struct ceph_connection *con)
+{
+	WARN_ON(iov_iter_count(&con->v2.in_iter));
+
+	con->v2.in_kvec_cnt = 0;
+	iov_iter_kvec(&con->v2.in_iter, READ, con->v2.in_kvecs, 0, 0);
+}
+
+static void set_in_bvec(struct ceph_connection *con, const struct bio_vec *bv)
+{
+	WARN_ON(iov_iter_count(&con->v2.in_iter));
+
+	con->v2.in_bvec = *bv;
+	iov_iter_bvec(&con->v2.in_iter, READ, &con->v2.in_bvec, 1, bv->bv_len);
+}
+
+static void set_in_skip(struct ceph_connection *con, int len)
+{
+	WARN_ON(iov_iter_count(&con->v2.in_iter));
+
+	dout("%s con %p len %d\n", __func__, con, len);
+	iov_iter_discard(&con->v2.in_iter, READ, len);
+}
+
+static void add_out_kvec(struct ceph_connection *con, void *buf, int len)
+{
+	BUG_ON(con->v2.out_kvec_cnt >= ARRAY_SIZE(con->v2.out_kvecs));
+	WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter));
+	WARN_ON(con->v2.out_zero);
+
+	con->v2.out_kvecs[con->v2.out_kvec_cnt].iov_base = buf;
+	con->v2.out_kvecs[con->v2.out_kvec_cnt].iov_len = len;
+	con->v2.out_kvec_cnt++;
+
+	con->v2.out_iter.nr_segs++;
+	con->v2.out_iter.count += len;
+}
+
+static void reset_out_kvecs(struct ceph_connection *con)
+{
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+	WARN_ON(con->v2.out_zero);
+
+	con->v2.out_kvec_cnt = 0;
+
+	iov_iter_kvec(&con->v2.out_iter, WRITE, con->v2.out_kvecs, 0, 0);
+	con->v2.out_iter_sendpage = false;
+}
+
+static void set_out_bvec(struct ceph_connection *con, const struct bio_vec *bv,
+			 bool zerocopy)
+{
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+	WARN_ON(con->v2.out_zero);
+
+	con->v2.out_bvec = *bv;
+	con->v2.out_iter_sendpage = zerocopy;
+	iov_iter_bvec(&con->v2.out_iter, WRITE, &con->v2.out_bvec, 1,
+		      con->v2.out_bvec.bv_len);
+}
+
+static void set_out_bvec_zero(struct ceph_connection *con)
+{
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+	WARN_ON(!con->v2.out_zero);
+
+	con->v2.out_bvec.bv_page = ceph_zero_page;
+	con->v2.out_bvec.bv_offset = 0;
+	con->v2.out_bvec.bv_len = min(con->v2.out_zero, (int)PAGE_SIZE);
+	con->v2.out_iter_sendpage = true;
+	iov_iter_bvec(&con->v2.out_iter, WRITE, &con->v2.out_bvec, 1,
+		      con->v2.out_bvec.bv_len);
+}
+
+static void out_zero_add(struct ceph_connection *con, int len)
+{
+	dout("%s con %p len %d\n", __func__, con, len);
+	con->v2.out_zero += len;
+}
+
+static void *alloc_conn_buf(struct ceph_connection *con, int len)
+{
+	void *buf;
+
+	dout("%s con %p len %d\n", __func__, con, len);
+
+	if (WARN_ON(con->v2.conn_buf_cnt >= ARRAY_SIZE(con->v2.conn_bufs)))
+		return NULL;
+
+	buf = ceph_kvmalloc(len, GFP_NOIO);
+	if (!buf)
+		return NULL;
+
+	con->v2.conn_bufs[con->v2.conn_buf_cnt++] = buf;
+	return buf;
+}
+
+static void free_conn_bufs(struct ceph_connection *con)
+{
+	while (con->v2.conn_buf_cnt)
+		kvfree(con->v2.conn_bufs[--con->v2.conn_buf_cnt]);
+}
+
+static void add_in_sign_kvec(struct ceph_connection *con, void *buf, int len)
+{
+	BUG_ON(con->v2.in_sign_kvec_cnt >= ARRAY_SIZE(con->v2.in_sign_kvecs));
+
+	con->v2.in_sign_kvecs[con->v2.in_sign_kvec_cnt].iov_base = buf;
+	con->v2.in_sign_kvecs[con->v2.in_sign_kvec_cnt].iov_len = len;
+	con->v2.in_sign_kvec_cnt++;
+}
+
+static void clear_in_sign_kvecs(struct ceph_connection *con)
+{
+	con->v2.in_sign_kvec_cnt = 0;
+}
+
+static void add_out_sign_kvec(struct ceph_connection *con, void *buf, int len)
+{
+	BUG_ON(con->v2.out_sign_kvec_cnt >= ARRAY_SIZE(con->v2.out_sign_kvecs));
+
+	con->v2.out_sign_kvecs[con->v2.out_sign_kvec_cnt].iov_base = buf;
+	con->v2.out_sign_kvecs[con->v2.out_sign_kvec_cnt].iov_len = len;
+	con->v2.out_sign_kvec_cnt++;
+}
+
+static void clear_out_sign_kvecs(struct ceph_connection *con)
+{
+	con->v2.out_sign_kvec_cnt = 0;
+}
+
+static bool con_secure(struct ceph_connection *con)
+{
+	return con->v2.con_mode == CEPH_CON_MODE_SECURE;
+}
+
+static int front_len(const struct ceph_msg *msg)
+{
+	return le32_to_cpu(msg->hdr.front_len);
+}
+
+static int middle_len(const struct ceph_msg *msg)
+{
+	return le32_to_cpu(msg->hdr.middle_len);
+}
+
+static int data_len(const struct ceph_msg *msg)
+{
+	return le32_to_cpu(msg->hdr.data_len);
+}
+
+static bool need_padding(int len)
+{
+	return !IS_ALIGNED(len, CEPH_GCM_BLOCK_LEN);
+}
+
+static int padded_len(int len)
+{
+	return ALIGN(len, CEPH_GCM_BLOCK_LEN);
+}
+
+static int padding_len(int len)
+{
+	return padded_len(len) - len;
+}
+
+/* preamble + control segment */
+static int head_onwire_len(int ctrl_len, bool secure)
+{
+	int head_len;
+	int rem_len;
+
+	if (secure) {
+		head_len = CEPH_PREAMBLE_SECURE_LEN;
+		if (ctrl_len > CEPH_PREAMBLE_INLINE_LEN) {
+			rem_len = ctrl_len - CEPH_PREAMBLE_INLINE_LEN;
+			head_len += padded_len(rem_len) + CEPH_GCM_TAG_LEN;
+		}
+	} else {
+		head_len = CEPH_PREAMBLE_PLAIN_LEN;
+		if (ctrl_len)
+			head_len += ctrl_len + CEPH_CRC_LEN;
+	}
+	return head_len;
+}
+
+/* front, middle and data segments + epilogue */
+static int __tail_onwire_len(int front_len, int middle_len, int data_len,
+			     bool secure)
+{
+	if (!front_len && !middle_len && !data_len)
+		return 0;
+
+	if (!secure)
+		return front_len + middle_len + data_len +
+		       CEPH_EPILOGUE_PLAIN_LEN;
+
+	return padded_len(front_len) + padded_len(middle_len) +
+	       padded_len(data_len) + CEPH_EPILOGUE_SECURE_LEN;
+}
+
+static int tail_onwire_len(const struct ceph_msg *msg, bool secure)
+{
+	return __tail_onwire_len(front_len(msg), middle_len(msg),
+				 data_len(msg), secure);
+}
+
+/* head_onwire_len(sizeof(struct ceph_msg_header2), false) */
+#define MESSAGE_HEAD_PLAIN_LEN	(CEPH_PREAMBLE_PLAIN_LEN +		\
+				 sizeof(struct ceph_msg_header2) +	\
+				 CEPH_CRC_LEN)
+
+static const int frame_aligns[] = {
+	sizeof(void *),
+	sizeof(void *),
+	sizeof(void *),
+	PAGE_SIZE
+};
+
+/*
+ * Discards trailing empty segments, unless there is just one segment.
+ * A frame always has at least one (possibly empty) segment.
+ */
+static int calc_segment_count(const int *lens, int len_cnt)
+{
+	int i;
+
+	for (i = len_cnt - 1; i >= 0; i--) {
+		if (lens[i])
+			return i + 1;
+	}
+
+	return 1;
+}
+
+static void init_frame_desc(struct ceph_frame_desc *desc, int tag,
+			    const int *lens, int len_cnt)
+{
+	int i;
+
+	memset(desc, 0, sizeof(*desc));
+
+	desc->fd_tag = tag;
+	desc->fd_seg_cnt = calc_segment_count(lens, len_cnt);
+	BUG_ON(desc->fd_seg_cnt > CEPH_FRAME_MAX_SEGMENT_COUNT);
+	for (i = 0; i < desc->fd_seg_cnt; i++) {
+		desc->fd_lens[i] = lens[i];
+		desc->fd_aligns[i] = frame_aligns[i];
+	}
+}
+
+/*
+ * Preamble crc covers everything up to itself (28 bytes) and
+ * is calculated and verified irrespective of the connection mode
+ * (i.e. even if the frame is encrypted).
+ */
+static void encode_preamble(const struct ceph_frame_desc *desc, void *p)
+{
+	void *crcp = p + CEPH_PREAMBLE_LEN - CEPH_CRC_LEN;
+	void *start = p;
+	int i;
+
+	memset(p, 0, CEPH_PREAMBLE_LEN);
+
+	ceph_encode_8(&p, desc->fd_tag);
+	ceph_encode_8(&p, desc->fd_seg_cnt);
+	for (i = 0; i < desc->fd_seg_cnt; i++) {
+		ceph_encode_32(&p, desc->fd_lens[i]);
+		ceph_encode_16(&p, desc->fd_aligns[i]);
+	}
+
+	put_unaligned_le32(crc32c(0, start, crcp - start), crcp);
+}
+
+static int decode_preamble(void *p, struct ceph_frame_desc *desc)
+{
+	void *crcp = p + CEPH_PREAMBLE_LEN - CEPH_CRC_LEN;
+	u32 crc, expected_crc;
+	int i;
+
+	crc = crc32c(0, p, crcp - p);
+	expected_crc = get_unaligned_le32(crcp);
+	if (crc != expected_crc) {
+		pr_err("bad preamble crc, calculated %u, expected %u\n",
+		       crc, expected_crc);
+		return -EBADMSG;
+	}
+
+	memset(desc, 0, sizeof(*desc));
+
+	desc->fd_tag = ceph_decode_8(&p);
+	desc->fd_seg_cnt = ceph_decode_8(&p);
+	if (desc->fd_seg_cnt < 1 ||
+	    desc->fd_seg_cnt > CEPH_FRAME_MAX_SEGMENT_COUNT) {
+		pr_err("bad segment count %d\n", desc->fd_seg_cnt);
+		return -EINVAL;
+	}
+	for (i = 0; i < desc->fd_seg_cnt; i++) {
+		desc->fd_lens[i] = ceph_decode_32(&p);
+		desc->fd_aligns[i] = ceph_decode_16(&p);
+	}
+
+	/*
+	 * This would fire for FRAME_TAG_WAIT (it has one empty
+	 * segment), but we should never get it as client.
+	 */
+	if (!desc->fd_lens[desc->fd_seg_cnt - 1]) {
+		pr_err("last segment empty\n");
+		return -EINVAL;
+	}
+
+	if (desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) {
+		pr_err("control segment too big %d\n", desc->fd_lens[0]);
+		return -EINVAL;
+	}
+	if (desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) {
+		pr_err("front segment too big %d\n", desc->fd_lens[1]);
+		return -EINVAL;
+	}
+	if (desc->fd_lens[2] > CEPH_MSG_MAX_MIDDLE_LEN) {
+		pr_err("middle segment too big %d\n", desc->fd_lens[2]);
+		return -EINVAL;
+	}
+	if (desc->fd_lens[3] > CEPH_MSG_MAX_DATA_LEN) {
+		pr_err("data segment too big %d\n", desc->fd_lens[3]);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void encode_epilogue_plain(struct ceph_connection *con, bool aborted)
+{
+	con->v2.out_epil.late_status = aborted ? FRAME_LATE_STATUS_ABORTED :
+						 FRAME_LATE_STATUS_COMPLETE;
+	cpu_to_le32s(&con->v2.out_epil.front_crc);
+	cpu_to_le32s(&con->v2.out_epil.middle_crc);
+	cpu_to_le32s(&con->v2.out_epil.data_crc);
+}
+
+static void encode_epilogue_secure(struct ceph_connection *con, bool aborted)
+{
+	memset(&con->v2.out_epil, 0, sizeof(con->v2.out_epil));
+	con->v2.out_epil.late_status = aborted ? FRAME_LATE_STATUS_ABORTED :
+						 FRAME_LATE_STATUS_COMPLETE;
+}
+
+static int decode_epilogue(void *p, u32 *front_crc, u32 *middle_crc,
+			   u32 *data_crc)
+{
+	u8 late_status;
+
+	late_status = ceph_decode_8(&p);
+	if ((late_status & FRAME_LATE_STATUS_ABORTED_MASK) !=
+			FRAME_LATE_STATUS_COMPLETE) {
+		/* we should never get an aborted message as client */
+		pr_err("bad late_status 0x%x\n", late_status);
+		return -EINVAL;
+	}
+
+	if (front_crc && middle_crc && data_crc) {
+		*front_crc = ceph_decode_32(&p);
+		*middle_crc = ceph_decode_32(&p);
+		*data_crc = ceph_decode_32(&p);
+	}
+
+	return 0;
+}
+
+static void fill_header(struct ceph_msg_header *hdr,
+			const struct ceph_msg_header2 *hdr2,
+			int front_len, int middle_len, int data_len,
+			const struct ceph_entity_name *peer_name)
+{
+	hdr->seq = hdr2->seq;
+	hdr->tid = hdr2->tid;
+	hdr->type = hdr2->type;
+	hdr->priority = hdr2->priority;
+	hdr->version = hdr2->version;
+	hdr->front_len = cpu_to_le32(front_len);
+	hdr->middle_len = cpu_to_le32(middle_len);
+	hdr->data_len = cpu_to_le32(data_len);
+	hdr->data_off = hdr2->data_off;
+	hdr->src = *peer_name;
+	hdr->compat_version = hdr2->compat_version;
+	hdr->reserved = 0;
+	hdr->crc = 0;
+}
+
+static void fill_header2(struct ceph_msg_header2 *hdr2,
+			 const struct ceph_msg_header *hdr, u64 ack_seq)
+{
+	hdr2->seq = hdr->seq;
+	hdr2->tid = hdr->tid;
+	hdr2->type = hdr->type;
+	hdr2->priority = hdr->priority;
+	hdr2->version = hdr->version;
+	hdr2->data_pre_padding_len = 0;
+	hdr2->data_off = hdr->data_off;
+	hdr2->ack_seq = cpu_to_le64(ack_seq);
+	hdr2->flags = 0;
+	hdr2->compat_version = hdr->compat_version;
+	hdr2->reserved = 0;
+}
+
+static int verify_control_crc(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	u32 crc, expected_crc;
+
+	WARN_ON(con->v2.in_kvecs[0].iov_len != ctrl_len);
+	WARN_ON(con->v2.in_kvecs[1].iov_len != CEPH_CRC_LEN);
+
+	crc = crc32c(-1, con->v2.in_kvecs[0].iov_base, ctrl_len);
+	expected_crc = get_unaligned_le32(con->v2.in_kvecs[1].iov_base);
+	if (crc != expected_crc) {
+		pr_err("bad control crc, calculated %u, expected %u\n",
+		       crc, expected_crc);
+		return -EBADMSG;
+	}
+
+	return 0;
+}
+
+static int verify_epilogue_crcs(struct ceph_connection *con, u32 front_crc,
+				u32 middle_crc, u32 data_crc)
+{
+	if (front_len(con->in_msg)) {
+		con->in_front_crc = crc32c(-1, con->in_msg->front.iov_base,
+					   front_len(con->in_msg));
+	} else {
+		WARN_ON(!middle_len(con->in_msg) && !data_len(con->in_msg));
+		con->in_front_crc = -1;
+	}
+
+	if (middle_len(con->in_msg))
+		con->in_middle_crc = crc32c(-1,
+					    con->in_msg->middle->vec.iov_base,
+					    middle_len(con->in_msg));
+	else if (data_len(con->in_msg))
+		con->in_middle_crc = -1;
+	else
+		con->in_middle_crc = 0;
+
+	if (!data_len(con->in_msg))
+		con->in_data_crc = 0;
+
+	dout("%s con %p msg %p crcs %u %u %u\n", __func__, con, con->in_msg,
+	     con->in_front_crc, con->in_middle_crc, con->in_data_crc);
+
+	if (con->in_front_crc != front_crc) {
+		pr_err("bad front crc, calculated %u, expected %u\n",
+		       con->in_front_crc, front_crc);
+		return -EBADMSG;
+	}
+	if (con->in_middle_crc != middle_crc) {
+		pr_err("bad middle crc, calculated %u, expected %u\n",
+		       con->in_middle_crc, middle_crc);
+		return -EBADMSG;
+	}
+	if (con->in_data_crc != data_crc) {
+		pr_err("bad data crc, calculated %u, expected %u\n",
+		       con->in_data_crc, data_crc);
+		return -EBADMSG;
+	}
+
+	return 0;
+}
+
+static int setup_crypto(struct ceph_connection *con,
+			const u8 *session_key, int session_key_len,
+			const u8 *con_secret, int con_secret_len)
+{
+	unsigned int noio_flag;
+	int ret;
+
+	dout("%s con %p con_mode %d session_key_len %d con_secret_len %d\n",
+	     __func__, con, con->v2.con_mode, session_key_len, con_secret_len);
+	WARN_ON(con->v2.hmac_tfm || con->v2.gcm_tfm || con->v2.gcm_req);
+
+	if (con->v2.con_mode != CEPH_CON_MODE_CRC &&
+	    con->v2.con_mode != CEPH_CON_MODE_SECURE) {
+		pr_err("bad con_mode %d\n", con->v2.con_mode);
+		return -EINVAL;
+	}
+
+	if (!session_key_len) {
+		WARN_ON(con->v2.con_mode != CEPH_CON_MODE_CRC);
+		WARN_ON(con_secret_len);
+		return 0;  /* auth_none */
+	}
+
+	noio_flag = memalloc_noio_save();
+	con->v2.hmac_tfm = crypto_alloc_shash("hmac(sha256)", 0, 0);
+	memalloc_noio_restore(noio_flag);
+	if (IS_ERR(con->v2.hmac_tfm)) {
+		ret = PTR_ERR(con->v2.hmac_tfm);
+		con->v2.hmac_tfm = NULL;
+		pr_err("failed to allocate hmac tfm context: %d\n", ret);
+		return ret;
+	}
+
+	WARN_ON((unsigned long)session_key &
+		crypto_shash_alignmask(con->v2.hmac_tfm));
+	ret = crypto_shash_setkey(con->v2.hmac_tfm, session_key,
+				  session_key_len);
+	if (ret) {
+		pr_err("failed to set hmac key: %d\n", ret);
+		return ret;
+	}
+
+	if (con->v2.con_mode == CEPH_CON_MODE_CRC) {
+		WARN_ON(con_secret_len);
+		return 0;  /* auth_x, plain mode */
+	}
+
+	if (con_secret_len < CEPH_GCM_KEY_LEN + 2 * CEPH_GCM_IV_LEN) {
+		pr_err("con_secret too small %d\n", con_secret_len);
+		return -EINVAL;
+	}
+
+	noio_flag = memalloc_noio_save();
+	con->v2.gcm_tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
+	memalloc_noio_restore(noio_flag);
+	if (IS_ERR(con->v2.gcm_tfm)) {
+		ret = PTR_ERR(con->v2.gcm_tfm);
+		con->v2.gcm_tfm = NULL;
+		pr_err("failed to allocate gcm tfm context: %d\n", ret);
+		return ret;
+	}
+
+	WARN_ON((unsigned long)con_secret &
+		crypto_aead_alignmask(con->v2.gcm_tfm));
+	ret = crypto_aead_setkey(con->v2.gcm_tfm, con_secret, CEPH_GCM_KEY_LEN);
+	if (ret) {
+		pr_err("failed to set gcm key: %d\n", ret);
+		return ret;
+	}
+
+	WARN_ON(crypto_aead_ivsize(con->v2.gcm_tfm) != CEPH_GCM_IV_LEN);
+	ret = crypto_aead_setauthsize(con->v2.gcm_tfm, CEPH_GCM_TAG_LEN);
+	if (ret) {
+		pr_err("failed to set gcm tag size: %d\n", ret);
+		return ret;
+	}
+
+	con->v2.gcm_req = aead_request_alloc(con->v2.gcm_tfm, GFP_NOIO);
+	if (!con->v2.gcm_req) {
+		pr_err("failed to allocate gcm request\n");
+		return -ENOMEM;
+	}
+
+	crypto_init_wait(&con->v2.gcm_wait);
+	aead_request_set_callback(con->v2.gcm_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				  crypto_req_done, &con->v2.gcm_wait);
+
+	memcpy(&con->v2.in_gcm_nonce, con_secret + CEPH_GCM_KEY_LEN,
+	       CEPH_GCM_IV_LEN);
+	memcpy(&con->v2.out_gcm_nonce,
+	       con_secret + CEPH_GCM_KEY_LEN + CEPH_GCM_IV_LEN,
+	       CEPH_GCM_IV_LEN);
+	return 0;  /* auth_x, secure mode */
+}
+
+static int hmac_sha256(struct ceph_connection *con, const struct kvec *kvecs,
+		       int kvec_cnt, u8 *hmac)
+{
+	SHASH_DESC_ON_STACK(desc, con->v2.hmac_tfm);  /* tfm arg is ignored */
+	int ret;
+	int i;
+
+	dout("%s con %p hmac_tfm %p kvec_cnt %d\n", __func__, con,
+	     con->v2.hmac_tfm, kvec_cnt);
+
+	if (!con->v2.hmac_tfm) {
+		memset(hmac, 0, SHA256_DIGEST_SIZE);
+		return 0;  /* auth_none */
+	}
+
+	desc->tfm = con->v2.hmac_tfm;
+	ret = crypto_shash_init(desc);
+	if (ret)
+		goto out;
+
+	for (i = 0; i < kvec_cnt; i++) {
+		WARN_ON((unsigned long)kvecs[i].iov_base &
+			crypto_shash_alignmask(con->v2.hmac_tfm));
+		ret = crypto_shash_update(desc, kvecs[i].iov_base,
+					  kvecs[i].iov_len);
+		if (ret)
+			goto out;
+	}
+
+	ret = crypto_shash_final(desc, hmac);
+
+out:
+	shash_desc_zero(desc);
+	return ret;  /* auth_x, both plain and secure modes */
+}
+
+static void gcm_inc_nonce(struct ceph_gcm_nonce *nonce)
+{
+	u64 counter;
+
+	counter = le64_to_cpu(nonce->counter);
+	nonce->counter = cpu_to_le64(counter + 1);
+}
+
+static int gcm_crypt(struct ceph_connection *con, bool encrypt,
+		     struct scatterlist *src, struct scatterlist *dst,
+		     int src_len)
+{
+	struct ceph_gcm_nonce *nonce;
+	int ret;
+
+	nonce = encrypt ? &con->v2.out_gcm_nonce : &con->v2.in_gcm_nonce;
+
+	aead_request_set_ad(con->v2.gcm_req, 0);  /* no AAD */
+	aead_request_set_crypt(con->v2.gcm_req, src, dst, src_len, (u8 *)nonce);
+	ret = crypto_wait_req(encrypt ? crypto_aead_encrypt(con->v2.gcm_req) :
+					crypto_aead_decrypt(con->v2.gcm_req),
+			      &con->v2.gcm_wait);
+	if (ret)
+		return ret;
+
+	gcm_inc_nonce(nonce);
+	return 0;
+}
+
+static void get_bvec_at(struct ceph_msg_data_cursor *cursor,
+			struct bio_vec *bv)
+{
+	struct page *page;
+	size_t off, len;
+
+	WARN_ON(!cursor->total_resid);
+
+	/* skip zero-length data items */
+	while (!cursor->resid)
+		ceph_msg_data_advance(cursor, 0);
+
+	/* get a piece of data, cursor isn't advanced */
+	page = ceph_msg_data_next(cursor, &off, &len, NULL);
+
+	bv->bv_page = page;
+	bv->bv_offset = off;
+	bv->bv_len = len;
+}
+
+static int calc_sg_cnt(void *buf, int buf_len)
+{
+	int sg_cnt;
+
+	if (!buf_len)
+		return 0;
+
+	sg_cnt = need_padding(buf_len) ? 1 : 0;
+	if (is_vmalloc_addr(buf)) {
+		WARN_ON(offset_in_page(buf));
+		sg_cnt += PAGE_ALIGN(buf_len) >> PAGE_SHIFT;
+	} else {
+		sg_cnt++;
+	}
+
+	return sg_cnt;
+}
+
+static int calc_sg_cnt_cursor(struct ceph_msg_data_cursor *cursor)
+{
+	int data_len = cursor->total_resid;
+	struct bio_vec bv;
+	int sg_cnt;
+
+	if (!data_len)
+		return 0;
+
+	sg_cnt = need_padding(data_len) ? 1 : 0;
+	do {
+		get_bvec_at(cursor, &bv);
+		sg_cnt++;
+
+		ceph_msg_data_advance(cursor, bv.bv_len);
+	} while (cursor->total_resid);
+
+	return sg_cnt;
+}
+
+static void init_sgs(struct scatterlist **sg, void *buf, int buf_len, u8 *pad)
+{
+	void *end = buf + buf_len;
+	struct page *page;
+	int len;
+	void *p;
+
+	if (!buf_len)
+		return;
+
+	if (is_vmalloc_addr(buf)) {
+		p = buf;
+		do {
+			page = vmalloc_to_page(p);
+			len = min_t(int, end - p, PAGE_SIZE);
+			WARN_ON(!page || !len || offset_in_page(p));
+			sg_set_page(*sg, page, len, 0);
+			*sg = sg_next(*sg);
+			p += len;
+		} while (p != end);
+	} else {
+		sg_set_buf(*sg, buf, buf_len);
+		*sg = sg_next(*sg);
+	}
+
+	if (need_padding(buf_len)) {
+		sg_set_buf(*sg, pad, padding_len(buf_len));
+		*sg = sg_next(*sg);
+	}
+}
+
+static void init_sgs_cursor(struct scatterlist **sg,
+			    struct ceph_msg_data_cursor *cursor, u8 *pad)
+{
+	int data_len = cursor->total_resid;
+	struct bio_vec bv;
+
+	if (!data_len)
+		return;
+
+	do {
+		get_bvec_at(cursor, &bv);
+		sg_set_page(*sg, bv.bv_page, bv.bv_len, bv.bv_offset);
+		*sg = sg_next(*sg);
+
+		ceph_msg_data_advance(cursor, bv.bv_len);
+	} while (cursor->total_resid);
+
+	if (need_padding(data_len)) {
+		sg_set_buf(*sg, pad, padding_len(data_len));
+		*sg = sg_next(*sg);
+	}
+}
+
+static int setup_message_sgs(struct sg_table *sgt, struct ceph_msg *msg,
+			     u8 *front_pad, u8 *middle_pad, u8 *data_pad,
+			     void *epilogue, bool add_tag)
+{
+	struct ceph_msg_data_cursor cursor;
+	struct scatterlist *cur_sg;
+	int sg_cnt;
+	int ret;
+
+	if (!front_len(msg) && !middle_len(msg) && !data_len(msg))
+		return 0;
+
+	sg_cnt = 1;  /* epilogue + [auth tag] */
+	if (front_len(msg))
+		sg_cnt += calc_sg_cnt(msg->front.iov_base,
+				      front_len(msg));
+	if (middle_len(msg))
+		sg_cnt += calc_sg_cnt(msg->middle->vec.iov_base,
+				      middle_len(msg));
+	if (data_len(msg)) {
+		ceph_msg_data_cursor_init(&cursor, msg, data_len(msg));
+		sg_cnt += calc_sg_cnt_cursor(&cursor);
+	}
+
+	ret = sg_alloc_table(sgt, sg_cnt, GFP_NOIO);
+	if (ret)
+		return ret;
+
+	cur_sg = sgt->sgl;
+	if (front_len(msg))
+		init_sgs(&cur_sg, msg->front.iov_base, front_len(msg),
+			 front_pad);
+	if (middle_len(msg))
+		init_sgs(&cur_sg, msg->middle->vec.iov_base, middle_len(msg),
+			 middle_pad);
+	if (data_len(msg)) {
+		ceph_msg_data_cursor_init(&cursor, msg, data_len(msg));
+		init_sgs_cursor(&cur_sg, &cursor, data_pad);
+	}
+
+	WARN_ON(!sg_is_last(cur_sg));
+	sg_set_buf(cur_sg, epilogue,
+		   CEPH_GCM_BLOCK_LEN + (add_tag ? CEPH_GCM_TAG_LEN : 0));
+	return 0;
+}
+
+static int decrypt_preamble(struct ceph_connection *con)
+{
+	struct scatterlist sg;
+
+	sg_init_one(&sg, con->v2.in_buf, CEPH_PREAMBLE_SECURE_LEN);
+	return gcm_crypt(con, false, &sg, &sg, CEPH_PREAMBLE_SECURE_LEN);
+}
+
+static int decrypt_control_remainder(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	int rem_len = ctrl_len - CEPH_PREAMBLE_INLINE_LEN;
+	int pt_len = padding_len(rem_len) + CEPH_GCM_TAG_LEN;
+	struct scatterlist sgs[2];
+
+	WARN_ON(con->v2.in_kvecs[0].iov_len != rem_len);
+	WARN_ON(con->v2.in_kvecs[1].iov_len != pt_len);
+
+	sg_init_table(sgs, 2);
+	sg_set_buf(&sgs[0], con->v2.in_kvecs[0].iov_base, rem_len);
+	sg_set_buf(&sgs[1], con->v2.in_buf, pt_len);
+
+	return gcm_crypt(con, false, sgs, sgs,
+			 padded_len(rem_len) + CEPH_GCM_TAG_LEN);
+}
+
+static int decrypt_message(struct ceph_connection *con)
+{
+	struct sg_table sgt = {};
+	int ret;
+
+	ret = setup_message_sgs(&sgt, con->in_msg, FRONT_PAD(con->v2.in_buf),
+			MIDDLE_PAD(con->v2.in_buf), DATA_PAD(con->v2.in_buf),
+			con->v2.in_buf, true);
+	if (ret)
+		goto out;
+
+	ret = gcm_crypt(con, false, sgt.sgl, sgt.sgl,
+			tail_onwire_len(con->in_msg, true));
+
+out:
+	sg_free_table(&sgt);
+	return ret;
+}
+
+static int prepare_banner(struct ceph_connection *con)
+{
+	int buf_len = CEPH_BANNER_V2_LEN + 2 + 8 + 8;
+	void *buf, *p;
+
+	buf = alloc_conn_buf(con, buf_len);
+	if (!buf)
+		return -ENOMEM;
+
+	p = buf;
+	ceph_encode_copy(&p, CEPH_BANNER_V2, CEPH_BANNER_V2_LEN);
+	ceph_encode_16(&p, sizeof(u64) + sizeof(u64));
+	ceph_encode_64(&p, CEPH_MSGR2_SUPPORTED_FEATURES);
+	ceph_encode_64(&p, CEPH_MSGR2_REQUIRED_FEATURES);
+	WARN_ON(p != buf + buf_len);
+
+	add_out_kvec(con, buf, buf_len);
+	add_out_sign_kvec(con, buf, buf_len);
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	return 0;
+}
+
+/*
+ * base:
+ *   preamble
+ *   control body (ctrl_len bytes)
+ *   space for control crc
+ *
+ * extdata (optional):
+ *   control body (extdata_len bytes)
+ *
+ * Compute control crc and gather base and extdata into:
+ *
+ *   preamble
+ *   control body (ctrl_len + extdata_len bytes)
+ *   control crc
+ *
+ * Preamble should already be encoded at the start of base.
+ */
+static void prepare_head_plain(struct ceph_connection *con, void *base,
+			       int ctrl_len, void *extdata, int extdata_len,
+			       bool to_be_signed)
+{
+	int base_len = CEPH_PREAMBLE_LEN + ctrl_len + CEPH_CRC_LEN;
+	void *crcp = base + base_len - CEPH_CRC_LEN;
+	u32 crc;
+
+	crc = crc32c(-1, CTRL_BODY(base), ctrl_len);
+	if (extdata_len)
+		crc = crc32c(crc, extdata, extdata_len);
+	put_unaligned_le32(crc, crcp);
+
+	if (!extdata_len) {
+		add_out_kvec(con, base, base_len);
+		if (to_be_signed)
+			add_out_sign_kvec(con, base, base_len);
+		return;
+	}
+
+	add_out_kvec(con, base, crcp - base);
+	add_out_kvec(con, extdata, extdata_len);
+	add_out_kvec(con, crcp, CEPH_CRC_LEN);
+	if (to_be_signed) {
+		add_out_sign_kvec(con, base, crcp - base);
+		add_out_sign_kvec(con, extdata, extdata_len);
+		add_out_sign_kvec(con, crcp, CEPH_CRC_LEN);
+	}
+}
+
+static int prepare_head_secure_small(struct ceph_connection *con,
+				     void *base, int ctrl_len)
+{
+	struct scatterlist sg;
+	int ret;
+
+	/* inline buffer padding? */
+	if (ctrl_len < CEPH_PREAMBLE_INLINE_LEN)
+		memset(CTRL_BODY(base) + ctrl_len, 0,
+		       CEPH_PREAMBLE_INLINE_LEN - ctrl_len);
+
+	sg_init_one(&sg, base, CEPH_PREAMBLE_SECURE_LEN);
+	ret = gcm_crypt(con, true, &sg, &sg,
+			CEPH_PREAMBLE_SECURE_LEN - CEPH_GCM_TAG_LEN);
+	if (ret)
+		return ret;
+
+	add_out_kvec(con, base, CEPH_PREAMBLE_SECURE_LEN);
+	return 0;
+}
+
+/*
+ * base:
+ *   preamble
+ *   control body (ctrl_len bytes)
+ *   space for padding, if needed
+ *   space for control remainder auth tag
+ *   space for preamble auth tag
+ *
+ * Encrypt preamble and the inline portion, then encrypt the remainder
+ * and gather into:
+ *
+ *   preamble
+ *   control body (48 bytes)
+ *   preamble auth tag
+ *   control body (ctrl_len - 48 bytes)
+ *   zero padding, if needed
+ *   control remainder auth tag
+ *
+ * Preamble should already be encoded at the start of base.
+ */
+static int prepare_head_secure_big(struct ceph_connection *con,
+				   void *base, int ctrl_len)
+{
+	int rem_len = ctrl_len - CEPH_PREAMBLE_INLINE_LEN;
+	void *rem = CTRL_BODY(base) + CEPH_PREAMBLE_INLINE_LEN;
+	void *rem_tag = rem + padded_len(rem_len);
+	void *pmbl_tag = rem_tag + CEPH_GCM_TAG_LEN;
+	struct scatterlist sgs[2];
+	int ret;
+
+	sg_init_table(sgs, 2);
+	sg_set_buf(&sgs[0], base, rem - base);
+	sg_set_buf(&sgs[1], pmbl_tag, CEPH_GCM_TAG_LEN);
+	ret = gcm_crypt(con, true, sgs, sgs, rem - base);
+	if (ret)
+		return ret;
+
+	/* control remainder padding? */
+	if (need_padding(rem_len))
+		memset(rem + rem_len, 0, padding_len(rem_len));
+
+	sg_init_one(&sgs[0], rem, pmbl_tag - rem);
+	ret = gcm_crypt(con, true, sgs, sgs, rem_tag - rem);
+	if (ret)
+		return ret;
+
+	add_out_kvec(con, base, rem - base);
+	add_out_kvec(con, pmbl_tag, CEPH_GCM_TAG_LEN);
+	add_out_kvec(con, rem, pmbl_tag - rem);
+	return 0;
+}
+
+static int __prepare_control(struct ceph_connection *con, int tag,
+			     void *base, int ctrl_len, void *extdata,
+			     int extdata_len, bool to_be_signed)
+{
+	int total_len = ctrl_len + extdata_len;
+	struct ceph_frame_desc desc;
+	int ret;
+
+	dout("%s con %p tag %d len %d (%d+%d)\n", __func__, con, tag,
+	     total_len, ctrl_len, extdata_len);
+
+	/* extdata may be vmalloc'ed but not base */
+	if (WARN_ON(is_vmalloc_addr(base) || !ctrl_len))
+		return -EINVAL;
+
+	init_frame_desc(&desc, tag, &total_len, 1);
+	encode_preamble(&desc, base);
+
+	if (con_secure(con)) {
+		if (WARN_ON(extdata_len || to_be_signed))
+			return -EINVAL;
+
+		if (ctrl_len <= CEPH_PREAMBLE_INLINE_LEN)
+			/* fully inlined, inline buffer may need padding */
+			ret = prepare_head_secure_small(con, base, ctrl_len);
+		else
+			/* partially inlined, inline buffer is full */
+			ret = prepare_head_secure_big(con, base, ctrl_len);
+		if (ret)
+			return ret;
+	} else {
+		prepare_head_plain(con, base, ctrl_len, extdata, extdata_len,
+				   to_be_signed);
+	}
+
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	return 0;
+}
+
+static int prepare_control(struct ceph_connection *con, int tag,
+			   void *base, int ctrl_len)
+{
+	return __prepare_control(con, tag, base, ctrl_len, NULL, 0, false);
+}
+
+static int prepare_hello(struct ceph_connection *con)
+{
+	void *buf, *p;
+	int ctrl_len;
+
+	ctrl_len = 1 + ceph_entity_addr_encoding_len(&con->peer_addr);
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, false));
+	if (!buf)
+		return -ENOMEM;
+
+	p = CTRL_BODY(buf);
+	ceph_encode_8(&p, CEPH_ENTITY_TYPE_CLIENT);
+	ceph_encode_entity_addr(&p, &con->peer_addr);
+	WARN_ON(p != CTRL_BODY(buf) + ctrl_len);
+
+	return __prepare_control(con, FRAME_TAG_HELLO, buf, ctrl_len,
+				 NULL, 0, true);
+}
+
+/* so that head_onwire_len(AUTH_BUF_LEN, false) is 512 */
+#define AUTH_BUF_LEN	(512 - CEPH_CRC_LEN - CEPH_PREAMBLE_PLAIN_LEN)
+
+static int prepare_auth_request(struct ceph_connection *con)
+{
+	void *authorizer, *authorizer_copy;
+	int ctrl_len, authorizer_len;
+	void *buf;
+	int ret;
+
+	ctrl_len = AUTH_BUF_LEN;
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, false));
+	if (!buf)
+		return -ENOMEM;
+
+	mutex_unlock(&con->mutex);
+	ret = con->ops->get_auth_request(con, CTRL_BODY(buf), &ctrl_len,
+					 &authorizer, &authorizer_len);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_HELLO) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	dout("%s con %p get_auth_request ret %d\n", __func__, con, ret);
+	if (ret)
+		return ret;
+
+	authorizer_copy = alloc_conn_buf(con, authorizer_len);
+	if (!authorizer_copy)
+		return -ENOMEM;
+
+	memcpy(authorizer_copy, authorizer, authorizer_len);
+
+	return __prepare_control(con, FRAME_TAG_AUTH_REQUEST, buf, ctrl_len,
+				 authorizer_copy, authorizer_len, true);
+}
+
+static int prepare_auth_request_more(struct ceph_connection *con,
+				     void *reply, int reply_len)
+{
+	int ctrl_len, authorizer_len;
+	void *authorizer;
+	void *buf;
+	int ret;
+
+	ctrl_len = AUTH_BUF_LEN;
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, false));
+	if (!buf)
+		return -ENOMEM;
+
+	mutex_unlock(&con->mutex);
+	ret = con->ops->handle_auth_reply_more(con, reply, reply_len,
+					       CTRL_BODY(buf), &ctrl_len,
+					       &authorizer, &authorizer_len);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	dout("%s con %p handle_auth_reply_more ret %d\n", __func__, con, ret);
+	if (ret)
+		return ret;
+
+	return __prepare_control(con, FRAME_TAG_AUTH_REQUEST_MORE, buf,
+				 ctrl_len, authorizer, authorizer_len, true);
+}
+
+static int prepare_auth_signature(struct ceph_connection *con)
+{
+	void *buf;
+	int ret;
+
+	buf = alloc_conn_buf(con, head_onwire_len(SHA256_DIGEST_SIZE,
+						  con_secure(con)));
+	if (!buf)
+		return -ENOMEM;
+
+	ret = hmac_sha256(con, con->v2.in_sign_kvecs, con->v2.in_sign_kvec_cnt,
+			  CTRL_BODY(buf));
+	if (ret)
+		return ret;
+
+	return prepare_control(con, FRAME_TAG_AUTH_SIGNATURE, buf,
+			       SHA256_DIGEST_SIZE);
+}
+
+static int prepare_client_ident(struct ceph_connection *con)
+{
+	struct ceph_entity_addr *my_addr = &con->msgr->inst.addr;
+	struct ceph_client *client = from_msgr(con->msgr);
+	u64 global_id = ceph_client_gid(client);
+	void *buf, *p;
+	int ctrl_len;
+
+	WARN_ON(con->v2.server_cookie);
+	WARN_ON(con->v2.connect_seq);
+	WARN_ON(con->v2.peer_global_seq);
+
+	if (!con->v2.client_cookie) {
+		do {
+			get_random_bytes(&con->v2.client_cookie,
+					 sizeof(con->v2.client_cookie));
+		} while (!con->v2.client_cookie);
+		dout("%s con %p generated cookie 0x%llx\n", __func__, con,
+		     con->v2.client_cookie);
+	} else {
+		dout("%s con %p cookie already set 0x%llx\n", __func__, con,
+		     con->v2.client_cookie);
+	}
+
+	dout("%s con %p my_addr %s/%u peer_addr %s/%u global_id %llu global_seq %llu features 0x%llx required_features 0x%llx cookie 0x%llx\n",
+	     __func__, con, ceph_pr_addr(my_addr), le32_to_cpu(my_addr->nonce),
+	     ceph_pr_addr(&con->peer_addr), le32_to_cpu(con->peer_addr.nonce),
+	     global_id, con->v2.global_seq, client->supported_features,
+	     client->required_features, con->v2.client_cookie);
+
+	ctrl_len = 1 + 4 + ceph_entity_addr_encoding_len(my_addr) +
+		   ceph_entity_addr_encoding_len(&con->peer_addr) + 6 * 8;
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, con_secure(con)));
+	if (!buf)
+		return -ENOMEM;
+
+	p = CTRL_BODY(buf);
+	ceph_encode_8(&p, 2);  /* addrvec marker */
+	ceph_encode_32(&p, 1);  /* addr_cnt */
+	ceph_encode_entity_addr(&p, my_addr);
+	ceph_encode_entity_addr(&p, &con->peer_addr);
+	ceph_encode_64(&p, global_id);
+	ceph_encode_64(&p, con->v2.global_seq);
+	ceph_encode_64(&p, client->supported_features);
+	ceph_encode_64(&p, client->required_features);
+	ceph_encode_64(&p, 0);  /* flags */
+	ceph_encode_64(&p, con->v2.client_cookie);
+	WARN_ON(p != CTRL_BODY(buf) + ctrl_len);
+
+	return prepare_control(con, FRAME_TAG_CLIENT_IDENT, buf, ctrl_len);
+}
+
+static int prepare_session_reconnect(struct ceph_connection *con)
+{
+	struct ceph_entity_addr *my_addr = &con->msgr->inst.addr;
+	void *buf, *p;
+	int ctrl_len;
+
+	WARN_ON(!con->v2.client_cookie);
+	WARN_ON(!con->v2.server_cookie);
+	WARN_ON(!con->v2.connect_seq);
+	WARN_ON(!con->v2.peer_global_seq);
+
+	dout("%s con %p my_addr %s/%u client_cookie 0x%llx server_cookie 0x%llx global_seq %llu connect_seq %llu in_seq %llu\n",
+	     __func__, con, ceph_pr_addr(my_addr), le32_to_cpu(my_addr->nonce),
+	     con->v2.client_cookie, con->v2.server_cookie, con->v2.global_seq,
+	     con->v2.connect_seq, con->in_seq);
+
+	ctrl_len = 1 + 4 + ceph_entity_addr_encoding_len(my_addr) + 5 * 8;
+	buf = alloc_conn_buf(con, head_onwire_len(ctrl_len, con_secure(con)));
+	if (!buf)
+		return -ENOMEM;
+
+	p = CTRL_BODY(buf);
+	ceph_encode_8(&p, 2);  /* entity_addrvec_t marker */
+	ceph_encode_32(&p, 1);  /* my_addrs len */
+	ceph_encode_entity_addr(&p, my_addr);
+	ceph_encode_64(&p, con->v2.client_cookie);
+	ceph_encode_64(&p, con->v2.server_cookie);
+	ceph_encode_64(&p, con->v2.global_seq);
+	ceph_encode_64(&p, con->v2.connect_seq);
+	ceph_encode_64(&p, con->in_seq);
+	WARN_ON(p != CTRL_BODY(buf) + ctrl_len);
+
+	return prepare_control(con, FRAME_TAG_SESSION_RECONNECT, buf, ctrl_len);
+}
+
+static int prepare_keepalive2(struct ceph_connection *con)
+{
+	struct ceph_timespec *ts = CTRL_BODY(con->v2.out_buf);
+	struct timespec64 now;
+
+	ktime_get_real_ts64(&now);
+	dout("%s con %p timestamp %lld.%09ld\n", __func__, con, now.tv_sec,
+	     now.tv_nsec);
+
+	ceph_encode_timespec64(ts, &now);
+
+	reset_out_kvecs(con);
+	return prepare_control(con, FRAME_TAG_KEEPALIVE2, con->v2.out_buf,
+			       sizeof(struct ceph_timespec));
+}
+
+static int prepare_ack(struct ceph_connection *con)
+{
+	void *p;
+
+	dout("%s con %p in_seq_acked %llu -> %llu\n", __func__, con,
+	     con->in_seq_acked, con->in_seq);
+	con->in_seq_acked = con->in_seq;
+
+	p = CTRL_BODY(con->v2.out_buf);
+	ceph_encode_64(&p, con->in_seq_acked);
+
+	reset_out_kvecs(con);
+	return prepare_control(con, FRAME_TAG_ACK, con->v2.out_buf, 8);
+}
+
+static void prepare_epilogue_plain(struct ceph_connection *con, bool aborted)
+{
+	dout("%s con %p msg %p aborted %d crcs %u %u %u\n", __func__, con,
+	     con->out_msg, aborted, con->v2.out_epil.front_crc,
+	     con->v2.out_epil.middle_crc, con->v2.out_epil.data_crc);
+
+	encode_epilogue_plain(con, aborted);
+	add_out_kvec(con, &con->v2.out_epil, CEPH_EPILOGUE_PLAIN_LEN);
+}
+
+/*
+ * For "used" empty segments, crc is -1.  For unused (trailing)
+ * segments, crc is 0.
+ */
+static void prepare_message_plain(struct ceph_connection *con)
+{
+	struct ceph_msg *msg = con->out_msg;
+
+	prepare_head_plain(con, con->v2.out_buf,
+			   sizeof(struct ceph_msg_header2), NULL, 0, false);
+
+	if (!front_len(msg) && !middle_len(msg)) {
+		if (!data_len(msg)) {
+			/*
+			 * Empty message: once the head is written,
+			 * we are done -- there is no epilogue.
+			 */
+			con->v2.out_state = OUT_S_FINISH_MESSAGE;
+			return;
+		}
+
+		con->v2.out_epil.front_crc = -1;
+		con->v2.out_epil.middle_crc = -1;
+		con->v2.out_state = OUT_S_QUEUE_DATA;
+		return;
+	}
+
+	if (front_len(msg)) {
+		con->v2.out_epil.front_crc = crc32c(-1, msg->front.iov_base,
+						    front_len(msg));
+		add_out_kvec(con, msg->front.iov_base, front_len(msg));
+	} else {
+		/* middle (at least) is there, checked above */
+		con->v2.out_epil.front_crc = -1;
+	}
+
+	if (middle_len(msg)) {
+		con->v2.out_epil.middle_crc =
+			crc32c(-1, msg->middle->vec.iov_base, middle_len(msg));
+		add_out_kvec(con, msg->middle->vec.iov_base, middle_len(msg));
+	} else {
+		con->v2.out_epil.middle_crc = data_len(msg) ? -1 : 0;
+	}
+
+	if (data_len(msg)) {
+		con->v2.out_state = OUT_S_QUEUE_DATA;
+	} else {
+		con->v2.out_epil.data_crc = 0;
+		prepare_epilogue_plain(con, false);
+		con->v2.out_state = OUT_S_FINISH_MESSAGE;
+	}
+}
+
+/*
+ * Unfortunately the kernel crypto API doesn't support streaming
+ * (piecewise) operation for AEAD algorithms, so we can't get away
+ * with a fixed size buffer and a couple sgs.  Instead, we have to
+ * allocate pages for the entire tail of the message (currently up
+ * to ~32M) and two sgs arrays (up to ~256K each)...
+ */
+static int prepare_message_secure(struct ceph_connection *con)
+{
+	void *zerop = page_address(ceph_zero_page);
+	struct sg_table enc_sgt = {};
+	struct sg_table sgt = {};
+	struct page **enc_pages;
+	int enc_page_cnt;
+	int tail_len;
+	int ret;
+
+	ret = prepare_head_secure_small(con, con->v2.out_buf,
+					sizeof(struct ceph_msg_header2));
+	if (ret)
+		return ret;
+
+	tail_len = tail_onwire_len(con->out_msg, true);
+	if (!tail_len) {
+		/*
+		 * Empty message: once the head is written,
+		 * we are done -- there is no epilogue.
+		 */
+		con->v2.out_state = OUT_S_FINISH_MESSAGE;
+		return 0;
+	}
+
+	encode_epilogue_secure(con, false);
+	ret = setup_message_sgs(&sgt, con->out_msg, zerop, zerop, zerop,
+				&con->v2.out_epil, false);
+	if (ret)
+		goto out;
+
+	enc_page_cnt = calc_pages_for(0, tail_len);
+	enc_pages = ceph_alloc_page_vector(enc_page_cnt, GFP_NOIO);
+	if (IS_ERR(enc_pages)) {
+		ret = PTR_ERR(enc_pages);
+		goto out;
+	}
+
+	WARN_ON(con->v2.out_enc_pages || con->v2.out_enc_page_cnt);
+	con->v2.out_enc_pages = enc_pages;
+	con->v2.out_enc_page_cnt = enc_page_cnt;
+	con->v2.out_enc_resid = tail_len;
+	con->v2.out_enc_i = 0;
+
+	ret = sg_alloc_table_from_pages(&enc_sgt, enc_pages, enc_page_cnt,
+					0, tail_len, GFP_NOIO);
+	if (ret)
+		goto out;
+
+	ret = gcm_crypt(con, true, sgt.sgl, enc_sgt.sgl,
+			tail_len - CEPH_GCM_TAG_LEN);
+	if (ret)
+		goto out;
+
+	dout("%s con %p msg %p sg_cnt %d enc_page_cnt %d\n", __func__, con,
+	     con->out_msg, sgt.orig_nents, enc_page_cnt);
+	con->v2.out_state = OUT_S_QUEUE_ENC_PAGE;
+
+out:
+	sg_free_table(&sgt);
+	sg_free_table(&enc_sgt);
+	return ret;
+}
+
+static int prepare_message(struct ceph_connection *con)
+{
+	int lens[] = {
+		sizeof(struct ceph_msg_header2),
+		front_len(con->out_msg),
+		middle_len(con->out_msg),
+		data_len(con->out_msg)
+	};
+	struct ceph_frame_desc desc;
+	int ret;
+
+	dout("%s con %p msg %p logical %d+%d+%d+%d\n", __func__, con,
+	     con->out_msg, lens[0], lens[1], lens[2], lens[3]);
+
+	if (con->in_seq > con->in_seq_acked) {
+		dout("%s con %p in_seq_acked %llu -> %llu\n", __func__, con,
+		     con->in_seq_acked, con->in_seq);
+		con->in_seq_acked = con->in_seq;
+	}
+
+	reset_out_kvecs(con);
+	init_frame_desc(&desc, FRAME_TAG_MESSAGE, lens, 4);
+	encode_preamble(&desc, con->v2.out_buf);
+	fill_header2(CTRL_BODY(con->v2.out_buf), &con->out_msg->hdr,
+		     con->in_seq_acked);
+
+	if (con_secure(con)) {
+		ret = prepare_message_secure(con);
+		if (ret)
+			return ret;
+	} else {
+		prepare_message_plain(con);
+	}
+
+	ceph_con_flag_set(con, CEPH_CON_F_WRITE_PENDING);
+	return 0;
+}
+
+static int prepare_read_banner_prefix(struct ceph_connection *con)
+{
+	void *buf;
+
+	buf = alloc_conn_buf(con, CEPH_BANNER_V2_PREFIX_LEN);
+	if (!buf)
+		return -ENOMEM;
+
+	reset_in_kvecs(con);
+	add_in_kvec(con, buf, CEPH_BANNER_V2_PREFIX_LEN);
+	add_in_sign_kvec(con, buf, CEPH_BANNER_V2_PREFIX_LEN);
+	con->state = CEPH_CON_S_V2_BANNER_PREFIX;
+	return 0;
+}
+
+static int prepare_read_banner_payload(struct ceph_connection *con,
+				       int payload_len)
+{
+	void *buf;
+
+	buf = alloc_conn_buf(con, payload_len);
+	if (!buf)
+		return -ENOMEM;
+
+	reset_in_kvecs(con);
+	add_in_kvec(con, buf, payload_len);
+	add_in_sign_kvec(con, buf, payload_len);
+	con->state = CEPH_CON_S_V2_BANNER_PAYLOAD;
+	return 0;
+}
+
+static void prepare_read_preamble(struct ceph_connection *con)
+{
+	reset_in_kvecs(con);
+	add_in_kvec(con, con->v2.in_buf,
+		    con_secure(con) ? CEPH_PREAMBLE_SECURE_LEN :
+				      CEPH_PREAMBLE_PLAIN_LEN);
+	con->v2.in_state = IN_S_HANDLE_PREAMBLE;
+}
+
+static int prepare_read_control(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	int head_len;
+	void *buf;
+
+	reset_in_kvecs(con);
+	if (con->state == CEPH_CON_S_V2_HELLO ||
+	    con->state == CEPH_CON_S_V2_AUTH) {
+		head_len = head_onwire_len(ctrl_len, false);
+		buf = alloc_conn_buf(con, head_len);
+		if (!buf)
+			return -ENOMEM;
+
+		/* preserve preamble */
+		memcpy(buf, con->v2.in_buf, CEPH_PREAMBLE_LEN);
+
+		add_in_kvec(con, CTRL_BODY(buf), ctrl_len);
+		add_in_kvec(con, CTRL_BODY(buf) + ctrl_len, CEPH_CRC_LEN);
+		add_in_sign_kvec(con, buf, head_len);
+	} else {
+		if (ctrl_len > CEPH_PREAMBLE_INLINE_LEN) {
+			buf = alloc_conn_buf(con, ctrl_len);
+			if (!buf)
+				return -ENOMEM;
+
+			add_in_kvec(con, buf, ctrl_len);
+		} else {
+			add_in_kvec(con, CTRL_BODY(con->v2.in_buf), ctrl_len);
+		}
+		add_in_kvec(con, con->v2.in_buf, CEPH_CRC_LEN);
+	}
+	con->v2.in_state = IN_S_HANDLE_CONTROL;
+	return 0;
+}
+
+static int prepare_read_control_remainder(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	int rem_len = ctrl_len - CEPH_PREAMBLE_INLINE_LEN;
+	void *buf;
+
+	buf = alloc_conn_buf(con, ctrl_len);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, CTRL_BODY(con->v2.in_buf), CEPH_PREAMBLE_INLINE_LEN);
+
+	reset_in_kvecs(con);
+	add_in_kvec(con, buf + CEPH_PREAMBLE_INLINE_LEN, rem_len);
+	add_in_kvec(con, con->v2.in_buf,
+		    padding_len(rem_len) + CEPH_GCM_TAG_LEN);
+	con->v2.in_state = IN_S_HANDLE_CONTROL_REMAINDER;
+	return 0;
+}
+
+static void prepare_read_data(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	if (!con_secure(con))
+		con->in_data_crc = -1;
+	ceph_msg_data_cursor_init(&con->v2.in_cursor, con->in_msg,
+				  data_len(con->in_msg));
+
+	get_bvec_at(&con->v2.in_cursor, &bv);
+	set_in_bvec(con, &bv);
+	con->v2.in_state = IN_S_PREPARE_READ_DATA_CONT;
+}
+
+static void prepare_read_data_cont(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	if (!con_secure(con))
+		con->in_data_crc = ceph_crc32c_page(con->in_data_crc,
+						    con->v2.in_bvec.bv_page,
+						    con->v2.in_bvec.bv_offset,
+						    con->v2.in_bvec.bv_len);
+
+	ceph_msg_data_advance(&con->v2.in_cursor, con->v2.in_bvec.bv_len);
+	if (con->v2.in_cursor.total_resid) {
+		get_bvec_at(&con->v2.in_cursor, &bv);
+		set_in_bvec(con, &bv);
+		WARN_ON(con->v2.in_state != IN_S_PREPARE_READ_DATA_CONT);
+		return;
+	}
+
+	/*
+	 * We've read all data.  Prepare to read data padding (if any)
+	 * and epilogue.
+	 */
+	reset_in_kvecs(con);
+	if (con_secure(con)) {
+		if (need_padding(data_len(con->in_msg)))
+			add_in_kvec(con, DATA_PAD(con->v2.in_buf),
+				    padding_len(data_len(con->in_msg)));
+		add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_SECURE_LEN);
+	} else {
+		add_in_kvec(con, con->v2.in_buf, CEPH_EPILOGUE_PLAIN_LEN);
+	}
+	con->v2.in_state = IN_S_HANDLE_EPILOGUE;
+}
+
+static void __finish_skip(struct ceph_connection *con)
+{
+	con->in_seq++;
+	prepare_read_preamble(con);
+}
+
+static void prepare_skip_message(struct ceph_connection *con)
+{
+	struct ceph_frame_desc *desc = &con->v2.in_desc;
+	int tail_len;
+
+	dout("%s con %p %d+%d+%d\n", __func__, con, desc->fd_lens[1],
+	     desc->fd_lens[2], desc->fd_lens[3]);
+
+	tail_len = __tail_onwire_len(desc->fd_lens[1], desc->fd_lens[2],
+				     desc->fd_lens[3], con_secure(con));
+	if (!tail_len) {
+		__finish_skip(con);
+	} else {
+		set_in_skip(con, tail_len);
+		con->v2.in_state = IN_S_FINISH_SKIP;
+	}
+}
+
+static int process_banner_prefix(struct ceph_connection *con)
+{
+	int payload_len;
+	void *p;
+
+	WARN_ON(con->v2.in_kvecs[0].iov_len != CEPH_BANNER_V2_PREFIX_LEN);
+
+	p = con->v2.in_kvecs[0].iov_base;
+	if (memcmp(p, CEPH_BANNER_V2, CEPH_BANNER_V2_LEN)) {
+		if (!memcmp(p, CEPH_BANNER, CEPH_BANNER_LEN))
+			con->error_msg = "server is speaking msgr1 protocol";
+		else
+			con->error_msg = "protocol error, bad banner";
+		return -EINVAL;
+	}
+
+	p += CEPH_BANNER_V2_LEN;
+	payload_len = ceph_decode_16(&p);
+	dout("%s con %p payload_len %d\n", __func__, con, payload_len);
+
+	return prepare_read_banner_payload(con, payload_len);
+}
+
+static int process_banner_payload(struct ceph_connection *con)
+{
+	void *end = con->v2.in_kvecs[0].iov_base + con->v2.in_kvecs[0].iov_len;
+	u64 feat = CEPH_MSGR2_SUPPORTED_FEATURES;
+	u64 req_feat = CEPH_MSGR2_REQUIRED_FEATURES;
+	u64 server_feat, server_req_feat;
+	void *p;
+	int ret;
+
+	p = con->v2.in_kvecs[0].iov_base;
+	ceph_decode_64_safe(&p, end, server_feat, bad);
+	ceph_decode_64_safe(&p, end, server_req_feat, bad);
+
+	dout("%s con %p server_feat 0x%llx server_req_feat 0x%llx\n",
+	     __func__, con, server_feat, server_req_feat);
+
+	if (req_feat & ~server_feat) {
+		pr_err("msgr2 feature set mismatch: my required > server's supported 0x%llx, need 0x%llx\n",
+		       server_feat, req_feat & ~server_feat);
+		con->error_msg = "missing required protocol features";
+		return -EINVAL;
+	}
+	if (server_req_feat & ~feat) {
+		pr_err("msgr2 feature set mismatch: server's required > my supported 0x%llx, missing 0x%llx\n",
+		       feat, server_req_feat & ~feat);
+		con->error_msg = "missing required protocol features";
+		return -EINVAL;
+	}
+
+	/* no reset_out_kvecs() as our banner may still be pending */
+	ret = prepare_hello(con);
+	if (ret) {
+		pr_err("prepare_hello failed: %d\n", ret);
+		return ret;
+	}
+
+	con->state = CEPH_CON_S_V2_HELLO;
+	prepare_read_preamble(con);
+	return 0;
+
+bad:
+	pr_err("failed to decode banner payload\n");
+	return -EINVAL;
+}
+
+static int process_hello(struct ceph_connection *con, void *p, void *end)
+{
+	struct ceph_entity_addr *my_addr = &con->msgr->inst.addr;
+	struct ceph_entity_addr addr_for_me;
+	u8 entity_type;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_HELLO) {
+		con->error_msg = "protocol error, unexpected hello";
+		return -EINVAL;
+	}
+
+	ceph_decode_8_safe(&p, end, entity_type, bad);
+	ret = ceph_decode_entity_addr(&p, end, &addr_for_me);
+	if (ret) {
+		pr_err("failed to decode addr_for_me: %d\n", ret);
+		return ret;
+	}
+
+	dout("%s con %p entity_type %d addr_for_me %s\n", __func__, con,
+	     entity_type, ceph_pr_addr(&addr_for_me));
+
+	if (entity_type != con->peer_name.type) {
+		pr_err("bad peer type, want %d, got %d\n",
+		       con->peer_name.type, entity_type);
+		con->error_msg = "wrong peer at address";
+		return -EINVAL;
+	}
+
+	/*
+	 * Set our address to the address our first peer (i.e. monitor)
+	 * sees that we are connecting from.  If we are behind some sort
+	 * of NAT and want to be identified by some private (not NATed)
+	 * address, ip option should be used.
+	 */
+	if (ceph_addr_is_blank(my_addr)) {
+		memcpy(&my_addr->in_addr, &addr_for_me.in_addr,
+		       sizeof(my_addr->in_addr));
+		ceph_addr_set_port(my_addr, 0);
+		dout("%s con %p set my addr %s, as seen by peer %s\n",
+		     __func__, con, ceph_pr_addr(my_addr),
+		     ceph_pr_addr(&con->peer_addr));
+	} else {
+		dout("%s con %p my addr already set %s\n",
+		     __func__, con, ceph_pr_addr(my_addr));
+	}
+
+	WARN_ON(ceph_addr_is_blank(my_addr) || ceph_addr_port(my_addr));
+	WARN_ON(my_addr->type != CEPH_ENTITY_ADDR_TYPE_ANY);
+	WARN_ON(!my_addr->nonce);
+
+	/* no reset_out_kvecs() as our hello may still be pending */
+	ret = prepare_auth_request(con);
+	if (ret) {
+		if (ret != -EAGAIN)
+			pr_err("prepare_auth_request failed: %d\n", ret);
+		return ret;
+	}
+
+	con->state = CEPH_CON_S_V2_AUTH;
+	return 0;
+
+bad:
+	pr_err("failed to decode hello\n");
+	return -EINVAL;
+}
+
+static int process_auth_bad_method(struct ceph_connection *con,
+				   void *p, void *end)
+{
+	int allowed_protos[8], allowed_modes[8];
+	int allowed_proto_cnt, allowed_mode_cnt;
+	int used_proto, result;
+	int ret;
+	int i;
+
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		con->error_msg = "protocol error, unexpected auth_bad_method";
+		return -EINVAL;
+	}
+
+	ceph_decode_32_safe(&p, end, used_proto, bad);
+	ceph_decode_32_safe(&p, end, result, bad);
+	dout("%s con %p used_proto %d result %d\n", __func__, con, used_proto,
+	     result);
+
+	ceph_decode_32_safe(&p, end, allowed_proto_cnt, bad);
+	if (allowed_proto_cnt > ARRAY_SIZE(allowed_protos)) {
+		pr_err("allowed_protos too big %d\n", allowed_proto_cnt);
+		return -EINVAL;
+	}
+	for (i = 0; i < allowed_proto_cnt; i++) {
+		ceph_decode_32_safe(&p, end, allowed_protos[i], bad);
+		dout("%s con %p allowed_protos[%d] %d\n", __func__, con,
+		     i, allowed_protos[i]);
+	}
+
+	ceph_decode_32_safe(&p, end, allowed_mode_cnt, bad);
+	if (allowed_mode_cnt > ARRAY_SIZE(allowed_modes)) {
+		pr_err("allowed_modes too big %d\n", allowed_mode_cnt);
+		return -EINVAL;
+	}
+	for (i = 0; i < allowed_mode_cnt; i++) {
+		ceph_decode_32_safe(&p, end, allowed_modes[i], bad);
+		dout("%s con %p allowed_modes[%d] %d\n", __func__, con,
+		     i, allowed_modes[i]);
+	}
+
+	mutex_unlock(&con->mutex);
+	ret = con->ops->handle_auth_bad_method(con, used_proto, result,
+					       allowed_protos,
+					       allowed_proto_cnt,
+					       allowed_modes,
+					       allowed_mode_cnt);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	dout("%s con %p handle_auth_bad_method ret %d\n", __func__, con, ret);
+	return ret;
+
+bad:
+	pr_err("failed to decode auth_bad_method\n");
+	return -EINVAL;
+}
+
+static int process_auth_reply_more(struct ceph_connection *con,
+				   void *p, void *end)
+{
+	int payload_len;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		con->error_msg = "protocol error, unexpected auth_reply_more";
+		return -EINVAL;
+	}
+
+	ceph_decode_32_safe(&p, end, payload_len, bad);
+	ceph_decode_need(&p, end, payload_len, bad);
+
+	dout("%s con %p payload_len %d\n", __func__, con, payload_len);
+
+	reset_out_kvecs(con);
+	ret = prepare_auth_request_more(con, p, payload_len);
+	if (ret) {
+		if (ret != -EAGAIN)
+			pr_err("prepare_auth_request_more failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+
+bad:
+	pr_err("failed to decode auth_reply_more\n");
+	return -EINVAL;
+}
+
+/*
+ * Align session_key and con_secret to avoid GFP_ATOMIC allocation
+ * inside crypto_shash_setkey() and crypto_aead_setkey() called from
+ * setup_crypto().  __aligned(16) isn't guaranteed to work for stack
+ * objects, so do it by hand.
+ */
+static int process_auth_done(struct ceph_connection *con, void *p, void *end)
+{
+	u8 session_key_buf[CEPH_KEY_LEN + 16];
+	u8 con_secret_buf[CEPH_MAX_CON_SECRET_LEN + 16];
+	u8 *session_key = PTR_ALIGN(&session_key_buf[0], 16);
+	u8 *con_secret = PTR_ALIGN(&con_secret_buf[0], 16);
+	int session_key_len, con_secret_len;
+	int payload_len;
+	u64 global_id;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		con->error_msg = "protocol error, unexpected auth_done";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, global_id, bad);
+	ceph_decode_32_safe(&p, end, con->v2.con_mode, bad);
+	ceph_decode_32_safe(&p, end, payload_len, bad);
+
+	dout("%s con %p global_id %llu con_mode %d payload_len %d\n",
+	     __func__, con, global_id, con->v2.con_mode, payload_len);
+
+	mutex_unlock(&con->mutex);
+	session_key_len = 0;
+	con_secret_len = 0;
+	ret = con->ops->handle_auth_done(con, global_id, p, payload_len,
+					 session_key, &session_key_len,
+					 con_secret, &con_secret_len);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_AUTH) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		ret = -EAGAIN;
+		goto out;
+	}
+
+	dout("%s con %p handle_auth_done ret %d\n", __func__, con, ret);
+	if (ret)
+		goto out;
+
+	ret = setup_crypto(con, session_key, session_key_len, con_secret,
+			   con_secret_len);
+	if (ret)
+		goto out;
+
+	reset_out_kvecs(con);
+	ret = prepare_auth_signature(con);
+	if (ret) {
+		pr_err("prepare_auth_signature failed: %d\n", ret);
+		goto out;
+	}
+
+	con->state = CEPH_CON_S_V2_AUTH_SIGNATURE;
+
+out:
+	memzero_explicit(session_key_buf, sizeof(session_key_buf));
+	memzero_explicit(con_secret_buf, sizeof(con_secret_buf));
+	return ret;
+
+bad:
+	pr_err("failed to decode auth_done\n");
+	return -EINVAL;
+}
+
+static int process_auth_signature(struct ceph_connection *con,
+				  void *p, void *end)
+{
+	u8 hmac[SHA256_DIGEST_SIZE];
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_AUTH_SIGNATURE) {
+		con->error_msg = "protocol error, unexpected auth_signature";
+		return -EINVAL;
+	}
+
+	ret = hmac_sha256(con, con->v2.out_sign_kvecs,
+			  con->v2.out_sign_kvec_cnt, hmac);
+	if (ret)
+		return ret;
+
+	ceph_decode_need(&p, end, SHA256_DIGEST_SIZE, bad);
+	if (crypto_memneq(p, hmac, SHA256_DIGEST_SIZE)) {
+		con->error_msg = "integrity error, bad auth signature";
+		return -EBADMSG;
+	}
+
+	dout("%s con %p auth signature ok\n", __func__, con);
+
+	/* no reset_out_kvecs() as our auth_signature may still be pending */
+	if (!con->v2.server_cookie) {
+		ret = prepare_client_ident(con);
+		if (ret) {
+			pr_err("prepare_client_ident failed: %d\n", ret);
+			return ret;
+		}
+
+		con->state = CEPH_CON_S_V2_SESSION_CONNECT;
+	} else {
+		ret = prepare_session_reconnect(con);
+		if (ret) {
+			pr_err("prepare_session_reconnect failed: %d\n", ret);
+			return ret;
+		}
+
+		con->state = CEPH_CON_S_V2_SESSION_RECONNECT;
+	}
+
+	return 0;
+
+bad:
+	pr_err("failed to decode auth_signature\n");
+	return -EINVAL;
+}
+
+static int process_server_ident(struct ceph_connection *con,
+				void *p, void *end)
+{
+	struct ceph_client *client = from_msgr(con->msgr);
+	u64 features, required_features;
+	struct ceph_entity_addr addr;
+	u64 global_seq;
+	u64 global_id;
+	u64 cookie;
+	u64 flags;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_CONNECT) {
+		con->error_msg = "protocol error, unexpected server_ident";
+		return -EINVAL;
+	}
+
+	ret = ceph_decode_entity_addrvec(&p, end, true, &addr);
+	if (ret) {
+		pr_err("failed to decode server addrs: %d\n", ret);
+		return ret;
+	}
+
+	ceph_decode_64_safe(&p, end, global_id, bad);
+	ceph_decode_64_safe(&p, end, global_seq, bad);
+	ceph_decode_64_safe(&p, end, features, bad);
+	ceph_decode_64_safe(&p, end, required_features, bad);
+	ceph_decode_64_safe(&p, end, flags, bad);
+	ceph_decode_64_safe(&p, end, cookie, bad);
+
+	dout("%s con %p addr %s/%u global_id %llu global_seq %llu features 0x%llx required_features 0x%llx flags 0x%llx cookie 0x%llx\n",
+	     __func__, con, ceph_pr_addr(&addr), le32_to_cpu(addr.nonce),
+	     global_id, global_seq, features, required_features, flags, cookie);
+
+	/* is this who we intended to talk to? */
+	if (memcmp(&addr, &con->peer_addr, sizeof(con->peer_addr))) {
+		pr_err("bad peer addr/nonce, want %s/%u, got %s/%u\n",
+		       ceph_pr_addr(&con->peer_addr),
+		       le32_to_cpu(con->peer_addr.nonce),
+		       ceph_pr_addr(&addr), le32_to_cpu(addr.nonce));
+		con->error_msg = "wrong peer at address";
+		return -EINVAL;
+	}
+
+	if (client->required_features & ~features) {
+		pr_err("RADOS feature set mismatch: my required > server's supported 0x%llx, need 0x%llx\n",
+		       features, client->required_features & ~features);
+		con->error_msg = "missing required protocol features";
+		return -EINVAL;
+	}
+
+	/*
+	 * Both name->type and name->num are set in ceph_con_open() but
+	 * name->num may be bogus in the initial monmap.  name->type is
+	 * verified in handle_hello().
+	 */
+	WARN_ON(!con->peer_name.type);
+	con->peer_name.num = cpu_to_le64(global_id);
+	con->v2.peer_global_seq = global_seq;
+	con->peer_features = features;
+	WARN_ON(required_features & ~client->supported_features);
+	con->v2.server_cookie = cookie;
+
+	if (flags & CEPH_MSG_CONNECT_LOSSY) {
+		ceph_con_flag_set(con, CEPH_CON_F_LOSSYTX);
+		WARN_ON(con->v2.server_cookie);
+	} else {
+		WARN_ON(!con->v2.server_cookie);
+	}
+
+	clear_in_sign_kvecs(con);
+	clear_out_sign_kvecs(con);
+	free_conn_bufs(con);
+	con->delay = 0;  /* reset backoff memory */
+
+	con->state = CEPH_CON_S_OPEN;
+	con->v2.out_state = OUT_S_GET_NEXT;
+	return 0;
+
+bad:
+	pr_err("failed to decode server_ident\n");
+	return -EINVAL;
+}
+
+static int process_ident_missing_features(struct ceph_connection *con,
+					  void *p, void *end)
+{
+	struct ceph_client *client = from_msgr(con->msgr);
+	u64 missing_features;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_CONNECT) {
+		con->error_msg = "protocol error, unexpected ident_missing_features";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, missing_features, bad);
+	pr_err("RADOS feature set mismatch: server's required > my supported 0x%llx, missing 0x%llx\n",
+	       client->supported_features, missing_features);
+	con->error_msg = "missing required protocol features";
+	return -EINVAL;
+
+bad:
+	pr_err("failed to decode ident_missing_features\n");
+	return -EINVAL;
+}
+
+static int process_session_reconnect_ok(struct ceph_connection *con,
+					void *p, void *end)
+{
+	u64 seq;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		con->error_msg = "protocol error, unexpected session_reconnect_ok";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, seq, bad);
+
+	dout("%s con %p seq %llu\n", __func__, con, seq);
+	ceph_con_discard_requeued(con, seq);
+
+	clear_in_sign_kvecs(con);
+	clear_out_sign_kvecs(con);
+	free_conn_bufs(con);
+	con->delay = 0;  /* reset backoff memory */
+
+	con->state = CEPH_CON_S_OPEN;
+	con->v2.out_state = OUT_S_GET_NEXT;
+	return 0;
+
+bad:
+	pr_err("failed to decode session_reconnect_ok\n");
+	return -EINVAL;
+}
+
+static int process_session_retry(struct ceph_connection *con,
+				 void *p, void *end)
+{
+	u64 connect_seq;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		con->error_msg = "protocol error, unexpected session_retry";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, connect_seq, bad);
+
+	dout("%s con %p connect_seq %llu\n", __func__, con, connect_seq);
+	WARN_ON(connect_seq <= con->v2.connect_seq);
+	con->v2.connect_seq = connect_seq + 1;
+
+	free_conn_bufs(con);
+
+	reset_out_kvecs(con);
+	ret = prepare_session_reconnect(con);
+	if (ret) {
+		pr_err("prepare_session_reconnect (cseq) failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+
+bad:
+	pr_err("failed to decode session_retry\n");
+	return -EINVAL;
+}
+
+static int process_session_retry_global(struct ceph_connection *con,
+					void *p, void *end)
+{
+	u64 global_seq;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		con->error_msg = "protocol error, unexpected session_retry_global";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, global_seq, bad);
+
+	dout("%s con %p global_seq %llu\n", __func__, con, global_seq);
+	WARN_ON(global_seq <= con->v2.global_seq);
+	con->v2.global_seq = ceph_get_global_seq(con->msgr, global_seq);
+
+	free_conn_bufs(con);
+
+	reset_out_kvecs(con);
+	ret = prepare_session_reconnect(con);
+	if (ret) {
+		pr_err("prepare_session_reconnect (gseq) failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+
+bad:
+	pr_err("failed to decode session_retry_global\n");
+	return -EINVAL;
+}
+
+static int process_session_reset(struct ceph_connection *con,
+				 void *p, void *end)
+{
+	bool full;
+	int ret;
+
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		con->error_msg = "protocol error, unexpected session_reset";
+		return -EINVAL;
+	}
+
+	ceph_decode_8_safe(&p, end, full, bad);
+	if (!full) {
+		con->error_msg = "protocol error, bad session_reset";
+		return -EINVAL;
+	}
+
+	pr_info("%s%lld %s session reset\n", ENTITY_NAME(con->peer_name),
+		ceph_pr_addr(&con->peer_addr));
+	ceph_con_reset_session(con);
+
+	mutex_unlock(&con->mutex);
+	if (con->ops->peer_reset)
+		con->ops->peer_reset(con);
+	mutex_lock(&con->mutex);
+	if (con->state != CEPH_CON_S_V2_SESSION_RECONNECT) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	free_conn_bufs(con);
+
+	reset_out_kvecs(con);
+	ret = prepare_client_ident(con);
+	if (ret) {
+		pr_err("prepare_client_ident (rst) failed: %d\n", ret);
+		return ret;
+	}
+
+	con->state = CEPH_CON_S_V2_SESSION_CONNECT;
+	return 0;
+
+bad:
+	pr_err("failed to decode session_reset\n");
+	return -EINVAL;
+}
+
+static int process_keepalive2_ack(struct ceph_connection *con,
+				  void *p, void *end)
+{
+	if (con->state != CEPH_CON_S_OPEN) {
+		con->error_msg = "protocol error, unexpected keepalive2_ack";
+		return -EINVAL;
+	}
+
+	ceph_decode_need(&p, end, sizeof(struct ceph_timespec), bad);
+	ceph_decode_timespec64(&con->last_keepalive_ack, p);
+
+	dout("%s con %p timestamp %lld.%09ld\n", __func__, con,
+	     con->last_keepalive_ack.tv_sec, con->last_keepalive_ack.tv_nsec);
+
+	return 0;
+
+bad:
+	pr_err("failed to decode keepalive2_ack\n");
+	return -EINVAL;
+}
+
+static int process_ack(struct ceph_connection *con, void *p, void *end)
+{
+	u64 seq;
+
+	if (con->state != CEPH_CON_S_OPEN) {
+		con->error_msg = "protocol error, unexpected ack";
+		return -EINVAL;
+	}
+
+	ceph_decode_64_safe(&p, end, seq, bad);
+
+	dout("%s con %p seq %llu\n", __func__, con, seq);
+	ceph_con_discard_sent(con, seq);
+	return 0;
+
+bad:
+	pr_err("failed to decode ack\n");
+	return -EINVAL;
+}
+
+static int process_control(struct ceph_connection *con, void *p, void *end)
+{
+	int tag = con->v2.in_desc.fd_tag;
+	int ret;
+
+	dout("%s con %p tag %d len %d\n", __func__, con, tag, (int)(end - p));
+
+	switch (tag) {
+	case FRAME_TAG_HELLO:
+		ret = process_hello(con, p, end);
+		break;
+	case FRAME_TAG_AUTH_BAD_METHOD:
+		ret = process_auth_bad_method(con, p, end);
+		break;
+	case FRAME_TAG_AUTH_REPLY_MORE:
+		ret = process_auth_reply_more(con, p, end);
+		break;
+	case FRAME_TAG_AUTH_DONE:
+		ret = process_auth_done(con, p, end);
+		break;
+	case FRAME_TAG_AUTH_SIGNATURE:
+		ret = process_auth_signature(con, p, end);
+		break;
+	case FRAME_TAG_SERVER_IDENT:
+		ret = process_server_ident(con, p, end);
+		break;
+	case FRAME_TAG_IDENT_MISSING_FEATURES:
+		ret = process_ident_missing_features(con, p, end);
+		break;
+	case FRAME_TAG_SESSION_RECONNECT_OK:
+		ret = process_session_reconnect_ok(con, p, end);
+		break;
+	case FRAME_TAG_SESSION_RETRY:
+		ret = process_session_retry(con, p, end);
+		break;
+	case FRAME_TAG_SESSION_RETRY_GLOBAL:
+		ret = process_session_retry_global(con, p, end);
+		break;
+	case FRAME_TAG_SESSION_RESET:
+		ret = process_session_reset(con, p, end);
+		break;
+	case FRAME_TAG_KEEPALIVE2_ACK:
+		ret = process_keepalive2_ack(con, p, end);
+		break;
+	case FRAME_TAG_ACK:
+		ret = process_ack(con, p, end);
+		break;
+	default:
+		pr_err("bad tag %d\n", tag);
+		con->error_msg = "protocol error, bad tag";
+		return -EINVAL;
+	}
+	if (ret) {
+		dout("%s con %p error %d\n", __func__, con, ret);
+		return ret;
+	}
+
+	prepare_read_preamble(con);
+	return 0;
+}
+
+/*
+ * Return:
+ *   1 - con->in_msg set, read message
+ *   0 - skip message
+ *  <0 - error
+ */
+static int process_message_header(struct ceph_connection *con,
+				  void *p, void *end)
+{
+	struct ceph_frame_desc *desc = &con->v2.in_desc;
+	struct ceph_msg_header2 *hdr2 = p;
+	struct ceph_msg_header hdr;
+	int skip;
+	int ret;
+	u64 seq;
+
+	/* verify seq# */
+	seq = le64_to_cpu(hdr2->seq);
+	if ((s64)seq - (s64)con->in_seq < 1) {
+		pr_info("%s%lld %s skipping old message: seq %llu, expected %llu\n",
+			ENTITY_NAME(con->peer_name),
+			ceph_pr_addr(&con->peer_addr),
+			seq, con->in_seq + 1);
+		return 0;
+	}
+	if ((s64)seq - (s64)con->in_seq > 1) {
+		pr_err("bad seq %llu, expected %llu\n", seq, con->in_seq + 1);
+		con->error_msg = "bad message sequence # for incoming message";
+		return -EBADE;
+	}
+
+	ceph_con_discard_sent(con, le64_to_cpu(hdr2->ack_seq));
+
+	fill_header(&hdr, hdr2, desc->fd_lens[1], desc->fd_lens[2],
+		    desc->fd_lens[3], &con->peer_name);
+	ret = ceph_con_in_msg_alloc(con, &hdr, &skip);
+	if (ret)
+		return ret;
+
+	WARN_ON(!con->in_msg ^ skip);
+	if (skip)
+		return 0;
+
+	WARN_ON(!con->in_msg);
+	WARN_ON(con->in_msg->con != con);
+	return 1;
+}
+
+static int process_message(struct ceph_connection *con)
+{
+	ceph_con_process_message(con);
+
+	/*
+	 * We could have been closed by ceph_con_close() because
+	 * ceph_con_process_message() temporarily drops con->mutex.
+	 */
+	if (con->state != CEPH_CON_S_OPEN) {
+		dout("%s con %p state changed to %d\n", __func__, con,
+		     con->state);
+		return -EAGAIN;
+	}
+
+	prepare_read_preamble(con);
+	return 0;
+}
+
+static int __handle_control(struct ceph_connection *con, void *p)
+{
+	void *end = p + con->v2.in_desc.fd_lens[0];
+	struct ceph_msg *msg;
+	int ret;
+
+	if (con->v2.in_desc.fd_tag != FRAME_TAG_MESSAGE)
+		return process_control(con, p, end);
+
+	ret = process_message_header(con, p, end);
+	if (ret < 0)
+		return ret;
+	if (ret == 0) {
+		prepare_skip_message(con);
+		return 0;
+	}
+
+	msg = con->in_msg;  /* set in process_message_header() */
+	if (!front_len(msg) && !middle_len(msg)) {
+		if (!data_len(msg))
+			return process_message(con);
+
+		prepare_read_data(con);
+		return 0;
+	}
+
+	reset_in_kvecs(con);
+	if (front_len(msg)) {
+		WARN_ON(front_len(msg) > msg->front_alloc_len);
+		add_in_kvec(con, msg->front.iov_base, front_len(msg));
+		msg->front.iov_len = front_len(msg);
+
+		if (con_secure(con) && need_padding(front_len(msg)))
+			add_in_kvec(con, FRONT_PAD(con->v2.in_buf),
+				    padding_len(front_len(msg)));
+	} else {
+		msg->front.iov_len = 0;
+	}
+	if (middle_len(msg)) {
+		WARN_ON(middle_len(msg) > msg->middle->alloc_len);
+		add_in_kvec(con, msg->middle->vec.iov_base, middle_len(msg));
+		msg->middle->vec.iov_len = middle_len(msg);
+
+		if (con_secure(con) && need_padding(middle_len(msg)))
+			add_in_kvec(con, MIDDLE_PAD(con->v2.in_buf),
+				    padding_len(middle_len(msg)));
+	} else if (msg->middle) {
+		msg->middle->vec.iov_len = 0;
+	}
+
+	if (data_len(msg)) {
+		con->v2.in_state = IN_S_PREPARE_READ_DATA;
+	} else {
+		add_in_kvec(con, con->v2.in_buf,
+			    con_secure(con) ? CEPH_EPILOGUE_SECURE_LEN :
+					      CEPH_EPILOGUE_PLAIN_LEN);
+		con->v2.in_state = IN_S_HANDLE_EPILOGUE;
+	}
+	return 0;
+}
+
+static int handle_preamble(struct ceph_connection *con)
+{
+	struct ceph_frame_desc *desc = &con->v2.in_desc;
+	int ret;
+
+	if (con_secure(con)) {
+		ret = decrypt_preamble(con);
+		if (ret) {
+			if (ret == -EBADMSG)
+				con->error_msg = "integrity error, bad preamble auth tag";
+			return ret;
+		}
+	}
+
+	ret = decode_preamble(con->v2.in_buf, desc);
+	if (ret) {
+		if (ret == -EBADMSG)
+			con->error_msg = "integrity error, bad crc";
+		else
+			con->error_msg = "protocol error, bad preamble";
+		return ret;
+	}
+
+	dout("%s con %p tag %d seg_cnt %d %d+%d+%d+%d\n", __func__,
+	     con, desc->fd_tag, desc->fd_seg_cnt, desc->fd_lens[0],
+	     desc->fd_lens[1], desc->fd_lens[2], desc->fd_lens[3]);
+
+	if (!con_secure(con))
+		return prepare_read_control(con);
+
+	if (desc->fd_lens[0] > CEPH_PREAMBLE_INLINE_LEN)
+		return prepare_read_control_remainder(con);
+
+	return __handle_control(con, CTRL_BODY(con->v2.in_buf));
+}
+
+static int handle_control(struct ceph_connection *con)
+{
+	int ctrl_len = con->v2.in_desc.fd_lens[0];
+	void *buf;
+	int ret;
+
+	WARN_ON(con_secure(con));
+
+	ret = verify_control_crc(con);
+	if (ret) {
+		con->error_msg = "integrity error, bad crc";
+		return ret;
+	}
+
+	if (con->state == CEPH_CON_S_V2_AUTH) {
+		buf = alloc_conn_buf(con, ctrl_len);
+		if (!buf)
+			return -ENOMEM;
+
+		memcpy(buf, con->v2.in_kvecs[0].iov_base, ctrl_len);
+		return __handle_control(con, buf);
+	}
+
+	return __handle_control(con, con->v2.in_kvecs[0].iov_base);
+}
+
+static int handle_control_remainder(struct ceph_connection *con)
+{
+	int ret;
+
+	WARN_ON(!con_secure(con));
+
+	ret = decrypt_control_remainder(con);
+	if (ret) {
+		if (ret == -EBADMSG)
+			con->error_msg = "integrity error, bad control remainder auth tag";
+		return ret;
+	}
+
+	return __handle_control(con, con->v2.in_kvecs[0].iov_base -
+				     CEPH_PREAMBLE_INLINE_LEN);
+}
+
+static int handle_epilogue(struct ceph_connection *con)
+{
+	u32 front_crc, middle_crc, data_crc;
+	int ret;
+
+	if (con_secure(con)) {
+		ret = decrypt_message(con);
+		if (ret) {
+			if (ret == -EBADMSG)
+				con->error_msg = "integrity error, bad epilogue auth tag";
+			return ret;
+		}
+
+		/* just late_status */
+		ret = decode_epilogue(con->v2.in_buf, NULL, NULL, NULL);
+		if (ret) {
+			con->error_msg = "protocol error, bad epilogue";
+			return ret;
+		}
+	} else {
+		ret = decode_epilogue(con->v2.in_buf, &front_crc,
+				      &middle_crc, &data_crc);
+		if (ret) {
+			con->error_msg = "protocol error, bad epilogue";
+			return ret;
+		}
+
+		ret = verify_epilogue_crcs(con, front_crc, middle_crc,
+					   data_crc);
+		if (ret) {
+			con->error_msg = "integrity error, bad crc";
+			return ret;
+		}
+	}
+
+	return process_message(con);
+}
+
+static void finish_skip(struct ceph_connection *con)
+{
+	dout("%s con %p\n", __func__, con);
+
+	if (con_secure(con))
+		gcm_inc_nonce(&con->v2.in_gcm_nonce);
+
+	__finish_skip(con);
+}
+
+static int populate_in_iter(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p state %d in_state %d\n", __func__, con, con->state,
+	     con->v2.in_state);
+	WARN_ON(iov_iter_count(&con->v2.in_iter));
+
+	if (con->state == CEPH_CON_S_V2_BANNER_PREFIX) {
+		ret = process_banner_prefix(con);
+	} else if (con->state == CEPH_CON_S_V2_BANNER_PAYLOAD) {
+		ret = process_banner_payload(con);
+	} else if ((con->state >= CEPH_CON_S_V2_HELLO &&
+		    con->state <= CEPH_CON_S_V2_SESSION_RECONNECT) ||
+		   con->state == CEPH_CON_S_OPEN) {
+		switch (con->v2.in_state) {
+		case IN_S_HANDLE_PREAMBLE:
+			ret = handle_preamble(con);
+			break;
+		case IN_S_HANDLE_CONTROL:
+			ret = handle_control(con);
+			break;
+		case IN_S_HANDLE_CONTROL_REMAINDER:
+			ret = handle_control_remainder(con);
+			break;
+		case IN_S_PREPARE_READ_DATA:
+			prepare_read_data(con);
+			ret = 0;
+			break;
+		case IN_S_PREPARE_READ_DATA_CONT:
+			prepare_read_data_cont(con);
+			ret = 0;
+			break;
+		case IN_S_HANDLE_EPILOGUE:
+			ret = handle_epilogue(con);
+			break;
+		case IN_S_FINISH_SKIP:
+			finish_skip(con);
+			ret = 0;
+			break;
+		default:
+			WARN(1, "bad in_state %d", con->v2.in_state);
+			return -EINVAL;
+		}
+	} else {
+		WARN(1, "bad state %d", con->state);
+		return -EINVAL;
+	}
+	if (ret) {
+		dout("%s con %p error %d\n", __func__, con, ret);
+		return ret;
+	}
+
+	if (WARN_ON(!iov_iter_count(&con->v2.in_iter)))
+		return -ENODATA;
+	dout("%s con %p populated %zu\n", __func__, con,
+	     iov_iter_count(&con->v2.in_iter));
+	return 1;
+}
+
+int ceph_con_v2_try_read(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p state %d need %zu\n", __func__, con, con->state,
+	     iov_iter_count(&con->v2.in_iter));
+
+	if (con->state == CEPH_CON_S_PREOPEN)
+		return 0;
+
+	/*
+	 * We should always have something pending here.  If not,
+	 * avoid calling populate_in_iter() as if we read something
+	 * (ceph_tcp_recv() would immediately return 1).
+	 */
+	if (WARN_ON(!iov_iter_count(&con->v2.in_iter)))
+		return -ENODATA;
+
+	for (;;) {
+		ret = ceph_tcp_recv(con);
+		if (ret <= 0)
+			return ret;
+
+		ret = populate_in_iter(con);
+		if (ret <= 0) {
+			if (ret && ret != -EAGAIN && !con->error_msg)
+				con->error_msg = "read processing error";
+			return ret;
+		}
+	}
+}
+
+static void queue_data(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	con->v2.out_epil.data_crc = -1;
+	ceph_msg_data_cursor_init(&con->v2.out_cursor, con->out_msg,
+				  data_len(con->out_msg));
+
+	get_bvec_at(&con->v2.out_cursor, &bv);
+	set_out_bvec(con, &bv, true);
+	con->v2.out_state = OUT_S_QUEUE_DATA_CONT;
+}
+
+static void queue_data_cont(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	con->v2.out_epil.data_crc = ceph_crc32c_page(
+		con->v2.out_epil.data_crc, con->v2.out_bvec.bv_page,
+		con->v2.out_bvec.bv_offset, con->v2.out_bvec.bv_len);
+
+	ceph_msg_data_advance(&con->v2.out_cursor, con->v2.out_bvec.bv_len);
+	if (con->v2.out_cursor.total_resid) {
+		get_bvec_at(&con->v2.out_cursor, &bv);
+		set_out_bvec(con, &bv, true);
+		WARN_ON(con->v2.out_state != OUT_S_QUEUE_DATA_CONT);
+		return;
+	}
+
+	/*
+	 * We've written all data.  Queue epilogue.  Once it's written,
+	 * we are done.
+	 */
+	reset_out_kvecs(con);
+	prepare_epilogue_plain(con, false);
+	con->v2.out_state = OUT_S_FINISH_MESSAGE;
+}
+
+static void queue_enc_page(struct ceph_connection *con)
+{
+	struct bio_vec bv;
+
+	dout("%s con %p i %d resid %d\n", __func__, con, con->v2.out_enc_i,
+	     con->v2.out_enc_resid);
+	WARN_ON(!con->v2.out_enc_resid);
+
+	bv.bv_page = con->v2.out_enc_pages[con->v2.out_enc_i];
+	bv.bv_offset = 0;
+	bv.bv_len = min(con->v2.out_enc_resid, (int)PAGE_SIZE);
+
+	set_out_bvec(con, &bv, false);
+	con->v2.out_enc_i++;
+	con->v2.out_enc_resid -= bv.bv_len;
+
+	if (con->v2.out_enc_resid) {
+		WARN_ON(con->v2.out_state != OUT_S_QUEUE_ENC_PAGE);
+		return;
+	}
+
+	/*
+	 * We've queued the last piece of ciphertext (ending with
+	 * epilogue) + auth tag.  Once it's written, we are done.
+	 */
+	WARN_ON(con->v2.out_enc_i != con->v2.out_enc_page_cnt);
+	con->v2.out_state = OUT_S_FINISH_MESSAGE;
+}
+
+static void queue_zeros(struct ceph_connection *con)
+{
+	dout("%s con %p out_zero %d\n", __func__, con, con->v2.out_zero);
+
+	if (con->v2.out_zero) {
+		set_out_bvec_zero(con);
+		con->v2.out_zero -= con->v2.out_bvec.bv_len;
+		con->v2.out_state = OUT_S_QUEUE_ZEROS;
+		return;
+	}
+
+	/*
+	 * We've zero-filled everything up to epilogue.  Queue epilogue
+	 * with late_status set to ABORTED and crcs adjusted for zeros.
+	 * Once it's written, we are done patching up for the revoke.
+	 */
+	reset_out_kvecs(con);
+	prepare_epilogue_plain(con, true);
+	con->v2.out_state = OUT_S_FINISH_MESSAGE;
+}
+
+static void finish_message(struct ceph_connection *con)
+{
+	dout("%s con %p msg %p\n", __func__, con, con->out_msg);
+
+	/* we end up here both plain and secure modes */
+	if (con->v2.out_enc_pages) {
+		WARN_ON(!con->v2.out_enc_page_cnt);
+		ceph_release_page_vector(con->v2.out_enc_pages,
+					 con->v2.out_enc_page_cnt);
+		con->v2.out_enc_pages = NULL;
+		con->v2.out_enc_page_cnt = 0;
+	}
+	/* message may have been revoked */
+	if (con->out_msg) {
+		ceph_msg_put(con->out_msg);
+		con->out_msg = NULL;
+	}
+
+	con->v2.out_state = OUT_S_GET_NEXT;
+}
+
+static int populate_out_iter(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p state %d out_state %d\n", __func__, con, con->state,
+	     con->v2.out_state);
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+
+	if (con->state != CEPH_CON_S_OPEN) {
+		WARN_ON(con->state < CEPH_CON_S_V2_BANNER_PREFIX ||
+			con->state > CEPH_CON_S_V2_SESSION_RECONNECT);
+		goto nothing_pending;
+	}
+
+	switch (con->v2.out_state) {
+	case OUT_S_QUEUE_DATA:
+		WARN_ON(!con->out_msg);
+		queue_data(con);
+		goto populated;
+	case OUT_S_QUEUE_DATA_CONT:
+		WARN_ON(!con->out_msg);
+		queue_data_cont(con);
+		goto populated;
+	case OUT_S_QUEUE_ENC_PAGE:
+		queue_enc_page(con);
+		goto populated;
+	case OUT_S_QUEUE_ZEROS:
+		WARN_ON(con->out_msg);  /* revoked */
+		queue_zeros(con);
+		goto populated;
+	case OUT_S_FINISH_MESSAGE:
+		finish_message(con);
+		break;
+	case OUT_S_GET_NEXT:
+		break;
+	default:
+		WARN(1, "bad out_state %d", con->v2.out_state);
+		return -EINVAL;
+	}
+
+	WARN_ON(con->v2.out_state != OUT_S_GET_NEXT);
+	if (ceph_con_flag_test_and_clear(con, CEPH_CON_F_KEEPALIVE_PENDING)) {
+		ret = prepare_keepalive2(con);
+		if (ret) {
+			pr_err("prepare_keepalive2 failed: %d\n", ret);
+			return ret;
+		}
+	} else if (!list_empty(&con->out_queue)) {
+		ceph_con_get_out_msg(con);
+		ret = prepare_message(con);
+		if (ret) {
+			pr_err("prepare_message failed: %d\n", ret);
+			return ret;
+		}
+	} else if (con->in_seq > con->in_seq_acked) {
+		ret = prepare_ack(con);
+		if (ret) {
+			pr_err("prepare_ack failed: %d\n", ret);
+			return ret;
+		}
+	} else {
+		goto nothing_pending;
+	}
+
+populated:
+	if (WARN_ON(!iov_iter_count(&con->v2.out_iter)))
+		return -ENODATA;
+	dout("%s con %p populated %zu\n", __func__, con,
+	     iov_iter_count(&con->v2.out_iter));
+	return 1;
+
+nothing_pending:
+	WARN_ON(iov_iter_count(&con->v2.out_iter));
+	dout("%s con %p nothing pending\n", __func__, con);
+	ceph_con_flag_clear(con, CEPH_CON_F_WRITE_PENDING);
+	return 0;
+}
+
+int ceph_con_v2_try_write(struct ceph_connection *con)
+{
+	int ret;
+
+	dout("%s con %p state %d have %zu\n", __func__, con, con->state,
+	     iov_iter_count(&con->v2.out_iter));
+
+	/* open the socket first? */
+	if (con->state == CEPH_CON_S_PREOPEN) {
+		WARN_ON(con->peer_addr.type != CEPH_ENTITY_ADDR_TYPE_MSGR2);
+
+		/*
+		 * Always bump global_seq.  Bump connect_seq only if
+		 * there is a session (i.e. we are reconnecting and will
+		 * send session_reconnect instead of client_ident).
+		 */
+		con->v2.global_seq = ceph_get_global_seq(con->msgr, 0);
+		if (con->v2.server_cookie)
+			con->v2.connect_seq++;
+
+		ret = prepare_read_banner_prefix(con);
+		if (ret) {
+			pr_err("prepare_read_banner_prefix failed: %d\n", ret);
+			con->error_msg = "connect error";
+			return ret;
+		}
+
+		reset_out_kvecs(con);
+		ret = prepare_banner(con);
+		if (ret) {
+			pr_err("prepare_banner failed: %d\n", ret);
+			con->error_msg = "connect error";
+			return ret;
+		}
+
+		ret = ceph_tcp_connect(con);
+		if (ret) {
+			pr_err("ceph_tcp_connect failed: %d\n", ret);
+			con->error_msg = "connect error";
+			return ret;
+		}
+	}
+
+	if (!iov_iter_count(&con->v2.out_iter)) {
+		ret = populate_out_iter(con);
+		if (ret <= 0) {
+			if (ret && ret != -EAGAIN && !con->error_msg)
+				con->error_msg = "write processing error";
+			return ret;
+		}
+	}
+
+	tcp_sock_set_cork(con->sock->sk, true);
+	for (;;) {
+		ret = ceph_tcp_send(con);
+		if (ret <= 0)
+			break;
+
+		ret = populate_out_iter(con);
+		if (ret <= 0) {
+			if (ret && ret != -EAGAIN && !con->error_msg)
+				con->error_msg = "write processing error";
+			break;
+		}
+	}
+
+	tcp_sock_set_cork(con->sock->sk, false);
+	return ret;
+}
+
+static u32 crc32c_zeros(u32 crc, int zero_len)
+{
+	int len;
+
+	while (zero_len) {
+		len = min(zero_len, (int)PAGE_SIZE);
+		crc = crc32c(crc, page_address(ceph_zero_page), len);
+		zero_len -= len;
+	}
+
+	return crc;
+}
+
+static void prepare_zero_front(struct ceph_connection *con, int resid)
+{
+	int sent;
+
+	WARN_ON(!resid || resid > front_len(con->out_msg));
+	sent = front_len(con->out_msg) - resid;
+	dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid);
+
+	if (sent) {
+		con->v2.out_epil.front_crc =
+			crc32c(-1, con->out_msg->front.iov_base, sent);
+		con->v2.out_epil.front_crc =
+			crc32c_zeros(con->v2.out_epil.front_crc, resid);
+	} else {
+		con->v2.out_epil.front_crc = crc32c_zeros(-1, resid);
+	}
+
+	con->v2.out_iter.count -= resid;
+	out_zero_add(con, resid);
+}
+
+static void prepare_zero_middle(struct ceph_connection *con, int resid)
+{
+	int sent;
+
+	WARN_ON(!resid || resid > middle_len(con->out_msg));
+	sent = middle_len(con->out_msg) - resid;
+	dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid);
+
+	if (sent) {
+		con->v2.out_epil.middle_crc =
+			crc32c(-1, con->out_msg->middle->vec.iov_base, sent);
+		con->v2.out_epil.middle_crc =
+			crc32c_zeros(con->v2.out_epil.middle_crc, resid);
+	} else {
+		con->v2.out_epil.middle_crc = crc32c_zeros(-1, resid);
+	}
+
+	con->v2.out_iter.count -= resid;
+	out_zero_add(con, resid);
+}
+
+static void prepare_zero_data(struct ceph_connection *con)
+{
+	dout("%s con %p\n", __func__, con);
+	con->v2.out_epil.data_crc = crc32c_zeros(-1, data_len(con->out_msg));
+	out_zero_add(con, data_len(con->out_msg));
+}
+
+static void revoke_at_queue_data(struct ceph_connection *con)
+{
+	int boundary;
+	int resid;
+
+	WARN_ON(!data_len(con->out_msg));
+	WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter));
+	resid = iov_iter_count(&con->v2.out_iter);
+
+	boundary = front_len(con->out_msg) + middle_len(con->out_msg);
+	if (resid > boundary) {
+		resid -= boundary;
+		WARN_ON(resid > MESSAGE_HEAD_PLAIN_LEN);
+		dout("%s con %p was sending head\n", __func__, con);
+		if (front_len(con->out_msg))
+			prepare_zero_front(con, front_len(con->out_msg));
+		if (middle_len(con->out_msg))
+			prepare_zero_middle(con, middle_len(con->out_msg));
+		prepare_zero_data(con);
+		WARN_ON(iov_iter_count(&con->v2.out_iter) != resid);
+		con->v2.out_state = OUT_S_QUEUE_ZEROS;
+		return;
+	}
+
+	boundary = middle_len(con->out_msg);
+	if (resid > boundary) {
+		resid -= boundary;
+		dout("%s con %p was sending front\n", __func__, con);
+		prepare_zero_front(con, resid);
+		if (middle_len(con->out_msg))
+			prepare_zero_middle(con, middle_len(con->out_msg));
+		prepare_zero_data(con);
+		queue_zeros(con);
+		return;
+	}
+
+	WARN_ON(!resid);
+	dout("%s con %p was sending middle\n", __func__, con);
+	prepare_zero_middle(con, resid);
+	prepare_zero_data(con);
+	queue_zeros(con);
+}
+
+static void revoke_at_queue_data_cont(struct ceph_connection *con)
+{
+	int sent, resid;  /* current piece of data */
+
+	WARN_ON(!data_len(con->out_msg));
+	WARN_ON(!iov_iter_is_bvec(&con->v2.out_iter));
+	resid = iov_iter_count(&con->v2.out_iter);
+	WARN_ON(!resid || resid > con->v2.out_bvec.bv_len);
+	sent = con->v2.out_bvec.bv_len - resid;
+	dout("%s con %p sent %d resid %d\n", __func__, con, sent, resid);
+
+	if (sent) {
+		con->v2.out_epil.data_crc = ceph_crc32c_page(
+			con->v2.out_epil.data_crc, con->v2.out_bvec.bv_page,
+			con->v2.out_bvec.bv_offset, sent);
+		ceph_msg_data_advance(&con->v2.out_cursor, sent);
+	}
+	WARN_ON(resid > con->v2.out_cursor.total_resid);
+	con->v2.out_epil.data_crc = crc32c_zeros(con->v2.out_epil.data_crc,
+						con->v2.out_cursor.total_resid);
+
+	con->v2.out_iter.count -= resid;
+	out_zero_add(con, con->v2.out_cursor.total_resid);
+	queue_zeros(con);
+}
+
+static void revoke_at_finish_message(struct ceph_connection *con)
+{
+	int boundary;
+	int resid;
+
+	WARN_ON(!iov_iter_is_kvec(&con->v2.out_iter));
+	resid = iov_iter_count(&con->v2.out_iter);
+
+	if (!front_len(con->out_msg) && !middle_len(con->out_msg) &&
+	    !data_len(con->out_msg)) {
+		WARN_ON(!resid || resid > MESSAGE_HEAD_PLAIN_LEN);
+		dout("%s con %p was sending head (empty message) - noop\n",
+		     __func__, con);
+		return;
+	}
+
+	boundary = front_len(con->out_msg) + middle_len(con->out_msg) +
+		   CEPH_EPILOGUE_PLAIN_LEN;
+	if (resid > boundary) {
+		resid -= boundary;
+		WARN_ON(resid > MESSAGE_HEAD_PLAIN_LEN);
+		dout("%s con %p was sending head\n", __func__, con);
+		if (front_len(con->out_msg))
+			prepare_zero_front(con, front_len(con->out_msg));
+		if (middle_len(con->out_msg))
+			prepare_zero_middle(con, middle_len(con->out_msg));
+		con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN;
+		WARN_ON(iov_iter_count(&con->v2.out_iter) != resid);
+		con->v2.out_state = OUT_S_QUEUE_ZEROS;
+		return;
+	}
+
+	boundary = middle_len(con->out_msg) + CEPH_EPILOGUE_PLAIN_LEN;
+	if (resid > boundary) {
+		resid -= boundary;
+		dout("%s con %p was sending front\n", __func__, con);
+		prepare_zero_front(con, resid);
+		if (middle_len(con->out_msg))
+			prepare_zero_middle(con, middle_len(con->out_msg));
+		con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN;
+		queue_zeros(con);
+		return;
+	}
+
+	boundary = CEPH_EPILOGUE_PLAIN_LEN;
+	if (resid > boundary) {
+		resid -= boundary;
+		dout("%s con %p was sending middle\n", __func__, con);
+		prepare_zero_middle(con, resid);
+		con->v2.out_iter.count -= CEPH_EPILOGUE_PLAIN_LEN;
+		queue_zeros(con);
+		return;
+	}
+
+	WARN_ON(!resid);
+	dout("%s con %p was sending epilogue - noop\n", __func__, con);
+}
+
+void ceph_con_v2_revoke(struct ceph_connection *con)
+{
+	WARN_ON(con->v2.out_zero);
+
+	if (con_secure(con)) {
+		WARN_ON(con->v2.out_state != OUT_S_QUEUE_ENC_PAGE &&
+			con->v2.out_state != OUT_S_FINISH_MESSAGE);
+		dout("%s con %p secure - noop\n", __func__, con);
+		return;
+	}
+
+	switch (con->v2.out_state) {
+	case OUT_S_QUEUE_DATA:
+		revoke_at_queue_data(con);
+		break;
+	case OUT_S_QUEUE_DATA_CONT:
+		revoke_at_queue_data_cont(con);
+		break;
+	case OUT_S_FINISH_MESSAGE:
+		revoke_at_finish_message(con);
+		break;
+	default:
+		WARN(1, "bad out_state %d", con->v2.out_state);
+		break;
+	}
+}
+
+static void revoke_at_prepare_read_data(struct ceph_connection *con)
+{
+	int remaining;  /* data + [data padding] + epilogue */
+	int resid;
+
+	WARN_ON(!data_len(con->in_msg));
+	WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
+	resid = iov_iter_count(&con->v2.in_iter);
+	WARN_ON(!resid);
+
+	if (con_secure(con))
+		remaining = padded_len(data_len(con->in_msg)) +
+			    CEPH_EPILOGUE_SECURE_LEN;
+	else
+		remaining = data_len(con->in_msg) + CEPH_EPILOGUE_PLAIN_LEN;
+
+	dout("%s con %p resid %d remaining %d\n", __func__, con, resid,
+	     remaining);
+	con->v2.in_iter.count -= resid;
+	set_in_skip(con, resid + remaining);
+	con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
+static void revoke_at_prepare_read_data_cont(struct ceph_connection *con)
+{
+	int recved, resid;  /* current piece of data */
+	int remaining;  /* [data padding] + epilogue */
+
+	WARN_ON(!data_len(con->in_msg));
+	WARN_ON(!iov_iter_is_bvec(&con->v2.in_iter));
+	resid = iov_iter_count(&con->v2.in_iter);
+	WARN_ON(!resid || resid > con->v2.in_bvec.bv_len);
+	recved = con->v2.in_bvec.bv_len - resid;
+	dout("%s con %p recved %d resid %d\n", __func__, con, recved, resid);
+
+	if (recved)
+		ceph_msg_data_advance(&con->v2.in_cursor, recved);
+	WARN_ON(resid > con->v2.in_cursor.total_resid);
+
+	if (con_secure(con))
+		remaining = padding_len(data_len(con->in_msg)) +
+			    CEPH_EPILOGUE_SECURE_LEN;
+	else
+		remaining = CEPH_EPILOGUE_PLAIN_LEN;
+
+	dout("%s con %p total_resid %zu remaining %d\n", __func__, con,
+	     con->v2.in_cursor.total_resid, remaining);
+	con->v2.in_iter.count -= resid;
+	set_in_skip(con, con->v2.in_cursor.total_resid + remaining);
+	con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
+static void revoke_at_handle_epilogue(struct ceph_connection *con)
+{
+	int resid;
+
+	WARN_ON(!iov_iter_is_kvec(&con->v2.in_iter));
+	resid = iov_iter_count(&con->v2.in_iter);
+	WARN_ON(!resid);
+
+	dout("%s con %p resid %d\n", __func__, con, resid);
+	con->v2.in_iter.count -= resid;
+	set_in_skip(con, resid);
+	con->v2.in_state = IN_S_FINISH_SKIP;
+}
+
+void ceph_con_v2_revoke_incoming(struct ceph_connection *con)
+{
+	switch (con->v2.in_state) {
+	case IN_S_PREPARE_READ_DATA:
+		revoke_at_prepare_read_data(con);
+		break;
+	case IN_S_PREPARE_READ_DATA_CONT:
+		revoke_at_prepare_read_data_cont(con);
+		break;
+	case IN_S_HANDLE_EPILOGUE:
+		revoke_at_handle_epilogue(con);
+		break;
+	default:
+		WARN(1, "bad in_state %d", con->v2.in_state);
+		break;
+	}
+}
+
+bool ceph_con_v2_opened(struct ceph_connection *con)
+{
+	return con->v2.peer_global_seq;
+}
+
+void ceph_con_v2_reset_session(struct ceph_connection *con)
+{
+	con->v2.client_cookie = 0;
+	con->v2.server_cookie = 0;
+	con->v2.global_seq = 0;
+	con->v2.connect_seq = 0;
+	con->v2.peer_global_seq = 0;
+}
+
+void ceph_con_v2_reset_protocol(struct ceph_connection *con)
+{
+	iov_iter_truncate(&con->v2.in_iter, 0);
+	iov_iter_truncate(&con->v2.out_iter, 0);
+	con->v2.out_zero = 0;
+
+	clear_in_sign_kvecs(con);
+	clear_out_sign_kvecs(con);
+	free_conn_bufs(con);
+
+	if (con->v2.out_enc_pages) {
+		WARN_ON(!con->v2.out_enc_page_cnt);
+		ceph_release_page_vector(con->v2.out_enc_pages,
+					 con->v2.out_enc_page_cnt);
+		con->v2.out_enc_pages = NULL;
+		con->v2.out_enc_page_cnt = 0;
+	}
+
+	con->v2.con_mode = CEPH_CON_MODE_UNKNOWN;
+	memzero_explicit(&con->v2.in_gcm_nonce, CEPH_GCM_IV_LEN);
+	memzero_explicit(&con->v2.out_gcm_nonce, CEPH_GCM_IV_LEN);
+
+	if (con->v2.hmac_tfm) {
+		crypto_free_shash(con->v2.hmac_tfm);
+		con->v2.hmac_tfm = NULL;
+	}
+	if (con->v2.gcm_req) {
+		aead_request_free(con->v2.gcm_req);
+		con->v2.gcm_req = NULL;
+	}
+	if (con->v2.gcm_tfm) {
+		crypto_free_aead(con->v2.gcm_tfm);
+		con->v2.gcm_tfm = NULL;
+	}
+}
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index d633a0aeaa55..195ceb8afb06 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -36,57 +36,122 @@ static const struct ceph_connection_operations mon_con_ops;
 
 static int __validate_auth(struct ceph_mon_client *monc);
 
+static int decode_mon_info(void **p, void *end, bool msgr2,
+			   struct ceph_entity_addr *addr)
+{
+	void *mon_info_end;
+	u32 struct_len;
+	u8 struct_v;
+	int ret;
+
+	ret = ceph_start_decoding(p, end, 1, "mon_info_t", &struct_v,
+				  &struct_len);
+	if (ret)
+		return ret;
+
+	mon_info_end = *p + struct_len;
+	ceph_decode_skip_string(p, end, e_inval);  /* skip mon name */
+	ret = ceph_decode_entity_addrvec(p, end, msgr2, addr);
+	if (ret)
+		return ret;
+
+	*p = mon_info_end;
+	return 0;
+
+e_inval:
+	return -EINVAL;
+}
+
 /*
  * Decode a monmap blob (e.g., during mount).
+ *
+ * Assume MonMap v3 (i.e. encoding with MONNAMES and MONENC).
  */
-static struct ceph_monmap *ceph_monmap_decode(void *p, void *end)
+static struct ceph_monmap *ceph_monmap_decode(void **p, void *end, bool msgr2)
 {
-	struct ceph_monmap *m = NULL;
-	int i, err = -EINVAL;
+	struct ceph_monmap *monmap = NULL;
 	struct ceph_fsid fsid;
-	u32 epoch, num_mon;
-	u32 len;
+	u32 struct_len;
+	int blob_len;
+	int num_mon;
+	u8 struct_v;
+	u32 epoch;
+	int ret;
+	int i;
+
+	ceph_decode_32_safe(p, end, blob_len, e_inval);
+	ceph_decode_need(p, end, blob_len, e_inval);
+
+	ret = ceph_start_decoding(p, end, 6, "monmap", &struct_v, &struct_len);
+	if (ret)
+		goto fail;
 
-	ceph_decode_32_safe(&p, end, len, bad);
-	ceph_decode_need(&p, end, len, bad);
+	dout("%s struct_v %d\n", __func__, struct_v);
+	ceph_decode_copy_safe(p, end, &fsid, sizeof(fsid), e_inval);
+	ceph_decode_32_safe(p, end, epoch, e_inval);
+	if (struct_v >= 6) {
+		u32 feat_struct_len;
+		u8 feat_struct_v;
 
-	dout("monmap_decode %p %p len %d (%d)\n", p, end, len, (int)(end-p));
-	p += sizeof(u16);  /* skip version */
+		*p += sizeof(struct ceph_timespec);  /* skip last_changed */
+		*p += sizeof(struct ceph_timespec);  /* skip created */
 
-	ceph_decode_need(&p, end, sizeof(fsid) + 2*sizeof(u32), bad);
-	ceph_decode_copy(&p, &fsid, sizeof(fsid));
-	epoch = ceph_decode_32(&p);
+		ret = ceph_start_decoding(p, end, 1, "mon_feature_t",
+					  &feat_struct_v, &feat_struct_len);
+		if (ret)
+			goto fail;
 
-	num_mon = ceph_decode_32(&p);
+		*p += feat_struct_len;  /* skip persistent_features */
 
+		ret = ceph_start_decoding(p, end, 1, "mon_feature_t",
+					  &feat_struct_v, &feat_struct_len);
+		if (ret)
+			goto fail;
+
+		*p += feat_struct_len;  /* skip optional_features */
+	}
+	ceph_decode_32_safe(p, end, num_mon, e_inval);
+
+	dout("%s fsid %pU epoch %u num_mon %d\n", __func__, &fsid, epoch,
+	     num_mon);
 	if (num_mon > CEPH_MAX_MON)
-		goto bad;
-	m = kmalloc(struct_size(m, mon_inst, num_mon), GFP_NOFS);
-	if (m == NULL)
-		return ERR_PTR(-ENOMEM);
-	m->fsid = fsid;
-	m->epoch = epoch;
-	m->num_mon = num_mon;
-	for (i = 0; i < num_mon; ++i) {
-		struct ceph_entity_inst *inst = &m->mon_inst[i];
-
-		/* copy name portion */
-		ceph_decode_copy_safe(&p, end, &inst->name,
-					sizeof(inst->name), bad);
-		err = ceph_decode_entity_addr(&p, end, &inst->addr);
-		if (err)
-			goto bad;
+		goto e_inval;
+
+	monmap = kmalloc(struct_size(monmap, mon_inst, num_mon), GFP_NOIO);
+	if (!monmap) {
+		ret = -ENOMEM;
+		goto fail;
 	}
-	dout("monmap_decode epoch %d, num_mon %d\n", m->epoch,
-	     m->num_mon);
-	for (i = 0; i < m->num_mon; i++)
-		dout("monmap_decode  mon%d is %s\n", i,
-		     ceph_pr_addr(&m->mon_inst[i].addr));
-	return m;
-bad:
-	dout("monmap_decode failed with %d\n", err);
-	kfree(m);
-	return ERR_PTR(err);
+	monmap->fsid = fsid;
+	monmap->epoch = epoch;
+	monmap->num_mon = num_mon;
+
+	/* legacy_mon_addr map or mon_info map */
+	for (i = 0; i < num_mon; i++) {
+		struct ceph_entity_inst *inst = &monmap->mon_inst[i];
+
+		ceph_decode_skip_string(p, end, e_inval);  /* skip mon name */
+		inst->name.type = CEPH_ENTITY_TYPE_MON;
+		inst->name.num = cpu_to_le64(i);
+
+		if (struct_v >= 6)
+			ret = decode_mon_info(p, end, msgr2, &inst->addr);
+		else
+			ret = ceph_decode_entity_addr(p, end, &inst->addr);
+		if (ret)
+			goto fail;
+
+		dout("%s mon%d addr %s\n", __func__, i,
+		     ceph_pr_addr(&inst->addr));
+	}
+
+	return monmap;
+
+e_inval:
+	ret = -EINVAL;
+fail:
+	kfree(monmap);
+	return ERR_PTR(ret);
 }
 
 /*
@@ -96,9 +161,11 @@ int ceph_monmap_contains(struct ceph_monmap *m, struct ceph_entity_addr *addr)
 {
 	int i;
 
-	for (i = 0; i < m->num_mon; i++)
-		if (memcmp(addr, &m->mon_inst[i].addr, sizeof(*addr)) == 0)
+	for (i = 0; i < m->num_mon; i++) {
+		if (ceph_addr_equal_no_type(addr, &m->mon_inst[i].addr))
 			return 1;
+	}
+
 	return 0;
 }
 
@@ -190,10 +257,16 @@ static void __open_session(struct ceph_mon_client *monc)
 		      &monc->monmap->mon_inst[monc->cur_mon].addr);
 
 	/*
-	 * send an initial keepalive to ensure our timestamp is valid
-	 * by the time we are in an OPENED state
+	 * Queue a keepalive to ensure that in case of an early fault
+	 * the messenger doesn't put us into STANDBY state and instead
+	 * retries.  This also ensures that our timestamp is valid by
+	 * the time we finish hunting and delayed_work() checks it.
 	 */
 	ceph_con_keepalive(&monc->con);
+	if (ceph_msgr2(monc->client)) {
+		monc->pending_auth = 1;
+		return;
+	}
 
 	/* initiate authentication handshake */
 	ret = ceph_auth_build_hello(monc->auth,
@@ -476,7 +549,7 @@ static void ceph_monc_handle_map(struct ceph_mon_client *monc,
 	p = msg->front.iov_base;
 	end = p + msg->front.iov_len;
 
-	monmap = ceph_monmap_decode(p, end);
+	monmap = ceph_monmap_decode(&p, end, ceph_msgr2(client));
 	if (IS_ERR(monmap)) {
 		pr_err("problem decoding monmap, %d\n",
 		       (int)PTR_ERR(monmap));
@@ -896,8 +969,9 @@ bad:
 	ceph_msg_dump(msg);
 }
 
-int ceph_monc_blacklist_add(struct ceph_mon_client *monc,
-			    struct ceph_entity_addr *client_addr)
+static __printf(2, 0)
+int do_mon_command_vargs(struct ceph_mon_client *monc, const char *fmt,
+			 va_list ap)
 {
 	struct ceph_mon_generic_request *req;
 	struct ceph_mon_command *h;
@@ -925,29 +999,65 @@ int ceph_monc_blacklist_add(struct ceph_mon_client *monc,
 	h->monhdr.session_mon_tid = 0;
 	h->fsid = monc->monmap->fsid;
 	h->num_strs = cpu_to_le32(1);
-	len = sprintf(h->str, "{ \"prefix\": \"osd blacklist\", \
-		                 \"blacklistop\": \"add\", \
-				 \"addr\": \"%pISpc/%u\" }",
-		      &client_addr->in_addr, le32_to_cpu(client_addr->nonce));
+	len = vsprintf(h->str, fmt, ap);
 	h->str_len = cpu_to_le32(len);
 	send_generic_request(monc, req);
 	mutex_unlock(&monc->mutex);
 
 	ret = wait_generic_request(req);
-	if (!ret)
-		/*
-		 * Make sure we have the osdmap that includes the blacklist
-		 * entry.  This is needed to ensure that the OSDs pick up the
-		 * new blacklist before processing any future requests from
-		 * this client.
-		 */
-		ret = ceph_wait_for_latest_osdmap(monc->client, 0);
-
 out:
 	put_generic_request(req);
 	return ret;
 }
-EXPORT_SYMBOL(ceph_monc_blacklist_add);
+
+static __printf(2, 3)
+int do_mon_command(struct ceph_mon_client *monc, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = do_mon_command_vargs(monc, fmt, ap);
+	va_end(ap);
+	return ret;
+}
+
+int ceph_monc_blocklist_add(struct ceph_mon_client *monc,
+			    struct ceph_entity_addr *client_addr)
+{
+	int ret;
+
+	ret = do_mon_command(monc,
+			     "{ \"prefix\": \"osd blocklist\", \
+				\"blocklistop\": \"add\", \
+				\"addr\": \"%pISpc/%u\" }",
+			     &client_addr->in_addr,
+			     le32_to_cpu(client_addr->nonce));
+	if (ret == -EINVAL) {
+		/*
+		 * The monitor returns EINVAL on an unrecognized command.
+		 * Try the legacy command -- it is exactly the same except
+		 * for the name.
+		 */
+		ret = do_mon_command(monc,
+				     "{ \"prefix\": \"osd blacklist\", \
+					\"blacklistop\": \"add\", \
+					\"addr\": \"%pISpc/%u\" }",
+				     &client_addr->in_addr,
+				     le32_to_cpu(client_addr->nonce));
+	}
+	if (ret)
+		return ret;
+
+	/*
+	 * Make sure we have the osdmap that includes the blocklist
+	 * entry.  This is needed to ensure that the OSDs pick up the
+	 * new blocklist before processing any future requests from
+	 * this client.
+	 */
+	return ceph_wait_for_latest_osdmap(monc->client, 0);
+}
+EXPORT_SYMBOL(ceph_monc_blocklist_add);
 
 /*
  * Resend pending generic requests.
@@ -1015,8 +1125,9 @@ static void delayed_work(struct work_struct *work)
  */
 static int build_initial_monmap(struct ceph_mon_client *monc)
 {
+	__le32 my_type = ceph_msgr2(monc->client) ?
+		CEPH_ENTITY_ADDR_TYPE_MSGR2 : CEPH_ENTITY_ADDR_TYPE_LEGACY;
 	struct ceph_options *opt = monc->client->options;
-	struct ceph_entity_addr *mon_addr = opt->mon_addr;
 	int num_mon = opt->num_mon;
 	int i;
 
@@ -1025,12 +1136,16 @@ static int build_initial_monmap(struct ceph_mon_client *monc)
 			       GFP_KERNEL);
 	if (!monc->monmap)
 		return -ENOMEM;
+
 	for (i = 0; i < num_mon; i++) {
-		monc->monmap->mon_inst[i].addr = mon_addr[i];
-		monc->monmap->mon_inst[i].addr.nonce = 0;
-		monc->monmap->mon_inst[i].name.type =
-			CEPH_ENTITY_TYPE_MON;
-		monc->monmap->mon_inst[i].name.num = cpu_to_le64(i);
+		struct ceph_entity_inst *inst = &monc->monmap->mon_inst[i];
+
+		memcpy(&inst->addr.in_addr, &opt->mon_addr[i].in_addr,
+		       sizeof(inst->addr.in_addr));
+		inst->addr.type = my_type;
+		inst->addr.nonce = 0;
+		inst->name.type = CEPH_ENTITY_TYPE_MON;
+		inst->name.num = cpu_to_le64(i);
 	}
 	monc->monmap->num_mon = num_mon;
 	return 0;
@@ -1052,8 +1167,8 @@ int ceph_monc_init(struct ceph_mon_client *monc, struct ceph_client *cl)
 
 	/* connection */
 	/* authentication */
-	monc->auth = ceph_auth_init(cl->options->name,
-				    cl->options->key);
+	monc->auth = ceph_auth_init(cl->options->name, cl->options->key,
+				    cl->options->con_modes);
 	if (IS_ERR(monc->auth)) {
 		err = PTR_ERR(monc->auth);
 		goto out_monmap;
@@ -1157,30 +1272,22 @@ static void finish_hunting(struct ceph_mon_client *monc)
 	}
 }
 
-static void handle_auth_reply(struct ceph_mon_client *monc,
-			      struct ceph_msg *msg)
+static void finish_auth(struct ceph_mon_client *monc, int auth_err,
+			bool was_authed)
 {
-	int ret;
-	int was_auth = 0;
+	dout("%s auth_err %d was_authed %d\n", __func__, auth_err, was_authed);
+	WARN_ON(auth_err > 0);
 
-	mutex_lock(&monc->mutex);
-	was_auth = ceph_auth_is_authenticated(monc->auth);
 	monc->pending_auth = 0;
-	ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base,
-				     msg->front.iov_len,
-				     monc->m_auth->front.iov_base,
-				     monc->m_auth->front_alloc_len);
-	if (ret > 0) {
-		__send_prepared_auth_request(monc, ret);
-		goto out;
+	if (auth_err) {
+		monc->client->auth_err = auth_err;
+		wake_up_all(&monc->client->auth_wq);
+		return;
 	}
 
-	finish_hunting(monc);
-
-	if (ret < 0) {
-		monc->client->auth_err = ret;
-	} else if (!was_auth && ceph_auth_is_authenticated(monc->auth)) {
-		dout("authenticated, starting session\n");
+	if (!was_authed && ceph_auth_is_authenticated(monc->auth)) {
+		dout("%s authenticated, starting session global_id %llu\n",
+		     __func__, monc->auth->global_id);
 
 		monc->client->msgr.inst.name.type = CEPH_ENTITY_TYPE_CLIENT;
 		monc->client->msgr.inst.name.num =
@@ -1192,11 +1299,27 @@ static void handle_auth_reply(struct ceph_mon_client *monc,
 		pr_info("mon%d %s session established\n", monc->cur_mon,
 			ceph_pr_addr(&monc->con.peer_addr));
 	}
+}
 
-out:
+static void handle_auth_reply(struct ceph_mon_client *monc,
+			      struct ceph_msg *msg)
+{
+	bool was_authed;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	was_authed = ceph_auth_is_authenticated(monc->auth);
+	ret = ceph_handle_auth_reply(monc->auth, msg->front.iov_base,
+				     msg->front.iov_len,
+				     monc->m_auth->front.iov_base,
+				     monc->m_auth->front_alloc_len);
+	if (ret > 0) {
+		__send_prepared_auth_request(monc, ret);
+	} else {
+		finish_auth(monc, ret, was_authed);
+		finish_hunting(monc);
+	}
 	mutex_unlock(&monc->mutex);
-	if (monc->client->auth_err < 0)
-		wake_up_all(&monc->client->auth_wq);
 }
 
 static int __validate_auth(struct ceph_mon_client *monc)
@@ -1225,10 +1348,92 @@ int ceph_monc_validate_auth(struct ceph_mon_client *monc)
 }
 EXPORT_SYMBOL(ceph_monc_validate_auth);
 
+static int mon_get_auth_request(struct ceph_connection *con,
+				void *buf, int *buf_len,
+				void **authorizer, int *authorizer_len)
+{
+	struct ceph_mon_client *monc = con->private;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	ret = ceph_auth_get_request(monc->auth, buf, *buf_len);
+	mutex_unlock(&monc->mutex);
+	if (ret < 0)
+		return ret;
+
+	*buf_len = ret;
+	*authorizer = NULL;
+	*authorizer_len = 0;
+	return 0;
+}
+
+static int mon_handle_auth_reply_more(struct ceph_connection *con,
+				      void *reply, int reply_len,
+				      void *buf, int *buf_len,
+				      void **authorizer, int *authorizer_len)
+{
+	struct ceph_mon_client *monc = con->private;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	ret = ceph_auth_handle_reply_more(monc->auth, reply, reply_len,
+					  buf, *buf_len);
+	mutex_unlock(&monc->mutex);
+	if (ret < 0)
+		return ret;
+
+	*buf_len = ret;
+	*authorizer = NULL;
+	*authorizer_len = 0;
+	return 0;
+}
+
+static int mon_handle_auth_done(struct ceph_connection *con,
+				u64 global_id, void *reply, int reply_len,
+				u8 *session_key, int *session_key_len,
+				u8 *con_secret, int *con_secret_len)
+{
+	struct ceph_mon_client *monc = con->private;
+	bool was_authed;
+	int ret;
+
+	mutex_lock(&monc->mutex);
+	WARN_ON(!monc->hunting);
+	was_authed = ceph_auth_is_authenticated(monc->auth);
+	ret = ceph_auth_handle_reply_done(monc->auth, global_id,
+					  reply, reply_len,
+					  session_key, session_key_len,
+					  con_secret, con_secret_len);
+	finish_auth(monc, ret, was_authed);
+	if (!ret)
+		finish_hunting(monc);
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
+static int mon_handle_auth_bad_method(struct ceph_connection *con,
+				      int used_proto, int result,
+				      const int *allowed_protos, int proto_cnt,
+				      const int *allowed_modes, int mode_cnt)
+{
+	struct ceph_mon_client *monc = con->private;
+	bool was_authed;
+
+	mutex_lock(&monc->mutex);
+	WARN_ON(!monc->hunting);
+	was_authed = ceph_auth_is_authenticated(monc->auth);
+	ceph_auth_handle_bad_method(monc->auth, used_proto, result,
+				    allowed_protos, proto_cnt,
+				    allowed_modes, mode_cnt);
+	finish_auth(monc, -EACCES, was_authed);
+	mutex_unlock(&monc->mutex);
+	return 0;
+}
+
 /*
  * handle incoming message
  */
-static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
+static void mon_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 {
 	struct ceph_mon_client *monc = con->private;
 	int type = le16_to_cpu(msg->hdr.type);
@@ -1360,19 +1565,23 @@ static void mon_fault(struct ceph_connection *con)
  * will come from the messenger workqueue, which is drained prior to
  * mon_client destruction.
  */
-static struct ceph_connection *con_get(struct ceph_connection *con)
+static struct ceph_connection *mon_get_con(struct ceph_connection *con)
 {
 	return con;
 }
 
-static void con_put(struct ceph_connection *con)
+static void mon_put_con(struct ceph_connection *con)
 {
 }
 
 static const struct ceph_connection_operations mon_con_ops = {
-	.get = con_get,
-	.put = con_put,
-	.dispatch = dispatch,
-	.fault = mon_fault,
+	.get = mon_get_con,
+	.put = mon_put_con,
 	.alloc_msg = mon_alloc_msg,
+	.dispatch = mon_dispatch,
+	.fault = mon_fault,
+	.get_auth_request = mon_get_auth_request,
+	.handle_auth_reply_more = mon_handle_auth_reply_more,
+	.handle_auth_done = mon_handle_auth_done,
+	.handle_auth_bad_method = mon_handle_auth_bad_method,
 };
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 7901ab6c79fd..ff8624a7c964 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -3918,9 +3918,11 @@ static int handle_one_map(struct ceph_osd_client *osdc,
 	set_pool_was_full(osdc);
 
 	if (incremental)
-		newmap = osdmap_apply_incremental(&p, end, osdc->osdmap);
+		newmap = osdmap_apply_incremental(&p, end,
+						  ceph_msgr2(osdc->client),
+						  osdc->osdmap);
 	else
-		newmap = ceph_osdmap_decode(&p, end);
+		newmap = ceph_osdmap_decode(&p, end, ceph_msgr2(osdc->client));
 	if (IS_ERR(newmap))
 		return PTR_ERR(newmap);
 
@@ -5410,7 +5412,7 @@ void ceph_osdc_cleanup(void)
 /*
  * handle incoming message
  */
-static void dispatch(struct ceph_connection *con, struct ceph_msg *msg)
+static void osd_dispatch(struct ceph_connection *con, struct ceph_msg *msg)
 {
 	struct ceph_osd *osd = con->private;
 	struct ceph_osd_client *osdc = osd->o_osdc;
@@ -5532,9 +5534,9 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
 	return m;
 }
 
-static struct ceph_msg *alloc_msg(struct ceph_connection *con,
-				  struct ceph_msg_header *hdr,
-				  int *skip)
+static struct ceph_msg *osd_alloc_msg(struct ceph_connection *con,
+				      struct ceph_msg_header *hdr,
+				      int *skip)
 {
 	struct ceph_osd *osd = con->private;
 	int type = le16_to_cpu(hdr->type);
@@ -5558,7 +5560,7 @@ static struct ceph_msg *alloc_msg(struct ceph_connection *con,
 /*
  * Wrappers to refcount containing ceph_osd struct
  */
-static struct ceph_connection *get_osd_con(struct ceph_connection *con)
+static struct ceph_connection *osd_get_con(struct ceph_connection *con)
 {
 	struct ceph_osd *osd = con->private;
 	if (get_osd(osd))
@@ -5566,7 +5568,7 @@ static struct ceph_connection *get_osd_con(struct ceph_connection *con)
 	return NULL;
 }
 
-static void put_osd_con(struct ceph_connection *con)
+static void osd_put_con(struct ceph_connection *con)
 {
 	struct ceph_osd *osd = con->private;
 	put_osd(osd);
@@ -5575,39 +5577,29 @@ static void put_osd_con(struct ceph_connection *con)
 /*
  * authentication
  */
+
 /*
  * Note: returned pointer is the address of a structure that's
  * managed separately.  Caller must *not* attempt to free it.
  */
-static struct ceph_auth_handshake *get_authorizer(struct ceph_connection *con,
-					int *proto, int force_new)
+static struct ceph_auth_handshake *
+osd_get_authorizer(struct ceph_connection *con, int *proto, int force_new)
 {
 	struct ceph_osd *o = con->private;
 	struct ceph_osd_client *osdc = o->o_osdc;
 	struct ceph_auth_client *ac = osdc->client->monc.auth;
 	struct ceph_auth_handshake *auth = &o->o_auth;
+	int ret;
 
-	if (force_new && auth->authorizer) {
-		ceph_auth_destroy_authorizer(auth->authorizer);
-		auth->authorizer = NULL;
-	}
-	if (!auth->authorizer) {
-		int ret = ceph_auth_create_authorizer(ac, CEPH_ENTITY_TYPE_OSD,
-						      auth);
-		if (ret)
-			return ERR_PTR(ret);
-	} else {
-		int ret = ceph_auth_update_authorizer(ac, CEPH_ENTITY_TYPE_OSD,
-						     auth);
-		if (ret)
-			return ERR_PTR(ret);
-	}
-	*proto = ac->protocol;
+	ret = __ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_OSD,
+					 force_new, proto, NULL, NULL);
+	if (ret)
+		return ERR_PTR(ret);
 
 	return auth;
 }
 
-static int add_authorizer_challenge(struct ceph_connection *con,
+static int osd_add_authorizer_challenge(struct ceph_connection *con,
 				    void *challenge_buf, int challenge_buf_len)
 {
 	struct ceph_osd *o = con->private;
@@ -5618,16 +5610,19 @@ static int add_authorizer_challenge(struct ceph_connection *con,
 					    challenge_buf, challenge_buf_len);
 }
 
-static int verify_authorizer_reply(struct ceph_connection *con)
+static int osd_verify_authorizer_reply(struct ceph_connection *con)
 {
 	struct ceph_osd *o = con->private;
 	struct ceph_osd_client *osdc = o->o_osdc;
 	struct ceph_auth_client *ac = osdc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &o->o_auth;
 
-	return ceph_auth_verify_authorizer_reply(ac, o->o_auth.authorizer);
+	return ceph_auth_verify_authorizer_reply(ac, auth->authorizer,
+		auth->authorizer_reply_buf, auth->authorizer_reply_buf_len,
+		NULL, NULL, NULL, NULL);
 }
 
-static int invalidate_authorizer(struct ceph_connection *con)
+static int osd_invalidate_authorizer(struct ceph_connection *con)
 {
 	struct ceph_osd *o = con->private;
 	struct ceph_osd_client *osdc = o->o_osdc;
@@ -5637,6 +5632,80 @@ static int invalidate_authorizer(struct ceph_connection *con)
 	return ceph_monc_validate_auth(&osdc->client->monc);
 }
 
+static int osd_get_auth_request(struct ceph_connection *con,
+				void *buf, int *buf_len,
+				void **authorizer, int *authorizer_len)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_client *ac = o->o_osdc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	int ret;
+
+	ret = ceph_auth_get_authorizer(ac, auth, CEPH_ENTITY_TYPE_OSD,
+				       buf, buf_len);
+	if (ret)
+		return ret;
+
+	*authorizer = auth->authorizer_buf;
+	*authorizer_len = auth->authorizer_buf_len;
+	return 0;
+}
+
+static int osd_handle_auth_reply_more(struct ceph_connection *con,
+				      void *reply, int reply_len,
+				      void *buf, int *buf_len,
+				      void **authorizer, int *authorizer_len)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_client *ac = o->o_osdc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+	int ret;
+
+	ret = ceph_auth_handle_svc_reply_more(ac, auth, reply, reply_len,
+					      buf, buf_len);
+	if (ret)
+		return ret;
+
+	*authorizer = auth->authorizer_buf;
+	*authorizer_len = auth->authorizer_buf_len;
+	return 0;
+}
+
+static int osd_handle_auth_done(struct ceph_connection *con,
+				u64 global_id, void *reply, int reply_len,
+				u8 *session_key, int *session_key_len,
+				u8 *con_secret, int *con_secret_len)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_auth_client *ac = o->o_osdc->client->monc.auth;
+	struct ceph_auth_handshake *auth = &o->o_auth;
+
+	return ceph_auth_handle_svc_reply_done(ac, auth, reply, reply_len,
+					       session_key, session_key_len,
+					       con_secret, con_secret_len);
+}
+
+static int osd_handle_auth_bad_method(struct ceph_connection *con,
+				      int used_proto, int result,
+				      const int *allowed_protos, int proto_cnt,
+				      const int *allowed_modes, int mode_cnt)
+{
+	struct ceph_osd *o = con->private;
+	struct ceph_mon_client *monc = &o->o_osdc->client->monc;
+	int ret;
+
+	if (ceph_auth_handle_bad_authorizer(monc->auth, CEPH_ENTITY_TYPE_OSD,
+					    used_proto, result,
+					    allowed_protos, proto_cnt,
+					    allowed_modes, mode_cnt)) {
+		ret = ceph_monc_validate_auth(monc);
+		if (ret)
+			return ret;
+	}
+
+	return -EACCES;
+}
+
 static void osd_reencode_message(struct ceph_msg *msg)
 {
 	int type = le16_to_cpu(msg->hdr.type);
@@ -5662,16 +5731,20 @@ static int osd_check_message_signature(struct ceph_msg *msg)
 }
 
 static const struct ceph_connection_operations osd_con_ops = {
-	.get = get_osd_con,
-	.put = put_osd_con,
-	.dispatch = dispatch,
-	.get_authorizer = get_authorizer,
-	.add_authorizer_challenge = add_authorizer_challenge,
-	.verify_authorizer_reply = verify_authorizer_reply,
-	.invalidate_authorizer = invalidate_authorizer,
-	.alloc_msg = alloc_msg,
+	.get = osd_get_con,
+	.put = osd_put_con,
+	.alloc_msg = osd_alloc_msg,
+	.dispatch = osd_dispatch,
+	.fault = osd_fault,
 	.reencode_message = osd_reencode_message,
+	.get_authorizer = osd_get_authorizer,
+	.add_authorizer_challenge = osd_add_authorizer_challenge,
+	.verify_authorizer_reply = osd_verify_authorizer_reply,
+	.invalidate_authorizer = osd_invalidate_authorizer,
 	.sign_message = osd_sign_message,
 	.check_message_signature = osd_check_message_signature,
-	.fault = osd_fault,
+	.get_auth_request = osd_get_auth_request,
+	.handle_auth_reply_more = osd_handle_auth_reply_more,
+	.handle_auth_done = osd_handle_auth_done,
+	.handle_auth_bad_method = osd_handle_auth_bad_method,
 };
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 96c25f5e064a..2b1dd252f231 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -965,6 +965,143 @@ bad:
 }
 
 /*
+ * CRUSH workspaces
+ *
+ * workspace_manager framework borrowed from fs/btrfs/compression.c.
+ * Two simplifications: there is only one type of workspace and there
+ * is always at least one workspace.
+ */
+static struct crush_work *alloc_workspace(const struct crush_map *c)
+{
+	struct crush_work *work;
+	size_t work_size;
+
+	WARN_ON(!c->working_size);
+	work_size = crush_work_size(c, CEPH_PG_MAX_SIZE);
+	dout("%s work_size %zu bytes\n", __func__, work_size);
+
+	work = ceph_kvmalloc(work_size, GFP_NOIO);
+	if (!work)
+		return NULL;
+
+	INIT_LIST_HEAD(&work->item);
+	crush_init_workspace(c, work);
+	return work;
+}
+
+static void free_workspace(struct crush_work *work)
+{
+	WARN_ON(!list_empty(&work->item));
+	kvfree(work);
+}
+
+static void init_workspace_manager(struct workspace_manager *wsm)
+{
+	INIT_LIST_HEAD(&wsm->idle_ws);
+	spin_lock_init(&wsm->ws_lock);
+	atomic_set(&wsm->total_ws, 0);
+	wsm->free_ws = 0;
+	init_waitqueue_head(&wsm->ws_wait);
+}
+
+static void add_initial_workspace(struct workspace_manager *wsm,
+				  struct crush_work *work)
+{
+	WARN_ON(!list_empty(&wsm->idle_ws));
+
+	list_add(&work->item, &wsm->idle_ws);
+	atomic_set(&wsm->total_ws, 1);
+	wsm->free_ws = 1;
+}
+
+static void cleanup_workspace_manager(struct workspace_manager *wsm)
+{
+	struct crush_work *work;
+
+	while (!list_empty(&wsm->idle_ws)) {
+		work = list_first_entry(&wsm->idle_ws, struct crush_work,
+					item);
+		list_del_init(&work->item);
+		free_workspace(work);
+	}
+	atomic_set(&wsm->total_ws, 0);
+	wsm->free_ws = 0;
+}
+
+/*
+ * Finds an available workspace or allocates a new one.  If it's not
+ * possible to allocate a new one, waits until there is one.
+ */
+static struct crush_work *get_workspace(struct workspace_manager *wsm,
+					const struct crush_map *c)
+{
+	struct crush_work *work;
+	int cpus = num_online_cpus();
+
+again:
+	spin_lock(&wsm->ws_lock);
+	if (!list_empty(&wsm->idle_ws)) {
+		work = list_first_entry(&wsm->idle_ws, struct crush_work,
+					item);
+		list_del_init(&work->item);
+		wsm->free_ws--;
+		spin_unlock(&wsm->ws_lock);
+		return work;
+
+	}
+	if (atomic_read(&wsm->total_ws) > cpus) {
+		DEFINE_WAIT(wait);
+
+		spin_unlock(&wsm->ws_lock);
+		prepare_to_wait(&wsm->ws_wait, &wait, TASK_UNINTERRUPTIBLE);
+		if (atomic_read(&wsm->total_ws) > cpus && !wsm->free_ws)
+			schedule();
+		finish_wait(&wsm->ws_wait, &wait);
+		goto again;
+	}
+	atomic_inc(&wsm->total_ws);
+	spin_unlock(&wsm->ws_lock);
+
+	work = alloc_workspace(c);
+	if (!work) {
+		atomic_dec(&wsm->total_ws);
+		wake_up(&wsm->ws_wait);
+
+		/*
+		 * Do not return the error but go back to waiting.  We
+		 * have the inital workspace and the CRUSH computation
+		 * time is bounded so we will get it eventually.
+		 */
+		WARN_ON(atomic_read(&wsm->total_ws) < 1);
+		goto again;
+	}
+	return work;
+}
+
+/*
+ * Puts a workspace back on the list or frees it if we have enough
+ * idle ones sitting around.
+ */
+static void put_workspace(struct workspace_manager *wsm,
+			  struct crush_work *work)
+{
+	spin_lock(&wsm->ws_lock);
+	if (wsm->free_ws <= num_online_cpus()) {
+		list_add(&work->item, &wsm->idle_ws);
+		wsm->free_ws++;
+		spin_unlock(&wsm->ws_lock);
+		goto wake;
+	}
+	spin_unlock(&wsm->ws_lock);
+
+	free_workspace(work);
+	atomic_dec(&wsm->total_ws);
+wake:
+	if (wq_has_sleeper(&wsm->ws_wait))
+		wake_up(&wsm->ws_wait);
+}
+
+/*
  * osd map
  */
 struct ceph_osdmap *ceph_osdmap_alloc(void)
@@ -981,7 +1118,8 @@ struct ceph_osdmap *ceph_osdmap_alloc(void)
 	map->primary_temp = RB_ROOT;
 	map->pg_upmap = RB_ROOT;
 	map->pg_upmap_items = RB_ROOT;
-	mutex_init(&map->crush_workspace_mutex);
+
+	init_workspace_manager(&map->crush_wsm);
 
 	return map;
 }
@@ -989,8 +1127,11 @@ struct ceph_osdmap *ceph_osdmap_alloc(void)
 void ceph_osdmap_destroy(struct ceph_osdmap *map)
 {
 	dout("osdmap_destroy %p\n", map);
+
 	if (map->crush)
 		crush_destroy(map->crush);
+	cleanup_workspace_manager(&map->crush_wsm);
+
 	while (!RB_EMPTY_ROOT(&map->pg_temp)) {
 		struct ceph_pg_mapping *pg =
 			rb_entry(rb_first(&map->pg_temp),
@@ -1029,7 +1170,6 @@ void ceph_osdmap_destroy(struct ceph_osdmap *map)
 	kvfree(map->osd_weight);
 	kvfree(map->osd_addr);
 	kvfree(map->osd_primary_affinity);
-	kvfree(map->crush_workspace);
 	kfree(map);
 }
 
@@ -1104,26 +1244,22 @@ static int osdmap_set_max_osd(struct ceph_osdmap *map, u32 max)
 
 static int osdmap_set_crush(struct ceph_osdmap *map, struct crush_map *crush)
 {
-	void *workspace;
-	size_t work_size;
+	struct crush_work *work;
 
 	if (IS_ERR(crush))
 		return PTR_ERR(crush);
 
-	work_size = crush_work_size(crush, CEPH_PG_MAX_SIZE);
-	dout("%s work_size %zu bytes\n", __func__, work_size);
-	workspace = ceph_kvmalloc(work_size, GFP_NOIO);
-	if (!workspace) {
+	work = alloc_workspace(crush);
+	if (!work) {
 		crush_destroy(crush);
 		return -ENOMEM;
 	}
-	crush_init_workspace(crush, workspace);
 
 	if (map->crush)
 		crush_destroy(map->crush);
-	kvfree(map->crush_workspace);
+	cleanup_workspace_manager(&map->crush_wsm);
 	map->crush = crush;
-	map->crush_workspace = workspace;
+	add_initial_workspace(&map->crush_wsm, work);
 	return 0;
 }
 
@@ -1511,7 +1647,8 @@ static int decode_old_pg_upmap_items(void **p, void *end,
 /*
  * decode a full map.
  */
-static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
+static int osdmap_decode(void **p, void *end, bool msgr2,
+			 struct ceph_osdmap *map)
 {
 	u8 struct_v;
 	u32 epoch = 0;
@@ -1582,9 +1719,16 @@ static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map)
 		goto e_inval;
 
 	for (i = 0; i < map->max_osd; i++) {
-		err = ceph_decode_entity_addr(p, end, &map->osd_addr[i]);
+		struct ceph_entity_addr *addr = &map->osd_addr[i];
+
+		if (struct_v >= 8)
+			err = ceph_decode_entity_addrvec(p, end, msgr2, addr);
+		else
+			err = ceph_decode_entity_addr(p, end, addr);
 		if (err)
 			goto bad;
+
+		dout("%s osd%d addr %s\n", __func__, i, ceph_pr_addr(addr));
 	}
 
 	/* pg_temp */
@@ -1654,7 +1798,7 @@ bad:
 /*
  * Allocate and decode a full map.
  */
-struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
+struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end, bool msgr2)
 {
 	struct ceph_osdmap *map;
 	int ret;
@@ -1663,7 +1807,7 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
 	if (!map)
 		return ERR_PTR(-ENOMEM);
 
-	ret = osdmap_decode(p, end, map);
+	ret = osdmap_decode(p, end, msgr2, map);
 	if (ret) {
 		ceph_osdmap_destroy(map);
 		return ERR_PTR(ret);
@@ -1681,12 +1825,13 @@ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end)
  *     new_state: { osd=6, xorstate=EXISTS } # clear osd_state
  */
 static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
-				      struct ceph_osdmap *map)
+				      bool msgr2, struct ceph_osdmap *map)
 {
 	void *new_up_client;
 	void *new_state;
 	void *new_weight_end;
 	u32 len;
+	int ret;
 	int i;
 
 	new_up_client = *p;
@@ -1695,8 +1840,12 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 		struct ceph_entity_addr addr;
 
 		ceph_decode_skip_32(p, end, e_inval);
-		if (ceph_decode_entity_addr(p, end, &addr))
-			goto e_inval;
+		if (struct_v >= 7)
+			ret = ceph_decode_entity_addrvec(p, end, msgr2, &addr);
+		else
+			ret = ceph_decode_entity_addr(p, end, &addr);
+		if (ret)
+			return ret;
 	}
 
 	new_state = *p;
@@ -1738,7 +1887,6 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 	while (len--) {
 		s32 osd;
 		u32 xorstate;
-		int ret;
 
 		osd = ceph_decode_32(p);
 		if (struct_v >= 5)
@@ -1774,8 +1922,15 @@ static int decode_new_up_state_weight(void **p, void *end, u8 struct_v,
 
 		osd = ceph_decode_32(p);
 		BUG_ON(osd >= map->max_osd);
-		if (ceph_decode_entity_addr(p, end, &addr))
-			goto e_inval;
+		if (struct_v >= 7)
+			ret = ceph_decode_entity_addrvec(p, end, msgr2, &addr);
+		else
+			ret = ceph_decode_entity_addr(p, end, &addr);
+		if (ret)
+			return ret;
+
+		dout("%s osd%d addr %s\n", __func__, osd, ceph_pr_addr(&addr));
+
 		pr_info("osd%d up\n", osd);
 		map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP;
 		map->osd_addr[osd] = addr;
@@ -1791,7 +1946,7 @@ e_inval:
 /*
  * decode and apply an incremental map update.
  */
-struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
+struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, bool msgr2,
 					     struct ceph_osdmap *map)
 {
 	struct ceph_fsid fsid;
@@ -1826,7 +1981,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	if (len > 0) {
 		dout("apply_incremental full map len %d, %p to %p\n",
 		     len, *p, end);
-		return ceph_osdmap_decode(p, min(*p+len, end));
+		return ceph_osdmap_decode(p, min(*p+len, end), msgr2);
 	}
 
 	/* new crush? */
@@ -1878,7 +2033,7 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	}
 
 	/* new_up_client, new_state, new_weight */
-	err = decode_new_up_state_weight(p, end, struct_v, map);
+	err = decode_new_up_state_weight(p, end, struct_v, msgr2, map);
 	if (err)
 		goto bad;
 
@@ -2322,6 +2477,7 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
 		    s64 choose_args_index)
 {
 	struct crush_choose_arg_map *arg_map;
+	struct crush_work *work;
 	int r;
 
 	BUG_ON(result_max > CEPH_PG_MAX_SIZE);
@@ -2332,12 +2488,11 @@ static int do_crush(struct ceph_osdmap *map, int ruleno, int x,
 		arg_map = lookup_choose_arg_map(&map->crush->choose_args,
 						CEPH_DEFAULT_CHOOSE_ARGS);
 
-	mutex_lock(&map->crush_workspace_mutex);
+	work = get_workspace(&map->crush_wsm, map->crush);
 	r = crush_do_rule(map->crush, ruleno, x, result, result_max,
-			  weight, weight_max, map->crush_workspace,
+			  weight, weight_max, work,
 			  arg_map ? arg_map->args : NULL);
-	mutex_unlock(&map->crush_workspace_mutex);
-
+	put_workspace(&map->crush_wsm, work);
 	return r;
 }
 
diff --git a/net/compat.c b/net/compat.c
index 95ce707a30a3..ddd15af3a283 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -98,8 +98,8 @@ int get_compat_msghdr(struct msghdr *kmsg,
 	if (err)
 		return err;
 
-	err = compat_import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr),
-				   len, UIO_FASTIOV, iov, &kmsg->msg_iter);
+	err = import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr), len,
+			   UIO_FASTIOV, iov, &kmsg->msg_iter);
 	return err < 0 ? err : 0;
 }
 
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index b988f48153a4..4edd033e899c 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -6,550 +6,48 @@
 #include <linux/types.h>
 #include <linux/spinlock.h>
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/btf_ids.h>
+#include <linux/bpf_local_storage.h>
 #include <net/bpf_sk_storage.h>
 #include <net/sock.h>
 #include <uapi/linux/sock_diag.h>
 #include <uapi/linux/btf.h>
 
-#define SK_STORAGE_CREATE_FLAG_MASK					\
-	(BPF_F_NO_PREALLOC | BPF_F_CLONE)
+DEFINE_BPF_STORAGE_CACHE(sk_cache);
 
-struct bucket {
-	struct hlist_head list;
-	raw_spinlock_t lock;
-};
-
-/* Thp map is not the primary owner of a bpf_sk_storage_elem.
- * Instead, the sk->sk_bpf_storage is.
- *
- * The map (bpf_sk_storage_map) is for two purposes
- * 1. Define the size of the "sk local storage".  It is
- *    the map's value_size.
- *
- * 2. Maintain a list to keep track of all elems such
- *    that they can be cleaned up during the map destruction.
- *
- * When a bpf local storage is being looked up for a
- * particular sk,  the "bpf_map" pointer is actually used
- * as the "key" to search in the list of elem in
- * sk->sk_bpf_storage.
- *
- * Hence, consider sk->sk_bpf_storage is the mini-map
- * with the "bpf_map" pointer as the searching key.
- */
-struct bpf_sk_storage_map {
-	struct bpf_map map;
-	/* Lookup elem does not require accessing the map.
-	 *
-	 * Updating/Deleting requires a bucket lock to
-	 * link/unlink the elem from the map.  Having
-	 * multiple buckets to improve contention.
-	 */
-	struct bucket *buckets;
-	u32 bucket_log;
-	u16 elem_size;
-	u16 cache_idx;
-};
-
-struct bpf_sk_storage_data {
-	/* smap is used as the searching key when looking up
-	 * from sk->sk_bpf_storage.
-	 *
-	 * Put it in the same cacheline as the data to minimize
-	 * the number of cachelines access during the cache hit case.
-	 */
-	struct bpf_sk_storage_map __rcu *smap;
-	u8 data[] __aligned(8);
-};
-
-/* Linked to bpf_sk_storage and bpf_sk_storage_map */
-struct bpf_sk_storage_elem {
-	struct hlist_node map_node;	/* Linked to bpf_sk_storage_map */
-	struct hlist_node snode;	/* Linked to bpf_sk_storage */
-	struct bpf_sk_storage __rcu *sk_storage;
-	struct rcu_head rcu;
-	/* 8 bytes hole */
-	/* The data is stored in aother cacheline to minimize
-	 * the number of cachelines access during a cache hit.
-	 */
-	struct bpf_sk_storage_data sdata ____cacheline_aligned;
-};
-
-#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata)
-#define SDATA(_SELEM) (&(_SELEM)->sdata)
-#define BPF_SK_STORAGE_CACHE_SIZE	16
-
-static DEFINE_SPINLOCK(cache_idx_lock);
-static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE];
-
-struct bpf_sk_storage {
-	struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE];
-	struct hlist_head list;	/* List of bpf_sk_storage_elem */
-	struct sock *sk;	/* The sk that owns the the above "list" of
-				 * bpf_sk_storage_elem.
-				 */
-	struct rcu_head rcu;
-	raw_spinlock_t lock;	/* Protect adding/removing from the "list" */
-};
-
-static struct bucket *select_bucket(struct bpf_sk_storage_map *smap,
-				    struct bpf_sk_storage_elem *selem)
+static struct bpf_local_storage_data *
+bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
 {
-	return &smap->buckets[hash_ptr(selem, smap->bucket_log)];
-}
-
-static int omem_charge(struct sock *sk, unsigned int size)
-{
-	/* same check as in sock_kmalloc() */
-	if (size <= sysctl_optmem_max &&
-	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
-		atomic_add(size, &sk->sk_omem_alloc);
-		return 0;
-	}
-
-	return -ENOMEM;
-}
-
-static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem)
-{
-	return !hlist_unhashed(&selem->snode);
-}
-
-static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem)
-{
-	return !hlist_unhashed(&selem->map_node);
-}
-
-static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap,
-					       struct sock *sk, void *value,
-					       bool charge_omem)
-{
-	struct bpf_sk_storage_elem *selem;
-
-	if (charge_omem && omem_charge(sk, smap->elem_size))
-		return NULL;
-
-	selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN);
-	if (selem) {
-		if (value)
-			memcpy(SDATA(selem)->data, value, smap->map.value_size);
-		return selem;
-	}
-
-	if (charge_omem)
-		atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
-
-	return NULL;
-}
-
-/* sk_storage->lock must be held and selem->sk_storage == sk_storage.
- * The caller must ensure selem->smap is still valid to be
- * dereferenced for its smap->elem_size and smap->cache_idx.
- */
-static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage,
-			      struct bpf_sk_storage_elem *selem,
-			      bool uncharge_omem)
-{
-	struct bpf_sk_storage_map *smap;
-	bool free_sk_storage;
-	struct sock *sk;
-
-	smap = rcu_dereference(SDATA(selem)->smap);
-	sk = sk_storage->sk;
-
-	/* All uncharging on sk->sk_omem_alloc must be done first.
-	 * sk may be freed once the last selem is unlinked from sk_storage.
-	 */
-	if (uncharge_omem)
-		atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
-
-	free_sk_storage = hlist_is_singular_node(&selem->snode,
-						 &sk_storage->list);
-	if (free_sk_storage) {
-		atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc);
-		sk_storage->sk = NULL;
-		/* After this RCU_INIT, sk may be freed and cannot be used */
-		RCU_INIT_POINTER(sk->sk_bpf_storage, NULL);
-
-		/* sk_storage is not freed now.  sk_storage->lock is
-		 * still held and raw_spin_unlock_bh(&sk_storage->lock)
-		 * will be done by the caller.
-		 *
-		 * Although the unlock will be done under
-		 * rcu_read_lock(),  it is more intutivie to
-		 * read if kfree_rcu(sk_storage, rcu) is done
-		 * after the raw_spin_unlock_bh(&sk_storage->lock).
-		 *
-		 * Hence, a "bool free_sk_storage" is returned
-		 * to the caller which then calls the kfree_rcu()
-		 * after unlock.
-		 */
-	}
-	hlist_del_init_rcu(&selem->snode);
-	if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) ==
-	    SDATA(selem))
-		RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL);
-
-	kfree_rcu(selem, rcu);
-
-	return free_sk_storage;
-}
-
-static void selem_unlink_sk(struct bpf_sk_storage_elem *selem)
-{
-	struct bpf_sk_storage *sk_storage;
-	bool free_sk_storage = false;
-
-	if (unlikely(!selem_linked_to_sk(selem)))
-		/* selem has already been unlinked from sk */
-		return;
-
-	sk_storage = rcu_dereference(selem->sk_storage);
-	raw_spin_lock_bh(&sk_storage->lock);
-	if (likely(selem_linked_to_sk(selem)))
-		free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
-	raw_spin_unlock_bh(&sk_storage->lock);
-
-	if (free_sk_storage)
-		kfree_rcu(sk_storage, rcu);
-}
-
-static void __selem_link_sk(struct bpf_sk_storage *sk_storage,
-			    struct bpf_sk_storage_elem *selem)
-{
-	RCU_INIT_POINTER(selem->sk_storage, sk_storage);
-	hlist_add_head(&selem->snode, &sk_storage->list);
-}
-
-static void selem_unlink_map(struct bpf_sk_storage_elem *selem)
-{
-	struct bpf_sk_storage_map *smap;
-	struct bucket *b;
-
-	if (unlikely(!selem_linked_to_map(selem)))
-		/* selem has already be unlinked from smap */
-		return;
-
-	smap = rcu_dereference(SDATA(selem)->smap);
-	b = select_bucket(smap, selem);
-	raw_spin_lock_bh(&b->lock);
-	if (likely(selem_linked_to_map(selem)))
-		hlist_del_init_rcu(&selem->map_node);
-	raw_spin_unlock_bh(&b->lock);
-}
-
-static void selem_link_map(struct bpf_sk_storage_map *smap,
-			   struct bpf_sk_storage_elem *selem)
-{
-	struct bucket *b = select_bucket(smap, selem);
-
-	raw_spin_lock_bh(&b->lock);
-	RCU_INIT_POINTER(SDATA(selem)->smap, smap);
-	hlist_add_head_rcu(&selem->map_node, &b->list);
-	raw_spin_unlock_bh(&b->lock);
-}
-
-static void selem_unlink(struct bpf_sk_storage_elem *selem)
-{
-	/* Always unlink from map before unlinking from sk_storage
-	 * because selem will be freed after successfully unlinked from
-	 * the sk_storage.
-	 */
-	selem_unlink_map(selem);
-	selem_unlink_sk(selem);
-}
-
-static struct bpf_sk_storage_data *
-__sk_storage_lookup(struct bpf_sk_storage *sk_storage,
-		    struct bpf_sk_storage_map *smap,
-		    bool cacheit_lockit)
-{
-	struct bpf_sk_storage_data *sdata;
-	struct bpf_sk_storage_elem *selem;
-
-	/* Fast path (cache hit) */
-	sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]);
-	if (sdata && rcu_access_pointer(sdata->smap) == smap)
-		return sdata;
-
-	/* Slow path (cache miss) */
-	hlist_for_each_entry_rcu(selem, &sk_storage->list, snode)
-		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
-			break;
-
-	if (!selem)
-		return NULL;
-
-	sdata = SDATA(selem);
-	if (cacheit_lockit) {
-		/* spinlock is needed to avoid racing with the
-		 * parallel delete.  Otherwise, publishing an already
-		 * deleted sdata to the cache will become a use-after-free
-		 * problem in the next __sk_storage_lookup().
-		 */
-		raw_spin_lock_bh(&sk_storage->lock);
-		if (selem_linked_to_sk(selem))
-			rcu_assign_pointer(sk_storage->cache[smap->cache_idx],
-					   sdata);
-		raw_spin_unlock_bh(&sk_storage->lock);
-	}
-
-	return sdata;
-}
-
-static struct bpf_sk_storage_data *
-sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit)
-{
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_map *smap;
 
 	sk_storage = rcu_dereference(sk->sk_bpf_storage);
 	if (!sk_storage)
 		return NULL;
 
-	smap = (struct bpf_sk_storage_map *)map;
-	return __sk_storage_lookup(sk_storage, smap, cacheit_lockit);
-}
-
-static int check_flags(const struct bpf_sk_storage_data *old_sdata,
-		       u64 map_flags)
-{
-	if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST)
-		/* elem already exists */
-		return -EEXIST;
-
-	if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST)
-		/* elem doesn't exist, cannot update it */
-		return -ENOENT;
-
-	return 0;
-}
-
-static int sk_storage_alloc(struct sock *sk,
-			    struct bpf_sk_storage_map *smap,
-			    struct bpf_sk_storage_elem *first_selem)
-{
-	struct bpf_sk_storage *prev_sk_storage, *sk_storage;
-	int err;
-
-	err = omem_charge(sk, sizeof(*sk_storage));
-	if (err)
-		return err;
-
-	sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN);
-	if (!sk_storage) {
-		err = -ENOMEM;
-		goto uncharge;
-	}
-	INIT_HLIST_HEAD(&sk_storage->list);
-	raw_spin_lock_init(&sk_storage->lock);
-	sk_storage->sk = sk;
-
-	__selem_link_sk(sk_storage, first_selem);
-	selem_link_map(smap, first_selem);
-	/* Publish sk_storage to sk.  sk->sk_lock cannot be acquired.
-	 * Hence, atomic ops is used to set sk->sk_bpf_storage
-	 * from NULL to the newly allocated sk_storage ptr.
-	 *
-	 * From now on, the sk->sk_bpf_storage pointer is protected
-	 * by the sk_storage->lock.  Hence,  when freeing
-	 * the sk->sk_bpf_storage, the sk_storage->lock must
-	 * be held before setting sk->sk_bpf_storage to NULL.
-	 */
-	prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage,
-				  NULL, sk_storage);
-	if (unlikely(prev_sk_storage)) {
-		selem_unlink_map(first_selem);
-		err = -EAGAIN;
-		goto uncharge;
-
-		/* Note that even first_selem was linked to smap's
-		 * bucket->list, first_selem can be freed immediately
-		 * (instead of kfree_rcu) because
-		 * bpf_sk_storage_map_free() does a
-		 * synchronize_rcu() before walking the bucket->list.
-		 * Hence, no one is accessing selem from the
-		 * bucket->list under rcu_read_lock().
-		 */
-	}
-
-	return 0;
-
-uncharge:
-	kfree(sk_storage);
-	atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc);
-	return err;
-}
-
-/* sk cannot be going away because it is linking new elem
- * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0).
- * Otherwise, it will become a leak (and other memory issues
- * during map destruction).
- */
-static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk,
-						     struct bpf_map *map,
-						     void *value,
-						     u64 map_flags)
-{
-	struct bpf_sk_storage_data *old_sdata = NULL;
-	struct bpf_sk_storage_elem *selem;
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_map *smap;
-	int err;
-
-	/* BPF_EXIST and BPF_NOEXIST cannot be both set */
-	if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) ||
-	    /* BPF_F_LOCK can only be used in a value with spin_lock */
-	    unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map)))
-		return ERR_PTR(-EINVAL);
-
-	smap = (struct bpf_sk_storage_map *)map;
-	sk_storage = rcu_dereference(sk->sk_bpf_storage);
-	if (!sk_storage || hlist_empty(&sk_storage->list)) {
-		/* Very first elem for this sk */
-		err = check_flags(NULL, map_flags);
-		if (err)
-			return ERR_PTR(err);
-
-		selem = selem_alloc(smap, sk, value, true);
-		if (!selem)
-			return ERR_PTR(-ENOMEM);
-
-		err = sk_storage_alloc(sk, smap, selem);
-		if (err) {
-			kfree(selem);
-			atomic_sub(smap->elem_size, &sk->sk_omem_alloc);
-			return ERR_PTR(err);
-		}
-
-		return SDATA(selem);
-	}
-
-	if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) {
-		/* Hoping to find an old_sdata to do inline update
-		 * such that it can avoid taking the sk_storage->lock
-		 * and changing the lists.
-		 */
-		old_sdata = __sk_storage_lookup(sk_storage, smap, false);
-		err = check_flags(old_sdata, map_flags);
-		if (err)
-			return ERR_PTR(err);
-		if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) {
-			copy_map_value_locked(map, old_sdata->data,
-					      value, false);
-			return old_sdata;
-		}
-	}
-
-	raw_spin_lock_bh(&sk_storage->lock);
-
-	/* Recheck sk_storage->list under sk_storage->lock */
-	if (unlikely(hlist_empty(&sk_storage->list))) {
-		/* A parallel del is happening and sk_storage is going
-		 * away.  It has just been checked before, so very
-		 * unlikely.  Return instead of retry to keep things
-		 * simple.
-		 */
-		err = -EAGAIN;
-		goto unlock_err;
-	}
-
-	old_sdata = __sk_storage_lookup(sk_storage, smap, false);
-	err = check_flags(old_sdata, map_flags);
-	if (err)
-		goto unlock_err;
-
-	if (old_sdata && (map_flags & BPF_F_LOCK)) {
-		copy_map_value_locked(map, old_sdata->data, value, false);
-		selem = SELEM(old_sdata);
-		goto unlock;
-	}
-
-	/* sk_storage->lock is held.  Hence, we are sure
-	 * we can unlink and uncharge the old_sdata successfully
-	 * later.  Hence, instead of charging the new selem now
-	 * and then uncharge the old selem later (which may cause
-	 * a potential but unnecessary charge failure),  avoid taking
-	 * a charge at all here (the "!old_sdata" check) and the
-	 * old_sdata will not be uncharged later during __selem_unlink_sk().
-	 */
-	selem = selem_alloc(smap, sk, value, !old_sdata);
-	if (!selem) {
-		err = -ENOMEM;
-		goto unlock_err;
-	}
-
-	/* First, link the new selem to the map */
-	selem_link_map(smap, selem);
-
-	/* Second, link (and publish) the new selem to sk_storage */
-	__selem_link_sk(sk_storage, selem);
-
-	/* Third, remove old selem, SELEM(old_sdata) */
-	if (old_sdata) {
-		selem_unlink_map(SELEM(old_sdata));
-		__selem_unlink_sk(sk_storage, SELEM(old_sdata), false);
-	}
-
-unlock:
-	raw_spin_unlock_bh(&sk_storage->lock);
-	return SDATA(selem);
-
-unlock_err:
-	raw_spin_unlock_bh(&sk_storage->lock);
-	return ERR_PTR(err);
+	smap = (struct bpf_local_storage_map *)map;
+	return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit);
 }
 
-static int sk_storage_delete(struct sock *sk, struct bpf_map *map)
+static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map)
 {
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage_data *sdata;
 
-	sdata = sk_storage_lookup(sk, map, false);
+	sdata = bpf_sk_storage_lookup(sk, map, false);
 	if (!sdata)
 		return -ENOENT;
 
-	selem_unlink(SELEM(sdata));
+	bpf_selem_unlink(SELEM(sdata));
 
 	return 0;
 }
 
-static u16 cache_idx_get(void)
-{
-	u64 min_usage = U64_MAX;
-	u16 i, res = 0;
-
-	spin_lock(&cache_idx_lock);
-
-	for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) {
-		if (cache_idx_usage_counts[i] < min_usage) {
-			min_usage = cache_idx_usage_counts[i];
-			res = i;
-
-			/* Found a free cache_idx */
-			if (!min_usage)
-				break;
-		}
-	}
-	cache_idx_usage_counts[res]++;
-
-	spin_unlock(&cache_idx_lock);
-
-	return res;
-}
-
-static void cache_idx_free(u16 idx)
-{
-	spin_lock(&cache_idx_lock);
-	cache_idx_usage_counts[idx]--;
-	spin_unlock(&cache_idx_lock);
-}
-
 /* Called by __sk_destruct() & bpf_sk_storage_clone() */
 void bpf_sk_storage_free(struct sock *sk)
 {
-	struct bpf_sk_storage_elem *selem;
-	struct bpf_sk_storage *sk_storage;
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage *sk_storage;
 	bool free_sk_storage = false;
 	struct hlist_node *n;
 
@@ -565,7 +63,7 @@ void bpf_sk_storage_free(struct sock *sk)
 	 * Thus, no elem can be added-to or deleted-from the
 	 * sk_storage->list by the bpf_prog or by the bpf-map's syscall.
 	 *
-	 * It is racing with bpf_sk_storage_map_free() alone
+	 * It is racing with bpf_local_storage_map_free() alone
 	 * when unlinking elem from the sk_storage->list and
 	 * the map's bucket->list.
 	 */
@@ -574,8 +72,9 @@ void bpf_sk_storage_free(struct sock *sk)
 		/* Always unlink from map before unlinking from
 		 * sk_storage.
 		 */
-		selem_unlink_map(selem);
-		free_sk_storage = __selem_unlink_sk(sk_storage, selem, true);
+		bpf_selem_unlink_map(selem);
+		free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage,
+								  selem, true);
 	}
 	raw_spin_unlock_bh(&sk_storage->lock);
 	rcu_read_unlock();
@@ -586,130 +85,22 @@ void bpf_sk_storage_free(struct sock *sk)
 
 static void bpf_sk_storage_map_free(struct bpf_map *map)
 {
-	struct bpf_sk_storage_elem *selem;
-	struct bpf_sk_storage_map *smap;
-	struct bucket *b;
-	unsigned int i;
-
-	smap = (struct bpf_sk_storage_map *)map;
-
-	cache_idx_free(smap->cache_idx);
-
-	/* Note that this map might be concurrently cloned from
-	 * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone
-	 * RCU read section to finish before proceeding. New RCU
-	 * read sections should be prevented via bpf_map_inc_not_zero.
-	 */
-	synchronize_rcu();
+	struct bpf_local_storage_map *smap;
 
-	/* bpf prog and the userspace can no longer access this map
-	 * now.  No new selem (of this map) can be added
-	 * to the sk->sk_bpf_storage or to the map bucket's list.
-	 *
-	 * The elem of this map can be cleaned up here
-	 * or
-	 * by bpf_sk_storage_free() during __sk_destruct().
-	 */
-	for (i = 0; i < (1U << smap->bucket_log); i++) {
-		b = &smap->buckets[i];
-
-		rcu_read_lock();
-		/* No one is adding to b->list now */
-		while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)),
-						 struct bpf_sk_storage_elem,
-						 map_node))) {
-			selem_unlink(selem);
-			cond_resched_rcu();
-		}
-		rcu_read_unlock();
-	}
-
-	/* bpf_sk_storage_free() may still need to access the map.
-	 * e.g. bpf_sk_storage_free() has unlinked selem from the map
-	 * which then made the above while((selem = ...)) loop
-	 * exited immediately.
-	 *
-	 * However, the bpf_sk_storage_free() still needs to access
-	 * the smap->elem_size to do the uncharging in
-	 * __selem_unlink_sk().
-	 *
-	 * Hence, wait another rcu grace period for the
-	 * bpf_sk_storage_free() to finish.
-	 */
-	synchronize_rcu();
-
-	kvfree(smap->buckets);
-	kfree(map);
-}
-
-/* U16_MAX is much more than enough for sk local storage
- * considering a tcp_sock is ~2k.
- */
-#define MAX_VALUE_SIZE							\
-	min_t(u32,							\
-	      (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \
-	      (U16_MAX - sizeof(struct bpf_sk_storage_elem)))
-
-static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr)
-{
-	if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK ||
-	    !(attr->map_flags & BPF_F_NO_PREALLOC) ||
-	    attr->max_entries ||
-	    attr->key_size != sizeof(int) || !attr->value_size ||
-	    /* Enforce BTF for userspace sk dumping */
-	    !attr->btf_key_type_id || !attr->btf_value_type_id)
-		return -EINVAL;
-
-	if (!bpf_capable())
-		return -EPERM;
-
-	if (attr->value_size > MAX_VALUE_SIZE)
-		return -E2BIG;
-
-	return 0;
+	smap = (struct bpf_local_storage_map *)map;
+	bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx);
+	bpf_local_storage_map_free(smap);
 }
 
 static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr)
 {
-	struct bpf_sk_storage_map *smap;
-	unsigned int i;
-	u32 nbuckets;
-	u64 cost;
-	int ret;
-
-	smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN);
-	if (!smap)
-		return ERR_PTR(-ENOMEM);
-	bpf_map_init_from_attr(&smap->map, attr);
-
-	nbuckets = roundup_pow_of_two(num_possible_cpus());
-	/* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */
-	nbuckets = max_t(u32, 2, nbuckets);
-	smap->bucket_log = ilog2(nbuckets);
-	cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap);
-
-	ret = bpf_map_charge_init(&smap->map.memory, cost);
-	if (ret < 0) {
-		kfree(smap);
-		return ERR_PTR(ret);
-	}
-
-	smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets,
-				 GFP_USER | __GFP_NOWARN);
-	if (!smap->buckets) {
-		bpf_map_charge_finish(&smap->map.memory);
-		kfree(smap);
-		return ERR_PTR(-ENOMEM);
-	}
+	struct bpf_local_storage_map *smap;
 
-	for (i = 0; i < nbuckets; i++) {
-		INIT_HLIST_HEAD(&smap->buckets[i].list);
-		raw_spin_lock_init(&smap->buckets[i].lock);
-	}
-
-	smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size;
-	smap->cache_idx = cache_idx_get();
+	smap = bpf_local_storage_map_alloc(attr);
+	if (IS_ERR(smap))
+		return ERR_CAST(smap);
 
+	smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache);
 	return &smap->map;
 }
 
@@ -719,33 +110,16 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key,
 	return -ENOTSUPP;
 }
 
-static int bpf_sk_storage_map_check_btf(const struct bpf_map *map,
-					const struct btf *btf,
-					const struct btf_type *key_type,
-					const struct btf_type *value_type)
-{
-	u32 int_data;
-
-	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
-		return -EINVAL;
-
-	int_data = *(u32 *)(key_type + 1);
-	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
-		return -EINVAL;
-
-	return 0;
-}
-
 static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
 {
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage_data *sdata;
 	struct socket *sock;
 	int fd, err;
 
 	fd = *(int *)key;
 	sock = sockfd_lookup(fd, &err);
 	if (sock) {
-		sdata = sk_storage_lookup(sock->sk, map, true);
+		sdata = bpf_sk_storage_lookup(sock->sk, map, true);
 		sockfd_put(sock);
 		return sdata ? sdata->data : NULL;
 	}
@@ -756,14 +130,16 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key)
 static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key,
 					 void *value, u64 map_flags)
 {
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage_data *sdata;
 	struct socket *sock;
 	int fd, err;
 
 	fd = *(int *)key;
 	sock = sockfd_lookup(fd, &err);
 	if (sock) {
-		sdata = sk_storage_update(sock->sk, map, value, map_flags);
+		sdata = bpf_local_storage_update(
+			sock->sk, (struct bpf_local_storage_map *)map, value,
+			map_flags);
 		sockfd_put(sock);
 		return PTR_ERR_OR_ZERO(sdata);
 	}
@@ -779,7 +155,7 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
 	fd = *(int *)key;
 	sock = sockfd_lookup(fd, &err);
 	if (sock) {
-		err = sk_storage_delete(sock->sk, map);
+		err = bpf_sk_storage_del(sock->sk, map);
 		sockfd_put(sock);
 		return err;
 	}
@@ -787,14 +163,14 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key)
 	return err;
 }
 
-static struct bpf_sk_storage_elem *
+static struct bpf_local_storage_elem *
 bpf_sk_storage_clone_elem(struct sock *newsk,
-			  struct bpf_sk_storage_map *smap,
-			  struct bpf_sk_storage_elem *selem)
+			  struct bpf_local_storage_map *smap,
+			  struct bpf_local_storage_elem *selem)
 {
-	struct bpf_sk_storage_elem *copy_selem;
+	struct bpf_local_storage_elem *copy_selem;
 
-	copy_selem = selem_alloc(smap, newsk, NULL, true);
+	copy_selem = bpf_selem_alloc(smap, newsk, NULL, true);
 	if (!copy_selem)
 		return NULL;
 
@@ -810,9 +186,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk,
 
 int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 {
-	struct bpf_sk_storage *new_sk_storage = NULL;
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_elem *selem;
+	struct bpf_local_storage *new_sk_storage = NULL;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_elem *selem;
 	int ret = 0;
 
 	RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL);
@@ -824,8 +200,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 		goto out;
 
 	hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) {
-		struct bpf_sk_storage_elem *copy_selem;
-		struct bpf_sk_storage_map *smap;
+		struct bpf_local_storage_elem *copy_selem;
+		struct bpf_local_storage_map *smap;
 		struct bpf_map *map;
 
 		smap = rcu_dereference(SDATA(selem)->smap);
@@ -833,7 +209,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 			continue;
 
 		/* Note that for lockless listeners adding new element
-		 * here can race with cleanup in bpf_sk_storage_map_free.
+		 * here can race with cleanup in bpf_local_storage_map_free.
 		 * Try to grab map refcnt to make sure that it's still
 		 * alive and prevent concurrent removal.
 		 */
@@ -849,10 +225,10 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 		}
 
 		if (new_sk_storage) {
-			selem_link_map(smap, copy_selem);
-			__selem_link_sk(new_sk_storage, copy_selem);
+			bpf_selem_link_map(smap, copy_selem);
+			bpf_selem_link_storage_nolock(new_sk_storage, copy_selem);
 		} else {
-			ret = sk_storage_alloc(newsk, smap, copy_selem);
+			ret = bpf_local_storage_alloc(newsk, smap, copy_selem);
 			if (ret) {
 				kfree(copy_selem);
 				atomic_sub(smap->elem_size,
@@ -861,7 +237,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk)
 				goto out;
 			}
 
-			new_sk_storage = rcu_dereference(copy_selem->sk_storage);
+			new_sk_storage =
+				rcu_dereference(copy_selem->local_storage);
 		}
 		bpf_map_put(map);
 	}
@@ -879,12 +256,12 @@ out:
 BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 	   void *, value, u64, flags)
 {
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage_data *sdata;
 
-	if (flags > BPF_SK_STORAGE_GET_F_CREATE)
+	if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE)
 		return (unsigned long)NULL;
 
-	sdata = sk_storage_lookup(sk, map, true);
+	sdata = bpf_sk_storage_lookup(sk, map, true);
 	if (sdata)
 		return (unsigned long)sdata->data;
 
@@ -895,7 +272,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 	     *  destruction).
 	     */
 	    refcount_inc_not_zero(&sk->sk_refcnt)) {
-		sdata = sk_storage_update(sk, map, value, BPF_NOEXIST);
+		sdata = bpf_local_storage_update(
+			sk, (struct bpf_local_storage_map *)map, value,
+			BPF_NOEXIST);
 		/* sk must be a fullsock (guaranteed by verifier),
 		 * so sock_gen_put() is unnecessary.
 		 */
@@ -909,10 +288,13 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk,
 
 BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 {
+	if (!sk || !sk_fullsock(sk))
+		return -EINVAL;
+
 	if (refcount_inc_not_zero(&sk->sk_refcnt)) {
 		int err;
 
-		err = sk_storage_delete(sk, map);
+		err = bpf_sk_storage_del(sk, map);
 		sock_put(sk);
 		return err;
 	}
@@ -920,18 +302,53 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk)
 	return -ENOENT;
 }
 
+static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap,
+				 void *owner, u32 size)
+{
+	struct sock *sk = (struct sock *)owner;
+
+	/* same check as in sock_kmalloc() */
+	if (size <= sysctl_optmem_max &&
+	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
+		atomic_add(size, &sk->sk_omem_alloc);
+		return 0;
+	}
+
+	return -ENOMEM;
+}
+
+static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap,
+				    void *owner, u32 size)
+{
+	struct sock *sk = owner;
+
+	atomic_sub(size, &sk->sk_omem_alloc);
+}
+
+static struct bpf_local_storage __rcu **
+bpf_sk_storage_ptr(void *owner)
+{
+	struct sock *sk = owner;
+
+	return &sk->sk_bpf_storage;
+}
+
 static int sk_storage_map_btf_id;
 const struct bpf_map_ops sk_storage_map_ops = {
-	.map_alloc_check = bpf_sk_storage_map_alloc_check,
+	.map_meta_equal = bpf_map_meta_equal,
+	.map_alloc_check = bpf_local_storage_map_alloc_check,
 	.map_alloc = bpf_sk_storage_map_alloc,
 	.map_free = bpf_sk_storage_map_free,
 	.map_get_next_key = notsupp_get_next_key,
 	.map_lookup_elem = bpf_fd_sk_storage_lookup_elem,
 	.map_update_elem = bpf_fd_sk_storage_update_elem,
 	.map_delete_elem = bpf_fd_sk_storage_delete_elem,
-	.map_check_btf = bpf_sk_storage_map_check_btf,
-	.map_btf_name = "bpf_sk_storage_map",
+	.map_check_btf = bpf_local_storage_map_check_btf,
+	.map_btf_name = "bpf_local_storage_map",
 	.map_btf_id = &sk_storage_map_btf_id,
+	.map_local_storage_charge = bpf_sk_storage_charge,
+	.map_local_storage_uncharge = bpf_sk_storage_uncharge,
+	.map_owner_storage_ptr = bpf_sk_storage_ptr,
 };
 
 const struct bpf_func_proto bpf_sk_storage_get_proto = {
@@ -939,7 +356,7 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_SOCKET,
+	.arg2_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
 	.arg4_type	= ARG_ANYTHING,
 };
@@ -959,7 +376,81 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_SOCKET,
+	.arg2_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
+};
+
+static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
+{
+	const struct btf *btf_vmlinux;
+	const struct btf_type *t;
+	const char *tname;
+	u32 btf_id;
+
+	if (prog->aux->dst_prog)
+		return false;
+
+	/* Ensure the tracing program is not tracing
+	 * any bpf_sk_storage*() function and also
+	 * use the bpf_sk_storage_(get|delete) helper.
+	 */
+	switch (prog->expected_attach_type) {
+	case BPF_TRACE_ITER:
+	case BPF_TRACE_RAW_TP:
+		/* bpf_sk_storage has no trace point */
+		return true;
+	case BPF_TRACE_FENTRY:
+	case BPF_TRACE_FEXIT:
+		btf_vmlinux = bpf_get_btf_vmlinux();
+		btf_id = prog->aux->attach_btf_id;
+		t = btf_type_by_id(btf_vmlinux, btf_id);
+		tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+		return !!strncmp(tname, "bpf_sk_storage",
+				 strlen("bpf_sk_storage"));
+	default:
+		return false;
+	}
+
+	return false;
+}
+
+BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
+	   void *, value, u64, flags)
+{
+	if (in_irq() || in_nmi())
+		return (unsigned long)NULL;
+
+	return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags);
+}
+
+BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map,
+	   struct sock *, sk)
+{
+	if (in_irq() || in_nmi())
+		return -EPERM;
+
+	return ____bpf_sk_storage_delete(map, sk);
+}
+
+const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = {
+	.func		= bpf_sk_storage_get_tracing,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.arg3_type	= ARG_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg4_type	= ARG_ANYTHING,
+	.allowed	= bpf_sk_storage_tracing_allowed,
+};
+
+const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = {
+	.func		= bpf_sk_storage_delete_tracing,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_BTF_ID,
+	.arg2_btf_id	= &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+	.allowed	= bpf_sk_storage_tracing_allowed,
 };
 
 struct bpf_sk_storage_diag {
@@ -1022,7 +513,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs)
 	u32 nr_maps = 0;
 	int rem, err;
 
-	/* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as
+	/* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as
 	 * the map_alloc_check() side also does.
 	 */
 	if (!bpf_capable())
@@ -1072,13 +563,13 @@ err_free:
 }
 EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc);
 
-static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb)
+static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb)
 {
 	struct nlattr *nla_stg, *nla_value;
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage_map *smap;
 
 	/* It cannot exceed max nlattr's payload */
-	BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE);
+	BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE);
 
 	nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE);
 	if (!nla_stg)
@@ -1114,9 +605,9 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb,
 {
 	/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
 	unsigned int diag_size = nla_total_size(0);
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_elem *selem;
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_elem *selem;
+	struct bpf_local_storage_map *smap;
 	struct nlattr *nla_stgs;
 	unsigned int saved_len;
 	int err = 0;
@@ -1169,8 +660,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
 {
 	/* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */
 	unsigned int diag_size = nla_total_size(0);
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_data *sdata;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_data *sdata;
 	struct nlattr *nla_stgs;
 	unsigned int saved_len;
 	int err = 0;
@@ -1197,8 +688,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag,
 
 	saved_len = skb->len;
 	for (i = 0; i < diag->nr_maps; i++) {
-		sdata = __sk_storage_lookup(sk_storage,
-				(struct bpf_sk_storage_map *)diag->maps[i],
+		sdata = bpf_local_storage_lookup(sk_storage,
+				(struct bpf_local_storage_map *)diag->maps[i],
 				false);
 
 		if (!sdata)
@@ -1235,19 +726,20 @@ struct bpf_iter_seq_sk_storage_map_info {
 	unsigned skip_elems;
 };
 
-static struct bpf_sk_storage_elem *
+static struct bpf_local_storage_elem *
 bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
-				 struct bpf_sk_storage_elem *prev_selem)
+				 struct bpf_local_storage_elem *prev_selem)
+	__acquires(RCU) __releases(RCU)
 {
-	struct bpf_sk_storage *sk_storage;
-	struct bpf_sk_storage_elem *selem;
+	struct bpf_local_storage *sk_storage;
+	struct bpf_local_storage_elem *selem;
 	u32 skip_elems = info->skip_elems;
-	struct bpf_sk_storage_map *smap;
+	struct bpf_local_storage_map *smap;
 	u32 bucket_id = info->bucket_id;
 	u32 i, count, n_buckets;
-	struct bucket *b;
+	struct bpf_local_storage_map_bucket *b;
 
-	smap = (struct bpf_sk_storage_map *)info->map;
+	smap = (struct bpf_local_storage_map *)info->map;
 	n_buckets = 1U << smap->bucket_log;
 	if (bucket_id >= n_buckets)
 		return NULL;
@@ -1256,16 +748,16 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 	selem = prev_selem;
 	count = 0;
 	while (selem) {
-		selem = hlist_entry_safe(selem->map_node.next,
-					 struct bpf_sk_storage_elem, map_node);
+		selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)),
+					 struct bpf_local_storage_elem, map_node);
 		if (!selem) {
 			/* not found, unlock and go to the next bucket */
 			b = &smap->buckets[bucket_id++];
-			raw_spin_unlock_bh(&b->lock);
+			rcu_read_unlock();
 			skip_elems = 0;
 			break;
 		}
-		sk_storage = rcu_dereference_raw(selem->sk_storage);
+		sk_storage = rcu_dereference(selem->local_storage);
 		if (sk_storage) {
 			info->skip_elems = skip_elems + count;
 			return selem;
@@ -1275,10 +767,10 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 
 	for (i = bucket_id; i < (1U << smap->bucket_log); i++) {
 		b = &smap->buckets[i];
-		raw_spin_lock_bh(&b->lock);
+		rcu_read_lock();
 		count = 0;
-		hlist_for_each_entry(selem, &b->list, map_node) {
-			sk_storage = rcu_dereference_raw(selem->sk_storage);
+		hlist_for_each_entry_rcu(selem, &b->list, map_node) {
+			sk_storage = rcu_dereference(selem->local_storage);
 			if (sk_storage && count >= skip_elems) {
 				info->bucket_id = i;
 				info->skip_elems = count;
@@ -1286,7 +778,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 			}
 			count++;
 		}
-		raw_spin_unlock_bh(&b->lock);
+		rcu_read_unlock();
 		skip_elems = 0;
 	}
 
@@ -1297,7 +789,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info,
 
 static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	struct bpf_sk_storage_elem *selem;
+	struct bpf_local_storage_elem *selem;
 
 	selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL);
 	if (!selem)
@@ -1330,11 +822,11 @@ DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta,
 		     void *value)
 
 static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
-					 struct bpf_sk_storage_elem *selem)
+					 struct bpf_local_storage_elem *selem)
 {
 	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
 	struct bpf_iter__bpf_sk_storage_map ctx = {};
-	struct bpf_sk_storage *sk_storage;
+	struct bpf_local_storage *sk_storage;
 	struct bpf_iter_meta meta;
 	struct bpf_prog *prog;
 	int ret = 0;
@@ -1345,8 +837,8 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq,
 		ctx.meta = &meta;
 		ctx.map = info->map;
 		if (selem) {
-			sk_storage = rcu_dereference_raw(selem->sk_storage);
-			ctx.sk = sk_storage->sk;
+			sk_storage = rcu_dereference(selem->local_storage);
+			ctx.sk = sk_storage->owner;
 			ctx.value = SDATA(selem)->data;
 		}
 		ret = bpf_iter_run_prog(prog, &ctx);
@@ -1361,18 +853,12 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v)
 }
 
 static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU)
 {
-	struct bpf_iter_seq_sk_storage_map_info *info = seq->private;
-	struct bpf_sk_storage_map *smap;
-	struct bucket *b;
-
-	if (!v) {
+	if (!v)
 		(void)__bpf_sk_storage_map_seq_show(seq, v);
-	} else {
-		smap = (struct bpf_sk_storage_map *)info->map;
-		b = &smap->buckets[info->bucket_id];
-		raw_spin_unlock_bh(&b->lock);
-	}
+	else
+		rcu_read_unlock();
 }
 
 static int bpf_iter_init_sk_storage_map(void *priv_data,
@@ -1437,6 +923,8 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = {
 	.target			= "bpf_sk_storage_map",
 	.attach_target		= bpf_iter_attach_map,
 	.detach_target		= bpf_iter_detach_map,
+	.show_fdinfo		= bpf_iter_map_show_fdinfo,
+	.fill_link_info		= bpf_iter_map_fill_link_info,
 	.ctx_arg_info_size	= 2,
 	.ctx_arg_info		= {
 		{ offsetof(struct bpf_iter__bpf_sk_storage_map, sk),
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 639745d4f3b9..15ab9ffb27fe 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -623,10 +623,11 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 
 	while (length && iov_iter_count(from)) {
 		struct page *pages[MAX_SKB_FRAGS];
+		struct page *last_head = NULL;
 		size_t start;
 		ssize_t copied;
 		unsigned long truesize;
-		int n = 0;
+		int refs, n = 0;
 
 		if (frag == MAX_SKB_FRAGS)
 			return -EMSGSIZE;
@@ -649,13 +650,37 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb,
 		} else {
 			refcount_add(truesize, &skb->sk->sk_wmem_alloc);
 		}
-		while (copied) {
+		for (refs = 0; copied != 0; start = 0) {
 			int size = min_t(int, copied, PAGE_SIZE - start);
-			skb_fill_page_desc(skb, frag++, pages[n], start, size);
-			start = 0;
+			struct page *head = compound_head(pages[n]);
+
+			start += (pages[n] - head) << PAGE_SHIFT;
 			copied -= size;
 			n++;
+			if (frag) {
+				skb_frag_t *last = &skb_shinfo(skb)->frags[frag - 1];
+
+				if (head == skb_frag_page(last) &&
+				    start == skb_frag_off(last) + skb_frag_size(last)) {
+					skb_frag_size_add(last, size);
+					/* We combined this page, we need to release
+					 * a reference. Since compound pages refcount
+					 * is shared among many pages, batch the refcount
+					 * adjustments to limit false sharing.
+					 */
+					last_head = head;
+					refs++;
+					continue;
+				}
+			}
+			if (refs) {
+				page_ref_sub(last_head, refs);
+				refs = 0;
+			}
+			skb_fill_page_desc(skb, frag++, head, start, size);
 		}
+		if (refs)
+			page_ref_sub(last_head, refs);
 	}
 	return 0;
 }
@@ -684,7 +709,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
 EXPORT_SYMBOL(zerocopy_sg_from_iter);
 
 /**
- *	skb_copy_and_csum_datagram_iter - Copy datagram to an iovec iterator
+ *	skb_copy_and_csum_datagram - Copy datagram to an iovec iterator
  *          and update a checksum.
  *	@skb: buffer to copy
  *	@offset: offset in the buffer to start copying from
@@ -696,8 +721,16 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
 				      struct iov_iter *to, int len,
 				      __wsum *csump)
 {
-	return __skb_datagram_iter(skb, offset, to, len, true,
-			csum_and_copy_to_iter, csump);
+	struct csum_state csdata = { .csum = *csump };
+	int ret;
+
+	ret = __skb_datagram_iter(skb, offset, to, len, true,
+				  csum_and_copy_to_iter, &csdata);
+	if (ret)
+		return ret;
+
+	*csump = csdata.csum;
+	return 0;
 }
 
 /**
diff --git a/net/core/dev.c b/net/core/dev.c
index 4906b44af850..449b45b843d4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -98,6 +98,7 @@
 #include <net/busy_poll.h>
 #include <linux/rtnetlink.h>
 #include <linux/stat.h>
+#include <net/dsa.h>
 #include <net/dst.h>
 #include <net/dst_metadata.h>
 #include <net/pkt_sched.h>
@@ -144,6 +145,7 @@
 #include <linux/indirect_call_wrapper.h>
 #include <net/devlink.h>
 #include <linux/pm_runtime.h>
+#include <linux/prandom.h>
 
 #include "net-sysfs.h"
 
@@ -1067,19 +1069,6 @@ struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
 }
 EXPORT_SYMBOL(dev_getbyhwaddr_rcu);
 
-struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type)
-{
-	struct net_device *dev;
-
-	ASSERT_RTNL();
-	for_each_netdev(net, dev)
-		if (dev->type == type)
-			return dev;
-
-	return NULL;
-}
-EXPORT_SYMBOL(__dev_getfirstbyhwtype);
-
 struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 {
 	struct net_device *dev, *ret = NULL;
@@ -1130,7 +1119,7 @@ EXPORT_SYMBOL(__dev_get_by_flags);
  *	@name: name string
  *
  *	Network device names need to be valid file names to
- *	to allow sysfs to work.  We also disallow any kind of
+ *	allow sysfs to work.  We also disallow any kind of
  *	whitespace.
  */
 bool dev_valid_name(const char *name)
@@ -1468,6 +1457,25 @@ void netdev_state_change(struct net_device *dev)
 EXPORT_SYMBOL(netdev_state_change);
 
 /**
+ * __netdev_notify_peers - notify network peers about existence of @dev,
+ * to be called when rtnl lock is already held.
+ * @dev: network device
+ *
+ * Generate traffic such that interested network peers are aware of
+ * @dev, such as by generating a gratuitous ARP. This may be used when
+ * a device wants to inform the rest of the network about some sort of
+ * reconfiguration such as a failover event or virtual machine
+ * migration.
+ */
+void __netdev_notify_peers(struct net_device *dev)
+{
+	ASSERT_RTNL();
+	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
+	call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
+}
+EXPORT_SYMBOL(__netdev_notify_peers);
+
+/**
  * netdev_notify_peers - notify network peers about existence of @dev
  * @dev: network device
  *
@@ -1480,8 +1488,7 @@ EXPORT_SYMBOL(netdev_state_change);
 void netdev_notify_peers(struct net_device *dev)
 {
 	rtnl_lock();
-	call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, dev);
-	call_netdevice_notifiers(NETDEV_RESEND_IGMP, dev);
+	__netdev_notify_peers(dev);
 	rtnl_unlock();
 }
 EXPORT_SYMBOL(netdev_notify_peers);
@@ -3204,7 +3211,7 @@ int skb_checksum_help(struct sk_buff *skb)
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		goto out_set_summed;
 
-	if (unlikely(skb_shinfo(skb)->gso_size)) {
+	if (unlikely(skb_is_gso(skb))) {
 		skb_warn_bad_offload(skb);
 		return -EINVAL;
 	}
@@ -3493,6 +3500,11 @@ static netdev_features_t gso_features_check(const struct sk_buff *skb,
 	if (gso_segs > dev->gso_max_segs)
 		return features & ~NETIF_F_GSO_MASK;
 
+	if (!skb_shinfo(skb)->gso_type) {
+		skb_warn_bad_offload(skb);
+		return features & ~NETIF_F_GSO_MASK;
+	}
+
 	/* Support for GSO partial features requires software
 	 * intervention before we can actually process the packets
 	 * so we need to strip support for any partial features now
@@ -3557,6 +3569,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 		dev_queue_xmit_nit(skb, dev);
 
 	len = skb->len;
+	PRANDOM_ADD_NOISE(skb, dev, txq, len + jiffies);
 	trace_net_dev_start_xmit(skb, dev);
 	rc = netdev_start_xmit(skb, dev, txq, more);
 	trace_net_dev_xmit(skb, rc, dev, len);
@@ -3864,6 +3877,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 		return skb;
 
 	/* qdisc_skb_cb(skb)->pkt_len was already set by the caller. */
+	qdisc_skb_cb(skb)->mru = 0;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
 	switch (tcf_classify(skb, miniq->filter_list, &cl_res, false)) {
@@ -4129,6 +4143,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 			if (!skb)
 				goto out;
 
+			PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 			HARD_TX_LOCK(dev, txq, cpu);
 
 			if (!netif_xmit_stopped(txq)) {
@@ -4176,7 +4191,7 @@ int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
 }
 EXPORT_SYMBOL(dev_queue_xmit_accel);
 
-int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
+int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 {
 	struct net_device *dev = skb->dev;
 	struct sk_buff *orig_skb = skb;
@@ -4194,6 +4209,7 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 
 	skb_set_queue_mapping(skb, queue_id);
 	txq = skb_get_tx_queue(dev, skb);
+	PRANDOM_ADD_NOISE(skb, dev, txq, jiffies);
 
 	local_bh_disable();
 
@@ -4205,17 +4221,13 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id)
 	dev_xmit_recursion_dec();
 
 	local_bh_enable();
-
-	if (!dev_xmit_complete(ret))
-		kfree_skb(skb);
-
 	return ret;
 drop:
 	atomic_long_inc(&dev->tx_dropped);
 	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
-EXPORT_SYMBOL(dev_direct_xmit);
+EXPORT_SYMBOL(__dev_direct_xmit);
 
 /*************************************************************************
  *			Receiver routines
@@ -4840,6 +4852,21 @@ int netif_rx_ni(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(netif_rx_ni);
 
+int netif_rx_any_context(struct sk_buff *skb)
+{
+	/*
+	 * If invoked from contexts which do not invoke bottom half
+	 * processing either at return from interrupt or when softrqs are
+	 * reenabled, use netif_rx_ni() which invokes bottomhalf processing
+	 * directly.
+	 */
+	if (in_interrupt())
+		return netif_rx(skb);
+	else
+		return netif_rx_ni(skb);
+}
+EXPORT_SYMBOL(netif_rx_any_context);
+
 static __latent_entropy void net_tx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
@@ -4914,7 +4941,7 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
 
 static inline struct sk_buff *
 sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
-		   struct net_device *orig_dev)
+		   struct net_device *orig_dev, bool *another)
 {
 #ifdef CONFIG_NET_CLS_ACT
 	struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
@@ -4934,6 +4961,7 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 	}
 
 	qdisc_skb_cb(skb)->pkt_len = skb->len;
+	qdisc_skb_cb(skb)->mru = 0;
 	skb->tc_at_ingress = 1;
 	mini_qdisc_bstats_cpu_update(miniq, skb);
 
@@ -4958,7 +4986,11 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		 * redirecting to another netdev
 		 */
 		__skb_push(skb, skb->mac_len);
-		skb_do_redirect(skb);
+		if (skb_do_redirect(skb) == -EAGAIN) {
+			__skb_pull(skb, skb->mac_len);
+			*another = true;
+			break;
+		}
 		return NULL;
 	case TC_ACT_CONSUMED:
 		return NULL;
@@ -5147,7 +5179,12 @@ another_round:
 skip_taps:
 #ifdef CONFIG_NET_INGRESS
 	if (static_branch_unlikely(&ingress_needed_key)) {
-		skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev);
+		bool another = false;
+
+		skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev,
+					 &another);
+		if (another)
+			goto another_round;
 		if (!skb)
 			goto out;
 
@@ -5192,7 +5229,7 @@ skip_classify:
 		}
 	}
 
-	if (unlikely(skb_vlan_tag_present(skb))) {
+	if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) {
 check_vlan_id:
 		if (skb_vlan_tag_get_id(skb)) {
 			/* Vlan id is non 0 and vlan_do_receive() above couldn't
@@ -5441,15 +5478,20 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	if (new) {
 		u32 i;
 
+		mutex_lock(&new->aux->used_maps_mutex);
+
 		/* generic XDP does not work with DEVMAPs that can
 		 * have a bpf_prog installed on an entry
 		 */
 		for (i = 0; i < new->aux->used_map_cnt; i++) {
-			if (dev_map_can_have_prog(new->aux->used_maps[i]))
-				return -EINVAL;
-			if (cpu_map_prog_allowed(new->aux->used_maps[i]))
+			if (dev_map_can_have_prog(new->aux->used_maps[i]) ||
+			    cpu_map_prog_allowed(new->aux->used_maps[i])) {
+				mutex_unlock(&new->aux->used_maps_mutex);
 				return -EINVAL;
+			}
 		}
+
+		mutex_unlock(&new->aux->used_maps_mutex);
 	}
 
 	switch (xdp->command) {
@@ -5621,17 +5663,60 @@ static void flush_backlog(struct work_struct *work)
 	local_bh_enable();
 }
 
+static bool flush_required(int cpu)
+{
+#if IS_ENABLED(CONFIG_RPS)
+	struct softnet_data *sd = &per_cpu(softnet_data, cpu);
+	bool do_flush;
+
+	local_irq_disable();
+	rps_lock(sd);
+
+	/* as insertion into process_queue happens with the rps lock held,
+	 * process_queue access may race only with dequeue
+	 */
+	do_flush = !skb_queue_empty(&sd->input_pkt_queue) ||
+		   !skb_queue_empty_lockless(&sd->process_queue);
+	rps_unlock(sd);
+	local_irq_enable();
+
+	return do_flush;
+#endif
+	/* without RPS we can't safely check input_pkt_queue: during a
+	 * concurrent remote skb_queue_splice() we can detect as empty both
+	 * input_pkt_queue and process_queue even if the latter could end-up
+	 * containing a lot of packets.
+	 */
+	return true;
+}
+
 static void flush_all_backlogs(void)
 {
+	static cpumask_t flush_cpus;
 	unsigned int cpu;
 
+	/* since we are under rtnl lock protection we can use static data
+	 * for the cpumask and avoid allocating on stack the possibly
+	 * large mask
+	 */
+	ASSERT_RTNL();
+
 	get_online_cpus();
 
-	for_each_online_cpu(cpu)
-		queue_work_on(cpu, system_highpri_wq,
-			      per_cpu_ptr(&flush_works, cpu));
+	cpumask_clear(&flush_cpus);
+	for_each_online_cpu(cpu) {
+		if (flush_required(cpu)) {
+			queue_work_on(cpu, system_highpri_wq,
+				      per_cpu_ptr(&flush_works, cpu));
+			cpumask_set_cpu(cpu, &flush_cpus);
+		}
+	}
 
-	for_each_online_cpu(cpu)
+	/* we can have in flight packet[s] on the cpus we are not flushing,
+	 * synchronize_net() in rollback_registered_many() will take care of
+	 * them
+	 */
+	for_each_cpu(cpu, &flush_cpus)
 		flush_work(per_cpu_ptr(&flush_works, cpu));
 
 	put_online_cpus();
@@ -5650,10 +5735,11 @@ static void gro_normal_list(struct napi_struct *napi)
 /* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
  * pass the whole batch up to the stack.
  */
-static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb)
+static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs)
 {
 	list_add_tail(&skb->list, &napi->rx_list);
-	if (++napi->rx_count >= gro_normal_batch)
+	napi->rx_count += segs;
+	if (napi->rx_count >= gro_normal_batch)
 		gro_normal_list(napi);
 }
 
@@ -5692,7 +5778,7 @@ static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
 	}
 
 out:
-	gro_normal_one(napi, skb);
+	gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count);
 	return NET_RX_SUCCESS;
 }
 
@@ -5982,7 +6068,7 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi,
 {
 	switch (ret) {
 	case GRO_NORMAL:
-		gro_normal_one(napi, skb);
+		gro_normal_one(napi, skb, 1);
 		break;
 
 	case GRO_DROP:
@@ -6070,7 +6156,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi,
 		__skb_push(skb, ETH_HLEN);
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		if (ret == GRO_NORMAL)
-			gro_normal_one(napi, skb);
+			gro_normal_one(napi, skb, 1);
 		break;
 
 	case GRO_DROP:
@@ -6293,7 +6379,7 @@ EXPORT_SYMBOL(__napi_schedule);
  *	@n: napi context
  *
  * Test if NAPI routine is already running, and if not mark
- * it as running.  This is used as a condition variable
+ * it as running.  This is used as a condition variable to
  * insure only one NAPI poll instance runs.  We also make
  * sure there is no pending NAPI disable.
  */
@@ -6381,7 +6467,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 
 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
 
-		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
+		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+			      NAPIF_STATE_PREFER_BUSY_POLL);
 
 		/* If STATE_MISSED was set, leave STATE_SCHED set,
 		 * because we will call napi->poll() one more time.
@@ -6418,10 +6505,30 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)
 
 #if defined(CONFIG_NET_RX_BUSY_POLL)
 
-#define BUSY_POLL_BUDGET 8
+static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
+{
+	if (!skip_schedule) {
+		gro_normal_list(napi);
+		__napi_schedule(napi);
+		return;
+	}
+
+	if (napi->gro_bitmask) {
+		/* flush too old packets
+		 * If HZ < 1000, flush all packets.
+		 */
+		napi_gro_flush(napi, HZ >= 1000);
+	}
+
+	gro_normal_list(napi);
+	clear_bit(NAPI_STATE_SCHED, &napi->state);
+}
 
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
+			   u16 budget)
 {
+	bool skip_schedule = false;
+	unsigned long timeout;
 	int rc;
 
 	/* Busy polling means there is a high chance device driver hard irq
@@ -6438,29 +6545,33 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 
 	local_bh_disable();
 
+	if (prefer_busy_poll) {
+		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
+		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
+		if (napi->defer_hard_irqs_count && timeout) {
+			hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
+			skip_schedule = true;
+		}
+	}
+
 	/* All we really want here is to re-enable device interrupts.
 	 * Ideally, a new ndo_busy_poll_stop() could avoid another round.
 	 */
-	rc = napi->poll(napi, BUSY_POLL_BUDGET);
+	rc = napi->poll(napi, budget);
 	/* We can't gro_normal_list() here, because napi->poll() might have
 	 * rearmed the napi (napi_complete_done()) in which case it could
 	 * already be running on another CPU.
 	 */
-	trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+	trace_napi_poll(napi, rc, budget);
 	netpoll_poll_unlock(have_poll_lock);
-	if (rc == BUSY_POLL_BUDGET) {
-		/* As the whole budget was spent, we still own the napi so can
-		 * safely handle the rx_list.
-		 */
-		gro_normal_list(napi);
-		__napi_schedule(napi);
-	}
+	if (rc == budget)
+		__busy_poll_stop(napi, skip_schedule);
 	local_bh_enable();
 }
 
 void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg)
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
@@ -6488,17 +6599,23 @@ restart:
 			 * we avoid dirtying napi->state as much as we can.
 			 */
 			if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
-				   NAPIF_STATE_IN_BUSY_POLL))
+				   NAPIF_STATE_IN_BUSY_POLL)) {
+				if (prefer_busy_poll)
+					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
+			}
 			if (cmpxchg(&napi->state, val,
 				    val | NAPIF_STATE_IN_BUSY_POLL |
-					  NAPIF_STATE_SCHED) != val)
+					  NAPIF_STATE_SCHED) != val) {
+				if (prefer_busy_poll)
+					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
+			}
 			have_poll_lock = netpoll_poll_lock(napi);
 			napi_poll = napi->poll;
 		}
-		work = napi_poll(napi, BUSY_POLL_BUDGET);
-		trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
+		work = napi_poll(napi, budget);
+		trace_napi_poll(napi, work, budget);
 		gro_normal_list(napi);
 count:
 		if (work > 0)
@@ -6511,7 +6628,7 @@ count:
 
 		if (unlikely(need_resched())) {
 			if (napi_poll)
-				busy_poll_stop(napi, have_poll_lock);
+				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
 			preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
@@ -6522,7 +6639,7 @@ count:
 		cpu_relax();
 	}
 	if (napi_poll)
-		busy_poll_stop(napi, have_poll_lock);
+		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
 	preempt_enable();
 out:
 	rcu_read_unlock();
@@ -6533,8 +6650,7 @@ EXPORT_SYMBOL(napi_busy_loop);
 
 static void napi_hash_add(struct napi_struct *napi)
 {
-	if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) ||
-	    test_and_set_bit(NAPI_STATE_HASHED, &napi->state))
+	if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state))
 		return;
 
 	spin_lock(&napi_hash_lock);
@@ -6555,20 +6671,14 @@ static void napi_hash_add(struct napi_struct *napi)
 /* Warning : caller is responsible to make sure rcu grace period
  * is respected before freeing memory containing @napi
  */
-bool napi_hash_del(struct napi_struct *napi)
+static void napi_hash_del(struct napi_struct *napi)
 {
-	bool rcu_sync_needed = false;
-
 	spin_lock(&napi_hash_lock);
 
-	if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) {
-		rcu_sync_needed = true;
-		hlist_del_rcu(&napi->napi_hash_node);
-	}
+	hlist_del_init_rcu(&napi->napi_hash_node);
+
 	spin_unlock(&napi_hash_lock);
-	return rcu_sync_needed;
 }
-EXPORT_SYMBOL_GPL(napi_hash_del);
 
 static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 {
@@ -6580,8 +6690,10 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
 	if (!napi_disable_pending(napi) &&
-	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
+	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) {
+		clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 		__napi_schedule_irqoff(napi);
+	}
 
 	return HRTIMER_NORESTART;
 }
@@ -6600,7 +6712,11 @@ static void init_gro_hash(struct napi_struct *napi)
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
+	if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state)))
+		return;
+
 	INIT_LIST_HEAD(&napi->poll_list);
+	INIT_HLIST_NODE(&napi->napi_hash_node);
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
 	init_gro_hash(napi);
@@ -6635,6 +6751,7 @@ void napi_disable(struct napi_struct *n)
 
 	hrtimer_cancel(&n->timer);
 
+	clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
 	clear_bit(NAPI_STATE_DISABLE, &n->state);
 }
 EXPORT_SYMBOL(napi_disable);
@@ -6653,18 +6770,19 @@ static void flush_gro_hash(struct napi_struct *napi)
 }
 
 /* Must be called in process context */
-void netif_napi_del(struct napi_struct *napi)
+void __netif_napi_del(struct napi_struct *napi)
 {
-	might_sleep();
-	if (napi_hash_del(napi))
-		synchronize_net();
-	list_del_init(&napi->dev_list);
+	if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state))
+		return;
+
+	napi_hash_del(napi);
+	list_del_rcu(&napi->dev_list);
 	napi_free_frags(napi);
 
 	flush_gro_hash(napi);
 	napi->gro_bitmask = 0;
 }
-EXPORT_SYMBOL(netif_napi_del);
+EXPORT_SYMBOL(__netif_napi_del);
 
 static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 {
@@ -6706,6 +6824,19 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
+	/* The NAPI context has more processing work, but busy-polling
+	 * is preferred. Exit early.
+	 */
+	if (napi_prefer_busy_poll(n)) {
+		if (napi_complete_done(n, work)) {
+			/* If timeout is not set, we need to make sure
+			 * that the NAPI is re-scheduled.
+			 */
+			napi_schedule(n);
+		}
+		goto out_unlock;
+	}
+
 	if (n->gro_bitmask) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
@@ -6844,7 +6975,7 @@ bool netdev_has_upper_dev(struct net_device *dev,
 EXPORT_SYMBOL(netdev_has_upper_dev);
 
 /**
- * netdev_has_upper_dev_all - Check if device is linked to an upper device
+ * netdev_has_upper_dev_all_rcu - Check if device is linked to an upper device
  * @dev: device
  * @upper_dev: upper device to check
  *
@@ -8082,7 +8213,7 @@ EXPORT_SYMBOL(netdev_lower_dev_get_private);
 
 
 /**
- * netdev_lower_change - Dispatch event about lower device state change
+ * netdev_lower_state_changed - Dispatch event about lower device state change
  * @lower_dev: device
  * @lower_state_info: state to dispatch
  *
@@ -8827,7 +8958,7 @@ static bpf_op_t dev_xdp_bpf_op(struct net_device *dev, enum bpf_xdp_mode mode)
 		return dev->netdev_ops->ndo_bpf;
 	default:
 		return NULL;
-	};
+	}
 }
 
 static struct bpf_xdp_link *dev_xdp_link(struct net_device *dev,
@@ -8846,6 +8977,17 @@ static struct bpf_prog *dev_xdp_prog(struct net_device *dev,
 	return dev->xdp_state[mode].prog;
 }
 
+static u8 dev_xdp_prog_count(struct net_device *dev)
+{
+	u8 count = 0;
+	int i;
+
+	for (i = 0; i < __MAX_XDP_MODE; i++)
+		if (dev->xdp_state[i].prog || dev->xdp_state[i].link)
+			count++;
+	return count;
+}
+
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
 {
 	struct bpf_prog *prog = dev_xdp_prog(dev, mode);
@@ -8936,6 +9078,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 			  struct bpf_xdp_link *link, struct bpf_prog *new_prog,
 			  struct bpf_prog *old_prog, u32 flags)
 {
+	unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES);
 	struct bpf_prog *cur_prog;
 	enum bpf_xdp_mode mode;
 	bpf_op_t bpf_op;
@@ -8951,11 +9094,17 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment");
 		return -EINVAL;
 	}
-	/* just one XDP mode bit should be set, zero defaults to SKB mode */
-	if (hweight32(flags & XDP_FLAGS_MODES) > 1) {
+	/* just one XDP mode bit should be set, zero defaults to drv/skb mode */
+	if (num_modes > 1) {
 		NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set");
 		return -EINVAL;
 	}
+	/* avoid ambiguity if offload + drv/skb mode progs are both loaded */
+	if (!num_modes && dev_xdp_prog_count(dev) > 1) {
+		NL_SET_ERR_MSG(extack,
+			       "More than one program loaded, unset mode is ambiguous");
+		return -EINVAL;
+	}
 	/* old_prog != NULL implies XDP_FLAGS_REPLACE is set */
 	if (old_prog && !(flags & XDP_FLAGS_REPLACE)) {
 		NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified");
@@ -9513,6 +9662,22 @@ static netdev_features_t netdev_fix_features(struct net_device *dev,
 		}
 	}
 
+	if (features & NETIF_F_HW_TLS_TX) {
+		bool ip_csum = (features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM)) ==
+			(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+		bool hw_csum = features & NETIF_F_HW_CSUM;
+
+		if (!ip_csum && !hw_csum) {
+			netdev_dbg(dev, "Dropping TLS TX HW offload feature since no CSUM feature.\n");
+			features &= ~NETIF_F_HW_TLS_TX;
+		}
+	}
+
+	if ((features & NETIF_F_HW_TLS_RX) && !(features & NETIF_F_RXCSUM)) {
+		netdev_dbg(dev, "Dropping TLS RX HW offload feature since no RXCSUM feature.\n");
+		features &= ~NETIF_F_HW_TLS_RX;
+	}
+
 	return features;
 }
 
@@ -9533,7 +9698,7 @@ int __netdev_update_features(struct net_device *dev)
 	/* driver might be less strict about feature dependencies */
 	features = netdev_fix_features(dev, features);
 
-	/* some features can't be enabled if they're off an an upper device */
+	/* some features can't be enabled if they're off on an upper device */
 	netdev_for_each_upper_dev_rcu(dev, upper, iter)
 		features = netdev_sync_upper_features(dev, upper, features);
 
@@ -9688,7 +9853,7 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 		rx[i].dev = dev;
 
 		/* XDP RX-queue setup */
-		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i);
+		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0);
 		if (err < 0)
 			goto err_rxq_info;
 	}
@@ -9924,17 +10089,11 @@ int register_netdevice(struct net_device *dev)
 	ret = call_netdevice_notifiers(NETDEV_REGISTER, dev);
 	ret = notifier_to_errno(ret);
 	if (ret) {
+		/* Expect explicit free_netdev() on failure */
+		dev->needs_free_netdev = false;
 		rollback_registered(dev);
-		rcu_barrier();
-
-		dev->reg_state = NETREG_UNREGISTERED;
-		/* We should put the kobject that hold in
-		 * netdev_unregister_kobject(), otherwise
-		 * the net device cannot be freed when
-		 * driver calls free_netdev(), because the
-		 * kobject is being hold.
-		 */
-		kobject_put(&dev->dev.kobj);
+		net_set_todo(dev);
+		goto out;
 	}
 	/*
 	 *	Prevent userspace races by waiting until the network
@@ -10037,6 +10196,8 @@ int netdev_refcnt_read(const struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_refcnt_read);
 
+#define WAIT_REFS_MIN_MSECS 1
+#define WAIT_REFS_MAX_MSECS 250
 /**
  * netdev_wait_allrefs - wait until all references are gone.
  * @dev: target net_device
@@ -10052,7 +10213,7 @@ EXPORT_SYMBOL(netdev_refcnt_read);
 static void netdev_wait_allrefs(struct net_device *dev)
 {
 	unsigned long rebroadcast_time, warning_time;
-	int refcnt;
+	int wait = 0, refcnt;
 
 	linkwatch_forget_dev(dev);
 
@@ -10086,7 +10247,13 @@ static void netdev_wait_allrefs(struct net_device *dev)
 			rebroadcast_time = jiffies;
 		}
 
-		msleep(250);
+		if (!wait) {
+			rcu_barrier();
+			wait = WAIT_REFS_MIN_MSECS;
+		} else {
+			msleep(wait);
+			wait = min(wait << 1, WAIT_REFS_MAX_MSECS);
+		}
 
 		refcnt = netdev_refcnt_read(dev);
 
@@ -10134,7 +10301,7 @@ void netdev_run_todo(void)
 		struct net_device *dev = list_first_entry(&unlink_list,
 							  struct net_device,
 							  unlink_list);
-		list_del(&dev->unlink_list);
+		list_del_init(&dev->unlink_list);
 		dev->nested_level = dev->lower_level - 1;
 	}
 #endif
@@ -10249,6 +10416,55 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev,
 }
 EXPORT_SYMBOL(dev_get_stats);
 
+/**
+ *	dev_fetch_sw_netstats - get per-cpu network device statistics
+ *	@s: place to store stats
+ *	@netstats: per-cpu network stats to read from
+ *
+ *	Read per-cpu network statistics and populate the related fields in @s.
+ */
+void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
+			   const struct pcpu_sw_netstats __percpu *netstats)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		const struct pcpu_sw_netstats *stats;
+		struct pcpu_sw_netstats tmp;
+		unsigned int start;
+
+		stats = per_cpu_ptr(netstats, cpu);
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			tmp.rx_packets = stats->rx_packets;
+			tmp.rx_bytes   = stats->rx_bytes;
+			tmp.tx_packets = stats->tx_packets;
+			tmp.tx_bytes   = stats->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		s->rx_packets += tmp.rx_packets;
+		s->rx_bytes   += tmp.rx_bytes;
+		s->tx_packets += tmp.tx_packets;
+		s->tx_bytes   += tmp.tx_bytes;
+	}
+}
+EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats);
+
+/**
+ *	dev_get_tstats64 - ndo_get_stats64 implementation
+ *	@dev: device to get statistics from
+ *	@s: place to store stats
+ *
+ *	Populate @s from dev->stats and dev->tstats. Can be used as
+ *	ndo_get_stats64() callback.
+ */
+void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s)
+{
+	netdev_stats_to_stats64(s, &dev->stats);
+	dev_fetch_sw_netstats(s, dev->tstats);
+}
+EXPORT_SYMBOL_GPL(dev_get_tstats64);
+
 struct netdev_queue *dev_ingress_queue_create(struct net_device *dev)
 {
 	struct netdev_queue *queue = dev_ingress_queue(dev);
@@ -10421,6 +10637,17 @@ void free_netdev(struct net_device *dev)
 	struct napi_struct *p, *n;
 
 	might_sleep();
+
+	/* When called immediately after register_netdevice() failed the unwind
+	 * handling may still be dismantling the device. Handle that case by
+	 * deferring the free.
+	 */
+	if (dev->reg_state == NETREG_UNREGISTERING) {
+		ASSERT_RTNL();
+		dev->needs_free_netdev = true;
+		return;
+	}
+
 	netif_free_tx_queues(dev);
 	netif_free_rx_queues(dev);
 
@@ -11048,8 +11275,7 @@ static int __init net_dev_init(void)
 		INIT_LIST_HEAD(&sd->poll_list);
 		sd->output_queue_tailp = &sd->output_queue;
 #ifdef CONFIG_RPS
-		sd->csd.func = rps_trigger_softirq;
-		sd->csd.info = sd;
+		INIT_CSD(&sd->csd, rps_trigger_softirq, sd);
 		sd->cpu = i;
 #endif
 
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 205e92e604ef..db8a0ff86f36 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -230,7 +230,7 @@ static int dev_do_ioctl(struct net_device *dev,
 			struct ifreq *ifr, unsigned int cmd)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
-	int err = -EOPNOTSUPP;
+	int err;
 
 	err = dsa_ndo_do_ioctl(dev, ifr, cmd);
 	if (err == 0 || err != -EOPNOTSUPP)
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 80ec1cd81c64..738d4344d679 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -27,7 +27,6 @@
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/devlink.h>
-#include <net/drop_monitor.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/devlink.h>
 
@@ -84,6 +83,7 @@ EXPORT_SYMBOL(devlink_dpipe_header_ipv6);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg);
 EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr);
+EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report);
 
 static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = {
 	[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY },
@@ -347,8 +347,12 @@ devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
 
 struct devlink_region {
 	struct devlink *devlink;
+	struct devlink_port *port;
 	struct list_head list;
-	const struct devlink_region_ops *ops;
+	union {
+		const struct devlink_region_ops *ops;
+		const struct devlink_port_region_ops *port_ops;
+	};
 	struct list_head snapshot_list;
 	u32 max_snapshots;
 	u32 cur_snapshots;
@@ -374,6 +378,19 @@ devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
 	return NULL;
 }
 
+static struct devlink_region *
+devlink_port_region_get_by_name(struct devlink_port *port,
+				const char *region_name)
+{
+	struct devlink_region *region;
+
+	list_for_each_entry(region, &port->region_list, list)
+		if (!strcmp(region->ops->name, region_name))
+			return region;
+
+	return NULL;
+}
+
 static struct devlink_snapshot *
 devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
 {
@@ -462,10 +479,132 @@ static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink)
 	return 0;
 }
 
+struct devlink_reload_combination {
+	enum devlink_reload_action action;
+	enum devlink_reload_limit limit;
+};
+
+static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = {
+	{
+		/* can't reinitialize driver with no down time */
+		.action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+		.limit = DEVLINK_RELOAD_LIMIT_NO_RESET,
+	},
+};
+
+static bool
+devlink_reload_combination_is_invalid(enum devlink_reload_action action,
+				      enum devlink_reload_limit limit)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++)
+		if (devlink_reload_invalid_combinations[i].action == action &&
+		    devlink_reload_invalid_combinations[i].limit == limit)
+			return true;
+	return false;
+}
+
+static bool
+devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action)
+{
+	return test_bit(action, &devlink->ops->reload_actions);
+}
+
+static bool
+devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit)
+{
+	return test_bit(limit, &devlink->ops->reload_limits);
+}
+
+static int devlink_reload_stat_put(struct sk_buff *msg,
+				   enum devlink_reload_limit limit, u32 value)
+{
+	struct nlattr *reload_stats_entry;
+
+	reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY);
+	if (!reload_stats_entry)
+		return -EMSGSIZE;
+
+	if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) ||
+	    nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value))
+		goto nla_put_failure;
+	nla_nest_end(msg, reload_stats_entry);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, reload_stats_entry);
+	return -EMSGSIZE;
+}
+
+static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote)
+{
+	struct nlattr *reload_stats_attr, *act_info, *act_stats;
+	int i, j, stat_idx;
+	u32 value;
+
+	if (!is_remote)
+		reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS);
+	else
+		reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS);
+
+	if (!reload_stats_attr)
+		return -EMSGSIZE;
+
+	for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) {
+		if ((!is_remote &&
+		     !devlink_reload_action_is_supported(devlink, i)) ||
+		    i == DEVLINK_RELOAD_ACTION_UNSPEC)
+			continue;
+		act_info = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_INFO);
+		if (!act_info)
+			goto nla_put_failure;
+
+		if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i))
+			goto action_info_nest_cancel;
+		act_stats = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTION_STATS);
+		if (!act_stats)
+			goto action_info_nest_cancel;
+
+		for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) {
+			/* Remote stats are shown even if not locally supported.
+			 * Stats of actions with unspecified limit are shown
+			 * though drivers don't need to register unspecified
+			 * limit.
+			 */
+			if ((!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC &&
+			     !devlink_reload_limit_is_supported(devlink, j)) ||
+			    devlink_reload_combination_is_invalid(i, j))
+				continue;
+
+			stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i;
+			if (!is_remote)
+				value = devlink->stats.reload_stats[stat_idx];
+			else
+				value = devlink->stats.remote_reload_stats[stat_idx];
+			if (devlink_reload_stat_put(msg, j, value))
+				goto action_stats_nest_cancel;
+		}
+		nla_nest_end(msg, act_stats);
+		nla_nest_end(msg, act_info);
+	}
+	nla_nest_end(msg, reload_stats_attr);
+	return 0;
+
+action_stats_nest_cancel:
+	nla_nest_cancel(msg, act_stats);
+action_info_nest_cancel:
+	nla_nest_cancel(msg, act_info);
+nla_put_failure:
+	nla_nest_cancel(msg, reload_stats_attr);
+	return -EMSGSIZE;
+}
+
 static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 			   enum devlink_command cmd, u32 portid,
 			   u32 seq, int flags)
 {
+	struct nlattr *dev_stats;
 	void *hdr;
 
 	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
@@ -477,9 +616,21 @@ static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed))
 		goto nla_put_failure;
 
+	dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS);
+	if (!dev_stats)
+		goto nla_put_failure;
+
+	if (devlink_reload_stats_put(msg, devlink, false))
+		goto dev_stats_nest_cancel;
+	if (devlink_reload_stats_put(msg, devlink, true))
+		goto dev_stats_nest_cancel;
+
+	nla_nest_end(msg, dev_stats);
 	genlmsg_end(msg, hdr);
 	return 0;
 
+dev_stats_nest_cancel:
+	nla_nest_cancel(msg, dev_stats);
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	return -EMSGSIZE;
@@ -523,15 +674,20 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg,
 		return -EMSGSIZE;
 	switch (devlink_port->attrs.flavour) {
 	case DEVLINK_PORT_FLAVOUR_PCI_PF:
-		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
-				attrs->pci_pf.pf))
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
+				attrs->pci_pf.controller) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf))
+			return -EMSGSIZE;
+		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external))
 			return -EMSGSIZE;
 		break;
 	case DEVLINK_PORT_FLAVOUR_PCI_VF:
-		if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER,
-				attrs->pci_vf.pf) ||
-		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER,
-				attrs->pci_vf.vf))
+		if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER,
+				attrs->pci_vf.controller) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) ||
+		    nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf))
+			return -EMSGSIZE;
+		if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external))
 			return -EMSGSIZE;
 		break;
 	case DEVLINK_PORT_FLAVOUR_PHYSICAL:
@@ -616,6 +772,8 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index))
 		goto nla_put_failure;
 
+	/* Hold rtnl lock while accessing port's netdev attributes. */
+	rtnl_lock();
 	spin_lock_bh(&devlink_port->type_lock);
 	if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type))
 		goto nla_put_failure_type_locked;
@@ -624,9 +782,10 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
 			devlink_port->desired_type))
 		goto nla_put_failure_type_locked;
 	if (devlink_port->type == DEVLINK_PORT_TYPE_ETH) {
+		struct net *net = devlink_net(devlink_port->devlink);
 		struct net_device *netdev = devlink_port->type_dev;
 
-		if (netdev &&
+		if (netdev && net_eq(net, dev_net(netdev)) &&
 		    (nla_put_u32(msg, DEVLINK_ATTR_PORT_NETDEV_IFINDEX,
 				 netdev->ifindex) ||
 		     nla_put_string(msg, DEVLINK_ATTR_PORT_NETDEV_NAME,
@@ -642,6 +801,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
 			goto nla_put_failure_type_locked;
 	}
 	spin_unlock_bh(&devlink_port->type_lock);
+	rtnl_unlock();
 	if (devlink_nl_port_attrs_put(msg, devlink_port))
 		goto nla_put_failure;
 	if (devlink_nl_port_function_attrs_put(msg, devlink_port, extack))
@@ -652,6 +812,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink,
 
 nla_put_failure_type_locked:
 	spin_unlock_bh(&devlink_port->type_lock);
+	rtnl_unlock();
 nla_put_failure:
 	genlmsg_cancel(msg, hdr);
 	return -EMSGSIZE;
@@ -806,8 +967,6 @@ static int devlink_port_type_set(struct devlink *devlink,
 	int err;
 
 	if (devlink->ops->port_type_set) {
-		if (port_type == DEVLINK_PORT_TYPE_NOTSET)
-			return -EINVAL;
 		if (port_type == devlink_port->type)
 			return 0;
 		err = devlink->ops->port_type_set(devlink_port, port_type);
@@ -1311,7 +1470,7 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg,
 		err = ops->sb_occ_port_pool_get(devlink_port, devlink_sb->index,
 						pool_index, &cur, &max);
 		if (err && err != -EOPNOTSUPP)
-			return err;
+			goto sb_occ_get_failure;
 		if (!err) {
 			if (nla_put_u32(msg, DEVLINK_ATTR_SB_OCC_CUR, cur))
 				goto nla_put_failure;
@@ -1324,8 +1483,10 @@ static int devlink_nl_sb_port_pool_fill(struct sk_buff *msg,
 	return 0;
 
 nla_put_failure:
+	err = -EMSGSIZE;
+sb_occ_get_failure:
 	genlmsg_cancel(msg, hdr);
-	return -EMSGSIZE;
+	return err;
 }
 
 static int devlink_nl_cmd_sb_port_pool_get_doit(struct sk_buff *skb,
@@ -2943,9 +3104,9 @@ static void devlink_reload_netns_change(struct devlink *devlink,
 				     DEVLINK_CMD_PARAM_NEW);
 }
 
-static bool devlink_reload_supported(const struct devlink *devlink)
+static bool devlink_reload_supported(const struct devlink_ops *ops)
 {
-	return devlink->ops->reload_down && devlink->ops->reload_up;
+	return ops->reload_down && ops->reload_up;
 }
 
 static void devlink_reload_failed_set(struct devlink *devlink,
@@ -2963,33 +3124,132 @@ bool devlink_is_reload_failed(const struct devlink *devlink)
 }
 EXPORT_SYMBOL_GPL(devlink_is_reload_failed);
 
+static void
+__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats,
+			      enum devlink_reload_limit limit, u32 actions_performed)
+{
+	unsigned long actions = actions_performed;
+	int stat_idx;
+	int action;
+
+	for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) {
+		stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action;
+		reload_stats[stat_idx]++;
+	}
+	devlink_notify(devlink, DEVLINK_CMD_NEW);
+}
+
+static void
+devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit,
+			    u32 actions_performed)
+{
+	__devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit,
+				      actions_performed);
+}
+
+/**
+ *	devlink_remote_reload_actions_performed - Update devlink on reload actions
+ *	  performed which are not a direct result of devlink reload call.
+ *
+ *	This should be called by a driver after performing reload actions in case it was not
+ *	a result of devlink reload call. For example fw_activate was performed as a result
+ *	of devlink reload triggered fw_activate on another host.
+ *	The motivation for this function is to keep data on reload actions performed on this
+ *	function whether it was done due to direct devlink reload call or not.
+ *
+ *	@devlink: devlink
+ *	@limit: reload limit
+ *	@actions_performed: bitmask of actions performed
+ */
+void devlink_remote_reload_actions_performed(struct devlink *devlink,
+					     enum devlink_reload_limit limit,
+					     u32 actions_performed)
+{
+	if (WARN_ON(!actions_performed ||
+		    actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) ||
+		    actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) ||
+		    limit > DEVLINK_RELOAD_LIMIT_MAX))
+		return;
+
+	__devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit,
+				      actions_performed);
+}
+EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed);
+
 static int devlink_reload(struct devlink *devlink, struct net *dest_net,
-			  struct netlink_ext_ack *extack)
+			  enum devlink_reload_action action, enum devlink_reload_limit limit,
+			  u32 *actions_performed, struct netlink_ext_ack *extack)
 {
+	u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE];
 	int err;
 
 	if (!devlink->reload_enabled)
 		return -EOPNOTSUPP;
 
-	err = devlink->ops->reload_down(devlink, !!dest_net, extack);
+	memcpy(remote_reload_stats, devlink->stats.remote_reload_stats,
+	       sizeof(remote_reload_stats));
+	err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack);
 	if (err)
 		return err;
 
 	if (dest_net && !net_eq(dest_net, devlink_net(devlink)))
 		devlink_reload_netns_change(devlink, dest_net);
 
-	err = devlink->ops->reload_up(devlink, extack);
+	err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack);
 	devlink_reload_failed_set(devlink, !!err);
-	return err;
+	if (err)
+		return err;
+
+	WARN_ON(!(*actions_performed & BIT(action)));
+	/* Catch driver on updating the remote action within devlink reload */
+	WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats,
+		       sizeof(remote_reload_stats)));
+	devlink_reload_stats_update(devlink, limit, *actions_performed);
+	return 0;
+}
+
+static int
+devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed,
+					enum devlink_command cmd, struct genl_info *info)
+{
+	struct sk_buff *msg;
+	void *hdr;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd);
+	if (!hdr)
+		goto free_msg;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto nla_put_failure;
+
+	if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed,
+			       actions_performed))
+		goto nla_put_failure;
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_reply(msg, info);
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+free_msg:
+	nlmsg_free(msg);
+	return -EMSGSIZE;
 }
 
 static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
+	enum devlink_reload_action action;
+	enum devlink_reload_limit limit;
 	struct net *dest_net = NULL;
+	u32 actions_performed;
 	int err;
 
-	if (!devlink_reload_supported(devlink))
+	if (!devlink_reload_supported(devlink->ops))
 		return -EOPNOTSUPP;
 
 	err = devlink_resources_validate(devlink, NULL, info);
@@ -3006,20 +3266,67 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 			return PTR_ERR(dest_net);
 	}
 
-	err = devlink_reload(devlink, dest_net, info->extack);
+	if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION])
+		action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]);
+	else
+		action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT;
+
+	if (!devlink_reload_action_is_supported(devlink, action)) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "Requested reload action is not supported by the driver");
+		return -EOPNOTSUPP;
+	}
+
+	limit = DEVLINK_RELOAD_LIMIT_UNSPEC;
+	if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) {
+		struct nla_bitfield32 limits;
+		u32 limits_selected;
+
+		limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]);
+		limits_selected = limits.value & limits.selector;
+		if (!limits_selected) {
+			NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected");
+			return -EINVAL;
+		}
+		for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++)
+			if (limits_selected & BIT(limit))
+				break;
+		/* UAPI enables multiselection, but currently it is not used */
+		if (limits_selected != BIT(limit)) {
+			NL_SET_ERR_MSG_MOD(info->extack,
+					   "Multiselection of limit is not supported");
+			return -EOPNOTSUPP;
+		}
+		if (!devlink_reload_limit_is_supported(devlink, limit)) {
+			NL_SET_ERR_MSG_MOD(info->extack,
+					   "Requested limit is not supported by the driver");
+			return -EOPNOTSUPP;
+		}
+		if (devlink_reload_combination_is_invalid(action, limit)) {
+			NL_SET_ERR_MSG_MOD(info->extack,
+					   "Requested limit is invalid for this action");
+			return -EINVAL;
+		}
+	}
+	err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack);
 
 	if (dest_net)
 		put_net(dest_net);
 
-	return err;
+	if (err)
+		return err;
+	/* For backward compatibility generate reply only if attributes used by user */
+	if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS])
+		return 0;
+
+	return devlink_nl_reload_actions_performed_snd(devlink, actions_performed,
+						       DEVLINK_CMD_RELOAD, info);
 }
 
 static int devlink_nl_flash_update_fill(struct sk_buff *msg,
 					struct devlink *devlink,
 					enum devlink_command cmd,
-					const char *status_msg,
-					const char *component,
-					unsigned long done, unsigned long total)
+					struct devlink_flash_notify *params)
 {
 	void *hdr;
 
@@ -3033,19 +3340,22 @@ static int devlink_nl_flash_update_fill(struct sk_buff *msg,
 	if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS)
 		goto out;
 
-	if (status_msg &&
+	if (params->status_msg &&
 	    nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG,
-			   status_msg))
+			   params->status_msg))
 		goto nla_put_failure;
-	if (component &&
+	if (params->component &&
 	    nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT,
-			   component))
+			   params->component))
 		goto nla_put_failure;
 	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE,
-			      done, DEVLINK_ATTR_PAD))
+			      params->done, DEVLINK_ATTR_PAD))
 		goto nla_put_failure;
 	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL,
-			      total, DEVLINK_ATTR_PAD))
+			      params->total, DEVLINK_ATTR_PAD))
+		goto nla_put_failure;
+	if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT,
+			      params->timeout, DEVLINK_ATTR_PAD))
 		goto nla_put_failure;
 
 out:
@@ -3059,10 +3369,7 @@ nla_put_failure:
 
 static void __devlink_flash_update_notify(struct devlink *devlink,
 					  enum devlink_command cmd,
-					  const char *status_msg,
-					  const char *component,
-					  unsigned long done,
-					  unsigned long total)
+					  struct devlink_flash_notify *params)
 {
 	struct sk_buff *msg;
 	int err;
@@ -3075,8 +3382,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink,
 	if (!msg)
 		return;
 
-	err = devlink_nl_flash_update_fill(msg, devlink, cmd, status_msg,
-					   component, done, total);
+	err = devlink_nl_flash_update_fill(msg, devlink, cmd, params);
 	if (err)
 		goto out_free_msg;
 
@@ -3088,21 +3394,23 @@ out_free_msg:
 	nlmsg_free(msg);
 }
 
-void devlink_flash_update_begin_notify(struct devlink *devlink)
+static void devlink_flash_update_begin_notify(struct devlink *devlink)
 {
+	struct devlink_flash_notify params = { 0 };
+
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE,
-				      NULL, NULL, 0, 0);
+				      &params);
 }
-EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify);
 
-void devlink_flash_update_end_notify(struct devlink *devlink)
+static void devlink_flash_update_end_notify(struct devlink *devlink)
 {
+	struct devlink_flash_notify params = { 0 };
+
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE_END,
-				      NULL, NULL, 0, 0);
+				      &params);
 }
-EXPORT_SYMBOL_GPL(devlink_flash_update_end_notify);
 
 void devlink_flash_update_status_notify(struct devlink *devlink,
 					const char *status_msg,
@@ -3110,31 +3418,92 @@ void devlink_flash_update_status_notify(struct devlink *devlink,
 					unsigned long done,
 					unsigned long total)
 {
+	struct devlink_flash_notify params = {
+		.status_msg = status_msg,
+		.component = component,
+		.done = done,
+		.total = total,
+	};
+
 	__devlink_flash_update_notify(devlink,
 				      DEVLINK_CMD_FLASH_UPDATE_STATUS,
-				      status_msg, component, done, total);
+				      &params);
 }
 EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify);
 
+void devlink_flash_update_timeout_notify(struct devlink *devlink,
+					 const char *status_msg,
+					 const char *component,
+					 unsigned long timeout)
+{
+	struct devlink_flash_notify params = {
+		.status_msg = status_msg,
+		.component = component,
+		.timeout = timeout,
+	};
+
+	__devlink_flash_update_notify(devlink,
+				      DEVLINK_CMD_FLASH_UPDATE_STATUS,
+				      &params);
+}
+EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify);
+
 static int devlink_nl_cmd_flash_update(struct sk_buff *skb,
 				       struct genl_info *info)
 {
+	struct nlattr *nla_component, *nla_overwrite_mask, *nla_file_name;
+	struct devlink_flash_update_params params = {};
 	struct devlink *devlink = info->user_ptr[0];
-	const char *file_name, *component;
-	struct nlattr *nla_component;
+	const char *file_name;
+	u32 supported_params;
+	int ret;
 
 	if (!devlink->ops->flash_update)
 		return -EOPNOTSUPP;
 
 	if (!info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME])
 		return -EINVAL;
-	file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]);
+
+	supported_params = devlink->ops->supported_flash_update_params;
 
 	nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT];
-	component = nla_component ? nla_data(nla_component) : NULL;
+	if (nla_component) {
+		if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT)) {
+			NL_SET_ERR_MSG_ATTR(info->extack, nla_component,
+					    "component update is not supported by this device");
+			return -EOPNOTSUPP;
+		}
+		params.component = nla_data(nla_component);
+	}
+
+	nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK];
+	if (nla_overwrite_mask) {
+		struct nla_bitfield32 sections;
+
+		if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) {
+			NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask,
+					    "overwrite settings are not supported by this device");
+			return -EOPNOTSUPP;
+		}
+		sections = nla_get_bitfield32(nla_overwrite_mask);
+		params.overwrite_mask = sections.value & sections.selector;
+	}
+
+	nla_file_name = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME];
+	file_name = nla_data(nla_file_name);
+	ret = request_firmware(&params.fw, file_name, devlink->dev);
+	if (ret) {
+		NL_SET_ERR_MSG_ATTR(info->extack, nla_file_name, "failed to locate the requested firmware file");
+		return ret;
+	}
+
+	devlink_flash_update_begin_notify(devlink);
+	ret = devlink->ops->flash_update(devlink, &params, info->extack);
+	devlink_flash_update_end_notify(devlink);
 
-	return devlink->ops->flash_update(devlink, file_name, component,
-					  info->extack);
+	release_firmware(params.fw);
+
+	return ret;
 }
 
 static const struct devlink_param devlink_param_generic[] = {
@@ -3188,6 +3557,11 @@ static const struct devlink_param devlink_param_generic[] = {
 		.name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME,
 		.type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE,
 	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE,
+	},
 };
 
 static int devlink_param_generic_verify(const struct devlink_param *param)
@@ -3772,7 +4146,7 @@ out:
 static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb,
 					      struct genl_info *info)
 {
-	struct devlink_port *devlink_port = info->user_ptr[0];
+	struct devlink_port *devlink_port = info->user_ptr[1];
 	struct devlink_param_item *param_item;
 	struct sk_buff *msg;
 	int err;
@@ -3801,7 +4175,7 @@ static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb,
 static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb,
 					      struct genl_info *info)
 {
-	struct devlink_port *devlink_port = info->user_ptr[0];
+	struct devlink_port *devlink_port = info->user_ptr[1];
 
 	return __devlink_nl_cmd_param_set_doit(devlink_port->devlink,
 					       devlink_port->index,
@@ -3875,6 +4249,13 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (err)
 		goto nla_put_failure;
 
+	if (region->port) {
+		err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				  region->port->index);
+		if (err)
+			goto nla_put_failure;
+	}
+
 	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name);
 	if (err)
 		goto nla_put_failure;
@@ -3922,6 +4303,13 @@ devlink_nl_region_notify_build(struct devlink_region *region,
 	if (err)
 		goto out_cancel_msg;
 
+	if (region->port) {
+		err = nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX,
+				  region->port->index);
+		if (err)
+			goto out_cancel_msg;
+	}
+
 	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
 			     region->ops->name);
 	if (err)
@@ -4168,16 +4556,30 @@ static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
 					  struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_port *port = NULL;
 	struct devlink_region *region;
 	const char *region_name;
 	struct sk_buff *msg;
+	unsigned int index;
 	int err;
 
 	if (!info->attrs[DEVLINK_ATTR_REGION_NAME])
 		return -EINVAL;
 
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
 	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
-	region = devlink_region_get_by_name(devlink, region_name);
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
 	if (!region)
 		return -EINVAL;
 
@@ -4196,10 +4598,75 @@ static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
 	return genlmsg_reply(msg, info);
 }
 
+static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg,
+						 struct netlink_callback *cb,
+						 struct devlink_port *port,
+						 int *idx,
+						 int start)
+{
+	struct devlink_region *region;
+	int err = 0;
+
+	list_for_each_entry(region, &port->region_list, list) {
+		if (*idx < start) {
+			(*idx)++;
+			continue;
+		}
+		err = devlink_nl_region_fill(msg, port->devlink,
+					     DEVLINK_CMD_REGION_GET,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq,
+					     NLM_F_MULTI, region);
+		if (err)
+			goto out;
+		(*idx)++;
+	}
+
+out:
+	return err;
+}
+
+static int devlink_nl_cmd_region_get_devlink_dumpit(struct sk_buff *msg,
+						    struct netlink_callback *cb,
+						    struct devlink *devlink,
+						    int *idx,
+						    int start)
+{
+	struct devlink_region *region;
+	struct devlink_port *port;
+	int err = 0;
+
+	mutex_lock(&devlink->lock);
+	list_for_each_entry(region, &devlink->region_list, list) {
+		if (*idx < start) {
+			(*idx)++;
+			continue;
+		}
+		err = devlink_nl_region_fill(msg, devlink,
+					     DEVLINK_CMD_REGION_GET,
+					     NETLINK_CB(cb->skb).portid,
+					     cb->nlh->nlmsg_seq,
+					     NLM_F_MULTI, region);
+		if (err)
+			goto out;
+		(*idx)++;
+	}
+
+	list_for_each_entry(port, &devlink->port_list, list) {
+		err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, idx,
+							    start);
+		if (err)
+			goto out;
+	}
+
+out:
+	mutex_unlock(&devlink->lock);
+	return err;
+}
+
 static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
 					    struct netlink_callback *cb)
 {
-	struct devlink_region *region;
 	struct devlink *devlink;
 	int start = cb->args[0];
 	int idx = 0;
@@ -4209,25 +4676,10 @@ static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
 	list_for_each_entry(devlink, &devlink_list, list) {
 		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
 			continue;
-
-		mutex_lock(&devlink->lock);
-		list_for_each_entry(region, &devlink->region_list, list) {
-			if (idx < start) {
-				idx++;
-				continue;
-			}
-			err = devlink_nl_region_fill(msg, devlink,
-						     DEVLINK_CMD_REGION_GET,
-						     NETLINK_CB(cb->skb).portid,
-						     cb->nlh->nlmsg_seq,
-						     NLM_F_MULTI, region);
-			if (err) {
-				mutex_unlock(&devlink->lock);
-				goto out;
-			}
-			idx++;
-		}
-		mutex_unlock(&devlink->lock);
+		err = devlink_nl_cmd_region_get_devlink_dumpit(msg, cb, devlink,
+							       &idx, start);
+		if (err)
+			goto out;
 	}
 out:
 	mutex_unlock(&devlink_mutex);
@@ -4240,8 +4692,10 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb,
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_snapshot *snapshot;
+	struct devlink_port *port = NULL;
 	struct devlink_region *region;
 	const char *region_name;
+	unsigned int index;
 	u32 snapshot_id;
 
 	if (!info->attrs[DEVLINK_ATTR_REGION_NAME] ||
@@ -4251,7 +4705,19 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb,
 	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
 	snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
 
-	region = devlink_region_get_by_name(devlink, region_name);
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
 	if (!region)
 		return -EINVAL;
 
@@ -4268,9 +4734,11 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 {
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_snapshot *snapshot;
+	struct devlink_port *port = NULL;
 	struct nlattr *snapshot_id_attr;
 	struct devlink_region *region;
 	const char *region_name;
+	unsigned int index;
 	u32 snapshot_id;
 	u8 *data;
 	int err;
@@ -4281,7 +4749,20 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
-	region = devlink_region_get_by_name(devlink, region_name);
+
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port)
+			return -ENODEV;
+	}
+
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
 	if (!region) {
 		NL_SET_ERR_MSG_MOD(info->extack, "The requested region does not exist");
 		return -EINVAL;
@@ -4317,7 +4798,12 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 
-	err = region->ops->snapshot(devlink, info->extack, &data);
+	if (port)
+		err = region->port_ops->snapshot(port, region->port_ops,
+						 info->extack, &data);
+	else
+		err = region->ops->snapshot(devlink, region->ops,
+					    info->extack, &data);
 	if (err)
 		goto err_snapshot_capture;
 
@@ -4439,10 +4925,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
 	u64 ret_offset, start_offset, end_offset = U64_MAX;
 	struct nlattr **attrs = info->attrs;
+	struct devlink_port *port = NULL;
 	struct devlink_region *region;
 	struct nlattr *chunks_attr;
 	const char *region_name;
 	struct devlink *devlink;
+	unsigned int index;
 	void *hdr;
 	int err;
 
@@ -4463,8 +4951,23 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 		goto out_unlock;
 	}
 
+	if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) {
+		index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]);
+
+		port = devlink_port_get_by_index(devlink, index);
+		if (!port) {
+			err = -ENODEV;
+			goto out_unlock;
+		}
+	}
+
 	region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]);
-	region = devlink_region_get_by_name(devlink, region_name);
+
+	if (port)
+		region = devlink_port_region_get_by_name(port, region_name);
+	else
+		region = devlink_region_get_by_name(devlink, region_name);
+
 	if (!region) {
 		err = -EINVAL;
 		goto out_unlock;
@@ -4501,6 +5004,13 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
 	if (err)
 		goto nla_put_failure;
 
+	if (region->port) {
+		err = nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX,
+				  region->port->index);
+		if (err)
+			goto nla_put_failure;
+	}
+
 	err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
 	if (err)
 		goto nla_put_failure;
@@ -5895,6 +6405,7 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg,
 	list_for_each_entry(devlink, &devlink_list, list) {
 		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
 			continue;
+		mutex_lock(&devlink->lock);
 		list_for_each_entry(port, &devlink->port_list, list) {
 			mutex_lock(&port->reporters_lock);
 			list_for_each_entry(reporter, &port->reporter_list, list) {
@@ -5909,12 +6420,14 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg,
 								      NLM_F_MULTI);
 				if (err) {
 					mutex_unlock(&port->reporters_lock);
+					mutex_unlock(&devlink->lock);
 					goto out;
 				}
 				idx++;
 			}
 			mutex_unlock(&port->reporters_lock);
 		}
+		mutex_unlock(&devlink->lock);
 	}
 out:
 	mutex_unlock(&devlink_mutex);
@@ -6088,6 +6601,28 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb,
 	return 0;
 }
 
+static int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb,
+						    struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_health_reporter *reporter;
+	int err;
+
+	reporter = devlink_health_reporter_get_from_info(devlink, info);
+	if (!reporter)
+		return -EINVAL;
+
+	if (!reporter->ops->test) {
+		devlink_health_reporter_put(reporter);
+		return -EOPNOTSUPP;
+	}
+
+	err = reporter->ops->test(reporter, info->extack);
+
+	devlink_health_reporter_put(reporter);
+	return err;
+}
+
 struct devlink_stats {
 	u64 rx_bytes;
 	u64 rx_packets;
@@ -6458,7 +6993,6 @@ static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb,
 	struct netlink_ext_ack *extack = info->extack;
 	struct devlink *devlink = info->user_ptr[0];
 	struct devlink_trap_item *trap_item;
-	int err;
 
 	if (list_empty(&devlink->trap_list))
 		return -EOPNOTSUPP;
@@ -6469,11 +7003,7 @@ static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb,
 		return -ENOENT;
 	}
 
-	err = devlink_trap_action_set(devlink, trap_item, info);
-	if (err)
-		return err;
-
-	return 0;
+	return devlink_trap_action_set(devlink, trap_item, info);
 }
 
 static struct devlink_trap_group_item *
@@ -6644,6 +7174,24 @@ __devlink_trap_group_action_set(struct devlink *devlink,
 	struct devlink_trap_item *trap_item;
 	int err;
 
+	if (devlink->ops->trap_group_action_set) {
+		err = devlink->ops->trap_group_action_set(devlink, group_item->group,
+							  trap_action, extack);
+		if (err)
+			return err;
+
+		list_for_each_entry(trap_item, &devlink->trap_list, list) {
+			if (strcmp(trap_item->group_item->group->name, group_name))
+				continue;
+			if (trap_item->action != trap_action &&
+			    trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP)
+				continue;
+			trap_item->action = trap_action;
+		}
+
+		return 0;
+	}
+
 	list_for_each_entry(trap_item, &devlink->trap_list, list) {
 		if (strcmp(trap_item->group_item->group->name, group_name))
 			continue;
@@ -7000,7 +7548,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 },
-	[DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO,
+						    DEVLINK_PORT_TYPE_IB),
 	[DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 },
@@ -7009,7 +7558,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 },
 	[DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 },
-	[DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 },
+	[DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY,
+						       DEVLINK_ESWITCH_MODE_SWITCHDEV),
 	[DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING },
@@ -7028,6 +7578,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] =
+		NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS),
 	[DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING },
@@ -7039,9 +7591,12 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 },
 	[DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED },
+	[DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+							DEVLINK_RELOAD_ACTION_MAX),
+	[DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK),
 };
 
-static const struct genl_ops devlink_nl_ops[] = {
+static const struct genl_small_ops devlink_nl_ops[] = {
 	{
 		.cmd = DEVLINK_CMD_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -7309,6 +7864,14 @@ static const struct genl_ops devlink_nl_ops[] = {
 				  DEVLINK_NL_FLAG_NO_LOCK,
 	},
 	{
+		.cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = devlink_nl_cmd_health_reporter_test_doit,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT |
+				  DEVLINK_NL_FLAG_NO_LOCK,
+	},
+	{
 		.cmd = DEVLINK_CMD_FLASH_UPDATE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = devlink_nl_cmd_flash_update,
@@ -7358,12 +7921,41 @@ static struct genl_family devlink_nl_family __ro_after_init = {
 	.pre_doit	= devlink_nl_pre_doit,
 	.post_doit	= devlink_nl_post_doit,
 	.module		= THIS_MODULE,
-	.ops		= devlink_nl_ops,
-	.n_ops		= ARRAY_SIZE(devlink_nl_ops),
+	.small_ops	= devlink_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(devlink_nl_ops),
 	.mcgrps		= devlink_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(devlink_nl_mcgrps),
 };
 
+static bool devlink_reload_actions_valid(const struct devlink_ops *ops)
+{
+	const struct devlink_reload_combination *comb;
+	int i;
+
+	if (!devlink_reload_supported(ops)) {
+		if (WARN_ON(ops->reload_actions))
+			return false;
+		return true;
+	}
+
+	if (WARN_ON(!ops->reload_actions ||
+		    ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) ||
+		    ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX)))
+		return false;
+
+	if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) ||
+		    ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX)))
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++)  {
+		comb = &devlink_reload_invalid_combinations[i];
+		if (ops->reload_actions == BIT(comb->action) &&
+		    ops->reload_limits == BIT(comb->limit))
+			return false;
+	}
+	return true;
+}
+
 /**
  *	devlink_alloc - Allocate new devlink instance resources
  *
@@ -7380,6 +7972,9 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	if (WARN_ON(!ops))
 		return NULL;
 
+	if (!devlink_reload_actions_valid(ops))
+		return NULL;
+
 	devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL);
 	if (!devlink)
 		return NULL;
@@ -7428,7 +8023,7 @@ EXPORT_SYMBOL_GPL(devlink_register);
 void devlink_unregister(struct devlink *devlink)
 {
 	mutex_lock(&devlink_mutex);
-	WARN_ON(devlink_reload_supported(devlink) &&
+	WARN_ON(devlink_reload_supported(devlink->ops) &&
 		devlink->reload_enabled);
 	devlink_notify(devlink, DEVLINK_CMD_DEL);
 	list_del(&devlink->list);
@@ -7506,7 +8101,8 @@ static bool devlink_port_type_should_warn(struct devlink_port *devlink_port)
 {
 	/* Ignore CPU and DSA flavours. */
 	return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU &&
-	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA;
+	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA &&
+	       devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED;
 }
 
 #define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600)
@@ -7555,11 +8151,12 @@ int devlink_port_register(struct devlink *devlink,
 	devlink_port->index = port_index;
 	devlink_port->registered = true;
 	spin_lock_init(&devlink_port->type_lock);
+	INIT_LIST_HEAD(&devlink_port->reporter_list);
+	mutex_init(&devlink_port->reporters_lock);
 	list_add_tail(&devlink_port->list, &devlink->port_list);
 	INIT_LIST_HEAD(&devlink_port->param_list);
+	INIT_LIST_HEAD(&devlink_port->region_list);
 	mutex_unlock(&devlink->lock);
-	INIT_LIST_HEAD(&devlink_port->reporter_list);
-	mutex_init(&devlink_port->reporters_lock);
 	INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn);
 	devlink_port_type_warn_schedule(devlink_port);
 	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
@@ -7576,13 +8173,14 @@ void devlink_port_unregister(struct devlink_port *devlink_port)
 {
 	struct devlink *devlink = devlink_port->devlink;
 
-	WARN_ON(!list_empty(&devlink_port->reporter_list));
-	mutex_destroy(&devlink_port->reporters_lock);
 	devlink_port_type_warn_cancel(devlink_port);
 	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL);
 	mutex_lock(&devlink->lock);
 	list_del(&devlink_port->list);
 	mutex_unlock(&devlink->lock);
+	WARN_ON(!list_empty(&devlink_port->reporter_list));
+	WARN_ON(!list_empty(&devlink_port->region_list));
+	mutex_destroy(&devlink_port->reporters_lock);
 }
 EXPORT_SYMBOL_GPL(devlink_port_unregister);
 
@@ -7600,14 +8198,8 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port,
 	devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW);
 }
 
-/**
- *	devlink_port_type_eth_set - Set port type to Ethernet
- *
- *	@devlink_port: devlink port
- *	@netdev: related netdevice
- */
-void devlink_port_type_eth_set(struct devlink_port *devlink_port,
-			       struct net_device *netdev)
+static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port,
+					    struct net_device *netdev)
 {
 	const struct net_device_ops *ops = netdev->netdev_ops;
 
@@ -7641,6 +8233,24 @@ void devlink_port_type_eth_set(struct devlink_port *devlink_port,
 		err = ops->ndo_get_port_parent_id(netdev, &ppid);
 		WARN_ON(err != -EOPNOTSUPP);
 	}
+}
+
+/**
+ *	devlink_port_type_eth_set - Set port type to Ethernet
+ *
+ *	@devlink_port: devlink port
+ *	@netdev: related netdevice
+ */
+void devlink_port_type_eth_set(struct devlink_port *devlink_port,
+			       struct net_device *netdev)
+{
+	if (netdev)
+		devlink_port_type_netdev_checks(devlink_port, netdev);
+	else
+		dev_warn(devlink_port->devlink->dev,
+			 "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n",
+			 devlink_port->index);
+
 	__devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev);
 }
 EXPORT_SYMBOL_GPL(devlink_port_type_eth_set);
@@ -7675,8 +8285,6 @@ static int __devlink_port_attrs_set(struct devlink_port *devlink_port,
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 
-	if (WARN_ON(devlink_port->registered))
-		return -EEXIST;
 	devlink_port->attrs_set = true;
 	attrs->flavour = flavour;
 	if (attrs->switch_id.id_len) {
@@ -7700,6 +8308,8 @@ void devlink_port_attrs_set(struct devlink_port *devlink_port,
 {
 	int ret;
 
+	if (WARN_ON(devlink_port->registered))
+		return;
 	devlink_port->attrs = *attrs;
 	ret = __devlink_port_attrs_set(devlink_port, attrs->flavour);
 	if (ret)
@@ -7712,19 +8322,25 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set);
  *	devlink_port_attrs_pci_pf_set - Set PCI PF port attributes
  *
  *	@devlink_port: devlink port
+ *	@controller: associated controller number for the devlink port instance
  *	@pf: associated PF for the devlink port instance
+ *	@external: indicates if the port is for an external controller
  */
-void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf)
+void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller,
+				   u16 pf, bool external)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
 
+	if (WARN_ON(devlink_port->registered))
+		return;
 	ret = __devlink_port_attrs_set(devlink_port,
 				       DEVLINK_PORT_FLAVOUR_PCI_PF);
 	if (ret)
 		return;
-
+	attrs->pci_pf.controller = controller;
 	attrs->pci_pf.pf = pf;
+	attrs->pci_pf.external = external;
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
 
@@ -7732,21 +8348,27 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set);
  *	devlink_port_attrs_pci_vf_set - Set PCI VF port attributes
  *
  *	@devlink_port: devlink port
+ *	@controller: associated controller number for the devlink port instance
  *	@pf: associated PF for the devlink port instance
  *	@vf: associated VF of a PF for the devlink port instance
+ *	@external: indicates if the port is for an external controller
  */
-void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port,
-				   u16 pf, u16 vf)
+void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller,
+				   u16 pf, u16 vf, bool external)
 {
 	struct devlink_port_attrs *attrs = &devlink_port->attrs;
 	int ret;
 
+	if (WARN_ON(devlink_port->registered))
+		return;
 	ret = __devlink_port_attrs_set(devlink_port,
 				       DEVLINK_PORT_FLAVOUR_PCI_VF);
 	if (ret)
 		return;
+	attrs->pci_vf.controller = controller;
 	attrs->pci_vf.pf = pf;
 	attrs->pci_vf.vf = vf;
+	attrs->pci_vf.external = external;
 }
 EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set);
 
@@ -7771,15 +8393,30 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port,
 		break;
 	case DEVLINK_PORT_FLAVOUR_CPU:
 	case DEVLINK_PORT_FLAVOUR_DSA:
+	case DEVLINK_PORT_FLAVOUR_UNUSED:
 		/* As CPU and DSA ports do not have a netdevice associated
 		 * case should not ever happen.
 		 */
 		WARN_ON(1);
 		return -EINVAL;
 	case DEVLINK_PORT_FLAVOUR_PCI_PF:
+		if (attrs->pci_pf.external) {
+			n = snprintf(name, len, "c%u", attrs->pci_pf.controller);
+			if (n >= len)
+				return -EINVAL;
+			len -= n;
+			name += n;
+		}
 		n = snprintf(name, len, "pf%u", attrs->pci_pf.pf);
 		break;
 	case DEVLINK_PORT_FLAVOUR_PCI_VF:
+		if (attrs->pci_vf.external) {
+			n = snprintf(name, len, "c%u", attrs->pci_vf.controller);
+			if (n >= len)
+				return -EINVAL;
+			len -= n;
+			name += n;
+		}
 		n = snprintf(name, len, "pf%uvf%u",
 			     attrs->pci_vf.pf, attrs->pci_vf.vf);
 		break;
@@ -8431,7 +9068,7 @@ __devlink_param_driverinit_value_set(struct devlink *devlink,
 int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
 				       union devlink_param_value *init_val)
 {
-	if (!devlink_reload_supported(devlink))
+	if (!devlink_reload_supported(devlink->ops))
 		return -EOPNOTSUPP;
 
 	return __devlink_param_driverinit_value_get(&devlink->param_list,
@@ -8478,7 +9115,7 @@ int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port,
 {
 	struct devlink *devlink = devlink_port->devlink;
 
-	if (!devlink_reload_supported(devlink))
+	if (!devlink_reload_supported(devlink->ops))
 		return -EOPNOTSUPP;
 
 	return __devlink_param_driverinit_value_get(&devlink_port->param_list,
@@ -8627,6 +9264,57 @@ unlock:
 EXPORT_SYMBOL_GPL(devlink_region_create);
 
 /**
+ *	devlink_port_region_create - create a new address region for a port
+ *
+ *	@port: devlink port
+ *	@ops: region operations and name
+ *	@region_max_snapshots: Maximum supported number of snapshots for region
+ *	@region_size: size of region
+ */
+struct devlink_region *
+devlink_port_region_create(struct devlink_port *port,
+			   const struct devlink_port_region_ops *ops,
+			   u32 region_max_snapshots, u64 region_size)
+{
+	struct devlink *devlink = port->devlink;
+	struct devlink_region *region;
+	int err = 0;
+
+	if (WARN_ON(!ops) || WARN_ON(!ops->destructor))
+		return ERR_PTR(-EINVAL);
+
+	mutex_lock(&devlink->lock);
+
+	if (devlink_port_region_get_by_name(port, ops->name)) {
+		err = -EEXIST;
+		goto unlock;
+	}
+
+	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	if (!region) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	region->devlink = devlink;
+	region->port = port;
+	region->max_snapshots = region_max_snapshots;
+	region->port_ops = ops;
+	region->size = region_size;
+	INIT_LIST_HEAD(&region->snapshot_list);
+	list_add_tail(&region->list, &port->region_list);
+	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
+
+	mutex_unlock(&devlink->lock);
+	return region;
+
+unlock:
+	mutex_unlock(&devlink->lock);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(devlink_port_region_create);
+
+/**
  *	devlink_region_destroy - destroy address region
  *
  *	@region: devlink region to destroy
@@ -8803,6 +9491,23 @@ static const struct devlink_trap devlink_trap_generic[] = {
 	DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL),
 	DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL),
 	DEVLINK_TRAP(EARLY_DROP, DROP),
+	DEVLINK_TRAP(VXLAN_PARSING, DROP),
+	DEVLINK_TRAP(LLC_SNAP_PARSING, DROP),
+	DEVLINK_TRAP(VLAN_PARSING, DROP),
+	DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP),
+	DEVLINK_TRAP(MPLS_PARSING, DROP),
+	DEVLINK_TRAP(ARP_PARSING, DROP),
+	DEVLINK_TRAP(IP_1_PARSING, DROP),
+	DEVLINK_TRAP(IP_N_PARSING, DROP),
+	DEVLINK_TRAP(GRE_PARSING, DROP),
+	DEVLINK_TRAP(UDP_PARSING, DROP),
+	DEVLINK_TRAP(TCP_PARSING, DROP),
+	DEVLINK_TRAP(IPSEC_PARSING, DROP),
+	DEVLINK_TRAP(SCTP_PARSING, DROP),
+	DEVLINK_TRAP(DCCP_PARSING, DROP),
+	DEVLINK_TRAP(GTP_PARSING, DROP),
+	DEVLINK_TRAP(ESP_PARSING, DROP),
+	DEVLINK_TRAP(BLACKHOLE_NEXTHOP, DROP),
 };
 
 #define DEVLINK_TRAP_GROUP(_id)						      \
@@ -8837,6 +9542,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = {
 	DEVLINK_TRAP_GROUP(PTP_GENERAL),
 	DEVLINK_TRAP_GROUP(ACL_SAMPLE),
 	DEVLINK_TRAP_GROUP(ACL_TRAP),
+	DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS),
 };
 
 static int devlink_trap_generic_verify(const struct devlink_trap *trap)
@@ -9139,20 +9845,19 @@ devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats,
 }
 
 static void
-devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata,
-				  const struct devlink_trap_item *trap_item,
-				  struct devlink_port *in_devlink_port,
-				  const struct flow_action_cookie *fa_cookie)
+devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata,
+				 const struct devlink_trap_item *trap_item,
+				 struct devlink_port *in_devlink_port,
+				 const struct flow_action_cookie *fa_cookie)
 {
-	struct devlink_trap_group_item *group_item = trap_item->group_item;
-
-	hw_metadata->trap_group_name = group_item->group->name;
-	hw_metadata->trap_name = trap_item->trap->name;
-	hw_metadata->fa_cookie = fa_cookie;
+	metadata->trap_name = trap_item->trap->name;
+	metadata->trap_group_name = trap_item->group_item->group->name;
+	metadata->fa_cookie = fa_cookie;
+	metadata->trap_type = trap_item->trap->type;
 
 	spin_lock(&in_devlink_port->type_lock);
 	if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH)
-		hw_metadata->input_dev = in_devlink_port->type_dev;
+		metadata->input_dev = in_devlink_port->type_dev;
 	spin_unlock(&in_devlink_port->type_lock);
 }
 
@@ -9170,21 +9875,17 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb,
 
 {
 	struct devlink_trap_item *trap_item = trap_ctx;
-	struct net_dm_hw_metadata hw_metadata = {};
 
 	devlink_trap_stats_update(trap_item->stats, skb->len);
 	devlink_trap_stats_update(trap_item->group_item->stats, skb->len);
 
-	/* Control packets were not dropped by the device or encountered an
-	 * exception during forwarding and therefore should not be reported to
-	 * the kernel's drop monitor.
-	 */
-	if (trap_item->trap->type == DEVLINK_TRAP_TYPE_CONTROL)
-		return;
+	if (trace_devlink_trap_report_enabled()) {
+		struct devlink_trap_metadata metadata = {};
 
-	devlink_trap_report_metadata_fill(&hw_metadata, trap_item,
-					  in_devlink_port, fa_cookie);
-	net_dm_hw_report(skb, &hw_metadata);
+		devlink_trap_report_metadata_set(&metadata, trap_item,
+						 in_devlink_port, fa_cookie);
+		trace_devlink_trap_report(devlink, skb, &metadata);
+	}
 }
 EXPORT_SYMBOL_GPL(devlink_trap_report);
 
@@ -9543,6 +10244,7 @@ out:
 
 int devlink_compat_flash_update(struct net_device *dev, const char *file_name)
 {
+	struct devlink_flash_update_params params = {};
 	struct devlink *devlink;
 	int ret;
 
@@ -9555,10 +10257,18 @@ int devlink_compat_flash_update(struct net_device *dev, const char *file_name)
 		goto out;
 	}
 
+	ret = request_firmware(&params.fw, file_name, devlink->dev);
+	if (ret)
+		goto out;
+
 	mutex_lock(&devlink->lock);
-	ret = devlink->ops->flash_update(devlink, file_name, NULL, NULL);
+	devlink_flash_update_begin_notify(devlink);
+	ret = devlink->ops->flash_update(devlink, &params, NULL);
+	devlink_flash_update_end_notify(devlink);
 	mutex_unlock(&devlink->lock);
 
+	release_firmware(params.fw);
+
 out:
 	rtnl_lock();
 	dev_put(dev);
@@ -9605,6 +10315,7 @@ int devlink_compat_switch_id_get(struct net_device *dev,
 static void __net_exit devlink_pernet_pre_exit(struct net *net)
 {
 	struct devlink *devlink;
+	u32 actions_performed;
 	int err;
 
 	/* In case network namespace is getting destroyed, reload
@@ -9613,9 +10324,12 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net)
 	mutex_lock(&devlink_mutex);
 	list_for_each_entry(devlink, &devlink_list, list) {
 		if (net_eq(devlink_net(devlink), net)) {
-			if (WARN_ON(!devlink_reload_supported(devlink)))
+			if (WARN_ON(!devlink_reload_supported(devlink->ops)))
 				continue;
-			err = devlink_reload(devlink, &init_net, NULL);
+			err = devlink_reload(devlink, &init_net,
+					     DEVLINK_RELOAD_ACTION_DRIVER_REINIT,
+					     DEVLINK_RELOAD_LIMIT_UNSPEC,
+					     &actions_performed, NULL);
 			if (err && err != -EOPNOTSUPP)
 				pr_warn("Failed to reload devlink instance into init_net\n");
 		}
diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c
index 9704522b0872..571f191c06d9 100644
--- a/net/core/drop_monitor.c
+++ b/net/core/drop_monitor.c
@@ -26,13 +26,14 @@
 #include <linux/bitops.h>
 #include <linux/slab.h>
 #include <linux/module.h>
-#include <net/drop_monitor.h>
 #include <net/genetlink.h>
 #include <net/netevent.h>
 #include <net/flow_offload.h>
+#include <net/devlink.h>
 
 #include <trace/events/skb.h>
 #include <trace/events/napi.h>
+#include <trace/events/devlink.h>
 
 #include <asm/unaligned.h>
 
@@ -114,13 +115,14 @@ struct net_dm_alert_ops {
 				int work, int budget);
 	void (*work_item_func)(struct work_struct *work);
 	void (*hw_work_item_func)(struct work_struct *work);
-	void (*hw_probe)(struct sk_buff *skb,
-			 const struct net_dm_hw_metadata *hw_metadata);
+	void (*hw_trap_probe)(void *ignore, const struct devlink *devlink,
+			      struct sk_buff *skb,
+			      const struct devlink_trap_metadata *metadata);
 };
 
 struct net_dm_skb_cb {
 	union {
-		struct net_dm_hw_metadata *hw_metadata;
+		struct devlink_trap_metadata *hw_metadata;
 		void *pc;
 	};
 };
@@ -432,8 +434,9 @@ out:
 }
 
 static void
-net_dm_hw_summary_probe(struct sk_buff *skb,
-			const struct net_dm_hw_metadata *hw_metadata)
+net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink,
+			     struct sk_buff *skb,
+			     const struct devlink_trap_metadata *metadata)
 {
 	struct net_dm_hw_entries *hw_entries;
 	struct net_dm_hw_entry *hw_entry;
@@ -441,6 +444,9 @@ net_dm_hw_summary_probe(struct sk_buff *skb,
 	unsigned long flags;
 	int i;
 
+	if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL)
+		return;
+
 	hw_data = this_cpu_ptr(&dm_hw_cpu_data);
 	spin_lock_irqsave(&hw_data->lock, flags);
 	hw_entries = hw_data->hw_entries;
@@ -450,7 +456,7 @@ net_dm_hw_summary_probe(struct sk_buff *skb,
 
 	for (i = 0; i < hw_entries->num_entries; i++) {
 		hw_entry = &hw_entries->entries[i];
-		if (!strncmp(hw_entry->trap_name, hw_metadata->trap_name,
+		if (!strncmp(hw_entry->trap_name, metadata->trap_name,
 			     NET_DM_MAX_HW_TRAP_NAME_LEN - 1)) {
 			hw_entry->count++;
 			goto out;
@@ -460,7 +466,7 @@ net_dm_hw_summary_probe(struct sk_buff *skb,
 		goto out;
 
 	hw_entry = &hw_entries->entries[hw_entries->num_entries];
-	strlcpy(hw_entry->trap_name, hw_metadata->trap_name,
+	strlcpy(hw_entry->trap_name, metadata->trap_name,
 		NET_DM_MAX_HW_TRAP_NAME_LEN - 1);
 	hw_entry->count = 1;
 	hw_entries->num_entries++;
@@ -479,7 +485,7 @@ static const struct net_dm_alert_ops net_dm_alert_summary_ops = {
 	.napi_poll_probe	= trace_napi_poll_hit,
 	.work_item_func		= send_dm_alert,
 	.hw_work_item_func	= net_dm_hw_summary_work,
-	.hw_probe		= net_dm_hw_summary_probe,
+	.hw_trap_probe		= net_dm_hw_trap_summary_probe,
 };
 
 static void net_dm_packet_trace_kfree_skb_hit(void *ignore,
@@ -705,7 +711,7 @@ static void net_dm_packet_work(struct work_struct *work)
 }
 
 static size_t
-net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata)
+net_dm_flow_action_cookie_size(const struct devlink_trap_metadata *hw_metadata)
 {
 	return hw_metadata->fa_cookie ?
 	       nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0;
@@ -713,7 +719,7 @@ net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata)
 
 static size_t
 net_dm_hw_packet_report_size(size_t payload_len,
-			     const struct net_dm_hw_metadata *hw_metadata)
+			     const struct devlink_trap_metadata *hw_metadata)
 {
 	size_t size;
 
@@ -743,7 +749,7 @@ net_dm_hw_packet_report_size(size_t payload_len,
 static int net_dm_hw_packet_report_fill(struct sk_buff *msg,
 					struct sk_buff *skb, size_t payload_len)
 {
-	struct net_dm_hw_metadata *hw_metadata;
+	struct devlink_trap_metadata *hw_metadata;
 	struct nlattr *attr;
 	void *hdr;
 
@@ -810,56 +816,56 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static struct net_dm_hw_metadata *
-net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata)
+static struct devlink_trap_metadata *
+net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata)
 {
 	const struct flow_action_cookie *fa_cookie;
-	struct net_dm_hw_metadata *n_hw_metadata;
+	struct devlink_trap_metadata *hw_metadata;
 	const char *trap_group_name;
 	const char *trap_name;
 
-	n_hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC);
-	if (!n_hw_metadata)
+	hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC);
+	if (!hw_metadata)
 		return NULL;
 
-	trap_group_name = kstrdup(hw_metadata->trap_group_name, GFP_ATOMIC);
+	trap_group_name = kstrdup(metadata->trap_group_name, GFP_ATOMIC);
 	if (!trap_group_name)
 		goto free_hw_metadata;
-	n_hw_metadata->trap_group_name = trap_group_name;
+	hw_metadata->trap_group_name = trap_group_name;
 
-	trap_name = kstrdup(hw_metadata->trap_name, GFP_ATOMIC);
+	trap_name = kstrdup(metadata->trap_name, GFP_ATOMIC);
 	if (!trap_name)
 		goto free_trap_group;
-	n_hw_metadata->trap_name = trap_name;
+	hw_metadata->trap_name = trap_name;
 
-	if (hw_metadata->fa_cookie) {
+	if (metadata->fa_cookie) {
 		size_t cookie_size = sizeof(*fa_cookie) +
-				     hw_metadata->fa_cookie->cookie_len;
+				     metadata->fa_cookie->cookie_len;
 
-		fa_cookie = kmemdup(hw_metadata->fa_cookie, cookie_size,
+		fa_cookie = kmemdup(metadata->fa_cookie, cookie_size,
 				    GFP_ATOMIC);
 		if (!fa_cookie)
 			goto free_trap_name;
-		n_hw_metadata->fa_cookie = fa_cookie;
+		hw_metadata->fa_cookie = fa_cookie;
 	}
 
-	n_hw_metadata->input_dev = hw_metadata->input_dev;
-	if (n_hw_metadata->input_dev)
-		dev_hold(n_hw_metadata->input_dev);
+	hw_metadata->input_dev = metadata->input_dev;
+	if (hw_metadata->input_dev)
+		dev_hold(hw_metadata->input_dev);
 
-	return n_hw_metadata;
+	return hw_metadata;
 
 free_trap_name:
 	kfree(trap_name);
 free_trap_group:
 	kfree(trap_group_name);
 free_hw_metadata:
-	kfree(n_hw_metadata);
+	kfree(hw_metadata);
 	return NULL;
 }
 
 static void
-net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata)
+net_dm_hw_metadata_free(const struct devlink_trap_metadata *hw_metadata)
 {
 	if (hw_metadata->input_dev)
 		dev_put(hw_metadata->input_dev);
@@ -871,7 +877,7 @@ net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata)
 
 static void net_dm_hw_packet_report(struct sk_buff *skb)
 {
-	struct net_dm_hw_metadata *hw_metadata;
+	struct devlink_trap_metadata *hw_metadata;
 	struct sk_buff *msg;
 	size_t payload_len;
 	int rc;
@@ -924,15 +930,19 @@ static void net_dm_hw_packet_work(struct work_struct *work)
 }
 
 static void
-net_dm_hw_packet_probe(struct sk_buff *skb,
-		       const struct net_dm_hw_metadata *hw_metadata)
+net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink,
+			    struct sk_buff *skb,
+			    const struct devlink_trap_metadata *metadata)
 {
-	struct net_dm_hw_metadata *n_hw_metadata;
+	struct devlink_trap_metadata *n_hw_metadata;
 	ktime_t tstamp = ktime_get_real();
 	struct per_cpu_dm_data *hw_data;
 	struct sk_buff *nskb;
 	unsigned long flags;
 
+	if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL)
+		return;
+
 	if (!skb_mac_header_was_set(skb))
 		return;
 
@@ -940,7 +950,7 @@ net_dm_hw_packet_probe(struct sk_buff *skb,
 	if (!nskb)
 		return;
 
-	n_hw_metadata = net_dm_hw_metadata_clone(hw_metadata);
+	n_hw_metadata = net_dm_hw_metadata_copy(metadata);
 	if (!n_hw_metadata)
 		goto free;
 
@@ -975,7 +985,7 @@ static const struct net_dm_alert_ops net_dm_alert_packet_ops = {
 	.napi_poll_probe	= net_dm_packet_trace_napi_poll_hit,
 	.work_item_func		= net_dm_packet_work,
 	.hw_work_item_func	= net_dm_hw_packet_work,
-	.hw_probe		= net_dm_hw_packet_probe,
+	.hw_trap_probe		= net_dm_hw_trap_packet_probe,
 };
 
 static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = {
@@ -983,25 +993,32 @@ static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = {
 	[NET_DM_ALERT_MODE_PACKET]	= &net_dm_alert_packet_ops,
 };
 
-void net_dm_hw_report(struct sk_buff *skb,
-		      const struct net_dm_hw_metadata *hw_metadata)
+#if IS_ENABLED(CONFIG_NET_DEVLINK)
+static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops)
 {
-	rcu_read_lock();
-
-	if (!monitor_hw)
-		goto out;
+	return register_trace_devlink_trap_report(ops->hw_trap_probe, NULL);
+}
 
-	net_dm_alert_ops_arr[net_dm_alert_mode]->hw_probe(skb, hw_metadata);
+static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops)
+{
+	unregister_trace_devlink_trap_report(ops->hw_trap_probe, NULL);
+	tracepoint_synchronize_unregister();
+}
+#else
+static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops)
+{
+	return -EOPNOTSUPP;
+}
 
-out:
-	rcu_read_unlock();
+static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops)
+{
 }
-EXPORT_SYMBOL_GPL(net_dm_hw_report);
+#endif
 
 static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 {
 	const struct net_dm_alert_ops *ops;
-	int cpu;
+	int cpu, rc;
 
 	if (monitor_hw) {
 		NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled");
@@ -1025,13 +1042,24 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack)
 		kfree(hw_entries);
 	}
 
+	rc = net_dm_hw_probe_register(ops);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to devlink_trap_probe() tracepoint");
+		goto err_module_put;
+	}
+
 	monitor_hw = true;
 
 	return 0;
+
+err_module_put:
+	module_put(THIS_MODULE);
+	return rc;
 }
 
 static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 {
+	const struct net_dm_alert_ops *ops;
 	int cpu;
 
 	if (!monitor_hw) {
@@ -1039,12 +1067,11 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 		return;
 	}
 
+	ops = net_dm_alert_ops_arr[net_dm_alert_mode];
+
 	monitor_hw = false;
 
-	/* After this call returns we are guaranteed that no CPU is processing
-	 * any hardware drops.
-	 */
-	synchronize_rcu();
+	net_dm_hw_probe_unregister(ops);
 
 	for_each_possible_cpu(cpu) {
 		struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu);
@@ -1053,7 +1080,7 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack)
 		del_timer_sync(&hw_data->send_timer);
 		cancel_work_sync(&hw_data->dm_alert_work);
 		while ((skb = __skb_dequeue(&hw_data->drop_queue))) {
-			struct net_dm_hw_metadata *hw_metadata;
+			struct devlink_trap_metadata *hw_metadata;
 
 			hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata;
 			net_dm_hw_metadata_free(hw_metadata);
@@ -1548,7 +1575,7 @@ static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = {
 	[NET_DM_ATTR_HW_DROPS]	= {. type = NLA_FLAG },
 };
 
-static const struct genl_ops dropmon_ops[] = {
+static const struct genl_small_ops dropmon_ops[] = {
 	{
 		.cmd = NET_DM_CMD_CONFIG,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -1598,8 +1625,8 @@ static struct genl_family net_drop_monitor_family __ro_after_init = {
 	.pre_doit	= net_dm_nl_pre_doit,
 	.post_doit	= net_dm_nl_post_doit,
 	.module		= THIS_MODULE,
-	.ops		= dropmon_ops,
-	.n_ops		= ARRAY_SIZE(dropmon_ops),
+	.small_ops	= dropmon_ops,
+	.n_small_ops	= ARRAY_SIZE(dropmon_ops),
 	.mcgrps		= dropmon_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(dropmon_mcgrps),
 };
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 7bcfb16854cb..cd80ffed6d26 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -563,7 +563,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct net_device *dev;
 
 		nlrule->iifindex = -1;
-		nla_strlcpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+		nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
 		dev = __dev_get_by_name(net, nlrule->iifname);
 		if (dev)
 			nlrule->iifindex = dev->ifindex;
@@ -573,7 +573,7 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		struct net_device *dev;
 
 		nlrule->oifindex = -1;
-		nla_strlcpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+		nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
 		dev = __dev_get_by_name(net, nlrule->oifname);
 		if (dev)
 			nlrule->oifindex = dev->ifindex;
diff --git a/net/core/filter.c b/net/core/filter.c
index b5f3faac5e3b..255aeee72402 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -76,6 +76,10 @@
 #include <net/bpf_sk_storage.h>
 #include <net/transp_v6.h>
 #include <linux/btf_ids.h>
+#include <net/tls.h>
+
+static const struct bpf_func_proto *
+bpf_sk_base_func_proto(enum bpf_func_id func_id);
 
 int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len)
 {
@@ -2160,13 +2164,266 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev,
 		return __bpf_redirect_no_mac(skb, dev, flags);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
+static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb,
+			    struct net_device *dev, struct bpf_nh_params *nh)
+{
+	u32 hh_len = LL_RESERVED_SPACE(dev);
+	const struct in6_addr *nexthop;
+	struct dst_entry *dst = NULL;
+	struct neighbour *neigh;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		goto out_drop;
+	}
+
+	skb->dev = dev;
+	skb->tstamp = 0;
+
+	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_realloc_headroom(skb, hh_len);
+		if (unlikely(!skb2)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	rcu_read_lock_bh();
+	if (!nh) {
+		dst = skb_dst(skb);
+		nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst),
+				      &ipv6_hdr(skb)->daddr);
+	} else {
+		nexthop = &nh->ipv6_nh;
+	}
+	neigh = ip_neigh_gw6(dev, nexthop);
+	if (likely(!IS_ERR(neigh))) {
+		int ret;
+
+		sock_confirm_neigh(skb, neigh);
+		dev_xmit_recursion_inc();
+		ret = neigh_output(neigh, skb, false);
+		dev_xmit_recursion_dec();
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
+	if (dst)
+		IP6_INC_STATS(dev_net(dst->dev),
+			      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
+out_drop:
+	kfree_skb(skb);
+	return -ENETDOWN;
+}
+
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	struct net *net = dev_net(dev);
+	int err, ret = NET_XMIT_DROP;
+
+	if (!nh) {
+		struct dst_entry *dst;
+		struct flowi6 fl6 = {
+			.flowi6_flags = FLOWI_FLAG_ANYSRC,
+			.flowi6_mark  = skb->mark,
+			.flowlabel    = ip6_flowinfo(ip6h),
+			.flowi6_oif   = dev->ifindex,
+			.flowi6_proto = ip6h->nexthdr,
+			.daddr	      = ip6h->daddr,
+			.saddr	      = ip6h->saddr,
+		};
+
+		dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL);
+		if (IS_ERR(dst))
+			goto out_drop;
+
+		skb_dst_set(skb, dst);
+	} else if (nh->nh_family != AF_INET6) {
+		goto out_drop;
+	}
+
+	err = bpf_out_neigh_v6(net, skb, dev, nh);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out_xmit;
+out_drop:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out_xmit:
+	return ret;
+}
+#else
+static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+#endif /* CONFIG_IPV6 */
+
+#if IS_ENABLED(CONFIG_INET)
+static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb,
+			    struct net_device *dev, struct bpf_nh_params *nh)
+{
+	u32 hh_len = LL_RESERVED_SPACE(dev);
+	struct neighbour *neigh;
+	bool is_v6gw = false;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n");
+		goto out_drop;
+	}
+
+	skb->dev = dev;
+	skb->tstamp = 0;
+
+	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
+		struct sk_buff *skb2;
+
+		skb2 = skb_realloc_headroom(skb, hh_len);
+		if (unlikely(!skb2)) {
+			kfree_skb(skb);
+			return -ENOMEM;
+		}
+		if (skb->sk)
+			skb_set_owner_w(skb2, skb->sk);
+		consume_skb(skb);
+		skb = skb2;
+	}
+
+	rcu_read_lock_bh();
+	if (!nh) {
+		struct dst_entry *dst = skb_dst(skb);
+		struct rtable *rt = container_of(dst, struct rtable, dst);
+
+		neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
+	} else if (nh->nh_family == AF_INET6) {
+		neigh = ip_neigh_gw6(dev, &nh->ipv6_nh);
+		is_v6gw = true;
+	} else if (nh->nh_family == AF_INET) {
+		neigh = ip_neigh_gw4(dev, nh->ipv4_nh);
+	} else {
+		rcu_read_unlock_bh();
+		goto out_drop;
+	}
+
+	if (likely(!IS_ERR(neigh))) {
+		int ret;
+
+		sock_confirm_neigh(skb, neigh);
+		dev_xmit_recursion_inc();
+		ret = neigh_output(neigh, skb, is_v6gw);
+		dev_xmit_recursion_dec();
+		rcu_read_unlock_bh();
+		return ret;
+	}
+	rcu_read_unlock_bh();
+out_drop:
+	kfree_skb(skb);
+	return -ENETDOWN;
+}
+
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
+{
+	const struct iphdr *ip4h = ip_hdr(skb);
+	struct net *net = dev_net(dev);
+	int err, ret = NET_XMIT_DROP;
+
+	if (!nh) {
+		struct flowi4 fl4 = {
+			.flowi4_flags = FLOWI_FLAG_ANYSRC,
+			.flowi4_mark  = skb->mark,
+			.flowi4_tos   = RT_TOS(ip4h->tos),
+			.flowi4_oif   = dev->ifindex,
+			.flowi4_proto = ip4h->protocol,
+			.daddr	      = ip4h->daddr,
+			.saddr	      = ip4h->saddr,
+		};
+		struct rtable *rt;
+
+		rt = ip_route_output_flow(net, &fl4, NULL);
+		if (IS_ERR(rt))
+			goto out_drop;
+		if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) {
+			ip_rt_put(rt);
+			goto out_drop;
+		}
+
+		skb_dst_set(skb, &rt->dst);
+	}
+
+	err = bpf_out_neigh_v4(net, skb, dev, nh);
+	if (unlikely(net_xmit_eval(err)))
+		dev->stats.tx_errors++;
+	else
+		ret = NET_XMIT_SUCCESS;
+	goto out_xmit;
+out_drop:
+	dev->stats.tx_errors++;
+	kfree_skb(skb);
+out_xmit:
+	return ret;
+}
+#else
+static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
+				   struct bpf_nh_params *nh)
+{
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
+#endif /* CONFIG_INET */
+
+static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev,
+				struct bpf_nh_params *nh)
+{
+	struct ethhdr *ethh = eth_hdr(skb);
+
+	if (unlikely(skb->mac_header >= skb->network_header))
+		goto out;
+	bpf_push_mac_rcsum(skb);
+	if (is_multicast_ether_addr(ethh->h_dest))
+		goto out;
+
+	skb_pull(skb, sizeof(*ethh));
+	skb_unset_mac_header(skb);
+	skb_reset_network_header(skb);
+
+	if (skb->protocol == htons(ETH_P_IP))
+		return __bpf_redirect_neigh_v4(skb, dev, nh);
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		return __bpf_redirect_neigh_v6(skb, dev, nh);
+out:
+	kfree_skb(skb);
+	return -ENOTSUPP;
+}
+
+/* Internal, non-exposed redirect flags. */
+enum {
+	BPF_F_NEIGH	= (1ULL << 1),
+	BPF_F_PEER	= (1ULL << 2),
+	BPF_F_NEXTHOP	= (1ULL << 3),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER | BPF_F_NEXTHOP)
+};
+
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
 {
 	struct net_device *dev;
 	struct sk_buff *clone;
 	int ret;
 
-	if (unlikely(flags & ~(BPF_F_INGRESS)))
+	if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
 		return -EINVAL;
 
 	dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex);
@@ -2203,11 +2460,46 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
 DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
 EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 
+int skb_do_redirect(struct sk_buff *skb)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct net *net = dev_net(skb->dev);
+	struct net_device *dev;
+	u32 flags = ri->flags;
+
+	dev = dev_get_by_index_rcu(net, ri->tgt_index);
+	ri->tgt_index = 0;
+	ri->flags = 0;
+	if (unlikely(!dev))
+		goto out_drop;
+	if (flags & BPF_F_PEER) {
+		const struct net_device_ops *ops = dev->netdev_ops;
+
+		if (unlikely(!ops->ndo_get_peer_dev ||
+			     !skb_at_tc_ingress(skb)))
+			goto out_drop;
+		dev = ops->ndo_get_peer_dev(dev);
+		if (unlikely(!dev ||
+			     !is_skb_forwardable(dev, skb) ||
+			     net_eq(net, dev_net(dev))))
+			goto out_drop;
+		skb->dev = dev;
+		return -EAGAIN;
+	}
+	return flags & BPF_F_NEIGH ?
+	       __bpf_redirect_neigh(skb, dev, flags & BPF_F_NEXTHOP ?
+				    &ri->nh : NULL) :
+	       __bpf_redirect(skb, dev, flags);
+out_drop:
+	kfree_skb(skb);
+	return -EINVAL;
+}
+
 BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
-	if (unlikely(flags & ~(BPF_F_INGRESS)))
+	if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
 		return TC_ACT_SHOT;
 
 	ri->flags = flags;
@@ -2216,29 +2508,63 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
 	return TC_ACT_REDIRECT;
 }
 
-int skb_do_redirect(struct sk_buff *skb)
+static const struct bpf_func_proto bpf_redirect_proto = {
+	.func           = bpf_redirect,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_ANYTHING,
+	.arg2_type      = ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
-	struct net_device *dev;
 
-	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
-	ri->tgt_index = 0;
-	if (unlikely(!dev)) {
-		kfree_skb(skb);
-		return -EINVAL;
-	}
+	if (unlikely(flags))
+		return TC_ACT_SHOT;
+
+	ri->flags = BPF_F_PEER;
+	ri->tgt_index = ifindex;
 
-	return __bpf_redirect(skb, dev, ri->flags);
+	return TC_ACT_REDIRECT;
 }
 
-static const struct bpf_func_proto bpf_redirect_proto = {
-	.func           = bpf_redirect,
+static const struct bpf_func_proto bpf_redirect_peer_proto = {
+	.func           = bpf_redirect_peer,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
 	.arg1_type      = ARG_ANYTHING,
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params,
+	   int, plen, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely((plen && plen < sizeof(*params)) || flags))
+		return TC_ACT_SHOT;
+
+	ri->flags = BPF_F_NEIGH | (plen ? BPF_F_NEXTHOP : 0);
+	ri->tgt_index = ifindex;
+
+	BUILD_BUG_ON(sizeof(struct bpf_redir_neigh) != sizeof(struct bpf_nh_params));
+	if (plen)
+		memcpy(&ri->nh, params, sizeof(ri->nh));
+
+	return TC_ACT_REDIRECT;
+}
+
+static const struct bpf_func_proto bpf_redirect_neigh_proto = {
+	.func		= bpf_redirect_neigh,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+	.arg2_type      = ARG_PTR_TO_MEM_OR_NULL,
+	.arg3_type      = ARG_CONST_SIZE_OR_ZERO,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes)
 {
 	msg->apply_bytes = bytes;
@@ -2704,6 +3030,23 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 };
+
+BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb)
+{
+	struct sock *sk = skb_to_full_sk(skb);
+
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
+	return sock_cgroup_classid(&sk->sk_cgrp_data);
+}
+
+static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = {
+	.func		= bpf_skb_cgroup_classid,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
 #endif
 
 BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb)
@@ -3215,6 +3558,48 @@ static u32 __bpf_skb_max_len(const struct sk_buff *skb)
 			  SKB_MAX_ALLOC;
 }
 
+BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
+	   u32, mode, u64, flags)
+{
+	u32 len_diff_abs = abs(len_diff);
+	bool shrink = len_diff < 0;
+	int ret = 0;
+
+	if (unlikely(flags || mode))
+		return -EINVAL;
+	if (unlikely(len_diff_abs > 0xfffU))
+		return -EFAULT;
+
+	if (!shrink) {
+		ret = skb_cow(skb, len_diff);
+		if (unlikely(ret < 0))
+			return ret;
+		__skb_push(skb, len_diff_abs);
+		memset(skb->data, 0, len_diff_abs);
+	} else {
+		if (unlikely(!pskb_may_pull(skb, len_diff_abs)))
+			return -ENOMEM;
+		__skb_pull(skb, len_diff_abs);
+	}
+	bpf_compute_data_end_sk_skb(skb);
+	if (tls_sw_has_ctx_rx(skb->sk)) {
+		struct strp_msg *rxm = strp_msg(skb);
+
+		rxm->full_len += len_diff;
+	}
+	return ret;
+}
+
+static const struct bpf_func_proto sk_skb_adjust_room_proto = {
+	.func		= sk_skb_adjust_room,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	   u32, mode, u64, flags)
 {
@@ -3803,19 +4188,18 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-BTF_ID_LIST(bpf_skb_output_btf_ids)
-BTF_ID(struct, sk_buff)
+BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff)
 
 const struct bpf_func_proto bpf_skb_output_proto = {
 	.func		= bpf_skb_event_output,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_skb_output_btf_ids[0],
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_skb_output_btf_ids,
 };
 
 static unsigned short bpf_tunnel_key_af(u64 flags)
@@ -4086,18 +4470,17 @@ static inline u64 __bpf_sk_cgroup_id(struct sock *sk)
 {
 	struct cgroup *cgrp;
 
+	sk = sk_to_full_sk(sk);
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 	return cgroup_id(cgrp);
 }
 
 BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb)
 {
-	struct sock *sk = skb_to_full_sk(skb);
-
-	if (!sk || !sk_fullsock(sk))
-		return 0;
-
-	return __bpf_sk_cgroup_id(sk);
+	return __bpf_sk_cgroup_id(skb->sk);
 }
 
 static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
@@ -4113,6 +4496,10 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk,
 	struct cgroup *ancestor;
 	struct cgroup *cgrp;
 
+	sk = sk_to_full_sk(sk);
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 	ancestor = cgroup_ancestor(cgrp, ancestor_level);
 	if (!ancestor)
@@ -4124,12 +4511,7 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk,
 BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
 	   ancestor_level)
 {
-	struct sock *sk = skb_to_full_sk(skb);
-
-	if (!sk || !sk_fullsock(sk))
-		return 0;
-
-	return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level);
+	return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level);
 }
 
 static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
@@ -4149,7 +4531,7 @@ static const struct bpf_func_proto bpf_sk_cgroup_id_proto = {
 	.func           = bpf_sk_cgroup_id,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_PTR_TO_SOCKET,
+	.arg1_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 };
 
 BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level)
@@ -4161,7 +4543,7 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = {
 	.func           = bpf_sk_ancestor_cgroup_id,
 	.gpl_only       = false,
 	.ret_type       = RET_INTEGER,
-	.arg1_type      = ARG_PTR_TO_SOCKET,
+	.arg1_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg2_type      = ARG_ANYTHING,
 };
 #endif
@@ -4199,24 +4581,23 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = {
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
-BTF_ID_LIST(bpf_xdp_output_btf_ids)
-BTF_ID(struct, xdp_buff)
+BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff)
 
 const struct bpf_func_proto bpf_xdp_output_proto = {
 	.func		= bpf_xdp_event_output,
 	.gpl_only	= true,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_xdp_output_btf_ids[0],
 	.arg2_type	= ARG_CONST_MAP_PTR,
 	.arg3_type	= ARG_ANYTHING,
 	.arg4_type	= ARG_PTR_TO_MEM,
 	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
-	.btf_id		= bpf_xdp_output_btf_ids,
 };
 
 BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb)
 {
-	return skb->sk ? sock_gen_cookie(skb->sk) : 0;
+	return skb->sk ? __sock_gen_cookie(skb->sk) : 0;
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
@@ -4228,7 +4609,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx)
 {
-	return sock_gen_cookie(ctx->sk);
+	return __sock_gen_cookie(ctx->sk);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
@@ -4240,7 +4621,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx)
 {
-	return sock_gen_cookie(ctx);
+	return __sock_gen_cookie(ctx);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
@@ -4252,7 +4633,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = {
 
 BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
 {
-	return sock_gen_cookie(ctx->sk);
+	return __sock_gen_cookie(ctx->sk);
 }
 
 static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
@@ -4265,7 +4646,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
 static u64 __bpf_get_netns_cookie(struct sock *sk)
 {
 #ifdef CONFIG_NET_NS
-	return net_gen_cookie(sk ? sk->sk_net.net : &init_net);
+	return __net_gen_cookie(sk ? sk->sk_net.net : &init_net);
 #else
 	return 0;
 #endif
@@ -4313,10 +4694,8 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-#define SOCKOPT_CC_REINIT (1 << 0)
-
 static int _bpf_setsockopt(struct sock *sk, int level, int optname,
-			   char *optval, int optlen, u32 flags)
+			   char *optval, int optlen)
 {
 	char devname[IFNAMSIZ];
 	int val, valbool;
@@ -4354,7 +4733,8 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 				cmpxchg(&sk->sk_pacing_status,
 					SK_PACING_NONE,
 					SK_PACING_NEEDED);
-			sk->sk_max_pacing_rate = (val == ~0U) ? ~0UL : val;
+			sk->sk_max_pacing_rate = (val == ~0U) ?
+						 ~0UL : (unsigned int)val;
 			sk->sk_pacing_rate = min(sk->sk_pacing_rate,
 						 sk->sk_max_pacing_rate);
 			break;
@@ -4449,16 +4829,15 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 		   sk->sk_prot->setsockopt == tcp_setsockopt) {
 		if (optname == TCP_CONGESTION) {
 			char name[TCP_CA_NAME_MAX];
-			bool reinit = flags & SOCKOPT_CC_REINIT;
 
 			strncpy(name, optval, min_t(long, optlen,
 						    TCP_CA_NAME_MAX-1));
 			name[TCP_CA_NAME_MAX-1] = 0;
-			ret = tcp_set_congestion_control(sk, name, false,
-							 reinit, true);
+			ret = tcp_set_congestion_control(sk, name, false, true);
 		} else {
 			struct inet_connection_sock *icsk = inet_csk(sk);
 			struct tcp_sock *tp = tcp_sk(sk);
+			unsigned long timeout;
 
 			if (optlen != sizeof(int))
 				return -EINVAL;
@@ -4480,6 +4859,20 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 					tp->snd_ssthresh = val;
 				}
 				break;
+			case TCP_BPF_DELACK_MAX:
+				timeout = usecs_to_jiffies(val);
+				if (timeout > TCP_DELACK_MAX ||
+				    timeout < TCP_TIMEOUT_MIN)
+					return -EINVAL;
+				inet_csk(sk)->icsk_delack_max = timeout;
+				break;
+			case TCP_BPF_RTO_MIN:
+				timeout = usecs_to_jiffies(val);
+				if (timeout > TCP_RTO_MIN ||
+				    timeout < TCP_TIMEOUT_MIN)
+					return -EINVAL;
+				inet_csk(sk)->icsk_rto_min = timeout;
+				break;
 			case TCP_SAVE_SYN:
 				if (val < 0 || val > 1)
 					ret = -EINVAL;
@@ -4513,6 +4906,13 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 				else
 					icsk->icsk_user_timeout = val;
 				break;
+			case TCP_NOTSENT_LOWAT:
+				tp->notsent_lowat = val;
+				sk->sk_write_space(sk);
+				break;
+			case TCP_WINDOW_CLAMP:
+				ret = tcp_set_window_clamp(sk, val);
+				break;
 			default:
 				ret = -EINVAL;
 			}
@@ -4550,9 +4950,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname,
 			tp = tcp_sk(sk);
 
 			if (optlen <= 0 || !tp->saved_syn ||
-			    optlen > tp->saved_syn[0])
+			    optlen > tcp_saved_syn_len(tp->saved_syn))
 				goto err_clear;
-			memcpy(optval, tp->saved_syn + 1, optlen);
+			memcpy(optval, tp->saved_syn->data, optlen);
 			break;
 		default:
 			goto err_clear;
@@ -4600,9 +5000,7 @@ err_clear:
 BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
-	u32 flags = 0;
-	return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen,
-			       flags);
+	return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = {
@@ -4636,11 +5034,7 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = {
 BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
-	u32 flags = 0;
-	if (bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN)
-		flags |= SOCKOPT_CC_REINIT;
-	return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen,
-			       flags);
+	return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen);
 }
 
 static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = {
@@ -4654,9 +5048,99 @@ static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock,
+				int optname, const u8 **start)
+{
+	struct sk_buff *syn_skb = bpf_sock->syn_skb;
+	const u8 *hdr_start;
+	int ret;
+
+	if (syn_skb) {
+		/* sk is a request_sock here */
+
+		if (optname == TCP_BPF_SYN) {
+			hdr_start = syn_skb->data;
+			ret = tcp_hdrlen(syn_skb);
+		} else if (optname == TCP_BPF_SYN_IP) {
+			hdr_start = skb_network_header(syn_skb);
+			ret = skb_network_header_len(syn_skb) +
+				tcp_hdrlen(syn_skb);
+		} else {
+			/* optname == TCP_BPF_SYN_MAC */
+			hdr_start = skb_mac_header(syn_skb);
+			ret = skb_mac_header_len(syn_skb) +
+				skb_network_header_len(syn_skb) +
+				tcp_hdrlen(syn_skb);
+		}
+	} else {
+		struct sock *sk = bpf_sock->sk;
+		struct saved_syn *saved_syn;
+
+		if (sk->sk_state == TCP_NEW_SYN_RECV)
+			/* synack retransmit. bpf_sock->syn_skb will
+			 * not be available.  It has to resort to
+			 * saved_syn (if it is saved).
+			 */
+			saved_syn = inet_reqsk(sk)->saved_syn;
+		else
+			saved_syn = tcp_sk(sk)->saved_syn;
+
+		if (!saved_syn)
+			return -ENOENT;
+
+		if (optname == TCP_BPF_SYN) {
+			hdr_start = saved_syn->data +
+				saved_syn->mac_hdrlen +
+				saved_syn->network_hdrlen;
+			ret = saved_syn->tcp_hdrlen;
+		} else if (optname == TCP_BPF_SYN_IP) {
+			hdr_start = saved_syn->data +
+				saved_syn->mac_hdrlen;
+			ret = saved_syn->network_hdrlen +
+				saved_syn->tcp_hdrlen;
+		} else {
+			/* optname == TCP_BPF_SYN_MAC */
+
+			/* TCP_SAVE_SYN may not have saved the mac hdr */
+			if (!saved_syn->mac_hdrlen)
+				return -ENOENT;
+
+			hdr_start = saved_syn->data;
+			ret = saved_syn->mac_hdrlen +
+				saved_syn->network_hdrlen +
+				saved_syn->tcp_hdrlen;
+		}
+	}
+
+	*start = hdr_start;
+	return ret;
+}
+
 BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
+	if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP &&
+	    optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) {
+		int ret, copy_len = 0;
+		const u8 *start;
+
+		ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start);
+		if (ret > 0) {
+			copy_len = ret;
+			if (optlen < copy_len) {
+				copy_len = optlen;
+				ret = -ENOSPC;
+			}
+
+			memcpy(optval, start, copy_len);
+		}
+
+		/* Zero out unused buffer at the end */
+		memset(optval + copy_len, 0, optlen - copy_len);
+
+		return ret;
+	}
+
 	return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen);
 }
 
@@ -4794,7 +5278,6 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params,
 	memcpy(params->smac, dev->dev_addr, ETH_ALEN);
 	params->h_vlan_TCI = 0;
 	params->h_vlan_proto = 0;
-	params->ifindex = dev->ifindex;
 
 	return 0;
 }
@@ -4891,6 +5374,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 	dev = nhc->nhc_dev;
 
 	params->rt_metric = res.fi->fib_priority;
+	params->ifindex = dev->ifindex;
 
 	/* xdp and cls_bpf programs are run in RCU-bh so
 	 * rcu_read_lock_bh is not needed here
@@ -5016,6 +5500,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params,
 
 	dev = res.nh->fib_nh_dev;
 	params->rt_metric = res.f6i->fib6_metric;
+	params->ifindex = dev->ifindex;
 
 	/* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is
 	 * not needed here.
@@ -5601,7 +6086,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
 
 BPF_CALL_1(bpf_sk_release, struct sock *, sk)
 {
-	if (sk_is_refcounted(sk))
+	if (sk && sk_is_refcounted(sk))
 		sock_gen_put(sk);
 	return 0;
 }
@@ -5610,7 +6095,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
 	.func		= bpf_sk_release,
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 };
 
 BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
@@ -5992,7 +6477,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len
 	u32 cookie;
 	int ret;
 
-	if (unlikely(th_len < sizeof(*th)))
+	if (unlikely(!sk || th_len < sizeof(*th)))
 		return -EINVAL;
 
 	/* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */
@@ -6045,7 +6530,7 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = {
 	.gpl_only	= true,
 	.pkt_access	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type	= ARG_PTR_TO_MEM,
@@ -6059,7 +6544,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
 	u32 cookie;
 	u16 mss;
 
-	if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4))
+	if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4))
 		return -EINVAL;
 
 	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
@@ -6114,7 +6599,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
 	.gpl_only	= true, /* __cookie_v*_init_sequence() is GPL */
 	.pkt_access	= true,
 	.ret_type	= RET_INTEGER,
-	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg1_type	= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.arg2_type	= ARG_PTR_TO_MEM,
 	.arg3_type	= ARG_CONST_SIZE,
 	.arg4_type	= ARG_PTR_TO_MEM,
@@ -6123,7 +6608,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = {
 
 BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags)
 {
-	if (flags != 0)
+	if (!sk || flags != 0)
 		return -EINVAL;
 	if (!skb_at_tc_ingress(skb))
 		return -EOPNOTSUPP;
@@ -6147,7 +6632,233 @@ static const struct bpf_func_proto bpf_sk_assign_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
-	.arg2_type      = ARG_PTR_TO_SOCK_COMMON,
+	.arg2_type      = ARG_PTR_TO_BTF_ID_SOCK_COMMON,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend,
+				    u8 search_kind, const u8 *magic,
+				    u8 magic_len, bool *eol)
+{
+	u8 kind, kind_len;
+
+	*eol = false;
+
+	while (op < opend) {
+		kind = op[0];
+
+		if (kind == TCPOPT_EOL) {
+			*eol = true;
+			return ERR_PTR(-ENOMSG);
+		} else if (kind == TCPOPT_NOP) {
+			op++;
+			continue;
+		}
+
+		if (opend - op < 2 || opend - op < op[1] || op[1] < 2)
+			/* Something is wrong in the received header.
+			 * Follow the TCP stack's tcp_parse_options()
+			 * and just bail here.
+			 */
+			return ERR_PTR(-EFAULT);
+
+		kind_len = op[1];
+		if (search_kind == kind) {
+			if (!magic_len)
+				return op;
+
+			if (magic_len > kind_len - 2)
+				return ERR_PTR(-ENOMSG);
+
+			if (!memcmp(&op[2], magic, magic_len))
+				return op;
+		}
+
+		op += kind_len;
+	}
+
+	return ERR_PTR(-ENOMSG);
+}
+
+BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
+	   void *, search_res, u32, len, u64, flags)
+{
+	bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN;
+	const u8 *op, *opend, *magic, *search = search_res;
+	u8 search_kind, search_len, copy_len, magic_len;
+	int ret;
+
+	/* 2 byte is the minimal option len except TCPOPT_NOP and
+	 * TCPOPT_EOL which are useless for the bpf prog to learn
+	 * and this helper disallow loading them also.
+	 */
+	if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN)
+		return -EINVAL;
+
+	search_kind = search[0];
+	search_len = search[1];
+
+	if (search_len > len || search_kind == TCPOPT_NOP ||
+	    search_kind == TCPOPT_EOL)
+		return -EINVAL;
+
+	if (search_kind == TCPOPT_EXP || search_kind == 253) {
+		/* 16 or 32 bit magic.  +2 for kind and kind length */
+		if (search_len != 4 && search_len != 6)
+			return -EINVAL;
+		magic = &search[2];
+		magic_len = search_len - 2;
+	} else {
+		if (search_len)
+			return -EINVAL;
+		magic = NULL;
+		magic_len = 0;
+	}
+
+	if (load_syn) {
+		ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op);
+		if (ret < 0)
+			return ret;
+
+		opend = op + ret;
+		op += sizeof(struct tcphdr);
+	} else {
+		if (!bpf_sock->skb ||
+		    bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB)
+			/* This bpf_sock->op cannot call this helper */
+			return -EPERM;
+
+		opend = bpf_sock->skb_data_end;
+		op = bpf_sock->skb->data + sizeof(struct tcphdr);
+	}
+
+	op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len,
+				&eol);
+	if (IS_ERR(op))
+		return PTR_ERR(op);
+
+	copy_len = op[1];
+	ret = copy_len;
+	if (copy_len > len) {
+		ret = -ENOSPC;
+		copy_len = len;
+	}
+
+	memcpy(search_res, op, copy_len);
+	return ret;
+}
+
+static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = {
+	.func		= bpf_sock_ops_load_hdr_opt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
+	   const void *, from, u32, len, u64, flags)
+{
+	u8 new_kind, new_kind_len, magic_len = 0, *opend;
+	const u8 *op, *new_op, *magic = NULL;
+	struct sk_buff *skb;
+	bool eol;
+
+	if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB)
+		return -EPERM;
+
+	if (len < 2 || flags)
+		return -EINVAL;
+
+	new_op = from;
+	new_kind = new_op[0];
+	new_kind_len = new_op[1];
+
+	if (new_kind_len > len || new_kind == TCPOPT_NOP ||
+	    new_kind == TCPOPT_EOL)
+		return -EINVAL;
+
+	if (new_kind_len > bpf_sock->remaining_opt_len)
+		return -ENOSPC;
+
+	/* 253 is another experimental kind */
+	if (new_kind == TCPOPT_EXP || new_kind == 253)  {
+		if (new_kind_len < 4)
+			return -EINVAL;
+		/* Match for the 2 byte magic also.
+		 * RFC 6994: the magic could be 2 or 4 bytes.
+		 * Hence, matching by 2 byte only is on the
+		 * conservative side but it is the right
+		 * thing to do for the 'search-for-duplication'
+		 * purpose.
+		 */
+		magic = &new_op[2];
+		magic_len = 2;
+	}
+
+	/* Check for duplication */
+	skb = bpf_sock->skb;
+	op = skb->data + sizeof(struct tcphdr);
+	opend = bpf_sock->skb_data_end;
+
+	op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len,
+				&eol);
+	if (!IS_ERR(op))
+		return -EEXIST;
+
+	if (PTR_ERR(op) != -ENOMSG)
+		return PTR_ERR(op);
+
+	if (eol)
+		/* The option has been ended.  Treat it as no more
+		 * header option can be written.
+		 */
+		return -ENOSPC;
+
+	/* No duplication found.  Store the header option. */
+	memcpy(opend, from, new_kind_len);
+
+	bpf_sock->remaining_opt_len -= new_kind_len;
+	bpf_sock->skb_data_end += new_kind_len;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = {
+	.func		= bpf_sock_ops_store_hdr_opt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
+	   u32, len, u64, flags)
+{
+	if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB)
+		return -EPERM;
+
+	if (flags || len < 2)
+		return -EINVAL;
+
+	if (len > bpf_sock->remaining_opt_len)
+		return -ENOSPC;
+
+	bpf_sock->remaining_opt_len -= len;
+
+	return 0;
+}
+
+static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = {
+	.func		= bpf_sock_ops_reserve_hdr_opt,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
 	.arg3_type	= ARG_ANYTHING,
 };
 
@@ -6164,6 +6875,7 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_skb_change_tail ||
 	    func == sk_skb_change_tail ||
 	    func == bpf_skb_adjust_room ||
+	    func == sk_skb_adjust_room ||
 	    func == bpf_skb_pull_data ||
 	    func == sk_skb_pull_data ||
 	    func == bpf_clone_redirect ||
@@ -6180,6 +6892,9 @@ bool bpf_helper_changes_pkt_data(void *func)
 	    func == bpf_lwt_seg6_adjust_srh ||
 	    func == bpf_lwt_seg6_action ||
 #endif
+#ifdef CONFIG_INET
+	    func == bpf_sock_ops_store_hdr_opt ||
+#endif
 	    func == bpf_lwt_in_push_encap ||
 	    func == bpf_lwt_xmit_push_encap)
 		return true;
@@ -6283,6 +6998,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_delete_proto;
 	case BPF_FUNC_setsockopt:
 		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_BIND:
+		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
 			return &bpf_sock_addr_setsockopt_proto;
@@ -6291,6 +7008,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		}
 	case BPF_FUNC_getsockopt:
 		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_BIND:
+		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
 			return &bpf_sock_addr_getsockopt_proto;
@@ -6298,7 +7017,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 			return NULL;
 		}
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6317,7 +7036,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_perf_event_output:
 		return &bpf_skb_event_output_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6419,6 +7138,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return bpf_get_skb_set_tunnel_proto(func_id);
 	case BPF_FUNC_redirect:
 		return &bpf_redirect_proto;
+	case BPF_FUNC_redirect_neigh:
+		return &bpf_redirect_neigh_proto;
+	case BPF_FUNC_redirect_peer:
+		return &bpf_redirect_peer_proto;
 	case BPF_FUNC_get_route_realm:
 		return &bpf_get_route_realm_proto;
 	case BPF_FUNC_get_hash_recalc:
@@ -6449,6 +7172,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_get_xfrm_state:
 		return &bpf_skb_get_xfrm_state_proto;
 #endif
+#ifdef CONFIG_CGROUP_NET_CLASSID
+	case BPF_FUNC_skb_cgroup_classid:
+		return &bpf_skb_cgroup_classid_proto;
+#endif
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case BPF_FUNC_skb_cgroup_id:
 		return &bpf_skb_cgroup_id_proto;
@@ -6478,7 +7205,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_assign_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6519,7 +7246,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_gen_syncookie_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6551,11 +7278,17 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_storage_delete:
 		return &bpf_sk_storage_delete_proto;
 #ifdef CONFIG_INET
+	case BPF_FUNC_load_hdr_opt:
+		return &bpf_sock_ops_load_hdr_opt_proto;
+	case BPF_FUNC_store_hdr_opt:
+		return &bpf_sock_ops_store_hdr_opt_proto;
+	case BPF_FUNC_reserve_hdr_opt:
+		return &bpf_sock_ops_reserve_hdr_opt_proto;
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
 #endif /* CONFIG_INET */
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6601,7 +7334,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_cgroup_classid_curr_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6622,6 +7355,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &sk_skb_change_tail_proto;
 	case BPF_FUNC_skb_change_head:
 		return &sk_skb_change_head_proto;
+	case BPF_FUNC_skb_adjust_room:
+		return &sk_skb_adjust_room_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
@@ -6643,7 +7378,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6654,7 +7389,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_load_bytes:
 		return &bpf_flow_dissector_load_bytes_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -6681,7 +7416,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_skb_under_cgroup:
 		return &bpf_skb_under_cgroup_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -7350,6 +8085,20 @@ static bool sock_ops_is_valid_access(int off, int size,
 				return false;
 			info->reg_type = PTR_TO_SOCKET_OR_NULL;
 			break;
+		case offsetof(struct bpf_sock_ops, skb_data):
+			if (size != sizeof(__u64))
+				return false;
+			info->reg_type = PTR_TO_PACKET;
+			break;
+		case offsetof(struct bpf_sock_ops, skb_data_end):
+			if (size != sizeof(__u64))
+				return false;
+			info->reg_type = PTR_TO_PACKET_END;
+			break;
+		case offsetof(struct bpf_sock_ops, skb_tcp_flags):
+			bpf_ctx_record_field_size(info, size_default);
+			return bpf_ctx_narrow_access_ok(off, size,
+							size_default);
 		default:
 			if (size != size_default)
 				return false;
@@ -8451,17 +9200,22 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		return insn - insn_buf;
 
 	switch (si->off) {
-	case offsetof(struct bpf_sock_ops, op) ...
+	case offsetof(struct bpf_sock_ops, op):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       op),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern, op));
+		break;
+
+	case offsetof(struct bpf_sock_ops, replylong[0]) ...
 	     offsetof(struct bpf_sock_ops, replylong[3]):
-		BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) !=
-			     sizeof_field(struct bpf_sock_ops_kern, op));
 		BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) !=
 			     sizeof_field(struct bpf_sock_ops_kern, reply));
 		BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) !=
 			     sizeof_field(struct bpf_sock_ops_kern, replylong));
 		off = si->off;
-		off -= offsetof(struct bpf_sock_ops, op);
-		off += offsetof(struct bpf_sock_ops_kern, op);
+		off -= offsetof(struct bpf_sock_ops, replylong[0]);
+		off += offsetof(struct bpf_sock_ops_kern, replylong[0]);
 		if (type == BPF_WRITE)
 			*insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg,
 					      off);
@@ -8682,6 +9436,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct bpf_sock_ops, sk):
 		SOCK_OPS_GET_SK();
 		break;
+	case offsetof(struct bpf_sock_ops, skb_data_end):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       skb_data_end),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern,
+					       skb_data_end));
+		break;
+	case offsetof(struct bpf_sock_ops, skb_data):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       skb),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern,
+					       skb));
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data),
+				      si->dst_reg, si->dst_reg,
+				      offsetof(struct sk_buff, data));
+		break;
+	case offsetof(struct bpf_sock_ops, skb_len):
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       skb),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern,
+					       skb));
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len),
+				      si->dst_reg, si->dst_reg,
+				      offsetof(struct sk_buff, len));
+		break;
+	case offsetof(struct bpf_sock_ops, skb_tcp_flags):
+		off = offsetof(struct sk_buff, cb);
+		off += offsetof(struct tcp_skb_cb, tcp_flags);
+		*target_size = sizeof_field(struct tcp_skb_cb, tcp_flags);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern,
+						       skb),
+				      si->dst_reg, si->src_reg,
+				      offsetof(struct bpf_sock_ops_kern,
+					       skb));
+		*insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1);
+		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb,
+						       tcp_flags),
+				      si->dst_reg, si->dst_reg, off);
+		break;
 	}
 	return insn - insn_buf;
 }
@@ -9356,7 +10153,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
 	default:
-		return bpf_base_func_proto(func_id);
+		return bpf_sk_base_func_proto(func_id);
 	}
 }
 
@@ -9506,17 +10303,6 @@ BTF_SOCK_TYPE_xxx
 u32 btf_sock_ids[MAX_BTF_SOCK_TYPE];
 #endif
 
-static bool check_arg_btf_id(u32 btf_id, u32 arg)
-{
-	int i;
-
-	/* only one argument, no need to check arg */
-	for (i = 0; i < MAX_BTF_SOCK_TYPE; i++)
-		if (btf_sock_ids[i] == btf_id)
-			return true;
-	return false;
-}
-
 BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk)
 {
 	/* tcp6_sock type is not generated in dwarf and hence btf,
@@ -9534,8 +10320,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = {
 	.func			= bpf_skc_to_tcp6_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP6],
 };
 
@@ -9551,8 +10336,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = {
 	.func			= bpf_skc_to_tcp_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP],
 };
 
@@ -9581,8 +10365,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = {
 	.func			= bpf_skc_to_tcp_timewait_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW],
 };
 
@@ -9605,8 +10388,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = {
 	.func			= bpf_skc_to_tcp_request_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ],
 };
 
@@ -9627,7 +10409,55 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = {
 	.func			= bpf_skc_to_udp6_sock,
 	.gpl_only		= false,
 	.ret_type		= RET_PTR_TO_BTF_ID_OR_NULL,
-	.arg1_type		= ARG_PTR_TO_BTF_ID,
-	.check_btf_id		= check_arg_btf_id,
+	.arg1_type		= ARG_PTR_TO_BTF_ID_SOCK_COMMON,
 	.ret_btf_id		= &btf_sock_ids[BTF_SOCK_TYPE_UDP6],
 };
+
+BPF_CALL_1(bpf_sock_from_file, struct file *, file)
+{
+	return (unsigned long)sock_from_file(file);
+}
+
+BTF_ID_LIST(bpf_sock_from_file_btf_ids)
+BTF_ID(struct, socket)
+BTF_ID(struct, file)
+
+const struct bpf_func_proto bpf_sock_from_file_proto = {
+	.func		= bpf_sock_from_file,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_BTF_ID_OR_NULL,
+	.ret_btf_id	= &bpf_sock_from_file_btf_ids[0],
+	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &bpf_sock_from_file_btf_ids[1],
+};
+
+static const struct bpf_func_proto *
+bpf_sk_base_func_proto(enum bpf_func_id func_id)
+{
+	const struct bpf_func_proto *func;
+
+	switch (func_id) {
+	case BPF_FUNC_skc_to_tcp6_sock:
+		func = &bpf_skc_to_tcp6_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_sock:
+		func = &bpf_skc_to_tcp_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_timewait_sock:
+		func = &bpf_skc_to_tcp_timewait_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_tcp_request_sock:
+		func = &bpf_skc_to_tcp_request_sock_proto;
+		break;
+	case BPF_FUNC_skc_to_udp6_sock:
+		func = &bpf_skc_to_udp6_sock_proto;
+		break;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+
+	if (!perfmon_capable())
+		return NULL;
+
+	return func;
+}
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 29806eb765cf..6f1adba6695f 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -48,7 +48,7 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 	memset(flow_dissector, 0, sizeof(*flow_dissector));
 
 	for (i = 0; i < key_count; i++, key++) {
-		/* User should make sure that every key target offset is withing
+		/* User should make sure that every key target offset is within
 		 * boundaries of unsigned short.
 		 */
 		BUG_ON(key->offset > USHRT_MAX);
@@ -932,8 +932,14 @@ bool __skb_flow_dissect(const struct net *net,
 			int offset = 0;
 
 			ops = skb->dev->dsa_ptr->tag_ops;
-			if (ops->flow_dissect &&
-			    !ops->flow_dissect(skb, &proto, &offset)) {
+			/* Tail taggers don't break flow dissection */
+			if (!ops->tail_tag) {
+				if (ops->flow_dissect)
+					ops->flow_dissect(skb, &proto, &offset);
+				else
+					dsa_tag_generic_flow_dissect(skb,
+								     &proto,
+								     &offset);
 				hlen -= offset;
 				nhoff += offset;
 			}
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index d4474c812b64..715b67f6c62f 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -381,10 +381,8 @@ static void __flow_block_indr_cleanup(void (*release)(void *cb_priv),
 
 	list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) {
 		if (this->release == release &&
-		    this->indr.cb_priv == cb_priv) {
+		    this->indr.cb_priv == cb_priv)
 			list_move(&this->indr.list, cleanup_list);
-			return;
-		}
 	}
 }
 
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 80dbf2f4016e..8e582e29a41e 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -80,11 +80,11 @@ static void est_timer(struct timer_list *t)
 	u64 rate, brate;
 
 	est_fetch_counters(est, &b);
-	brate = (b.bytes - est->last_bytes) << (10 - est->ewma_log - est->intvl_log);
-	brate -= (est->avbps >> est->ewma_log);
+	brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log);
+	brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log);
 
-	rate = (b.packets - est->last_packets) << (10 - est->ewma_log - est->intvl_log);
-	rate -= (est->avpps >> est->ewma_log);
+	rate = (b.packets - est->last_packets) << (10 - est->intvl_log);
+	rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log);
 
 	write_seqcount_begin(&est->seq);
 	est->avbps += brate;
@@ -143,6 +143,9 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 	if (parm->interval < -2 || parm->interval > 3)
 		return -EINVAL;
 
+	if (parm->ewma_log == 0 || parm->ewma_log >= 31)
+		return -EINVAL;
+
 	est = kzalloc(sizeof(*est), GFP_KERNEL);
 	if (!est)
 		return -ENOBUFS;
diff --git a/net/core/gro_cells.c b/net/core/gro_cells.c
index e095fb871d91..6eb2e5ec2c50 100644
--- a/net/core/gro_cells.c
+++ b/net/core/gro_cells.c
@@ -99,9 +99,14 @@ void gro_cells_destroy(struct gro_cells *gcells)
 		struct gro_cell *cell = per_cpu_ptr(gcells->cells, i);
 
 		napi_disable(&cell->napi);
-		netif_napi_del(&cell->napi);
+		__netif_napi_del(&cell->napi);
 		__skb_queue_purge(&cell->napi_skbs);
 	}
+	/* This barrier is needed because netpoll could access dev->napi_list
+	 * under rcu protection.
+	 */
+	synchronize_net();
+
 	free_percpu(gcells->cells);
 	gcells->cells = NULL;
 }
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 7d3438215f32..2f7940bcf715 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -39,12 +39,11 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 {
 	int ret;
 
-	/* Preempt disable is needed to protect per-cpu redirect_info between
-	 * BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and
-	 * access to maps strictly require a rcu_read_lock() for protection,
-	 * mixing with BH RCU lock doesn't work.
+	/* Migration disable and BH disable are needed to protect per-cpu
+	 * redirect_info between BPF prog and skb_do_redirect().
 	 */
-	preempt_disable();
+	migrate_disable();
+	local_bh_disable();
 	bpf_compute_data_pointers(skb);
 	ret = bpf_prog_run_save_cb(lwt->prog, skb);
 
@@ -78,7 +77,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 		break;
 	}
 
-	preempt_enable();
+	local_bh_enable();
+	migrate_enable();
 
 	return ret;
 }
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8e39e28b0a8d..6d2d557442dc 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -235,6 +235,8 @@ static int neigh_forced_gc(struct neigh_table *tbl)
 
 			write_lock(&n->lock);
 			if ((n->nud_state == NUD_FAILED) ||
+			    (tbl->is_multicast &&
+			     tbl->is_multicast(n->primary_key)) ||
 			    time_after(tref, n->updated))
 				remove = true;
 			write_unlock(&n->lock);
@@ -1243,13 +1245,14 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr,
 	old    = neigh->nud_state;
 	err    = -EPERM;
 
-	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
-	    (old & (NUD_NOARP | NUD_PERMANENT)))
-		goto out;
 	if (neigh->dead) {
 		NL_SET_ERR_MSG(extack, "Neighbor entry is now dead");
+		new = old;
 		goto out;
 	}
+	if (!(flags & NEIGH_UPDATE_F_ADMIN) &&
+	    (old & (NUD_NOARP | NUD_PERMANENT)))
+		goto out;
 
 	ext_learn_change = neigh_update_ext_learned(neigh, flags, &notify);
 
@@ -1567,10 +1570,8 @@ static void neigh_proxy_process(struct timer_list *t)
 void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p,
 		    struct sk_buff *skb)
 {
-	unsigned long now = jiffies;
-
-	unsigned long sched_next = now + (prandom_u32() %
-					  NEIGH_VAR(p, PROXY_DELAY));
+	unsigned long sched_next = jiffies +
+			prandom_u32_max(NEIGH_VAR(p, PROXY_DELAY));
 
 	if (tbl->proxy_queue.qlen > NEIGH_VAR(p, PROXY_QLEN)) {
 		kfree_skb(skb);
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index 6bbd06f7dc7d..c714e6a9dad4 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -116,6 +116,12 @@ static int dev_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
+static u32 softnet_backlog_len(struct softnet_data *sd)
+{
+	return skb_queue_len_lockless(&sd->input_pkt_queue) +
+	       skb_queue_len_lockless(&sd->process_queue);
+}
+
 static struct softnet_data *softnet_get_online(loff_t *pos)
 {
 	struct softnet_data *sd = NULL;
@@ -159,12 +165,17 @@ static int softnet_seq_show(struct seq_file *seq, void *v)
 	rcu_read_unlock();
 #endif
 
+	/* the index is the CPU id owing this sd. Since offline CPUs are not
+	 * displayed, it would be othrwise not trivial for the user-space
+	 * mapping the data a specific CPU
+	 */
 	seq_printf(seq,
-		   "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+		   "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
 		   sd->processed, sd->dropped, sd->time_squeeze, 0,
 		   0, 0, 0, 0, /* was fastroute */
 		   0,	/* was cpu_collision */
-		   sd->received_rps, flow_limit_count);
+		   sd->received_rps, flow_limit_count,
+		   softnet_backlog_len(sd), (int)seq->index);
 	return 0;
 }
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index efec66fa78b7..daf502c13d6d 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1027,7 +1027,7 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	while (--i >= new_num) {
 		struct kobject *kobj = &dev->_rx[i].kobj;
 
-		if (!refcount_read(&dev_net(dev)->count))
+		if (!refcount_read(&dev_net(dev)->ns.count))
 			kobj->uevent_suppress = 1;
 		if (dev->sysfs_rx_queue_group)
 			sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
@@ -1158,8 +1158,8 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
 	 * belongs to the root device it will be reported with just the
 	 * traffic class, so just "0" for TC 0 for example.
 	 */
-	return dev->num_tc < 0 ? sprintf(buf, "%u%d\n", tc, dev->num_tc) :
-				 sprintf(buf, "%u\n", tc);
+	return dev->num_tc < 0 ? sprintf(buf, "%d%d\n", tc, dev->num_tc) :
+				 sprintf(buf, "%d\n", tc);
 }
 
 #ifdef CONFIG_XPS
@@ -1317,8 +1317,8 @@ static const struct attribute_group dql_group = {
 static ssize_t xps_cpus_show(struct netdev_queue *queue,
 			     char *buf)
 {
+	int cpu, len, ret, num_tc = 1, tc = 0;
 	struct net_device *dev = queue->dev;
-	int cpu, len, num_tc = 1, tc = 0;
 	struct xps_dev_maps *dev_maps;
 	cpumask_var_t mask;
 	unsigned long index;
@@ -1328,22 +1328,31 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 
 	index = get_netdev_queue_index(queue);
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
 	if (dev->num_tc) {
 		/* Do not allow XPS on subordinate device directly */
 		num_tc = dev->num_tc;
-		if (num_tc < 0)
-			return -EINVAL;
+		if (num_tc < 0) {
+			ret = -EINVAL;
+			goto err_rtnl_unlock;
+		}
 
 		/* If queue belongs to subordinate dev use its map */
 		dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
 
 		tc = netdev_txq_to_tc(dev, index);
-		if (tc < 0)
-			return -EINVAL;
+		if (tc < 0) {
+			ret = -EINVAL;
+			goto err_rtnl_unlock;
+		}
 	}
 
-	if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
-		return -ENOMEM;
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto err_rtnl_unlock;
+	}
 
 	rcu_read_lock();
 	dev_maps = rcu_dereference(dev->xps_cpus_map);
@@ -1366,9 +1375,15 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 	}
 	rcu_read_unlock();
 
+	rtnl_unlock();
+
 	len = snprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask));
 	free_cpumask_var(mask);
 	return len < PAGE_SIZE ? len : -EINVAL;
+
+err_rtnl_unlock:
+	rtnl_unlock();
+	return ret;
 }
 
 static ssize_t xps_cpus_store(struct netdev_queue *queue,
@@ -1396,7 +1411,13 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
 		return err;
 	}
 
+	if (!rtnl_trylock()) {
+		free_cpumask_var(mask);
+		return restart_syscall();
+	}
+
 	err = netif_set_xps_queue(dev, mask, index);
+	rtnl_unlock();
 
 	free_cpumask_var(mask);
 
@@ -1408,22 +1429,29 @@ static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init
 
 static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
 {
+	int j, len, ret, num_tc = 1, tc = 0;
 	struct net_device *dev = queue->dev;
 	struct xps_dev_maps *dev_maps;
 	unsigned long *mask, index;
-	int j, len, num_tc = 1, tc = 0;
 
 	index = get_netdev_queue_index(queue);
 
+	if (!rtnl_trylock())
+		return restart_syscall();
+
 	if (dev->num_tc) {
 		num_tc = dev->num_tc;
 		tc = netdev_txq_to_tc(dev, index);
-		if (tc < 0)
-			return -EINVAL;
+		if (tc < 0) {
+			ret = -EINVAL;
+			goto err_rtnl_unlock;
+		}
 	}
 	mask = bitmap_zalloc(dev->num_rx_queues, GFP_KERNEL);
-	if (!mask)
-		return -ENOMEM;
+	if (!mask) {
+		ret = -ENOMEM;
+		goto err_rtnl_unlock;
+	}
 
 	rcu_read_lock();
 	dev_maps = rcu_dereference(dev->xps_rxqs_map);
@@ -1449,10 +1477,16 @@ static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
 out_no_maps:
 	rcu_read_unlock();
 
+	rtnl_unlock();
+
 	len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues);
 	bitmap_free(mask);
 
 	return len < PAGE_SIZE ? len : -EINVAL;
+
+err_rtnl_unlock:
+	rtnl_unlock();
+	return ret;
 }
 
 static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
@@ -1478,10 +1512,17 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
 		return err;
 	}
 
+	if (!rtnl_trylock()) {
+		bitmap_free(mask);
+		return restart_syscall();
+	}
+
 	cpus_read_lock();
 	err = __netif_set_xps_queue(dev, mask, index, true);
 	cpus_read_unlock();
 
+	rtnl_unlock();
+
 	bitmap_free(mask);
 	return err ? : len;
 }
@@ -1605,7 +1646,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	while (--i >= new_num) {
 		struct netdev_queue *queue = dev->_tx + i;
 
-		if (!refcount_read(&dev_net(dev)->count))
+		if (!refcount_read(&dev_net(dev)->ns.count))
 			queue->kobj.uevent_suppress = 1;
 #ifdef CONFIG_BQL
 		sysfs_remove_group(&queue->kobj, &dql_group);
@@ -1852,7 +1893,7 @@ void netdev_unregister_kobject(struct net_device *ndev)
 {
 	struct device *dev = &ndev->dev;
 
-	if (!refcount_read(&dev_net(ndev)->count))
+	if (!refcount_read(&dev_net(ndev)->ns.count))
 		dev_set_uevent_suppress(dev, 1);
 
 	kobject_get(&dev->kobj);
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 944ab214e5ae..2ef3b4557f40 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -19,6 +19,7 @@
 #include <linux/net_namespace.h>
 #include <linux/sched/task.h>
 #include <linux/uidgid.h>
+#include <linux/cookie.h>
 
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -44,7 +45,7 @@ static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) };
 #endif
 
 struct net init_net = {
-	.count		= REFCOUNT_INIT(1),
+	.ns.count	= REFCOUNT_INIT(1),
 	.dev_base_head	= LIST_HEAD_INIT(init_net.dev_base_head),
 #ifdef CONFIG_KEYS
 	.key_domain	= &init_net_key_domain,
@@ -69,16 +70,16 @@ EXPORT_SYMBOL_GPL(pernet_ops_rwsem);
 
 static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS;
 
-static atomic64_t cookie_gen;
+DEFINE_COOKIE(net_cookie);
 
-u64 net_gen_cookie(struct net *net)
+u64 __net_gen_cookie(struct net *net)
 {
 	while (1) {
 		u64 res = atomic64_read(&net->net_cookie);
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&cookie_gen);
+		res = gen_cookie_next(&net_cookie);
 		atomic64_cmpxchg(&net->net_cookie, 0, res);
 	}
 }
@@ -248,7 +249,7 @@ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp)
 {
 	int id;
 
-	if (refcount_read(&net->count) == 0)
+	if (refcount_read(&net->ns.count) == 0)
 		return NETNSA_NSID_NOT_ASSIGNED;
 
 	spin_lock_bh(&net->nsid_lock);
@@ -328,7 +329,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	int error = 0;
 	LIST_HEAD(net_exit_list);
 
-	refcount_set(&net->count, 1);
+	refcount_set(&net->ns.count, 1);
 	refcount_set(&net->passive, 1);
 	get_random_bytes(&net->hash_mix, sizeof(u32));
 	net->dev_base_seq = 1;
@@ -1101,7 +1102,10 @@ static int __init net_ns_init(void)
 		panic("Could not allocate generic netns");
 
 	rcu_assign_pointer(init_net.gen, ng);
-	net_gen_cookie(&init_net);
+
+	preempt_disable();
+	__net_gen_cookie(&init_net);
+	preempt_enable();
 
 	down_write(&pernet_ops_rwsem);
 	if (setup_net(&init_net, &init_user_ns))
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 41b24cd31562..b49c57d35a88 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -68,9 +68,8 @@ struct update_classid_context {
 
 static int update_classid_sock(const void *v, struct file *file, unsigned n)
 {
-	int err;
 	struct update_classid_context *ctx = (void *)v;
-	struct socket *sock = sock_from_file(file, &err);
+	struct socket *sock = sock_from_file(file);
 
 	if (sock) {
 		spin_lock(&cgroup_sk_update_lock);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 2338753e936b..960948290001 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -29,6 +29,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/if_vlan.h>
+#include <net/dsa.h>
 #include <net/tcp.h>
 #include <net/udp.h>
 #include <net/addrconf.h>
@@ -297,7 +298,7 @@ static int netpoll_owner_active(struct net_device *dev)
 {
 	struct napi_struct *napi;
 
-	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+	list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) {
 		if (napi->poll_owner == smp_processor_id())
 			return 1;
 	}
@@ -657,15 +658,15 @@ EXPORT_SYMBOL_GPL(__netpoll_setup);
 
 int netpoll_setup(struct netpoll *np)
 {
-	struct net_device *ndev = NULL;
+	struct net_device *ndev = NULL, *dev = NULL;
+	struct net *net = current->nsproxy->net_ns;
 	struct in_device *in_dev;
 	int err;
 
 	rtnl_lock();
-	if (np->dev_name[0]) {
-		struct net *net = current->nsproxy->net_ns;
+	if (np->dev_name[0])
 		ndev = __dev_get_by_name(net, np->dev_name);
-	}
+
 	if (!ndev) {
 		np_err(np, "%s doesn't exist, aborting\n", np->dev_name);
 		err = -ENODEV;
@@ -673,6 +674,19 @@ int netpoll_setup(struct netpoll *np)
 	}
 	dev_hold(ndev);
 
+	/* bring up DSA management network devices up first */
+	for_each_netdev(net, dev) {
+		if (!netdev_uses_dsa(dev))
+			continue;
+
+		err = dev_change_flags(dev, dev->flags | IFF_UP, NULL);
+		if (err < 0) {
+			np_err(np, "%s failed to open %s\n",
+			       np->dev_name, dev->name);
+			goto put;
+		}
+	}
+
 	if (netdev_master_upper_dev_get(ndev)) {
 		np_err(np, "%s is a slave device, aborting\n", np->dev_name);
 		err = -EBUSY;
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 9bd4cab7d510..99a431c56f23 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -220,8 +220,7 @@ static ssize_t write_priomap(struct kernfs_open_file *of,
 
 static int update_netprio(const void *v, struct file *file, unsigned n)
 {
-	int err;
-	struct socket *sock = sock_from_file(file, &err);
+	struct socket *sock = sock_from_file(file);
 	if (sock) {
 		spin_lock(&cgroup_sk_update_lock);
 		sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data,
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index ef98372facf6..f3c690b8c8e3 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -11,6 +11,8 @@
 #include <linux/device.h>
 
 #include <net/page_pool.h>
+#include <net/xdp.h>
+
 #include <linux/dma-direction.h>
 #include <linux/dma-mapping.h>
 #include <linux/page-flags.h>
@@ -362,8 +364,9 @@ static bool pool_page_reusable(struct page_pool *pool, struct page *page)
  * If the page refcnt != 1, then the page will be returned to memory
  * subsystem.
  */
-void page_pool_put_page(struct page_pool *pool, struct page *page,
-			unsigned int dma_sync_size, bool allow_direct)
+static __always_inline struct page *
+__page_pool_put_page(struct page_pool *pool, struct page *page,
+		     unsigned int dma_sync_size, bool allow_direct)
 {
 	/* This allocator is optimized for the XDP mode that uses
 	 * one-frame-per-page, but have fallbacks that act like the
@@ -379,15 +382,12 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
 			page_pool_dma_sync_for_device(pool, page,
 						      dma_sync_size);
 
-		if (allow_direct && in_serving_softirq())
-			if (page_pool_recycle_in_cache(page, pool))
-				return;
+		if (allow_direct && in_serving_softirq() &&
+		    page_pool_recycle_in_cache(page, pool))
+			return NULL;
 
-		if (!page_pool_recycle_in_ring(pool, page)) {
-			/* Cache full, fallback to free pages */
-			page_pool_return_page(pool, page);
-		}
-		return;
+		/* Page found as candidate for recycling */
+		return page;
 	}
 	/* Fallback/non-XDP mode: API user have elevated refcnt.
 	 *
@@ -405,9 +405,59 @@ void page_pool_put_page(struct page_pool *pool, struct page *page,
 	/* Do not replace this with page_pool_return_page() */
 	page_pool_release_page(pool, page);
 	put_page(page);
+
+	return NULL;
+}
+
+void page_pool_put_page(struct page_pool *pool, struct page *page,
+			unsigned int dma_sync_size, bool allow_direct)
+{
+	page = __page_pool_put_page(pool, page, dma_sync_size, allow_direct);
+	if (page && !page_pool_recycle_in_ring(pool, page)) {
+		/* Cache full, fallback to free pages */
+		page_pool_return_page(pool, page);
+	}
 }
 EXPORT_SYMBOL(page_pool_put_page);
 
+/* Caller must not use data area after call, as this function overwrites it */
+void page_pool_put_page_bulk(struct page_pool *pool, void **data,
+			     int count)
+{
+	int i, bulk_len = 0;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = virt_to_head_page(data[i]);
+
+		page = __page_pool_put_page(pool, page, -1, false);
+		/* Approved for bulk recycling in ptr_ring cache */
+		if (page)
+			data[bulk_len++] = page;
+	}
+
+	if (unlikely(!bulk_len))
+		return;
+
+	/* Bulk producer into ptr_ring page_pool cache */
+	page_pool_ring_lock(pool);
+	for (i = 0; i < bulk_len; i++) {
+		if (__ptr_ring_produce(&pool->ring, data[i]))
+			break; /* ring full */
+	}
+	page_pool_ring_unlock(pool);
+
+	/* Hopefully all pages was return into ptr_ring */
+	if (likely(i == bulk_len))
+		return;
+
+	/* ptr_ring cache full, free remaining pages outside producer lock
+	 * since put_page() with refcnt == 1 can be an expensive operation
+	 */
+	for (; i < bulk_len; i++)
+		page_pool_return_page(pool, data[i]);
+}
+EXPORT_SYMBOL(page_pool_put_page_bulk);
+
 static void page_pool_empty_ring(struct page_pool *pool)
 {
 	struct page *page;
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 44fdbb9c6e53..105978604ffd 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -922,7 +922,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			pkt_dev->min_pkt_size = value;
 			pkt_dev->cur_pkt_size = value;
 		}
-		sprintf(pg_result, "OK: min_pkt_size=%u",
+		sprintf(pg_result, "OK: min_pkt_size=%d",
 			pkt_dev->min_pkt_size);
 		return count;
 	}
@@ -939,7 +939,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			pkt_dev->max_pkt_size = value;
 			pkt_dev->cur_pkt_size = value;
 		}
-		sprintf(pg_result, "OK: max_pkt_size=%u",
+		sprintf(pg_result, "OK: max_pkt_size=%d",
 			pkt_dev->max_pkt_size);
 		return count;
 	}
@@ -959,7 +959,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			pkt_dev->max_pkt_size = value;
 			pkt_dev->cur_pkt_size = value;
 		}
-		sprintf(pg_result, "OK: pkt_size=%u", pkt_dev->min_pkt_size);
+		sprintf(pg_result, "OK: pkt_size=%d", pkt_dev->min_pkt_size);
 		return count;
 	}
 
@@ -981,7 +981,7 @@ static ssize_t pktgen_if_write(struct file *file,
 
 		i += len;
 		pkt_dev->nfrags = value;
-		sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags);
+		sprintf(pg_result, "OK: frags=%d", pkt_dev->nfrags);
 		return count;
 	}
 	if (!strcmp(name, "delay")) {
@@ -1146,7 +1146,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		     (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))))
 			return -ENOTSUPP;
 		pkt_dev->burst = value < 1 ? 1 : value;
-		sprintf(pg_result, "OK: burst=%d", pkt_dev->burst);
+		sprintf(pg_result, "OK: burst=%u", pkt_dev->burst);
 		return count;
 	}
 	if (!strcmp(name, "node")) {
diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c
index d964a5147f22..e33fde06d528 100644
--- a/net/core/ptp_classifier.c
+++ b/net/core/ptp_classifier.c
@@ -107,6 +107,36 @@ unsigned int ptp_classify_raw(const struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(ptp_classify_raw);
 
+struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type)
+{
+	u8 *ptr = skb_mac_header(skb);
+
+	if (type & PTP_CLASS_VLAN)
+		ptr += VLAN_HLEN;
+
+	switch (type & PTP_CLASS_PMASK) {
+	case PTP_CLASS_IPV4:
+		ptr += IPV4_HLEN(ptr) + UDP_HLEN;
+		break;
+	case PTP_CLASS_IPV6:
+		ptr += IP6_HLEN + UDP_HLEN;
+		break;
+	case PTP_CLASS_L2:
+		break;
+	default:
+		return NULL;
+	}
+
+	ptr += ETH_HLEN;
+
+	/* Ensure that the entire header is present in this packet. */
+	if (ptr + sizeof(struct ptp_header) > skb->data + skb->len)
+		return NULL;
+
+	return (struct ptp_header *)ptr;
+}
+EXPORT_SYMBOL_GPL(ptp_parse_header);
+
 void __init ptp_classifier_init(void)
 {
 	static struct sock_filter ptp_filter[] __initdata = {
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 68e0682450c6..3d6ab194d0f5 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -139,7 +139,7 @@ bool lockdep_rtnl_is_held(void)
 EXPORT_SYMBOL(lockdep_rtnl_is_held);
 #endif /* #ifdef CONFIG_PROVE_LOCKING */
 
-static struct rtnl_link *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
+static struct rtnl_link __rcu *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];
 
 static inline int rtm_msgindex(int msgtype)
 {
@@ -157,7 +157,7 @@ static inline int rtm_msgindex(int msgtype)
 
 static struct rtnl_link *rtnl_get_link(int protocol, int msgtype)
 {
-	struct rtnl_link **tab;
+	struct rtnl_link __rcu **tab;
 
 	if (protocol >= ARRAY_SIZE(rtnl_msg_handlers))
 		protocol = PF_UNSPEC;
@@ -166,7 +166,7 @@ static struct rtnl_link *rtnl_get_link(int protocol, int msgtype)
 	if (!tab)
 		tab = rcu_dereference_rtnl(rtnl_msg_handlers[PF_UNSPEC]);
 
-	return tab[msgtype];
+	return rcu_dereference_rtnl(tab[msgtype]);
 }
 
 static int rtnl_register_internal(struct module *owner,
@@ -183,7 +183,7 @@ static int rtnl_register_internal(struct module *owner,
 	msgindex = rtm_msgindex(msgtype);
 
 	rtnl_lock();
-	tab = rtnl_msg_handlers[protocol];
+	tab = rtnl_dereference(rtnl_msg_handlers[protocol]);
 	if (tab == NULL) {
 		tab = kcalloc(RTM_NR_MSGTYPES, sizeof(void *), GFP_KERNEL);
 		if (!tab)
@@ -286,7 +286,8 @@ void rtnl_register(int protocol, int msgtype,
  */
 int rtnl_unregister(int protocol, int msgtype)
 {
-	struct rtnl_link **tab, *link;
+	struct rtnl_link __rcu **tab;
+	struct rtnl_link *link;
 	int msgindex;
 
 	BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
@@ -299,7 +300,7 @@ int rtnl_unregister(int protocol, int msgtype)
 		return -ENOENT;
 	}
 
-	link = tab[msgindex];
+	link = rtnl_dereference(tab[msgindex]);
 	rcu_assign_pointer(tab[msgindex], NULL);
 	rtnl_unlock();
 
@@ -318,20 +319,21 @@ EXPORT_SYMBOL_GPL(rtnl_unregister);
  */
 void rtnl_unregister_all(int protocol)
 {
-	struct rtnl_link **tab, *link;
+	struct rtnl_link __rcu **tab;
+	struct rtnl_link *link;
 	int msgindex;
 
 	BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);
 
 	rtnl_lock();
-	tab = rtnl_msg_handlers[protocol];
+	tab = rtnl_dereference(rtnl_msg_handlers[protocol]);
 	if (!tab) {
 		rtnl_unlock();
 		return;
 	}
 	RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL);
 	for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) {
-		link = tab[msgindex];
+		link = rtnl_dereference(tab[msgindex]);
 		if (!link)
 			continue;
 
@@ -1939,7 +1941,7 @@ static const struct rtnl_link_ops *linkinfo_to_kind_ops(const struct nlattr *nla
 	if (linfo[IFLA_INFO_KIND]) {
 		char kind[MODULE_NAME_LEN];
 
-		nla_strlcpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
+		nla_strscpy(kind, linfo[IFLA_INFO_KIND], sizeof(kind));
 		ops = rtnl_link_ops_get(kind);
 	}
 
@@ -2953,9 +2955,9 @@ static struct net_device *rtnl_dev_get(struct net *net,
 	if (!ifname) {
 		ifname = buffer;
 		if (ifname_attr)
-			nla_strlcpy(ifname, ifname_attr, IFNAMSIZ);
+			nla_strscpy(ifname, ifname_attr, IFNAMSIZ);
 		else if (altifname_attr)
-			nla_strlcpy(ifname, altifname_attr, ALTIFNAMSIZ);
+			nla_strscpy(ifname, altifname_attr, ALTIFNAMSIZ);
 		else
 			return NULL;
 	}
@@ -2983,7 +2985,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 
 	if (tb[IFLA_IFNAME])
-		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
 	else
 		ifname[0] = '\0';
 
@@ -3264,7 +3266,7 @@ replay:
 		return err;
 
 	if (tb[IFLA_IFNAME])
-		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+		nla_strscpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
 	else
 		ifname[0] = '\0';
 
@@ -3296,7 +3298,7 @@ replay:
 		memset(linkinfo, 0, sizeof(linkinfo));
 
 	if (linkinfo[IFLA_INFO_KIND]) {
-		nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
+		nla_strscpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
 		ops = rtnl_link_ops_get(kind);
 	} else {
 		kind[0] = '\0';
@@ -3437,26 +3439,15 @@ replay:
 
 	dev->ifindex = ifm->ifi_index;
 
-	if (ops->newlink) {
+	if (ops->newlink)
 		err = ops->newlink(link_net ? : net, dev, tb, data, extack);
-		/* Drivers should call free_netdev() in ->destructor
-		 * and unregister it on failure after registration
-		 * so that device could be finally freed in rtnl_unlock.
-		 */
-		if (err < 0) {
-			/* If device is not registered at all, free it now */
-			if (dev->reg_state == NETREG_UNINITIALIZED ||
-			    dev->reg_state == NETREG_UNREGISTERED)
-				free_netdev(dev);
-			goto out;
-		}
-	} else {
+	else
 		err = register_netdevice(dev);
-		if (err < 0) {
-			free_netdev(dev);
-			goto out;
-		}
+	if (err < 0) {
+		free_netdev(dev);
+		goto out;
 	}
+
 	err = rtnl_configure_link(dev, ifm);
 	if (err < 0)
 		goto out_unregister;
@@ -3709,13 +3700,13 @@ static int rtnl_dellinkprop(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return rtnl_linkprop(RTM_DELLINKPROP, skb, nlh, extack);
 }
 
-static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
+static u32 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
 	struct net *net = sock_net(skb->sk);
-	struct net_device *dev;
+	size_t min_ifinfo_dump_size = 0;
 	struct nlattr *tb[IFLA_MAX+1];
 	u32 ext_filter_mask = 0;
-	u16 min_ifinfo_dump_size = 0;
+	struct net_device *dev;
 	int hdrlen;
 
 	/* Same kernel<->userspace interface hack as in rtnl_dump_ifinfo. */
@@ -3735,9 +3726,8 @@ static u16 rtnl_calcit(struct sk_buff *skb, struct nlmsghdr *nlh)
 	 */
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
-		min_ifinfo_dump_size = max_t(u16, min_ifinfo_dump_size,
-					     if_nlmsg_size(dev,
-						           ext_filter_mask));
+		min_ifinfo_dump_size = max(min_ifinfo_dump_size,
+					   if_nlmsg_size(dev, ext_filter_mask));
 	}
 	rcu_read_unlock();
 
@@ -3755,7 +3745,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 		s_idx = 1;
 
 	for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) {
-		struct rtnl_link **tab;
+		struct rtnl_link __rcu **tab;
 		struct rtnl_link *link;
 		rtnl_dumpit_func dumpit;
 
@@ -3769,7 +3759,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 		if (!tab)
 			continue;
 
-		link = tab[type];
+		link = rcu_dereference_rtnl(tab[type]);
 		if (!link)
 			continue;
 
@@ -5494,7 +5484,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
 		struct sock *rtnl;
 		rtnl_dumpit_func dumpit;
-		u16 min_dump_alloc = 0;
+		u32 min_dump_alloc = 0;
 
 		link = rtnl_get_link(family, type);
 		if (!link || !link->dumpit) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 2b48cb0cc684..785daff48030 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -249,6 +249,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask,
 
 		fclones->skb2.fclone = SKB_FCLONE_CLONE;
 	}
+
+	skb_set_kcov_handle(skb, kcov_common_handle());
+
 out:
 	return skb;
 nodata:
@@ -282,6 +285,8 @@ static struct sk_buff *__build_skb_around(struct sk_buff *skb,
 	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
 	atomic_set(&shinfo->dataref, 1);
 
+	skb_set_kcov_handle(skb, kcov_common_handle());
+
 	return skb;
 }
 
@@ -432,7 +437,11 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
 
 	len += NET_SKB_PAD;
 
-	if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
+	/* If requested length is either too small or too big,
+	 * we use kmalloc() for skb->head allocation.
+	 */
+	if (len <= SKB_WITH_OVERHEAD(1024) ||
+	    len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
 	    (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
 		skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
 		if (!skb)
@@ -496,13 +505,17 @@ EXPORT_SYMBOL(__netdev_alloc_skb);
 struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 				 gfp_t gfp_mask)
 {
-	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+	struct napi_alloc_cache *nc;
 	struct sk_buff *skb;
 	void *data;
 
 	len += NET_SKB_PAD + NET_IP_ALIGN;
 
-	if ((len > SKB_WITH_OVERHEAD(PAGE_SIZE)) ||
+	/* If requested length is either too small or too big,
+	 * we use kmalloc() for skb->head allocation.
+	 */
+	if (len <= SKB_WITH_OVERHEAD(1024) ||
+	    len > SKB_WITH_OVERHEAD(PAGE_SIZE) ||
 	    (gfp_mask & (__GFP_DIRECT_RECLAIM | GFP_DMA))) {
 		skb = __alloc_skb(len, gfp_mask, SKB_ALLOC_RX, NUMA_NO_NODE);
 		if (!skb)
@@ -510,6 +523,7 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len,
 		goto skb_success;
 	}
 
+	nc = this_cpu_ptr(&napi_alloc_cache);
 	len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 	len = SKB_DATA_ALIGN(len);
 
@@ -712,11 +726,10 @@ EXPORT_SYMBOL(kfree_skb_list);
  *
  * Must only be called from net_ratelimit()-ed paths.
  *
- * Dumps up to can_dump_full whole packets if full_pkt, headers otherwise.
+ * Dumps whole packets if full_pkt, only headers otherwise.
  */
 void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
 {
-	static atomic_t can_dump_full = ATOMIC_INIT(5);
 	struct skb_shared_info *sh = skb_shinfo(skb);
 	struct net_device *dev = skb->dev;
 	struct sock *sk = skb->sk;
@@ -726,9 +739,6 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt)
 	int i, len, seg_len;
 
 	if (full_pkt)
-		full_pkt = atomic_dec_if_positive(&can_dump_full) >= 0;
-
-	if (full_pkt)
 		len = skb->len;
 	else
 		len = min_t(int, skb->len, MAX_HEADER + 128);
@@ -841,7 +851,7 @@ EXPORT_SYMBOL(consume_skb);
 #endif
 
 /**
- *	consume_stateless_skb - free an skbuff, assuming it is stateless
+ *	__consume_stateless_skb - free an skbuff, assuming it is stateless
  *	@skb: buffer to free
  *
  *	Alike consume_skb(), but this variant assumes that this is the last
@@ -895,15 +905,14 @@ void __kfree_skb_defer(struct sk_buff *skb)
 
 void napi_consume_skb(struct sk_buff *skb, int budget)
 {
-	if (unlikely(!skb))
-		return;
-
 	/* Zero budget indicate non-NAPI context called us, like netpoll */
 	if (unlikely(!budget)) {
 		dev_consume_skb_any(skb);
 		return;
 	}
 
+	lockdep_assert_in_softirq();
+
 	if (!skb_unref(skb))
 		return;
 
@@ -2018,6 +2027,12 @@ int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len)
 		skb->csum = csum_block_sub(skb->csum,
 					   skb_checksum(skb, len, delta, 0),
 					   len);
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		int hdlen = (len > skb_headlen(skb)) ? skb_headlen(skb) : len;
+		int offset = skb_checksum_start_offset(skb) + skb->csum_offset;
+
+		if (offset + sizeof(__sum16) > hdlen)
+			return -EINVAL;
 	}
 	return __pskb_trim(skb, len);
 }
@@ -2725,19 +2740,20 @@ EXPORT_SYMBOL(skb_checksum);
 /* Both of above in one bottle. */
 
 __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
-				    u8 *to, int len, __wsum csum)
+				    u8 *to, int len)
 {
 	int start = skb_headlen(skb);
 	int i, copy = start - offset;
 	struct sk_buff *frag_iter;
 	int pos = 0;
+	__wsum csum = 0;
 
 	/* Copy header. */
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
 		csum = csum_partial_copy_nocheck(skb->data + offset, to,
-						 copy, csum);
+						 copy);
 		if ((len -= copy) == 0)
 			return csum;
 		offset += copy;
@@ -2767,7 +2783,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 				vaddr = kmap_atomic(p);
 				csum2 = csum_partial_copy_nocheck(vaddr + p_off,
 								  to + copied,
-								  p_len, 0);
+								  p_len);
 				kunmap_atomic(vaddr);
 				csum = csum_block_add(csum, csum2, pos);
 				pos += p_len;
@@ -2793,7 +2809,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset,
 				copy = len;
 			csum2 = skb_copy_and_csum_bits(frag_iter,
 						       offset - start,
-						       to, copy, 0);
+						       to, copy);
 			csum = csum_block_add(csum, csum2, pos);
 			if ((len -= copy) == 0)
 				return csum;
@@ -3013,7 +3029,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to)
 	csum = 0;
 	if (csstart != skb->len)
 		csum = skb_copy_and_csum_bits(skb, csstart, to + csstart,
-					      skb->len - csstart, 0);
+					      skb->len - csstart);
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		long csstuff = csstart + skb->csum_offset;
@@ -3435,6 +3451,7 @@ void skb_prepare_seq_read(struct sk_buff *skb, unsigned int from,
 	st->root_skb = st->cur_skb = skb;
 	st->frag_idx = st->stepped_offset = 0;
 	st->frag_data = NULL;
+	st->frag_off = 0;
 }
 EXPORT_SYMBOL(skb_prepare_seq_read);
 
@@ -3489,14 +3506,27 @@ next_skb:
 		st->stepped_offset += skb_headlen(st->cur_skb);
 
 	while (st->frag_idx < skb_shinfo(st->cur_skb)->nr_frags) {
+		unsigned int pg_idx, pg_off, pg_sz;
+
 		frag = &skb_shinfo(st->cur_skb)->frags[st->frag_idx];
-		block_limit = skb_frag_size(frag) + st->stepped_offset;
 
+		pg_idx = 0;
+		pg_off = skb_frag_off(frag);
+		pg_sz = skb_frag_size(frag);
+
+		if (skb_frag_must_loop(skb_frag_page(frag))) {
+			pg_idx = (pg_off + st->frag_off) >> PAGE_SHIFT;
+			pg_off = offset_in_page(pg_off + st->frag_off);
+			pg_sz = min_t(unsigned int, pg_sz - st->frag_off,
+						    PAGE_SIZE - pg_off);
+		}
+
+		block_limit = pg_sz + st->stepped_offset;
 		if (abs_offset < block_limit) {
 			if (!st->frag_data)
-				st->frag_data = kmap_atomic(skb_frag_page(frag));
+				st->frag_data = kmap_atomic(skb_frag_page(frag) + pg_idx);
 
-			*data = (u8 *) st->frag_data + skb_frag_off(frag) +
+			*data = (u8 *)st->frag_data + pg_off +
 				(abs_offset - st->stepped_offset);
 
 			return block_limit - abs_offset;
@@ -3507,8 +3537,12 @@ next_skb:
 			st->frag_data = NULL;
 		}
 
-		st->frag_idx++;
-		st->stepped_offset += skb_frag_size(frag);
+		st->stepped_offset += pg_sz;
+		st->frag_off += pg_sz;
+		if (st->frag_off == skb_frag_size(frag)) {
+			st->frag_off = 0;
+			st->frag_idx++;
+		}
 	}
 
 	if (st->frag_data) {
@@ -3648,7 +3682,8 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 	unsigned int delta_truesize = 0;
 	unsigned int delta_len = 0;
 	struct sk_buff *tail = NULL;
-	struct sk_buff *nskb;
+	struct sk_buff *nskb, *tmp;
+	int err;
 
 	skb_push(skb, -skb_network_offset(skb) + offset);
 
@@ -3658,11 +3693,28 @@ struct sk_buff *skb_segment_list(struct sk_buff *skb,
 		nskb = list_skb;
 		list_skb = list_skb->next;
 
+		err = 0;
+		if (skb_shared(nskb)) {
+			tmp = skb_clone(nskb, GFP_ATOMIC);
+			if (tmp) {
+				consume_skb(nskb);
+				nskb = tmp;
+				err = skb_unclone(nskb, GFP_ATOMIC);
+			} else {
+				err = -ENOMEM;
+			}
+		}
+
 		if (!tail)
 			skb->next = nskb;
 		else
 			tail->next = nskb;
 
+		if (unlikely(err)) {
+			nskb->next = list_skb;
+			goto err_linearize;
+		}
+
 		tail = nskb;
 
 		delta_len += nskb->len;
@@ -3934,7 +3986,7 @@ normal:
 					skb_copy_and_csum_bits(head_skb, offset,
 							       skb_put(nskb,
 								       len),
-							       len, 0);
+							       len);
 				SKB_GSO_CB(nskb)->csum_start =
 					skb_headroom(nskb) + doffset;
 			} else {
@@ -4555,7 +4607,7 @@ struct sk_buff *sock_dequeue_err_skb(struct sock *sk)
 	if (skb && (skb_next = skb_peek(q))) {
 		icmp_next = is_icmp_err_skb(skb_next);
 		if (icmp_next)
-			sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_origin;
+			sk->sk_err = SKB_EXT_ERR(skb_next)->ee.ee_errno;
 	}
 	spin_unlock_irqrestore(&q->lock, flags);
 
@@ -5436,7 +5488,8 @@ struct sk_buff *skb_vlan_untag(struct sk_buff *skb)
 		goto err_free;
 
 	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
+	if (!skb_transport_header_was_set(skb))
+		skb_reset_transport_header(skb);
 	skb_reset_mac_len(skb);
 
 	return skb;
@@ -5561,6 +5614,73 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci)
 }
 EXPORT_SYMBOL(skb_vlan_push);
 
+/**
+ * skb_eth_pop() - Drop the Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ *
+ * Drop the Ethernet header of @skb.
+ *
+ * Expects that skb->data points to the mac header and that no VLAN tags are
+ * present.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_pop(struct sk_buff *skb)
+{
+	if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) ||
+	    skb_network_offset(skb) < ETH_HLEN)
+		return -EPROTO;
+
+	skb_pull_rcsum(skb, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_eth_pop);
+
+/**
+ * skb_eth_push() - Add a new Ethernet header at the head of a packet
+ *
+ * @skb: Socket buffer to modify
+ * @dst: Destination MAC address of the new header
+ * @src: Source MAC address of the new header
+ *
+ * Prepend @skb with a new Ethernet header.
+ *
+ * Expects that skb->data points to the mac header, which must be empty.
+ *
+ * Returns 0 on success, -errno otherwise.
+ */
+int skb_eth_push(struct sk_buff *skb, const unsigned char *dst,
+		 const unsigned char *src)
+{
+	struct ethhdr *eth;
+	int err;
+
+	if (skb_network_offset(skb) || skb_vlan_tag_present(skb))
+		return -EPROTO;
+
+	err = skb_cow_head(skb, sizeof(*eth));
+	if (err < 0)
+		return err;
+
+	skb_push(skb, sizeof(*eth));
+	skb_reset_mac_header(skb);
+	skb_reset_mac_len(skb);
+
+	eth = eth_hdr(skb);
+	ether_addr_copy(eth->h_dest, dst);
+	ether_addr_copy(eth->h_source, src);
+	eth->h_proto = skb->protocol;
+
+	skb_postpush_rcsum(skb, eth, sizeof(*eth));
+
+	return 0;
+}
+EXPORT_SYMBOL(skb_eth_push);
+
 /* Update the ethertype of hdr and the skb csum value if required. */
 static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr,
 			     __be16 ethertype)
@@ -5725,6 +5845,9 @@ int skb_mpls_dec_ttl(struct sk_buff *skb)
 	if (unlikely(!eth_p_mpls(skb->protocol)))
 		return -EINVAL;
 
+	if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN))
+		return -ENOMEM;
+
 	lse = be32_to_cpu(mpls_hdr(skb)->label_stack_entry);
 	ttl = (lse & MPLS_LS_TTL_MASK) >> MPLS_LS_TTL_SHIFT;
 	if (!--ttl)
@@ -5955,8 +6078,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off,
 	size = SKB_WITH_OVERHEAD(ksize(data));
 
 	memcpy((struct skb_shared_info *)(data + size),
-	       skb_shinfo(skb), offsetof(struct skb_shared_info,
-					 frags[skb_shinfo(skb)->nr_frags]));
+	       skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0]));
 	if (skb_orphan_frags(skb, gfp_mask)) {
 		kfree(data);
 		return -ENOMEM;
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 649583158983..25cdbb20f3a0 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -170,10 +170,12 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i,
 	struct scatterlist *sge = sk_msg_elem(msg, i);
 	u32 len = sge->length;
 
-	if (charge)
-		sk_mem_uncharge(sk, len);
-	if (!msg->skb)
+	/* When the skb owns the memory we free it from consume_skb path. */
+	if (!msg->skb) {
+		if (charge)
+			sk_mem_uncharge(sk, len);
 		put_page(sg_page(sge));
+	}
 	memset(sge, 0, sizeof(*sge));
 	return len;
 }
@@ -397,28 +399,45 @@ out:
 }
 EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
 
-static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
+						  struct sk_buff *skb)
 {
-	struct sock *sk = psock->sk;
-	int copied = 0, num_sge;
 	struct sk_msg *msg;
 
+	if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
+		return NULL;
+
+	if (!sk_rmem_schedule(sk, skb, skb->truesize))
+		return NULL;
+
 	msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
 	if (unlikely(!msg))
-		return -EAGAIN;
-	if (!sk_rmem_schedule(sk, skb, skb->len)) {
-		kfree(msg);
-		return -EAGAIN;
-	}
+		return NULL;
 
 	sk_msg_init(msg);
+	return msg;
+}
+
+static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
+					struct sk_psock *psock,
+					struct sock *sk,
+					struct sk_msg *msg)
+{
+	int num_sge, copied;
+
+	/* skb linearize may fail with ENOMEM, but lets simply try again
+	 * later if this happens. Under memory pressure we don't want to
+	 * drop the skb. We need to linearize the skb so that the mapping
+	 * in skb_to_sgvec can not error.
+	 */
+	if (skb_linearize(skb))
+		return -EAGAIN;
 	num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
 	if (unlikely(num_sge < 0)) {
 		kfree(msg);
 		return num_sge;
 	}
 
-	sk_mem_charge(sk, skb->len);
 	copied = skb->len;
 	msg->sg.start = 0;
 	msg->sg.size = copied;
@@ -430,13 +449,57 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
 	return copied;
 }
 
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb);
+
+static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+{
+	struct sock *sk = psock->sk;
+	struct sk_msg *msg;
+
+	/* If we are receiving on the same sock skb->sk is already assigned,
+	 * skip memory accounting and owner transition seeing it already set
+	 * correctly.
+	 */
+	if (unlikely(skb->sk == sk))
+		return sk_psock_skb_ingress_self(psock, skb);
+	msg = sk_psock_create_ingress_msg(sk, skb);
+	if (!msg)
+		return -EAGAIN;
+
+	/* This will transition ownership of the data from the socket where
+	 * the BPF program was run initiating the redirect to the socket
+	 * we will eventually receive this data on. The data will be released
+	 * from skb_consume found in __tcp_bpf_recvmsg() after its been copied
+	 * into user buffers.
+	 */
+	skb_set_owner_r(skb, sk);
+	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+}
+
+/* Puts an skb on the ingress queue of the socket already assigned to the
+ * skb. In this case we do not need to check memory limits or skb_set_owner_r
+ * because the skb is already accounted for here.
+ */
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb)
+{
+	struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
+	struct sock *sk = psock->sk;
+
+	if (unlikely(!msg))
+		return -EAGAIN;
+	sk_msg_init(msg);
+	return sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+}
+
 static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
 			       u32 off, u32 len, bool ingress)
 {
-	if (ingress)
-		return sk_psock_skb_ingress(psock, skb);
-	else
+	if (!ingress) {
+		if (!sock_writeable(psock->sk))
+			return -EAGAIN;
 		return skb_send_sock_locked(psock->sk, skb, off, len);
+	}
+	return sk_psock_skb_ingress(psock, skb);
 }
 
 static void sk_psock_backlog(struct work_struct *work)
@@ -494,14 +557,34 @@ end:
 
 struct sk_psock *sk_psock_init(struct sock *sk, int node)
 {
-	struct sk_psock *psock = kzalloc_node(sizeof(*psock),
-					      GFP_ATOMIC | __GFP_NOWARN,
-					      node);
-	if (!psock)
-		return NULL;
+	struct sk_psock *psock;
+	struct proto *prot;
+
+	write_lock_bh(&sk->sk_callback_lock);
+
+	if (inet_csk_has_ulp(sk)) {
+		psock = ERR_PTR(-EINVAL);
+		goto out;
+	}
 
+	if (sk->sk_user_data) {
+		psock = ERR_PTR(-EBUSY);
+		goto out;
+	}
+
+	psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node);
+	if (!psock) {
+		psock = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	prot = READ_ONCE(sk->sk_prot);
 	psock->sk = sk;
-	psock->eval =  __SK_NONE;
+	psock->eval = __SK_NONE;
+	psock->sk_proto = prot;
+	psock->saved_unhash = prot->unhash;
+	psock->saved_close = prot->close;
+	psock->saved_write_space = sk->sk_write_space;
 
 	INIT_LIST_HEAD(&psock->link);
 	spin_lock_init(&psock->link_lock);
@@ -516,6 +599,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node)
 	rcu_assign_sk_user_data_nocopy(sk, psock);
 	sock_hold(sk);
 
+out:
+	write_unlock_bh(&sk->sk_callback_lock);
 	return psock;
 }
 EXPORT_SYMBOL_GPL(sk_psock_init);
@@ -603,6 +688,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock)
 	rcu_assign_sk_user_data(sk, NULL);
 	if (psock->progs.skb_parser)
 		sk_psock_stop_strp(sk, psock);
+	else if (psock->progs.skb_verdict)
+		sk_psock_stop_verdict(sk, psock);
 	write_unlock_bh(&sk->sk_callback_lock);
 	sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED);
 
@@ -660,19 +747,8 @@ EXPORT_SYMBOL_GPL(sk_psock_msg_verdict);
 static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog,
 			    struct sk_buff *skb)
 {
-	int ret;
-
-	skb->sk = psock->sk;
 	bpf_compute_data_end_sk_skb(skb);
-	ret = bpf_prog_run_pin_on_cpu(prog, skb);
-	/* strparser clones the skb before handing it to a upper layer,
-	 * meaning skb_orphan has been called. We NULL sk on the way out
-	 * to ensure we don't trigger a BUG_ON() in skb/sk operations
-	 * later and because we are not charging the memory of this skb
-	 * to any socket yet.
-	 */
-	skb->sk = NULL;
-	return ret;
+	return bpf_prog_run_pin_on_cpu(prog, skb);
 }
 
 static struct sk_psock *sk_psock_from_strp(struct strparser *strp)
@@ -687,38 +763,35 @@ static void sk_psock_skb_redirect(struct sk_buff *skb)
 {
 	struct sk_psock *psock_other;
 	struct sock *sk_other;
-	bool ingress;
 
 	sk_other = tcp_skb_bpf_redirect_fetch(skb);
+	/* This error is a buggy BPF program, it returned a redirect
+	 * return code, but then didn't set a redirect interface.
+	 */
 	if (unlikely(!sk_other)) {
 		kfree_skb(skb);
 		return;
 	}
 	psock_other = sk_psock(sk_other);
+	/* This error indicates the socket is being torn down or had another
+	 * error that caused the pipe to break. We can't send a packet on
+	 * a socket that is in this state so we drop the skb.
+	 */
 	if (!psock_other || sock_flag(sk_other, SOCK_DEAD) ||
 	    !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) {
 		kfree_skb(skb);
 		return;
 	}
 
-	ingress = tcp_skb_bpf_ingress(skb);
-	if ((!ingress && sock_writeable(sk_other)) ||
-	    (ingress &&
-	     atomic_read(&sk_other->sk_rmem_alloc) <=
-	     sk_other->sk_rcvbuf)) {
-		if (!ingress)
-			skb_set_owner_w(skb, sk_other);
-		skb_queue_tail(&psock_other->ingress_skb, skb);
-		schedule_work(&psock_other->work);
-	} else {
-		kfree_skb(skb);
-	}
+	skb_queue_tail(&psock_other->ingress_skb, skb);
+	schedule_work(&psock_other->work);
 }
 
-static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict)
+static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict)
 {
 	switch (verdict) {
 	case __SK_REDIRECT:
+		skb_set_owner_r(skb, sk);
 		sk_psock_skb_redirect(skb);
 		break;
 	case __SK_PASS:
@@ -736,11 +809,17 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb)
 	rcu_read_lock();
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
+		/* We skip full set_owner_r here because if we do a SK_PASS
+		 * or SK_DROP we can skip skb memory accounting and use the
+		 * TLS context.
+		 */
+		skb->sk = psock->sk;
 		tcp_skb_bpf_redirect_clear(skb);
 		ret = sk_psock_bpf_run(psock, prog, skb);
 		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+		skb->sk = NULL;
 	}
-	sk_psock_tls_verdict_apply(skb, ret);
+	sk_psock_tls_verdict_apply(skb, psock->sk, ret);
 	rcu_read_unlock();
 	return ret;
 }
@@ -749,7 +828,9 @@ EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read);
 static void sk_psock_verdict_apply(struct sk_psock *psock,
 				   struct sk_buff *skb, int verdict)
 {
+	struct tcp_skb_cb *tcp;
 	struct sock *sk_other;
+	int err = -EIO;
 
 	switch (verdict) {
 	case __SK_PASS:
@@ -758,16 +839,24 @@ static void sk_psock_verdict_apply(struct sk_psock *psock,
 		    !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) {
 			goto out_free;
 		}
-		if (atomic_read(&sk_other->sk_rmem_alloc) <=
-		    sk_other->sk_rcvbuf) {
-			struct tcp_skb_cb *tcp = TCP_SKB_CB(skb);
 
-			tcp->bpf.flags |= BPF_F_INGRESS;
+		tcp = TCP_SKB_CB(skb);
+		tcp->bpf.flags |= BPF_F_INGRESS;
+
+		/* If the queue is empty then we can submit directly
+		 * into the msg queue. If its not empty we have to
+		 * queue work otherwise we may get OOO data. Otherwise,
+		 * if sk_psock_skb_ingress errors will be handled by
+		 * retrying later from workqueue.
+		 */
+		if (skb_queue_empty(&psock->ingress_skb)) {
+			err = sk_psock_skb_ingress_self(psock, skb);
+		}
+		if (err < 0) {
 			skb_queue_tail(&psock->ingress_skb, skb);
 			schedule_work(&psock->work);
-			break;
 		}
-		goto out_free;
+		break;
 	case __SK_REDIRECT:
 		sk_psock_skb_redirect(skb);
 		break;
@@ -792,9 +881,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb)
 		kfree_skb(skb);
 		goto out;
 	}
+	skb_set_owner_r(skb, sk);
 	prog = READ_ONCE(psock->progs.skb_verdict);
 	if (likely(prog)) {
-		skb_orphan(skb);
 		tcp_skb_bpf_redirect_clear(skb);
 		ret = sk_psock_bpf_run(psock, prog, skb);
 		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
@@ -817,8 +906,11 @@ static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb)
 
 	rcu_read_lock();
 	prog = READ_ONCE(psock->progs.skb_parser);
-	if (likely(prog))
+	if (likely(prog)) {
+		skb->sk = psock->sk;
 		ret = sk_psock_bpf_run(psock, prog, skb);
+		skb->sk = NULL;
+	}
 	rcu_read_unlock();
 	return ret;
 }
@@ -842,6 +934,57 @@ static void sk_psock_strp_data_ready(struct sock *sk)
 	rcu_read_unlock();
 }
 
+static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb,
+				 unsigned int offset, size_t orig_len)
+{
+	struct sock *sk = (struct sock *)desc->arg.data;
+	struct sk_psock *psock;
+	struct bpf_prog *prog;
+	int ret = __SK_DROP;
+	int len = skb->len;
+
+	/* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */
+	skb = skb_clone(skb, GFP_ATOMIC);
+	if (!skb) {
+		desc->error = -ENOMEM;
+		return 0;
+	}
+
+	rcu_read_lock();
+	psock = sk_psock(sk);
+	if (unlikely(!psock)) {
+		len = 0;
+		kfree_skb(skb);
+		goto out;
+	}
+	skb_set_owner_r(skb, sk);
+	prog = READ_ONCE(psock->progs.skb_verdict);
+	if (likely(prog)) {
+		tcp_skb_bpf_redirect_clear(skb);
+		ret = sk_psock_bpf_run(psock, prog, skb);
+		ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb));
+	}
+	sk_psock_verdict_apply(psock, skb, ret);
+out:
+	rcu_read_unlock();
+	return len;
+}
+
+static void sk_psock_verdict_data_ready(struct sock *sk)
+{
+	struct socket *sock = sk->sk_socket;
+	read_descriptor_t desc;
+
+	if (unlikely(!sock || !sock->ops || !sock->ops->read_sock))
+		return;
+
+	desc.arg.data = sk;
+	desc.error = 0;
+	desc.count = 1;
+
+	sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv);
+}
+
 static void sk_psock_write_space(struct sock *sk)
 {
 	struct sk_psock *psock;
@@ -871,6 +1014,19 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock)
 	return strp_init(&psock->parser.strp, sk, &cb);
 }
 
+void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock)
+{
+	struct sk_psock_parser *parser = &psock->parser;
+
+	if (parser->enabled)
+		return;
+
+	parser->saved_data_ready = sk->sk_data_ready;
+	sk->sk_data_ready = sk_psock_verdict_data_ready;
+	sk->sk_write_space = sk_psock_write_space;
+	parser->enabled = true;
+}
+
 void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock)
 {
 	struct sk_psock_parser *parser = &psock->parser;
@@ -896,3 +1052,15 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock)
 	strp_stop(&parser->strp);
 	parser->enabled = false;
 }
+
+void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock)
+{
+	struct sk_psock_parser *parser = &psock->parser;
+
+	if (!parser->enabled)
+		return;
+
+	sk->sk_data_ready = parser->saved_data_ready;
+	parser->saved_data_ready = NULL;
+	parser->enabled = false;
+}
diff --git a/net/core/sock.c b/net/core/sock.c
index 6c5c6b18eff4..bbcd4b97eddd 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -413,18 +413,6 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen,
 	return 0;
 }
 
-static void sock_warn_obsolete_bsdism(const char *name)
-{
-	static int warned;
-	static char warncomm[TASK_COMM_LEN];
-	if (strcmp(warncomm, current->comm) && warned < 5) {
-		strcpy(warncomm,  current->comm);
-		pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n",
-			warncomm, name);
-		warned++;
-	}
-}
-
 static bool sock_needs_netstamp(const struct sock *sk)
 {
 	switch (sk->sk_family) {
@@ -769,7 +757,6 @@ static void __sock_set_timestamps(struct sock *sk, bool val, bool new, bool ns)
 	} else {
 		sock_reset_flag(sk, SOCK_RCVTSTAMP);
 		sock_reset_flag(sk, SOCK_RCVTSTAMPNS);
-		sock_reset_flag(sk, SOCK_TSTAMP_NEW);
 	}
 }
 
@@ -984,7 +971,6 @@ set_sndbuf:
 		break;
 
 	case SO_BSDCOMPAT:
-		sock_warn_obsolete_bsdism("setsockopt");
 		break;
 
 	case SO_PASSCRED:
@@ -1007,8 +993,6 @@ set_sndbuf:
 		__sock_set_timestamps(sk, valbool, true, true);
 		break;
 	case SO_TIMESTAMPING_NEW:
-		sock_set_flag(sk, SOCK_TSTAMP_NEW);
-		fallthrough;
 	case SO_TIMESTAMPING_OLD:
 		if (val & ~SOF_TIMESTAMPING_MASK) {
 			ret = -EINVAL;
@@ -1037,16 +1021,14 @@ set_sndbuf:
 		}
 
 		sk->sk_tsflags = val;
+		sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
+
 		if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
 			sock_enable_timestamp(sk,
 					      SOCK_TIMESTAMPING_RX_SOFTWARE);
-		else {
-			if (optname == SO_TIMESTAMPING_NEW)
-				sock_reset_flag(sk, SOCK_TSTAMP_NEW);
-
+		else
 			sock_disable_timestamp(sk,
 					       (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE));
-		}
 		break;
 
 	case SO_RCVLOWAT:
@@ -1177,11 +1159,27 @@ set_sndbuf:
 				sk->sk_ll_usec = val;
 		}
 		break;
+	case SO_PREFER_BUSY_POLL:
+		if (valbool && !capable(CAP_NET_ADMIN))
+			ret = -EPERM;
+		else
+			WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
+		break;
+	case SO_BUSY_POLL_BUDGET:
+		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
+			ret = -EPERM;
+		} else {
+			if (val < 0 || val > U16_MAX)
+				ret = -EINVAL;
+			else
+				WRITE_ONCE(sk->sk_busy_poll_budget, val);
+		}
+		break;
 #endif
 
 	case SO_MAX_PACING_RATE:
 		{
-		unsigned long ulval = (val == ~0U) ? ~0UL : val;
+		unsigned long ulval = (val == ~0U) ? ~0UL : (unsigned int)val;
 
 		if (sizeof(ulval) != sizeof(val) &&
 		    optlen >= sizeof(ulval) &&
@@ -1387,7 +1385,6 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		break;
 
 	case SO_BSDCOMPAT:
-		sock_warn_obsolete_bsdism("getsockopt");
 		break;
 
 	case SO_TIMESTAMP_OLD:
@@ -1542,6 +1539,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	case SO_BUSY_POLL:
 		v.val = sk->sk_ll_usec;
 		break;
+	case SO_PREFER_BUSY_POLL:
+		v.val = READ_ONCE(sk->sk_prefer_busy_poll);
+		break;
 #endif
 
 	case SO_MAX_PACING_RATE:
@@ -2505,7 +2505,7 @@ bool sk_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 }
 EXPORT_SYMBOL(sk_page_frag_refill);
 
-static void __lock_sock(struct sock *sk)
+void __lock_sock(struct sock *sk)
 	__releases(&sk->sk_lock.slock)
 	__acquires(&sk->sk_lock.slock)
 {
@@ -2827,14 +2827,8 @@ EXPORT_SYMBOL(sock_no_mmap);
 void __receive_sock(struct file *file)
 {
 	struct socket *sock;
-	int error;
 
-	/*
-	 * The resulting value of "error" is ignored here since we only
-	 * need to take action when the file is a socket and testing
-	 * "sock" for NULL is sufficient.
-	 */
-	sock = sock_from_file(file, &error);
+	sock = sock_from_file(file);
 	if (sock) {
 		sock_update_netprioidx(&sock->sk->sk_cgrp_data);
 		sock_update_classid(&sock->sk->sk_cgrp_data);
@@ -2961,6 +2955,13 @@ void sk_stop_timer(struct sock *sk, struct timer_list* timer)
 }
 EXPORT_SYMBOL(sk_stop_timer);
 
+void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer)
+{
+	if (del_timer_sync(timer))
+		__sock_put(sk);
+}
+EXPORT_SYMBOL(sk_stop_timer_sync);
+
 void sock_init_data(struct socket *sock, struct sock *sk)
 {
 	sk_init_common(sk);
@@ -3090,7 +3091,7 @@ EXPORT_SYMBOL(release_sock);
  *
  *   sk_lock.slock unlocked, owned = 1, BH enabled
  */
-bool lock_sock_fast(struct sock *sk)
+bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock)
 {
 	might_sleep();
 	spin_lock_bh(&sk->sk_lock.slock);
@@ -3108,6 +3109,7 @@ bool lock_sock_fast(struct sock *sk)
 	 * The sk_lock has mutex_lock() semantics here:
 	 */
 	mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
+	__acquire(&sk->sk_lock.slock);
 	local_bh_enable();
 	return true;
 }
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index c13ffbd33d8d..c9c45b935f99 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -11,7 +11,7 @@
 #include <linux/tcp.h>
 #include <linux/workqueue.h>
 #include <linux/nospec.h>
-
+#include <linux/cookie.h>
 #include <linux/inet_diag.h>
 #include <linux/sock_diag.h>
 
@@ -19,16 +19,17 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
 static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
-static atomic64_t cookie_gen;
 
-u64 sock_gen_cookie(struct sock *sk)
+DEFINE_COOKIE(sock_cookie);
+
+u64 __sock_gen_cookie(struct sock *sk)
 {
 	while (1) {
 		u64 res = atomic64_read(&sk->sk_cookie);
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&cookie_gen);
+		res = gen_cookie_next(&sock_cookie);
 		atomic64_cmpxchg(&sk->sk_cookie, 0, res);
 	}
 }
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 119f52a99dc1..64b5ec14ff50 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */
 
 #include <linux/bpf.h>
+#include <linux/btf_ids.h>
 #include <linux/filter.h>
 #include <linux/errno.h>
 #include <linux/file.h>
@@ -26,8 +27,6 @@ struct bpf_stab {
 static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_stab *stab;
-	u64 cost;
-	int err;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -38,29 +37,22 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	    attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
-	stab = kzalloc(sizeof(*stab), GFP_USER);
+	stab = kzalloc(sizeof(*stab), GFP_USER | __GFP_ACCOUNT);
 	if (!stab)
 		return ERR_PTR(-ENOMEM);
 
 	bpf_map_init_from_attr(&stab->map, attr);
 	raw_spin_lock_init(&stab->lock);
 
-	/* Make sure page count doesn't overflow. */
-	cost = (u64) stab->map.max_entries * sizeof(struct sock *);
-	err = bpf_map_charge_init(&stab->map.memory, cost);
-	if (err)
-		goto free_stab;
-
 	stab->sks = bpf_map_area_alloc(stab->map.max_entries *
 				       sizeof(struct sock *),
 				       stab->map.numa_node);
-	if (stab->sks)
-		return &stab->map;
-	err = -ENOMEM;
-	bpf_map_charge_finish(&stab->map.memory);
-free_stab:
-	kfree(stab);
-	return ERR_PTR(err);
+	if (!stab->sks) {
+		kfree(stab);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return &stab->map;
 }
 
 int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
@@ -147,8 +139,8 @@ static void sock_map_add_link(struct sk_psock *psock,
 static void sock_map_del_link(struct sock *sk,
 			      struct sk_psock *psock, void *link_raw)
 {
+	bool strp_stop = false, verdict_stop = false;
 	struct sk_psock_link *link, *tmp;
-	bool strp_stop = false;
 
 	spin_lock_bh(&psock->link_lock);
 	list_for_each_entry_safe(link, tmp, &psock->link, list) {
@@ -158,14 +150,19 @@ static void sock_map_del_link(struct sock *sk,
 							     map);
 			if (psock->parser.enabled && stab->progs.skb_parser)
 				strp_stop = true;
+			if (psock->parser.enabled && stab->progs.skb_verdict)
+				verdict_stop = true;
 			list_del(&link->list);
 			sk_psock_free_link(link);
 		}
 	}
 	spin_unlock_bh(&psock->link_lock);
-	if (strp_stop) {
+	if (strp_stop || verdict_stop) {
 		write_lock_bh(&sk->sk_callback_lock);
-		sk_psock_stop_strp(sk, psock);
+		if (strp_stop)
+			sk_psock_stop_strp(sk, psock);
+		else
+			sk_psock_stop_verdict(sk, psock);
 		write_unlock_bh(&sk->sk_callback_lock);
 	}
 }
@@ -184,8 +181,6 @@ static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock)
 {
 	struct proto *prot;
 
-	sock_owned_by_me(sk);
-
 	switch (sk->sk_type) {
 	case SOCK_STREAM:
 		prot = tcp_bpf_get_proto(sk, psock);
@@ -231,20 +226,21 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 {
 	struct bpf_prog *msg_parser, *skb_parser, *skb_verdict;
 	struct sk_psock *psock;
-	bool skb_progs;
 	int ret;
 
 	skb_verdict = READ_ONCE(progs->skb_verdict);
-	skb_parser = READ_ONCE(progs->skb_parser);
-	skb_progs = skb_parser && skb_verdict;
-	if (skb_progs) {
+	if (skb_verdict) {
 		skb_verdict = bpf_prog_inc_not_zero(skb_verdict);
 		if (IS_ERR(skb_verdict))
 			return PTR_ERR(skb_verdict);
+	}
+
+	skb_parser = READ_ONCE(progs->skb_parser);
+	if (skb_parser) {
 		skb_parser = bpf_prog_inc_not_zero(skb_parser);
 		if (IS_ERR(skb_parser)) {
-			bpf_prog_put(skb_verdict);
-			return PTR_ERR(skb_parser);
+			ret = PTR_ERR(skb_parser);
+			goto out_put_skb_verdict;
 		}
 	}
 
@@ -253,7 +249,7 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 		msg_parser = bpf_prog_inc_not_zero(msg_parser);
 		if (IS_ERR(msg_parser)) {
 			ret = PTR_ERR(msg_parser);
-			goto out;
+			goto out_put_skb_parser;
 		}
 	}
 
@@ -265,15 +261,16 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 
 	if (psock) {
 		if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) ||
-		    (skb_progs  && READ_ONCE(psock->progs.skb_parser))) {
+		    (skb_parser  && READ_ONCE(psock->progs.skb_parser)) ||
+		    (skb_verdict && READ_ONCE(psock->progs.skb_verdict))) {
 			sk_psock_put(sk, psock);
 			ret = -EBUSY;
 			goto out_progs;
 		}
 	} else {
 		psock = sk_psock_init(sk, map->numa_node);
-		if (!psock) {
-			ret = -ENOMEM;
+		if (IS_ERR(psock)) {
+			ret = PTR_ERR(psock);
 			goto out_progs;
 		}
 	}
@@ -286,28 +283,32 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs,
 		goto out_drop;
 
 	write_lock_bh(&sk->sk_callback_lock);
-	if (skb_progs && !psock->parser.enabled) {
+	if (skb_parser && skb_verdict && !psock->parser.enabled) {
 		ret = sk_psock_init_strp(sk, psock);
-		if (ret) {
-			write_unlock_bh(&sk->sk_callback_lock);
-			goto out_drop;
-		}
+		if (ret)
+			goto out_unlock_drop;
 		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
 		psock_set_prog(&psock->progs.skb_parser, skb_parser);
 		sk_psock_start_strp(sk, psock);
+	} else if (!skb_parser && skb_verdict && !psock->parser.enabled) {
+		psock_set_prog(&psock->progs.skb_verdict, skb_verdict);
+		sk_psock_start_verdict(sk,psock);
 	}
 	write_unlock_bh(&sk->sk_callback_lock);
 	return 0;
+out_unlock_drop:
+	write_unlock_bh(&sk->sk_callback_lock);
 out_drop:
 	sk_psock_put(sk, psock);
 out_progs:
 	if (msg_parser)
 		bpf_prog_put(msg_parser);
-out:
-	if (skb_progs) {
-		bpf_prog_put(skb_verdict);
+out_put_skb_parser:
+	if (skb_parser)
 		bpf_prog_put(skb_parser);
-	}
+out_put_skb_verdict:
+	if (skb_verdict)
+		bpf_prog_put(skb_verdict);
 	return ret;
 }
 
@@ -322,8 +323,8 @@ static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk)
 
 	if (!psock) {
 		psock = sk_psock_init(sk, map->numa_node);
-		if (!psock)
-			return -ENOMEM;
+		if (IS_ERR(psock))
+			return PTR_ERR(psock);
 	}
 
 	ret = sock_map_init_proto(sk, psock);
@@ -384,7 +385,7 @@ static void *sock_map_lookup(struct bpf_map *map, void *key)
 	struct sock *sk;
 
 	sk = __sock_map_lookup_elem(map, *(u32 *)key);
-	if (!sk || !sk_fullsock(sk))
+	if (!sk)
 		return NULL;
 	if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt))
 		return NULL;
@@ -402,7 +403,7 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key)
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
-	sock_gen_cookie(sk);
+	__sock_gen_cookie(sk);
 	return &sk->sk_cookie;
 }
 
@@ -478,8 +479,6 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx,
 		return -EINVAL;
 	if (unlikely(idx >= map->max_entries))
 		return -E2BIG;
-	if (inet_csk_has_ulp(sk))
-		return -EINVAL;
 
 	link = sk_psock_init_link();
 	if (!link)
@@ -563,10 +562,12 @@ static bool sock_map_sk_state_allowed(const struct sock *sk)
 	return false;
 }
 
-static int sock_map_update_elem(struct bpf_map *map, void *key,
-				void *value, u64 flags)
+static int sock_hash_update_common(struct bpf_map *map, void *key,
+				   struct sock *sk, u64 flags);
+
+int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value,
+			     u64 flags)
 {
-	u32 idx = *(u32 *)key;
 	struct socket *sock;
 	struct sock *sk;
 	int ret;
@@ -595,14 +596,41 @@ static int sock_map_update_elem(struct bpf_map *map, void *key,
 	sock_map_sk_acquire(sk);
 	if (!sock_map_sk_state_allowed(sk))
 		ret = -EOPNOTSUPP;
+	else if (map->map_type == BPF_MAP_TYPE_SOCKMAP)
+		ret = sock_map_update_common(map, *(u32 *)key, sk, flags);
 	else
-		ret = sock_map_update_common(map, idx, sk, flags);
+		ret = sock_hash_update_common(map, key, sk, flags);
 	sock_map_sk_release(sk);
 out:
 	fput(sock->file);
 	return ret;
 }
 
+static int sock_map_update_elem(struct bpf_map *map, void *key,
+				void *value, u64 flags)
+{
+	struct sock *sk = (struct sock *)value;
+	int ret;
+
+	if (unlikely(!sk || !sk_fullsock(sk)))
+		return -EINVAL;
+
+	if (!sock_map_sk_is_suitable(sk))
+		return -EOPNOTSUPP;
+
+	local_bh_disable();
+	bh_lock_sock(sk);
+	if (!sock_map_sk_state_allowed(sk))
+		ret = -EOPNOTSUPP;
+	else if (map->map_type == BPF_MAP_TYPE_SOCKMAP)
+		ret = sock_map_update_common(map, *(u32 *)key, sk, flags);
+	else
+		ret = sock_hash_update_common(map, key, sk, flags);
+	bh_unlock_sock(sk);
+	local_bh_enable();
+	return ret;
+}
+
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops,
 	   struct bpf_map *, map, void *, key, u64, flags)
 {
@@ -681,8 +709,116 @@ const struct bpf_func_proto bpf_msg_redirect_map_proto = {
 	.arg4_type      = ARG_ANYTHING,
 };
 
+struct sock_map_seq_info {
+	struct bpf_map *map;
+	struct sock *sk;
+	u32 index;
+};
+
+struct bpf_iter__sockmap {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct bpf_map *, map);
+	__bpf_md_ptr(void *, key);
+	__bpf_md_ptr(struct sock *, sk);
+};
+
+DEFINE_BPF_ITER_FUNC(sockmap, struct bpf_iter_meta *meta,
+		     struct bpf_map *map, void *key,
+		     struct sock *sk)
+
+static void *sock_map_seq_lookup_elem(struct sock_map_seq_info *info)
+{
+	if (unlikely(info->index >= info->map->max_entries))
+		return NULL;
+
+	info->sk = __sock_map_lookup_elem(info->map, info->index);
+
+	/* can't return sk directly, since that might be NULL */
+	return info;
+}
+
+static void *sock_map_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(rcu)
+{
+	struct sock_map_seq_info *info = seq->private;
+
+	if (*pos == 0)
+		++*pos;
+
+	/* pairs with sock_map_seq_stop */
+	rcu_read_lock();
+	return sock_map_seq_lookup_elem(info);
+}
+
+static void *sock_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+	__must_hold(rcu)
+{
+	struct sock_map_seq_info *info = seq->private;
+
+	++*pos;
+	++info->index;
+
+	return sock_map_seq_lookup_elem(info);
+}
+
+static int sock_map_seq_show(struct seq_file *seq, void *v)
+	__must_hold(rcu)
+{
+	struct sock_map_seq_info *info = seq->private;
+	struct bpf_iter__sockmap ctx = {};
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, !v);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.map = info->map;
+	if (v) {
+		ctx.key = &info->index;
+		ctx.sk = info->sk;
+	}
+
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static void sock_map_seq_stop(struct seq_file *seq, void *v)
+	__releases(rcu)
+{
+	if (!v)
+		(void)sock_map_seq_show(seq, NULL);
+
+	/* pairs with sock_map_seq_start */
+	rcu_read_unlock();
+}
+
+static const struct seq_operations sock_map_seq_ops = {
+	.start	= sock_map_seq_start,
+	.next	= sock_map_seq_next,
+	.stop	= sock_map_seq_stop,
+	.show	= sock_map_seq_show,
+};
+
+static int sock_map_init_seq_private(void *priv_data,
+				     struct bpf_iter_aux_info *aux)
+{
+	struct sock_map_seq_info *info = priv_data;
+
+	info->map = aux->map;
+	return 0;
+}
+
+static const struct bpf_iter_seq_info sock_map_iter_seq_info = {
+	.seq_ops		= &sock_map_seq_ops,
+	.init_seq_private	= sock_map_init_seq_private,
+	.seq_priv_size		= sizeof(struct sock_map_seq_info),
+};
+
 static int sock_map_btf_id;
 const struct bpf_map_ops sock_map_ops = {
+	.map_meta_equal		= bpf_map_meta_equal,
 	.map_alloc		= sock_map_alloc,
 	.map_free		= sock_map_free,
 	.map_get_next_key	= sock_map_get_next_key,
@@ -694,6 +830,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_check_btf		= map_check_no_btf,
 	.map_btf_name		= "bpf_stab",
 	.map_btf_id		= &sock_map_btf_id,
+	.iter_seq_info		= &sock_map_iter_seq_info,
 };
 
 struct bpf_shtab_elem {
@@ -829,8 +966,9 @@ static struct bpf_shtab_elem *sock_hash_alloc_elem(struct bpf_shtab *htab,
 		}
 	}
 
-	new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
-			   htab->map.numa_node);
+	new = bpf_map_kmalloc_node(&htab->map, htab->elem_size,
+				   GFP_ATOMIC | __GFP_NOWARN,
+				   htab->map.numa_node);
 	if (!new) {
 		atomic_dec(&htab->count);
 		return ERR_PTR(-ENOMEM);
@@ -855,8 +993,6 @@ static int sock_hash_update_common(struct bpf_map *map, void *key,
 	WARN_ON_ONCE(!rcu_read_lock_held());
 	if (unlikely(flags > BPF_EXIST))
 		return -EINVAL;
-	if (inet_csk_has_ulp(sk))
-		return -EINVAL;
 
 	link = sk_psock_init_link();
 	if (!link)
@@ -915,45 +1051,6 @@ out_free:
 	return ret;
 }
 
-static int sock_hash_update_elem(struct bpf_map *map, void *key,
-				 void *value, u64 flags)
-{
-	struct socket *sock;
-	struct sock *sk;
-	int ret;
-	u64 ufd;
-
-	if (map->value_size == sizeof(u64))
-		ufd = *(u64 *)value;
-	else
-		ufd = *(u32 *)value;
-	if (ufd > S32_MAX)
-		return -EINVAL;
-
-	sock = sockfd_lookup(ufd, &ret);
-	if (!sock)
-		return ret;
-	sk = sock->sk;
-	if (!sk) {
-		ret = -EINVAL;
-		goto out;
-	}
-	if (!sock_map_sk_is_suitable(sk)) {
-		ret = -EOPNOTSUPP;
-		goto out;
-	}
-
-	sock_map_sk_acquire(sk);
-	if (!sock_map_sk_state_allowed(sk))
-		ret = -EOPNOTSUPP;
-	else
-		ret = sock_hash_update_common(map, key, sk, flags);
-	sock_map_sk_release(sk);
-out:
-	fput(sock->file);
-	return ret;
-}
-
 static int sock_hash_get_next_key(struct bpf_map *map, void *key,
 				  void *key_next)
 {
@@ -971,7 +1068,7 @@ static int sock_hash_get_next_key(struct bpf_map *map, void *key,
 	if (!elem)
 		goto find_first_elem;
 
-	elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&elem->node)),
+	elem_next = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&elem->node)),
 				     struct bpf_shtab_elem, node);
 	if (elem_next) {
 		memcpy(key_next, elem_next->key, key_size);
@@ -983,7 +1080,7 @@ static int sock_hash_get_next_key(struct bpf_map *map, void *key,
 find_first_elem:
 	for (; i < htab->buckets_num; i++) {
 		head = &sock_hash_select_bucket(htab, i)->head;
-		elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),
+		elem_next = hlist_entry_safe(rcu_dereference(hlist_first_rcu(head)),
 					     struct bpf_shtab_elem, node);
 		if (elem_next) {
 			memcpy(key_next, elem_next->key, key_size);
@@ -998,7 +1095,6 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 {
 	struct bpf_shtab *htab;
 	int i, err;
-	u64 cost;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -1011,7 +1107,7 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 	if (attr->key_size > MAX_BPF_STACK)
 		return ERR_PTR(-E2BIG);
 
-	htab = kzalloc(sizeof(*htab), GFP_USER);
+	htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT);
 	if (!htab)
 		return ERR_PTR(-ENOMEM);
 
@@ -1026,21 +1122,10 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 		goto free_htab;
 	}
 
-	cost = (u64) htab->buckets_num * sizeof(struct bpf_shtab_bucket) +
-	       (u64) htab->elem_size * htab->map.max_entries;
-	if (cost >= U32_MAX - PAGE_SIZE) {
-		err = -EINVAL;
-		goto free_htab;
-	}
-	err = bpf_map_charge_init(&htab->map.memory, cost);
-	if (err)
-		goto free_htab;
-
 	htab->buckets = bpf_map_area_alloc(htab->buckets_num *
 					   sizeof(struct bpf_shtab_bucket),
 					   htab->map.numa_node);
 	if (!htab->buckets) {
-		bpf_map_charge_finish(&htab->map.memory);
 		err = -ENOMEM;
 		goto free_htab;
 	}
@@ -1119,7 +1204,7 @@ static void *sock_hash_lookup_sys(struct bpf_map *map, void *key)
 	if (!sk)
 		return ERR_PTR(-ENOENT);
 
-	sock_gen_cookie(sk);
+	__sock_gen_cookie(sk);
 	return &sk->sk_cookie;
 }
 
@@ -1128,7 +1213,7 @@ static void *sock_hash_lookup(struct bpf_map *map, void *key)
 	struct sock *sk;
 
 	sk = __sock_hash_lookup_elem(map, key);
-	if (!sk || !sk_fullsock(sk))
+	if (!sk)
 		return NULL;
 	if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt))
 		return NULL;
@@ -1217,12 +1302,128 @@ const struct bpf_func_proto bpf_msg_redirect_hash_proto = {
 	.arg4_type      = ARG_ANYTHING,
 };
 
+struct sock_hash_seq_info {
+	struct bpf_map *map;
+	struct bpf_shtab *htab;
+	u32 bucket_id;
+};
+
+static void *sock_hash_seq_find_next(struct sock_hash_seq_info *info,
+				     struct bpf_shtab_elem *prev_elem)
+{
+	const struct bpf_shtab *htab = info->htab;
+	struct bpf_shtab_bucket *bucket;
+	struct bpf_shtab_elem *elem;
+	struct hlist_node *node;
+
+	/* try to find next elem in the same bucket */
+	if (prev_elem) {
+		node = rcu_dereference(hlist_next_rcu(&prev_elem->node));
+		elem = hlist_entry_safe(node, struct bpf_shtab_elem, node);
+		if (elem)
+			return elem;
+
+		/* no more elements, continue in the next bucket */
+		info->bucket_id++;
+	}
+
+	for (; info->bucket_id < htab->buckets_num; info->bucket_id++) {
+		bucket = &htab->buckets[info->bucket_id];
+		node = rcu_dereference(hlist_first_rcu(&bucket->head));
+		elem = hlist_entry_safe(node, struct bpf_shtab_elem, node);
+		if (elem)
+			return elem;
+	}
+
+	return NULL;
+}
+
+static void *sock_hash_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(rcu)
+{
+	struct sock_hash_seq_info *info = seq->private;
+
+	if (*pos == 0)
+		++*pos;
+
+	/* pairs with sock_hash_seq_stop */
+	rcu_read_lock();
+	return sock_hash_seq_find_next(info, NULL);
+}
+
+static void *sock_hash_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+	__must_hold(rcu)
+{
+	struct sock_hash_seq_info *info = seq->private;
+
+	++*pos;
+	return sock_hash_seq_find_next(info, v);
+}
+
+static int sock_hash_seq_show(struct seq_file *seq, void *v)
+	__must_hold(rcu)
+{
+	struct sock_hash_seq_info *info = seq->private;
+	struct bpf_iter__sockmap ctx = {};
+	struct bpf_shtab_elem *elem = v;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, !elem);
+	if (!prog)
+		return 0;
+
+	ctx.meta = &meta;
+	ctx.map = info->map;
+	if (elem) {
+		ctx.key = elem->key;
+		ctx.sk = elem->sk;
+	}
+
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static void sock_hash_seq_stop(struct seq_file *seq, void *v)
+	__releases(rcu)
+{
+	if (!v)
+		(void)sock_hash_seq_show(seq, NULL);
+
+	/* pairs with sock_hash_seq_start */
+	rcu_read_unlock();
+}
+
+static const struct seq_operations sock_hash_seq_ops = {
+	.start	= sock_hash_seq_start,
+	.next	= sock_hash_seq_next,
+	.stop	= sock_hash_seq_stop,
+	.show	= sock_hash_seq_show,
+};
+
+static int sock_hash_init_seq_private(void *priv_data,
+				     struct bpf_iter_aux_info *aux)
+{
+	struct sock_hash_seq_info *info = priv_data;
+
+	info->map = aux->map;
+	info->htab = container_of(aux->map, struct bpf_shtab, map);
+	return 0;
+}
+
+static const struct bpf_iter_seq_info sock_hash_iter_seq_info = {
+	.seq_ops		= &sock_hash_seq_ops,
+	.init_seq_private	= sock_hash_init_seq_private,
+	.seq_priv_size		= sizeof(struct sock_hash_seq_info),
+};
+
 static int sock_hash_map_btf_id;
 const struct bpf_map_ops sock_hash_ops = {
+	.map_meta_equal		= bpf_map_meta_equal,
 	.map_alloc		= sock_hash_alloc,
 	.map_free		= sock_hash_free,
 	.map_get_next_key	= sock_hash_get_next_key,
-	.map_update_elem	= sock_hash_update_elem,
+	.map_update_elem	= sock_map_update_elem,
 	.map_delete_elem	= sock_hash_delete_elem,
 	.map_lookup_elem	= sock_hash_lookup,
 	.map_lookup_elem_sys_only = sock_hash_lookup_sys,
@@ -1230,6 +1431,7 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_check_btf		= map_check_no_btf,
 	.map_btf_name		= "bpf_shtab",
 	.map_btf_id		= &sock_hash_map_btf_id,
+	.iter_seq_info		= &sock_hash_iter_seq_info,
 };
 
 static struct sk_psock_progs *sock_map_progs(struct bpf_map *map)
@@ -1340,3 +1542,62 @@ void sock_map_close(struct sock *sk, long timeout)
 	release_sock(sk);
 	saved_close(sk, timeout);
 }
+
+static int sock_map_iter_attach_target(struct bpf_prog *prog,
+				       union bpf_iter_link_info *linfo,
+				       struct bpf_iter_aux_info *aux)
+{
+	struct bpf_map *map;
+	int err = -EINVAL;
+
+	if (!linfo->map.map_fd)
+		return -EBADF;
+
+	map = bpf_map_get_with_uref(linfo->map.map_fd);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	if (map->map_type != BPF_MAP_TYPE_SOCKMAP &&
+	    map->map_type != BPF_MAP_TYPE_SOCKHASH)
+		goto put_map;
+
+	if (prog->aux->max_rdonly_access > map->key_size) {
+		err = -EACCES;
+		goto put_map;
+	}
+
+	aux->map = map;
+	return 0;
+
+put_map:
+	bpf_map_put_with_uref(map);
+	return err;
+}
+
+static void sock_map_iter_detach_target(struct bpf_iter_aux_info *aux)
+{
+	bpf_map_put_with_uref(aux->map);
+}
+
+static struct bpf_iter_reg sock_map_iter_reg = {
+	.target			= "sockmap",
+	.attach_target		= sock_map_iter_attach_target,
+	.detach_target		= sock_map_iter_detach_target,
+	.show_fdinfo		= bpf_iter_map_show_fdinfo,
+	.fill_link_info		= bpf_iter_map_fill_link_info,
+	.ctx_arg_info_size	= 2,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__sockmap, key),
+		  PTR_TO_RDONLY_BUF_OR_NULL },
+		{ offsetof(struct bpf_iter__sockmap, sk),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+};
+
+static int __init bpf_sockmap_iter_init(void)
+{
+	sock_map_iter_reg.ctx_arg_info[1].btf_id =
+		btf_sock_ids[BTF_SOCK_TYPE_SOCK];
+	return bpf_iter_reg_target(&sock_map_iter_reg);
+}
+late_initcall(bpf_sockmap_iter_init);
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index bbdd3c7b6cb5..b065f0a103ed 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -293,7 +293,7 @@ select_by_hash:
 			i = j = reciprocal_scale(hash, socks);
 			while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) {
 				i++;
-				if (i >= reuse->num_socks)
+				if (i >= socks)
 					i = 0;
 				if (i == j)
 					goto out;
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index 6ada114bbcca..d86d8d11cfe4 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -22,7 +22,7 @@
 #include <net/busy_poll.h>
 #include <net/pkt_sched.h>
 
-static int two __maybe_unused = 2;
+static int two = 2;
 static int three = 3;
 static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
@@ -546,7 +546,7 @@ static struct ctl_table net_core_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
+		.extra2		= &two,
 	},
 	{
 		.procname	= "devconf_inherit_init_net",
@@ -587,6 +587,19 @@ static struct ctl_table netns_core_table[] = {
 	{ }
 };
 
+static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str)
+{
+	/* fallback tunnels for initns only */
+	if (!strncmp(str, "initns", 6))
+		sysctl_fb_tunnels_only_for_init_net = 1;
+	/* no fallback tunnels anywhere */
+	else if (!strncmp(str, "none", 4))
+		sysctl_fb_tunnels_only_for_init_net = 2;
+
+	return 1;
+}
+__setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup);
+
 static __net_init int sysctl_core_net_init(struct net *net)
 {
 	struct ctl_table *tbl;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 48aba933a5a8..3a8c9ab4ecbe 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -158,7 +158,7 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)
 
 /* Returns 0 on success, negative on failure */
 int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index)
+		     struct net_device *dev, u32 queue_index, unsigned int napi_id)
 {
 	if (xdp_rxq->reg_state == REG_STATE_UNUSED) {
 		WARN(1, "Driver promised not to register this");
@@ -179,6 +179,7 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
 	xdp_rxq_info_init(xdp_rxq);
 	xdp_rxq->dev = dev;
 	xdp_rxq->queue_index = queue_index;
+	xdp_rxq->napi_id = napi_id;
 
 	xdp_rxq->reg_state = REG_STATE_REGISTERED;
 	return 0;
@@ -335,11 +336,10 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model);
  * scenarios (e.g. queue full), it is possible to return the xdp_frame
  * while still leveraging this protection.  The @napi_direct boolean
  * is used for those calls sites.  Thus, allowing for faster recycling
- * of xdp_frames/pages in those cases. This path is never used by the
- * MEM_TYPE_XSK_BUFF_POOL memory type, so it's explicitly not part of
- * the switch-statement.
+ * of xdp_frames/pages in those cases.
  */
-static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct)
+static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
+			 struct xdp_buff *xdp)
 {
 	struct xdp_mem_allocator *xa;
 	struct page *page;
@@ -361,6 +361,10 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct)
 		page = virt_to_page(data); /* Assumes order0 page*/
 		put_page(page);
 		break;
+	case MEM_TYPE_XSK_BUFF_POOL:
+		/* NB! Only valid from an xdp_buff! */
+		xsk_buff_free(xdp);
+		break;
 	default:
 		/* Not possible, checked in xdp_rxq_info_reg_mem_model() */
 		WARN(1, "Incorrect XDP memory type (%d) usage", mem->type);
@@ -370,19 +374,73 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct)
 
 void xdp_return_frame(struct xdp_frame *xdpf)
 {
-	__xdp_return(xdpf->data, &xdpf->mem, false);
+	__xdp_return(xdpf->data, &xdpf->mem, false, NULL);
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame);
 
 void xdp_return_frame_rx_napi(struct xdp_frame *xdpf)
 {
-	__xdp_return(xdpf->data, &xdpf->mem, true);
+	__xdp_return(xdpf->data, &xdpf->mem, true, NULL);
 }
 EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi);
 
+/* XDP bulk APIs introduce a defer/flush mechanism to return
+ * pages belonging to the same xdp_mem_allocator object
+ * (identified via the mem.id field) in bulk to optimize
+ * I-cache and D-cache.
+ * The bulk queue size is set to 16 to be aligned to how
+ * XDP_REDIRECT bulking works. The bulk is flushed when
+ * it is full or when mem.id changes.
+ * xdp_frame_bulk is usually stored/allocated on the function
+ * call-stack to avoid locking penalties.
+ */
+void xdp_flush_frame_bulk(struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_allocator *xa = bq->xa;
+
+	if (unlikely(!xa || !bq->count))
+		return;
+
+	page_pool_put_page_bulk(xa->page_pool, bq->q, bq->count);
+	/* bq->xa is not cleared to save lookup, if mem.id same in next bulk */
+	bq->count = 0;
+}
+EXPORT_SYMBOL_GPL(xdp_flush_frame_bulk);
+
+/* Must be called with rcu_read_lock held */
+void xdp_return_frame_bulk(struct xdp_frame *xdpf,
+			   struct xdp_frame_bulk *bq)
+{
+	struct xdp_mem_info *mem = &xdpf->mem;
+	struct xdp_mem_allocator *xa;
+
+	if (mem->type != MEM_TYPE_PAGE_POOL) {
+		__xdp_return(xdpf->data, &xdpf->mem, false, NULL);
+		return;
+	}
+
+	xa = bq->xa;
+	if (unlikely(!xa)) {
+		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+		bq->count = 0;
+		bq->xa = xa;
+	}
+
+	if (bq->count == XDP_BULK_QUEUE_SIZE)
+		xdp_flush_frame_bulk(bq);
+
+	if (unlikely(mem->id != xa->mem.id)) {
+		xdp_flush_frame_bulk(bq);
+		bq->xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
+	}
+
+	bq->q[bq->count++] = xdpf->data;
+}
+EXPORT_SYMBOL_GPL(xdp_return_frame_bulk);
+
 void xdp_return_buff(struct xdp_buff *xdp)
 {
-	__xdp_return(xdp->data, &xdp->rxq->mem, true);
+	__xdp_return(xdp->data, &xdp->rxq->mem, true, xdp);
 }
 
 /* Only called for MEM_TYPE_PAGE_POOL see xdp.h */
@@ -400,18 +458,6 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem)
 }
 EXPORT_SYMBOL_GPL(__xdp_release_frame);
 
-bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
-			     struct netdev_bpf *bpf)
-{
-	if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) {
-		NL_SET_ERR_MSG(bpf->extack,
-			       "program loaded with different flags");
-		return false;
-	}
-	return true;
-}
-EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok);
-
 void xdp_attachment_setup(struct xdp_attachment_info *info,
 			  struct netdev_bpf *bpf)
 {
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 16014ad19406..653e3bc9c87b 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1765,6 +1765,8 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	fn = &reply_funcs[dcb->cmd];
 	if (!fn->cb)
 		return -EOPNOTSUPP;
+	if (fn->type == RTM_SETDCB && !netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
 
 	if (!tb[DCB_ATTR_IFNAME])
 		return -EINVAL;
@@ -1827,6 +1829,8 @@ static int dcb_app_add(const struct dcb_app *app, int ifindex)
 
 /**
  * dcb_getapp - retrieve the DCBX application user priority
+ * @dev: network interface
+ * @app: application to get user priority of
  *
  * On success returns a non-zero 802.1p user priority bitmap
  * otherwise returns 0 as the invalid user priority bitmap to
@@ -1849,6 +1853,8 @@ EXPORT_SYMBOL(dcb_getapp);
 
 /**
  * dcb_setapp - add CEE dcb application data to app list
+ * @dev: network interface
+ * @new: application data to add
  *
  * Priority 0 is an invalid priority in CEE spec. This routine
  * removes applications from the app list if the priority is
@@ -1890,6 +1896,8 @@ EXPORT_SYMBOL(dcb_setapp);
 
 /**
  * dcb_ieee_getapp_mask - retrieve the IEEE DCB application priority
+ * @dev: network interface
+ * @app: where to store the retrieve application data
  *
  * Helper routine which on success returns a non-zero 802.1Qaz user
  * priority bitmap otherwise returns 0 to indicate the dcb_app was
@@ -1912,6 +1920,8 @@ EXPORT_SYMBOL(dcb_ieee_getapp_mask);
 
 /**
  * dcb_ieee_setapp - add IEEE dcb application data to app list
+ * @dev: network interface
+ * @new: application data to add
  *
  * This adds Application data to the list. Multiple application
  * entries may exists for the same selector and protocol as long
@@ -1946,6 +1956,8 @@ EXPORT_SYMBOL(dcb_ieee_setapp);
 
 /**
  * dcb_ieee_delapp - delete IEEE dcb application data from list
+ * @dev: network interface
+ * @del: application data to delete
  *
  * This removes a matching APP data from the APP list
  */
@@ -1975,7 +1987,7 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del)
 }
 EXPORT_SYMBOL(dcb_ieee_delapp);
 
-/**
+/*
  * dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from
  * priorities to the DSCP values assigned to that priority. Initialize p_map
  * such that each map element holds a bit mask of DSCP values configured for
@@ -2004,7 +2016,7 @@ void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev,
 }
 EXPORT_SYMBOL(dcb_ieee_getapp_prio_dscp_mask_map);
 
-/**
+/*
  * dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from
  * DSCP values to the priorities assigned to that DSCP value. Initialize p_map
  * such that each map element holds a bit mask of priorities configured for a
@@ -2031,7 +2043,7 @@ dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev,
 }
 EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map);
 
-/**
+/*
  * Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet
  * type, with valid PID values >= 1536. A special meaning is then assigned to
  * protocol value of 0: "default priority. For use when priority is not
diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c
index 0a72510d5de1..c4bbac99740d 100644
--- a/net/dccp/ackvec.c
+++ b/net/dccp/ackvec.c
@@ -242,6 +242,8 @@ static void dccp_ackvec_add_new(struct dccp_ackvec *av, u32 num_packets,
 
 /**
  * dccp_ackvec_input  -  Register incoming packet in the buffer
+ * @av: Ack Vector to register packet to
+ * @skb: Packet to register
  */
 void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb)
 {
@@ -273,8 +275,11 @@ void dccp_ackvec_input(struct dccp_ackvec *av, struct sk_buff *skb)
 
 /**
  * dccp_ackvec_clear_state  -  Perform house-keeping / garbage-collection
+ * @av: Ack Vector record to clean
+ * @ackno: last Ack Vector which has been acknowledged
+ *
  * This routine is called when the peer acknowledges the receipt of Ack Vectors
- * up to and including @ackno. While based on on section A.3 of RFC 4340, here
+ * up to and including @ackno. While based on section A.3 of RFC 4340, here
  * are additional precautions to prevent corrupted buffer state. In particular,
  * we use tail_ackno to identify outdated records; it always marks the earliest
  * packet of group (2) in 11.4.2.
diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c
index 1e9bb121ba72..6beac5d348e2 100644
--- a/net/dccp/ccid.c
+++ b/net/dccp/ccid.c
@@ -76,7 +76,7 @@ int ccid_getsockopt_builtin_ccids(struct sock *sk, int len,
 	return err;
 }
 
-static struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...)
+static __printf(3, 4) struct kmem_cache *ccid_kmem_cache_create(int obj_size, char *slab_name_fmt, const char *fmt,...)
 {
 	struct kmem_cache *slab;
 	va_list args;
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 3da1f77bd039..4d9823d6dced 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -181,6 +181,9 @@ MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation");
 
 /**
  * ccid2_update_used_window  -  Track how much of cwnd is actually used
+ * @hc: socket to update window
+ * @new_wnd: new window values to add into the filter
+ *
  * This is done in addition to CWV. The sender needs to have an idea of how many
  * packets may be in flight, to set the local Sequence Window value accordingly
  * (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the
@@ -349,6 +352,8 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len)
 
 /**
  * ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm
+ * @sk: socket to perform estimator on
+ *
  * This code is almost identical with TCP's tcp_rtt_estimator(), since
  * - it has a higher sampling frequency (recommended by RFC 1323),
  * - the RTO does not collapse into RTT due to RTTVAR going towards zero,
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index b9ee1a4a8955..ca8670f78ac6 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -79,6 +79,8 @@ static inline u64 rfc3390_initial_rate(struct sock *sk)
 
 /**
  * ccid3_update_send_interval  -  Calculate new t_ipi = s / X_inst
+ * @hc: socket to have the send interval updated
+ *
  * This respects the granularity of X_inst (64 * bytes/second).
  */
 static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc)
@@ -99,6 +101,7 @@ static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now)
 
 /**
  * ccid3_hc_tx_update_x  -  Update allowed sending rate X
+ * @sk: socket to be updated
  * @stamp: most recent time if available - can be left NULL.
  *
  * This function tracks draft rfc3448bis, check there for latest details.
@@ -151,6 +154,7 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp)
 
 /**
  *	ccid3_hc_tx_update_s - Track the mean packet size `s'
+ *	@hc: socket to be updated
  *	@len: DCCP packet payload size in bytes
  *
  *	cf. RFC 4342, 5.3 and  RFC 3448, 4.1
@@ -259,6 +263,7 @@ out:
 
 /**
  * ccid3_hc_tx_send_packet  -  Delay-based dequeueing of TX packets
+ * @sk: socket to send packet from
  * @skb: next packet candidate to send on @sk
  *
  * This function uses the convention of ccid_packet_dequeue_eval() and
@@ -655,6 +660,7 @@ static int ccid3_hc_rx_insert_options(struct sock *sk, struct sk_buff *skb)
 
 /**
  * ccid3_first_li  -  Implements [RFC 5348, 6.3.1]
+ * @sk: socket to calculate loss interval for
  *
  * Determine the length of the first loss interval via inverse lookup.
  * Assume that X_recv can be computed by the throughput equation
diff --git a/net/dccp/ccids/lib/loss_interval.c b/net/dccp/ccids/lib/loss_interval.c
index 67abad695e66..da95319842bb 100644
--- a/net/dccp/ccids/lib/loss_interval.c
+++ b/net/dccp/ccids/lib/loss_interval.c
@@ -79,6 +79,9 @@ static void tfrc_lh_calc_i_mean(struct tfrc_loss_hist *lh)
 
 /**
  * tfrc_lh_update_i_mean  -  Update the `open' loss interval I_0
+ * @lh: histogram to update
+ * @skb: received socket triggering loss interval update
+ *
  * For recomputing p: returns `true' if p > p_prev  <=>  1/p < 1/p_prev
  */
 u8 tfrc_lh_update_i_mean(struct tfrc_loss_hist *lh, struct sk_buff *skb)
diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c
index af08e2df7108..0cdda3c66fb5 100644
--- a/net/dccp/ccids/lib/packet_history.c
+++ b/net/dccp/ccids/lib/packet_history.c
@@ -385,6 +385,9 @@ static inline struct tfrc_rx_hist_entry *
 
 /**
  * tfrc_rx_hist_sample_rtt  -  Sample RTT from timestamp / CCVal
+ * @h: receive histogram
+ * @skb: packet containing timestamp.
+ *
  * Based on ideas presented in RFC 4342, 8.1. Returns 0 if it was not able
  * to compute a sample with given data - calling function should check this.
  */
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 788dd629c420..305f56804832 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -996,6 +996,8 @@ int dccp_feat_finalise_settings(struct dccp_sock *dp)
 
 /**
  * dccp_feat_server_ccid_dependencies  -  Resolve CCID-dependent features
+ * @dreq: server socket to resolve
+ *
  * It is the server which resolves the dependencies once the CCID has been
  * fully negotiated. If no CCID has been negotiated, it uses the default CCID.
  */
@@ -1033,6 +1035,10 @@ static int dccp_feat_preflist_match(u8 *servlist, u8 slen, u8 *clilist, u8 clen)
 
 /**
  * dccp_feat_prefer  -  Move preferred entry to the start of array
+ * @preferred_value: entry to move to start of array
+ * @array: array of preferred entries
+ * @array_len: size of the array
+ *
  * Reorder the @array_len elements in @array so that @preferred_value comes
  * first. Returns >0 to indicate that @preferred_value does occur in @array.
  */
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 9c28c8251125..2455b0c0e486 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -427,7 +427,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
-	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
 	if (*own_req)
 		ireq->ireq_opt = NULL;
 	else
@@ -464,7 +464,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
 		.fl4_dport = dccp_hdr(skb)->dccph_sport,
 	};
 
-	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
 		IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
@@ -495,7 +495,8 @@ static int dccp_v4_send_response(const struct sock *sk, struct request_sock *req
 		rcu_read_lock();
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt));
+					    rcu_dereference(ireq->ireq_opt),
+					    inet_sk(sk)->tos);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -537,7 +538,8 @@ static void dccp_v4_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 	local_bh_disable();
 	bh_lock_sock(ctl_sk);
 	err = ip_build_and_send_pkt(skb, ctl_sk,
-				    rxiph->daddr, rxiph->saddr, NULL);
+				    rxiph->daddr, rxiph->saddr, NULL,
+				    inet_sk(ctl_sk)->tos);
 	bh_unlock_sock(ctl_sk);
 
 	if (net_xmit_eval(err) == 0) {
@@ -731,7 +733,7 @@ int dccp_invalid_packet(struct sk_buff *skb)
 		return 1;
 	}
 	/*
-	 * If P.Data Offset is too too large for packet, drop packet and return
+	 * If P.Data Offset is too large for packet, drop packet and return
 	 */
 	if (!pskb_may_pull(skb, dccph_doff * sizeof(u32))) {
 		DCCP_WARN("P.Data Offset(%u) too large\n", dccph_doff);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index ef4ab28cfde0..1f73603913f5 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -203,7 +203,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req
 	fl6.flowi6_oif = ireq->ir_iif;
 	fl6.fl6_dport = ireq->ir_rmt_port;
 	fl6.fl6_sport = htons(ireq->ir_num);
-	security_req_classify_flow(req, flowi6_to_flowi(&fl6));
+	security_req_classify_flow(req, flowi6_to_flowi_common(&fl6));
 
 
 	rcu_read_lock();
@@ -279,7 +279,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb)
 	fl6.flowi6_oif = inet6_iif(rxskb);
 	fl6.fl6_dport = dccp_hdr(skb)->dccph_dport;
 	fl6.fl6_sport = dccp_hdr(skb)->dccph_sport;
-	security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(rxskb, flowi6_to_flowi_common(&fl6));
 
 	/* sk = NULL, but it is safe for now. RST socket required. */
 	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
@@ -533,7 +533,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 		dccp_done(newsk);
 		goto out;
 	}
-	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), NULL);
 	/* Clone pktoptions received with SYN, if we own the req */
 	if (*own_req && ireq->pktopts) {
 		newnp->pktoptions = skb_clone(ireq->pktopts, GFP_ATOMIC);
@@ -907,7 +907,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	fl6.flowi6_oif = sk->sk_bound_dev_if;
 	fl6.fl6_dport = usin->sin6_port;
 	fl6.fl6_sport = inet->inet_sport;
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 50e6d5699bb2..b8a24734385e 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -143,6 +143,8 @@ static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
 
 /**
  * dccp_determine_ccmps  -  Find out about CCID-specific packet-size limits
+ * @dp: socket to find packet size limits of
+ *
  * We only consider the HC-sender CCID for setting the CCMPS (RFC 4340, 14.),
  * since the RX CCID is restricted to feedback packets (Acks), which are small
  * in comparison with the data traffic. A value of 0 means "no current CCMPS".
@@ -236,6 +238,8 @@ static int dccp_wait_for_ccid(struct sock *sk, unsigned long delay)
 
 /**
  * dccp_xmit_packet  -  Send data packet under control of CCID
+ * @sk: socket to send data packet on
+ *
  * Transmits next-queued payload and informs CCID to account for the packet.
  */
 static void dccp_xmit_packet(struct sock *sk)
@@ -296,6 +300,9 @@ static void dccp_xmit_packet(struct sock *sk)
 
 /**
  * dccp_flush_write_queue  -  Drain queue at end of connection
+ * @sk: socket to be drained
+ * @time_budget: time allowed to drain the queue
+ *
  * Since dccp_sendmsg queues packets without waiting for them to be sent, it may
  * happen that the TX queue is not empty at the end of a connection. We give the
  * HC-sender CCID a grace period of up to @time_budget jiffies. If this function
@@ -367,6 +374,8 @@ void dccp_write_xmit(struct sock *sk)
 
 /**
  * dccp_retransmit_skb  -  Retransmit Request, Close, or CloseReq packets
+ * @sk: socket to perform retransmit on
+ *
  * There are only four retransmittable packet types in DCCP:
  * - Request  in client-REQUEST  state (sec. 8.1.1),
  * - CloseReq in server-CLOSEREQ state (sec. 8.3),
diff --git a/net/dccp/qpolicy.c b/net/dccp/qpolicy.c
index db2448c33a62..5ba204ec0aca 100644
--- a/net/dccp/qpolicy.c
+++ b/net/dccp/qpolicy.c
@@ -65,14 +65,16 @@ static bool qpolicy_prio_full(struct sock *sk)
  * @push: add a new @skb to the write queue
  * @full: indicates that no more packets will be admitted
  * @top:  peeks at whatever the queueing policy defines as its `top'
+ * @params: parameter passed to policy operation
  */
-static struct dccp_qpolicy_operations {
+struct dccp_qpolicy_operations {
 	void		(*push)	(struct sock *sk, struct sk_buff *skb);
 	bool		(*full) (struct sock *sk);
 	struct sk_buff*	(*top)  (struct sock *sk);
 	__be32		params;
+};
 
-} qpol_table[DCCPQ_POLICY_MAX] = {
+static struct dccp_qpolicy_operations qpol_table[DCCPQ_POLICY_MAX] = {
 	[DCCPQ_POLICY_SIMPLE] = {
 		.push   = qpolicy_simple_push,
 		.full   = qpolicy_simple_full,
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 0e06dfc32273..db768f223ef7 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -85,7 +85,7 @@ static void dccp_retransmit_timer(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	/*
-	 * More than than 4MSL (8 minutes) has passed, a RESET(aborted) was
+	 * More than 4MSL (8 minutes) has passed, a RESET(aborted) was
 	 * sent, no need to retransmit, this sock is dead.
 	 */
 	if (dccp_write_timeout(sk))
@@ -176,7 +176,6 @@ static void dccp_delack_timer(struct timer_list *t)
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
 		/* Try again later. */
-		icsk->icsk_ack.blocked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		sk_reset_timer(sk, &icsk->icsk_delack_timer,
 			       jiffies + TCP_DELACK_MIN);
@@ -216,13 +215,14 @@ out:
 
 /**
  * dccp_write_xmitlet  -  Workhorse for CCID packet dequeueing interface
- * @data: Socket to act on
+ * @t: pointer to the tasklet associated with this handler
  *
  * See the comments above %ccid_dequeueing_decision for supported modes.
  */
-static void dccp_write_xmitlet(unsigned long data)
+static void dccp_write_xmitlet(struct tasklet_struct *t)
 {
-	struct sock *sk = (struct sock *)data;
+	struct dccp_sock *dp = from_tasklet(dp, t, dccps_xmitlet);
+	struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk))
@@ -236,16 +236,15 @@ static void dccp_write_xmitlet(unsigned long data)
 static void dccp_write_xmit_timer(struct timer_list *t)
 {
 	struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer);
-	struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
 
-	dccp_write_xmitlet((unsigned long)sk);
+	dccp_write_xmitlet(&dp->dccps_xmitlet);
 }
 
 void dccp_init_xmit_timers(struct sock *sk)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
 
-	tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk);
+	tasklet_setup(&dp->dccps_xmitlet, dccp_write_xmitlet);
 	timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0);
 	inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer,
 				  &dccp_keepalive_timer);
diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c
index 15d42353f1a3..d1c50a48614b 100644
--- a/net/decnet/dn_dev.c
+++ b/net/decnet/dn_dev.c
@@ -658,7 +658,7 @@ static int dn_nl_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	ifa->ifa_dev = dn_db;
 
 	if (tb[IFA_LABEL])
-		nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
+		nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
 	else
 		memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
 
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 4cac31d22a50..2193ae529e75 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1035,7 +1035,7 @@ source_ok:
 			fld.saddr = dnet_select_source(dev_out, 0,
 						       RT_SCOPE_HOST);
 			if (!fld.daddr)
-				goto out;
+				goto done;
 		}
 		fld.flowidn_oif = LOOPBACK_IFINDEX;
 		res.type = RTN_LOCAL;
diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig
index 1f9b9b11008c..dfecd7b22fd7 100644
--- a/net/dsa/Kconfig
+++ b/net/dsa/Kconfig
@@ -56,20 +56,31 @@ config NET_DSA_TAG_BRCM_PREPEND
 	  Broadcom switches which places the tag before the Ethernet header
 	  (prepended).
 
+config NET_DSA_TAG_HELLCREEK
+	tristate "Tag driver for Hirschmann Hellcreek TSN switches"
+	help
+	  Say Y or M if you want to enable support for tagging frames
+	  for the Hirschmann Hellcreek TSN switches.
+
 config NET_DSA_TAG_GSWIP
 	tristate "Tag driver for Lantiq / Intel GSWIP switches"
 	help
 	  Say Y or M if you want to enable support for tagging frames for the
 	  Lantiq / Intel GSWIP switches.
 
+config NET_DSA_TAG_DSA_COMMON
+	tristate
+
 config NET_DSA_TAG_DSA
 	tristate "Tag driver for Marvell switches using DSA headers"
+	select NET_DSA_TAG_DSA_COMMON
 	help
 	  Say Y or M if you want to enable support for tagging frames for the
 	  Marvell switches which use DSA headers.
 
 config NET_DSA_TAG_EDSA
 	tristate "Tag driver for Marvell switches using EtherType DSA headers"
+	select NET_DSA_TAG_DSA_COMMON
 	help
 	  Say Y or M if you want to enable support for tagging frames for the
 	  Marvell switches which use EtherType DSA headers.
diff --git a/net/dsa/Makefile b/net/dsa/Makefile
index 4f47b2025ff5..0fb2b75a7ae3 100644
--- a/net/dsa/Makefile
+++ b/net/dsa/Makefile
@@ -7,9 +7,9 @@ dsa_core-y += dsa.o dsa2.o master.o port.o slave.o switch.o
 obj-$(CONFIG_NET_DSA_TAG_8021Q) += tag_8021q.o
 obj-$(CONFIG_NET_DSA_TAG_AR9331) += tag_ar9331.o
 obj-$(CONFIG_NET_DSA_TAG_BRCM_COMMON) += tag_brcm.o
-obj-$(CONFIG_NET_DSA_TAG_DSA) += tag_dsa.o
-obj-$(CONFIG_NET_DSA_TAG_EDSA) += tag_edsa.o
+obj-$(CONFIG_NET_DSA_TAG_DSA_COMMON) += tag_dsa.o
 obj-$(CONFIG_NET_DSA_TAG_GSWIP) += tag_gswip.o
+obj-$(CONFIG_NET_DSA_TAG_HELLCREEK) += tag_hellcreek.o
 obj-$(CONFIG_NET_DSA_TAG_KSZ) += tag_ksz.o
 obj-$(CONFIG_NET_DSA_TAG_RTL4_A) += tag_rtl4_a.o
 obj-$(CONFIG_NET_DSA_TAG_LAN9303) += tag_lan9303.o
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 1ce9ba8cf545..a1b1dc8a4d87 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -201,7 +201,6 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 {
 	struct dsa_port *cpu_dp = dev->dsa_ptr;
 	struct sk_buff *nskb = NULL;
-	struct pcpu_sw_netstats *s;
 	struct dsa_slave_priv *p;
 
 	if (unlikely(!cpu_dp)) {
@@ -225,11 +224,16 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, skb->dev);
 
-	s = this_cpu_ptr(p->stats64);
-	u64_stats_update_begin(&s->syncp);
-	s->rx_packets++;
-	s->rx_bytes += skb->len;
-	u64_stats_update_end(&s->syncp);
+	if (unlikely(cpu_dp->ds->untag_bridge_pvid)) {
+		nskb = dsa_untag_bridge_pvid(skb);
+		if (!nskb) {
+			kfree_skb(skb);
+			return 0;
+		}
+		skb = nskb;
+	}
+
+	dev_sw_netstats_rx_add(skb->dev, skb->len);
 
 	if (dsa_skb_defer_rx_timestamp(p, skb))
 		return 0;
@@ -330,11 +334,7 @@ EXPORT_SYMBOL_GPL(call_dsa_notifiers);
 int dsa_devlink_param_get(struct devlink *dl, u32 id,
 			  struct devlink_param_gset_ctx *ctx)
 {
-	struct dsa_devlink_priv *dl_priv;
-	struct dsa_switch *ds;
-
-	dl_priv = devlink_priv(dl);
-	ds = dl_priv->ds;
+	struct dsa_switch *ds = dsa_devlink_to_ds(dl);
 
 	if (!ds->ops->devlink_param_get)
 		return -EOPNOTSUPP;
@@ -346,11 +346,7 @@ EXPORT_SYMBOL_GPL(dsa_devlink_param_get);
 int dsa_devlink_param_set(struct devlink *dl, u32 id,
 			  struct devlink_param_gset_ctx *ctx)
 {
-	struct dsa_devlink_priv *dl_priv;
-	struct dsa_switch *ds;
-
-	dl_priv = devlink_priv(dl);
-	ds = dl_priv->ds;
+	struct dsa_switch *ds = dsa_devlink_to_ds(dl);
 
 	if (!ds->ops->devlink_param_set)
 		return -EOPNOTSUPP;
@@ -412,6 +408,36 @@ void dsa_devlink_resource_occ_get_unregister(struct dsa_switch *ds,
 }
 EXPORT_SYMBOL_GPL(dsa_devlink_resource_occ_get_unregister);
 
+struct devlink_region *
+dsa_devlink_region_create(struct dsa_switch *ds,
+			  const struct devlink_region_ops *ops,
+			  u32 region_max_snapshots, u64 region_size)
+{
+	return devlink_region_create(ds->devlink, ops, region_max_snapshots,
+				     region_size);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_region_create);
+
+struct devlink_region *
+dsa_devlink_port_region_create(struct dsa_switch *ds,
+			       int port,
+			       const struct devlink_port_region_ops *ops,
+			       u32 region_max_snapshots, u64 region_size)
+{
+	struct dsa_port *dp = dsa_to_port(ds, port);
+
+	return devlink_port_region_create(&dp->devlink_port, ops,
+					  region_max_snapshots,
+					  region_size);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_port_region_create);
+
+void dsa_devlink_region_destroy(struct devlink_region *region)
+{
+	devlink_region_destroy(region);
+}
+EXPORT_SYMBOL_GPL(dsa_devlink_region_destroy);
+
 struct dsa_port *dsa_port_from_netdev(struct net_device *netdev)
 {
 	if (!netdev || !dsa_slave_dev_check(netdev))
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index c0ffc7a2b65f..a04fd637b4cd 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -21,9 +21,6 @@
 static DEFINE_MUTEX(dsa2_mutex);
 LIST_HEAD(dsa_tree_list);
 
-static const struct devlink_ops dsa_devlink_ops = {
-};
-
 struct dsa_switch *dsa_switch_find(int tree_index, int sw_index)
 {
 	struct dsa_switch_tree *dst;
@@ -254,22 +251,11 @@ static void dsa_tree_teardown_default_cpu(struct dsa_switch_tree *dst)
 
 static int dsa_port_setup(struct dsa_port *dp)
 {
-	struct dsa_switch *ds = dp->ds;
-	struct dsa_switch_tree *dst = ds->dst;
-	const unsigned char *id = (const unsigned char *)&dst->index;
-	const unsigned char len = sizeof(dst->index);
 	struct devlink_port *dlp = &dp->devlink_port;
 	bool dsa_port_link_registered = false;
-	bool devlink_port_registered = false;
-	struct devlink_port_attrs attrs = {};
-	struct devlink *dl = ds->devlink;
 	bool dsa_port_enabled = false;
 	int err = 0;
 
-	attrs.phys.port_number = dp->index;
-	memcpy(attrs.switch_id.id, id, len);
-	attrs.switch_id.id_len = len;
-
 	if (dp->setup)
 		return 0;
 
@@ -278,14 +264,6 @@ static int dsa_port_setup(struct dsa_port *dp)
 		dsa_port_disable(dp);
 		break;
 	case DSA_PORT_TYPE_CPU:
-		memset(dlp, 0, sizeof(*dlp));
-		attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU;
-		devlink_port_attrs_set(dlp, &attrs);
-		err = devlink_port_register(dl, dlp, dp->index);
-		if (err)
-			break;
-		devlink_port_registered = true;
-
 		err = dsa_port_link_register_of(dp);
 		if (err)
 			break;
@@ -298,14 +276,6 @@ static int dsa_port_setup(struct dsa_port *dp)
 
 		break;
 	case DSA_PORT_TYPE_DSA:
-		memset(dlp, 0, sizeof(*dlp));
-		attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA;
-		devlink_port_attrs_set(dlp, &attrs);
-		err = devlink_port_register(dl, dlp, dp->index);
-		if (err)
-			break;
-		devlink_port_registered = true;
-
 		err = dsa_port_link_register_of(dp);
 		if (err)
 			break;
@@ -318,14 +288,6 @@ static int dsa_port_setup(struct dsa_port *dp)
 
 		break;
 	case DSA_PORT_TYPE_USER:
-		memset(dlp, 0, sizeof(*dlp));
-		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-		devlink_port_attrs_set(dlp, &attrs);
-		err = devlink_port_register(dl, dlp, dp->index);
-		if (err)
-			break;
-		devlink_port_registered = true;
-
 		dp->mac = of_get_mac_address(dp->dn);
 		err = dsa_slave_create(dp);
 		if (err)
@@ -339,8 +301,6 @@ static int dsa_port_setup(struct dsa_port *dp)
 		dsa_port_disable(dp);
 	if (err && dsa_port_link_registered)
 		dsa_port_link_unregister_of(dp);
-	if (err && devlink_port_registered)
-		devlink_port_unregister(dlp);
 	if (err)
 		return err;
 
@@ -349,6 +309,48 @@ static int dsa_port_setup(struct dsa_port *dp)
 	return 0;
 }
 
+static int dsa_port_devlink_setup(struct dsa_port *dp)
+{
+	struct devlink_port *dlp = &dp->devlink_port;
+	struct dsa_switch_tree *dst = dp->ds->dst;
+	struct devlink_port_attrs attrs = {};
+	struct devlink *dl = dp->ds->devlink;
+	const unsigned char *id;
+	unsigned char len;
+	int err;
+
+	id = (const unsigned char *)&dst->index;
+	len = sizeof(dst->index);
+
+	attrs.phys.port_number = dp->index;
+	memcpy(attrs.switch_id.id, id, len);
+	attrs.switch_id.id_len = len;
+	memset(dlp, 0, sizeof(*dlp));
+
+	switch (dp->type) {
+	case DSA_PORT_TYPE_UNUSED:
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_UNUSED;
+		break;
+	case DSA_PORT_TYPE_CPU:
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_CPU;
+		break;
+	case DSA_PORT_TYPE_DSA:
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_DSA;
+		break;
+	case DSA_PORT_TYPE_USER:
+		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+		break;
+	}
+
+	devlink_port_attrs_set(dlp, &attrs);
+	err = devlink_port_register(dl, dlp, dp->index);
+
+	if (!err)
+		dp->devlink_port_setup = true;
+
+	return err;
+}
+
 static void dsa_port_teardown(struct dsa_port *dp)
 {
 	struct devlink_port *dlp = &dp->devlink_port;
@@ -356,22 +358,21 @@ static void dsa_port_teardown(struct dsa_port *dp)
 	if (!dp->setup)
 		return;
 
+	devlink_port_type_clear(dlp);
+
 	switch (dp->type) {
 	case DSA_PORT_TYPE_UNUSED:
 		break;
 	case DSA_PORT_TYPE_CPU:
 		dsa_port_disable(dp);
 		dsa_tag_driver_put(dp->tag_ops);
-		devlink_port_unregister(dlp);
 		dsa_port_link_unregister_of(dp);
 		break;
 	case DSA_PORT_TYPE_DSA:
 		dsa_port_disable(dp);
-		devlink_port_unregister(dlp);
 		dsa_port_link_unregister_of(dp);
 		break;
 	case DSA_PORT_TYPE_USER:
-		devlink_port_unregister(dlp);
 		if (dp->slave) {
 			dsa_slave_destroy(dp->slave);
 			dp->slave = NULL;
@@ -382,9 +383,35 @@ static void dsa_port_teardown(struct dsa_port *dp)
 	dp->setup = false;
 }
 
+static void dsa_port_devlink_teardown(struct dsa_port *dp)
+{
+	struct devlink_port *dlp = &dp->devlink_port;
+
+	if (dp->devlink_port_setup)
+		devlink_port_unregister(dlp);
+	dp->devlink_port_setup = false;
+}
+
+static int dsa_devlink_info_get(struct devlink *dl,
+				struct devlink_info_req *req,
+				struct netlink_ext_ack *extack)
+{
+	struct dsa_switch *ds = dsa_devlink_to_ds(dl);
+
+	if (ds->ops->devlink_info_get)
+		return ds->ops->devlink_info_get(ds, req, extack);
+
+	return -EOPNOTSUPP;
+}
+
+static const struct devlink_ops dsa_devlink_ops = {
+	.info_get = dsa_devlink_info_get,
+};
+
 static int dsa_switch_setup(struct dsa_switch *ds)
 {
 	struct dsa_devlink_priv *dl_priv;
+	struct dsa_port *dp;
 	int err;
 
 	if (ds->setup)
@@ -410,9 +437,20 @@ static int dsa_switch_setup(struct dsa_switch *ds)
 	if (err)
 		goto free_devlink;
 
+	/* Setup devlink port instances now, so that the switch
+	 * setup() can register regions etc, against the ports
+	 */
+	list_for_each_entry(dp, &ds->dst->ports, list) {
+		if (dp->ds == ds) {
+			err = dsa_port_devlink_setup(dp);
+			if (err)
+				goto unregister_devlink_ports;
+		}
+	}
+
 	err = dsa_switch_register_notifier(ds);
 	if (err)
-		goto unregister_devlink;
+		goto unregister_devlink_ports;
 
 	err = ds->ops->setup(ds);
 	if (err < 0)
@@ -424,23 +462,29 @@ static int dsa_switch_setup(struct dsa_switch *ds)
 		ds->slave_mii_bus = devm_mdiobus_alloc(ds->dev);
 		if (!ds->slave_mii_bus) {
 			err = -ENOMEM;
-			goto unregister_notifier;
+			goto teardown;
 		}
 
 		dsa_slave_mii_bus_init(ds);
 
 		err = mdiobus_register(ds->slave_mii_bus);
 		if (err < 0)
-			goto unregister_notifier;
+			goto teardown;
 	}
 
 	ds->setup = true;
 
 	return 0;
 
+teardown:
+	if (ds->ops->teardown)
+		ds->ops->teardown(ds);
 unregister_notifier:
 	dsa_switch_unregister_notifier(ds);
-unregister_devlink:
+unregister_devlink_ports:
+	list_for_each_entry(dp, &ds->dst->ports, list)
+		if (dp->ds == ds)
+			dsa_port_devlink_teardown(dp);
 	devlink_unregister(ds->devlink);
 free_devlink:
 	devlink_free(ds->devlink);
@@ -451,6 +495,8 @@ free_devlink:
 
 static void dsa_switch_teardown(struct dsa_switch *ds)
 {
+	struct dsa_port *dp;
+
 	if (!ds->setup)
 		return;
 
@@ -463,6 +509,9 @@ static void dsa_switch_teardown(struct dsa_switch *ds)
 		ds->ops->teardown(ds);
 
 	if (ds->devlink) {
+		list_for_each_entry(dp, &ds->dst->ports, list)
+			if (dp->ds == ds)
+				dsa_port_devlink_teardown(dp);
 		devlink_unregister(ds->devlink);
 		devlink_free(ds->devlink);
 		ds->devlink = NULL;
diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h
index 1653e3377cb3..7c96aae9062c 100644
--- a/net/dsa/dsa_priv.h
+++ b/net/dsa/dsa_priv.h
@@ -7,6 +7,7 @@
 #ifndef __DSA_PRIV_H
 #define __DSA_PRIV_H
 
+#include <linux/if_bridge.h>
 #include <linux/phy.h>
 #include <linux/netdevice.h>
 #include <linux/netpoll.h>
@@ -77,8 +78,6 @@ struct dsa_slave_priv {
 	struct sk_buff *	(*xmit)(struct sk_buff *skb,
 					struct net_device *dev);
 
-	struct pcpu_sw_netstats	__percpu *stats64;
-
 	struct gro_cells	gcells;
 
 	/* DSA port data, such as switch, port index, etc. */
@@ -164,8 +163,6 @@ int dsa_port_vlan_add(struct dsa_port *dp,
 		      struct switchdev_trans *trans);
 int dsa_port_vlan_del(struct dsa_port *dp,
 		      const struct switchdev_obj_port_vlan *vlan);
-int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags);
-int dsa_port_vid_del(struct dsa_port *dp, u16 vid);
 int dsa_port_link_register_of(struct dsa_port *dp);
 void dsa_port_link_unregister_of(struct dsa_port *dp);
 extern const struct phylink_mac_ops dsa_port_phylink_mac_ops;
@@ -196,6 +193,65 @@ dsa_slave_to_master(const struct net_device *dev)
 	return dp->cpu_dp->master;
 }
 
+/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged
+ * frames as untagged, since the bridge will not untag them.
+ */
+static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb)
+{
+	struct dsa_port *dp = dsa_slave_to_port(skb->dev);
+	struct net_device *br = dp->bridge_dev;
+	struct net_device *dev = skb->dev;
+	struct net_device *upper_dev;
+	u16 vid, pvid, proto;
+	int err;
+
+	if (!br || br_vlan_enabled(br))
+		return skb;
+
+	err = br_vlan_get_proto(br, &proto);
+	if (err)
+		return skb;
+
+	/* Move VLAN tag from data to hwaccel */
+	if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) {
+		skb = skb_vlan_untag(skb);
+		if (!skb)
+			return NULL;
+	}
+
+	if (!skb_vlan_tag_present(skb))
+		return skb;
+
+	vid = skb_vlan_tag_get_id(skb);
+
+	/* We already run under an RCU read-side critical section since
+	 * we are called from netif_receive_skb_list_internal().
+	 */
+	err = br_vlan_get_pvid_rcu(dev, &pvid);
+	if (err)
+		return skb;
+
+	if (vid != pvid)
+		return skb;
+
+	/* The sad part about attempting to untag from DSA is that we
+	 * don't know, unless we check, if the skb will end up in
+	 * the bridge's data path - br_allowed_ingress() - or not.
+	 * For example, there might be an 8021q upper for the
+	 * default_pvid of the bridge, which will steal VLAN-tagged traffic
+	 * from the bridge's data path. This is a configuration that DSA
+	 * supports because vlan_filtering is 0. In that case, we should
+	 * definitely keep the tag, to make sure it keeps working.
+	 */
+	upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid);
+	if (upper_dev)
+		return skb;
+
+	__vlan_hwaccel_clear_tag(skb);
+
+	return skb;
+}
+
 /* switch.c */
 int dsa_switch_register_notifier(struct dsa_switch *ds);
 void dsa_switch_unregister_notifier(struct dsa_switch *ds);
diff --git a/net/dsa/master.c b/net/dsa/master.c
index 61615ebc70e9..cb3a5cf99b25 100644
--- a/net/dsa/master.c
+++ b/net/dsa/master.c
@@ -259,6 +259,18 @@ static void dsa_netdev_ops_set(struct net_device *dev,
 	dev->dsa_ptr->netdev_ops = ops;
 }
 
+static void dsa_master_set_promiscuity(struct net_device *dev, int inc)
+{
+	const struct dsa_device_ops *ops = dev->dsa_ptr->tag_ops;
+
+	if (!ops->promisc_on_master)
+		return;
+
+	rtnl_lock();
+	dev_set_promiscuity(dev, inc);
+	rtnl_unlock();
+}
+
 static ssize_t tagging_show(struct device *d, struct device_attribute *attr,
 			    char *buf)
 {
@@ -296,14 +308,25 @@ static struct lock_class_key dsa_master_addr_list_lock_key;
 
 int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 {
+	int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead;
+	struct dsa_switch *ds = cpu_dp->ds;
+	struct device_link *consumer_link;
 	int ret;
 
+	/* The DSA master must use SET_NETDEV_DEV for this to work. */
+	consumer_link = device_link_add(ds->dev, dev->dev.parent,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
+	if (!consumer_link)
+		netdev_err(dev,
+			   "Failed to create a device link to DSA switch %s\n",
+			   dev_name(ds->dev));
+
 	rtnl_lock();
-	ret = dev_set_mtu(dev, ETH_DATA_LEN + cpu_dp->tag_ops->overhead);
+	ret = dev_set_mtu(dev, mtu);
 	rtnl_unlock();
 	if (ret)
-		netdev_warn(dev, "error %d setting MTU to include DSA overhead\n",
-			    ret);
+		netdev_warn(dev, "error %d setting MTU to %d to include DSA overhead\n",
+			    ret, mtu);
 
 	/* If we use a tagging format that doesn't have an ethertype
 	 * field, make sure that all packets from this point on get
@@ -314,9 +337,12 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 	dev->dsa_ptr = cpu_dp;
 	lockdep_set_class(&dev->addr_list_lock,
 			  &dsa_master_addr_list_lock_key);
+
+	dsa_master_set_promiscuity(dev, 1);
+
 	ret = dsa_master_ethtool_setup(dev);
 	if (ret)
-		return ret;
+		goto out_err_reset_promisc;
 
 	dsa_netdev_ops_set(dev, &dsa_netdev_ops);
 
@@ -329,6 +355,8 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp)
 out_err_ndo_teardown:
 	dsa_netdev_ops_set(dev, NULL);
 	dsa_master_ethtool_teardown(dev);
+out_err_reset_promisc:
+	dsa_master_set_promiscuity(dev, -1);
 	return ret;
 }
 
@@ -338,6 +366,7 @@ void dsa_master_teardown(struct net_device *dev)
 	dsa_netdev_ops_set(dev, NULL);
 	dsa_master_ethtool_teardown(dev);
 	dsa_master_reset_mtu(dev);
+	dsa_master_set_promiscuity(dev, -1);
 
 	dev->dsa_ptr = NULL;
 
diff --git a/net/dsa/port.c b/net/dsa/port.c
index e23ece229c7e..73569c9af3cc 100644
--- a/net/dsa/port.c
+++ b/net/dsa/port.c
@@ -193,11 +193,44 @@ void dsa_port_bridge_leave(struct dsa_port *dp, struct net_device *br)
 	dsa_port_set_state_now(dp, BR_STATE_FORWARDING);
 }
 
+/* Must be called under rcu_read_lock() */
 static bool dsa_port_can_apply_vlan_filtering(struct dsa_port *dp,
 					      bool vlan_filtering)
 {
 	struct dsa_switch *ds = dp->ds;
-	int i;
+	int err, i;
+
+	/* VLAN awareness was off, so the question is "can we turn it on".
+	 * We may have had 8021q uppers, those need to go. Make sure we don't
+	 * enter an inconsistent state: deny changing the VLAN awareness state
+	 * as long as we have 8021q uppers.
+	 */
+	if (vlan_filtering && dsa_is_user_port(ds, dp->index)) {
+		struct net_device *upper_dev, *slave = dp->slave;
+		struct net_device *br = dp->bridge_dev;
+		struct list_head *iter;
+
+		netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) {
+			struct bridge_vlan_info br_info;
+			u16 vid;
+
+			if (!is_vlan_dev(upper_dev))
+				continue;
+
+			vid = vlan_dev_vlan_id(upper_dev);
+
+			/* br_vlan_get_info() returns -EINVAL or -ENOENT if the
+			 * device, respectively the VID is not found, returning
+			 * 0 means success, which is a failure for us here.
+			 */
+			err = br_vlan_get_info(br, vid, &br_info);
+			if (err == 0) {
+				dev_err(ds->dev, "Must remove upper %s first\n",
+					upper_dev->name);
+				return false;
+			}
+		}
+	}
 
 	if (!ds->vlan_filtering_is_global)
 		return true;
@@ -232,28 +265,38 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering,
 	struct dsa_switch *ds = dp->ds;
 	int err;
 
-	/* bridge skips -EOPNOTSUPP, so skip the prepare phase */
-	if (switchdev_trans_ph_prepare(trans))
-		return 0;
+	if (switchdev_trans_ph_prepare(trans)) {
+		bool apply;
 
-	if (!ds->ops->port_vlan_filtering)
-		return 0;
+		if (!ds->ops->port_vlan_filtering)
+			return -EOPNOTSUPP;
 
-	if (!dsa_port_can_apply_vlan_filtering(dp, vlan_filtering))
-		return -EINVAL;
+		/* We are called from dsa_slave_switchdev_blocking_event(),
+		 * which is not under rcu_read_lock(), unlike
+		 * dsa_slave_switchdev_event().
+		 */
+		rcu_read_lock();
+		apply = dsa_port_can_apply_vlan_filtering(dp, vlan_filtering);
+		rcu_read_unlock();
+		if (!apply)
+			return -EINVAL;
+	}
 
 	if (dsa_port_is_vlan_filtering(dp) == vlan_filtering)
 		return 0;
 
-	err = ds->ops->port_vlan_filtering(ds, dp->index,
-					   vlan_filtering);
+	err = ds->ops->port_vlan_filtering(ds, dp->index, vlan_filtering,
+					   trans);
 	if (err)
 		return err;
 
-	if (ds->vlan_filtering_is_global)
-		ds->vlan_filtering = vlan_filtering;
-	else
-		dp->vlan_filtering = vlan_filtering;
+	if (switchdev_trans_ph_commit(trans)) {
+		if (ds->vlan_filtering_is_global)
+			ds->vlan_filtering = vlan_filtering;
+		else
+			dp->vlan_filtering = vlan_filtering;
+	}
+
 	return 0;
 }
 
@@ -433,39 +476,6 @@ int dsa_port_vlan_del(struct dsa_port *dp,
 	return dsa_port_notify(dp, DSA_NOTIFIER_VLAN_DEL, &info);
 }
 
-int dsa_port_vid_add(struct dsa_port *dp, u16 vid, u16 flags)
-{
-	struct switchdev_obj_port_vlan vlan = {
-		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
-		.flags = flags,
-		.vid_begin = vid,
-		.vid_end = vid,
-	};
-	struct switchdev_trans trans;
-	int err;
-
-	trans.ph_prepare = true;
-	err = dsa_port_vlan_add(dp, &vlan, &trans);
-	if (err)
-		return err;
-
-	trans.ph_prepare = false;
-	return dsa_port_vlan_add(dp, &vlan, &trans);
-}
-EXPORT_SYMBOL(dsa_port_vid_add);
-
-int dsa_port_vid_del(struct dsa_port *dp, u16 vid)
-{
-	struct switchdev_obj_port_vlan vlan = {
-		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
-		.vid_begin = vid,
-		.vid_end = vid,
-	};
-
-	return dsa_port_vlan_del(dp, &vlan);
-}
-EXPORT_SYMBOL(dsa_port_vid_del);
-
 static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp)
 {
 	struct device_node *phy_dn;
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 16e5f98d4882..4a0498bf6c65 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -303,13 +303,36 @@ static int dsa_slave_port_attr_set(struct net_device *dev,
 	return ret;
 }
 
+/* Must be called under rcu_read_lock() */
+static int
+dsa_slave_vlan_check_for_8021q_uppers(struct net_device *slave,
+				      const struct switchdev_obj_port_vlan *vlan)
+{
+	struct net_device *upper_dev;
+	struct list_head *iter;
+
+	netdev_for_each_upper_dev_rcu(slave, upper_dev, iter) {
+		u16 vid;
+
+		if (!is_vlan_dev(upper_dev))
+			continue;
+
+		vid = vlan_dev_vlan_id(upper_dev);
+		if (vid >= vlan->vid_begin && vid <= vlan->vid_end)
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
 static int dsa_slave_vlan_add(struct net_device *dev,
 			      const struct switchdev_obj *obj,
 			      struct switchdev_trans *trans)
 {
+	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	struct switchdev_obj_port_vlan vlan;
-	int err;
+	int vid, err;
 
 	if (obj->orig_dev != dev)
 		return -EOPNOTSUPP;
@@ -319,6 +342,17 @@ static int dsa_slave_vlan_add(struct net_device *dev,
 
 	vlan = *SWITCHDEV_OBJ_PORT_VLAN(obj);
 
+	/* Deny adding a bridge VLAN when there is already an 802.1Q upper with
+	 * the same VID.
+	 */
+	if (trans->ph_prepare && br_vlan_enabled(dp->bridge_dev)) {
+		rcu_read_lock();
+		err = dsa_slave_vlan_check_for_8021q_uppers(dev, &vlan);
+		rcu_read_unlock();
+		if (err)
+			return err;
+	}
+
 	err = dsa_port_vlan_add(dp, &vlan, trans);
 	if (err)
 		return err;
@@ -333,6 +367,12 @@ static int dsa_slave_vlan_add(struct net_device *dev,
 	if (err)
 		return err;
 
+	for (vid = vlan.vid_begin; vid <= vlan.vid_end; vid++) {
+		err = vlan_vid_add(master, htons(ETH_P_8021Q), vid);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
@@ -376,7 +416,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev,
 static int dsa_slave_vlan_del(struct net_device *dev,
 			      const struct switchdev_obj *obj)
 {
+	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct switchdev_obj_port_vlan *vlan;
+	int vid, err;
 
 	if (obj->orig_dev != dev)
 		return -EOPNOTSUPP;
@@ -384,10 +427,19 @@ static int dsa_slave_vlan_del(struct net_device *dev,
 	if (dsa_port_skip_vlan_configuration(dp))
 		return 0;
 
+	vlan = SWITCHDEV_OBJ_PORT_VLAN(obj);
+
 	/* Do not deprogram the CPU port as it may be shared with other user
 	 * ports which can be members of this VLAN as well.
 	 */
-	return dsa_port_vlan_del(dp, SWITCHDEV_OBJ_PORT_VLAN(obj));
+	err = dsa_port_vlan_del(dp, vlan);
+	if (err)
+		return err;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++)
+		vlan_vid_del(master, htons(ETH_P_8021Q), vid);
+
+	return 0;
 }
 
 static int dsa_slave_port_obj_del(struct net_device *dev,
@@ -470,10 +522,10 @@ static void dsa_skb_tx_timestamp(struct dsa_slave_priv *p,
 	if (!clone)
 		return;
 
-	DSA_SKB_CB(skb)->clone = clone;
-
-	if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type))
+	if (ds->ops->port_txtstamp(ds, p->dp->index, clone, type)) {
+		DSA_SKB_CB(skb)->clone = clone;
 		return;
+	}
 
 	kfree_skb(clone);
 }
@@ -496,17 +548,36 @@ netdev_tx_t dsa_enqueue_skb(struct sk_buff *skb, struct net_device *dev)
 }
 EXPORT_SYMBOL_GPL(dsa_enqueue_skb);
 
+static int dsa_realloc_skb(struct sk_buff *skb, struct net_device *dev)
+{
+	int needed_headroom = dev->needed_headroom;
+	int needed_tailroom = dev->needed_tailroom;
+
+	/* For tail taggers, we need to pad short frames ourselves, to ensure
+	 * that the tail tag does not fail at its role of being at the end of
+	 * the packet, once the master interface pads the frame. Account for
+	 * that pad length here, and pad later.
+	 */
+	if (unlikely(needed_tailroom && skb->len < ETH_ZLEN))
+		needed_tailroom += ETH_ZLEN - skb->len;
+	/* skb_headroom() returns unsigned int... */
+	needed_headroom = max_t(int, needed_headroom - skb_headroom(skb), 0);
+	needed_tailroom = max_t(int, needed_tailroom - skb_tailroom(skb), 0);
+
+	if (likely(!needed_headroom && !needed_tailroom && !skb_cloned(skb)))
+		/* No reallocation needed, yay! */
+		return 0;
+
+	return pskb_expand_head(skb, needed_headroom, needed_tailroom,
+				GFP_ATOMIC);
+}
+
 static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct pcpu_sw_netstats *s;
 	struct sk_buff *nskb;
 
-	s = this_cpu_ptr(p->stats64);
-	u64_stats_update_begin(&s->syncp);
-	s->tx_packets++;
-	s->tx_bytes += skb->len;
-	u64_stats_update_end(&s->syncp);
+	dev_sw_netstats_tx_add(dev, 1, skb->len);
 
 	DSA_SKB_CB(skb)->clone = NULL;
 
@@ -515,6 +586,17 @@ static netdev_tx_t dsa_slave_xmit(struct sk_buff *skb, struct net_device *dev)
 	 */
 	dsa_skb_tx_timestamp(p, skb);
 
+	if (dsa_realloc_skb(skb, dev)) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	/* needed_tailroom should still be 'warm' in the cache line from
+	 * dsa_realloc_skb(), which has also ensured that padding is safe.
+	 */
+	if (dev->needed_tailroom)
+		eth_skb_pad(skb);
+
 	/* Transmit function may have to reallocate the original SKB,
 	 * in which case it must have freed it. Only free it here on error.
 	 */
@@ -627,7 +709,6 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev,
 					uint64_t *data)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
-	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct dsa_switch *ds = dp->ds;
 	struct pcpu_sw_netstats *s;
 	unsigned int start;
@@ -636,7 +717,7 @@ static void dsa_slave_get_ethtool_stats(struct net_device *dev,
 	for_each_possible_cpu(i) {
 		u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
 
-		s = per_cpu_ptr(p->stats64, i);
+		s = per_cpu_ptr(dev->tstats, i);
 		do {
 			start = u64_stats_fetch_begin_irq(&s->syncp);
 			tx_packets = s->tx_packets;
@@ -1165,34 +1246,6 @@ static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	return ds->ops->port_setup_tc(ds, dp->index, type, type_data);
 }
 
-static void dsa_slave_get_stats64(struct net_device *dev,
-				  struct rtnl_link_stats64 *stats)
-{
-	struct dsa_slave_priv *p = netdev_priv(dev);
-	struct pcpu_sw_netstats *s;
-	unsigned int start;
-	int i;
-
-	netdev_stats_to_stats64(stats, &dev->stats);
-	for_each_possible_cpu(i) {
-		u64 tx_packets, tx_bytes, rx_packets, rx_bytes;
-
-		s = per_cpu_ptr(p->stats64, i);
-		do {
-			start = u64_stats_fetch_begin_irq(&s->syncp);
-			tx_packets = s->tx_packets;
-			tx_bytes = s->tx_bytes;
-			rx_packets = s->rx_packets;
-			rx_bytes = s->rx_bytes;
-		} while (u64_stats_fetch_retry_irq(&s->syncp, start));
-
-		stats->tx_packets += tx_packets;
-		stats->tx_bytes += tx_bytes;
-		stats->rx_packets += rx_packets;
-		stats->rx_bytes += rx_bytes;
-	}
-}
-
 static int dsa_slave_get_rxnfc(struct net_device *dev,
 			       struct ethtool_rxnfc *nfc, u32 *rule_locs)
 {
@@ -1232,64 +1285,66 @@ static int dsa_slave_get_ts_info(struct net_device *dev,
 static int dsa_slave_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
 				     u16 vid)
 {
+	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_port *dp = dsa_slave_to_port(dev);
-	struct bridge_vlan_info info;
+	struct switchdev_obj_port_vlan vlan = {
+		.obj.id = SWITCHDEV_OBJ_ID_PORT_VLAN,
+		.vid_begin = vid,
+		.vid_end = vid,
+		/* This API only allows programming tagged, non-PVID VIDs */
+		.flags = 0,
+	};
+	struct switchdev_trans trans;
 	int ret;
 
-	/* Check for a possible bridge VLAN entry now since there is no
-	 * need to emulate the switchdev prepare + commit phase.
-	 */
-	if (dp->bridge_dev) {
-		if (dsa_port_skip_vlan_configuration(dp))
-			return 0;
+	/* User port... */
+	trans.ph_prepare = true;
+	ret = dsa_port_vlan_add(dp, &vlan, &trans);
+	if (ret)
+		return ret;
 
-		/* br_vlan_get_info() returns -EINVAL or -ENOENT if the
-		 * device, respectively the VID is not found, returning
-		 * 0 means success, which is a failure for us here.
-		 */
-		ret = br_vlan_get_info(dp->bridge_dev, vid, &info);
-		if (ret == 0)
-			return -EBUSY;
-	}
+	trans.ph_prepare = false;
+	ret = dsa_port_vlan_add(dp, &vlan, &trans);
+	if (ret)
+		return ret;
 
-	ret = dsa_port_vid_add(dp, vid, 0);
+	/* And CPU port... */
+	trans.ph_prepare = true;
+	ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &trans);
 	if (ret)
 		return ret;
 
-	ret = dsa_port_vid_add(dp->cpu_dp, vid, 0);
+	trans.ph_prepare = false;
+	ret = dsa_port_vlan_add(dp->cpu_dp, &vlan, &trans);
 	if (ret)
 		return ret;
 
-	return 0;
+	return vlan_vid_add(master, proto, vid);
 }
 
 static int dsa_slave_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
 				      u16 vid)
 {
+	struct net_device *master = dsa_slave_to_master(dev);
 	struct dsa_port *dp = dsa_slave_to_port(dev);
-	struct bridge_vlan_info info;
-	int ret;
-
-	/* Check for a possible bridge VLAN entry now since there is no
-	 * need to emulate the switchdev prepare + commit phase.
-	 */
-	if (dp->bridge_dev) {
-		if (dsa_port_skip_vlan_configuration(dp))
-			return 0;
-
-		/* br_vlan_get_info() returns -EINVAL or -ENOENT if the
-		 * device, respectively the VID is not found, returning
-		 * 0 means success, which is a failure for us here.
-		 */
-		ret = br_vlan_get_info(dp->bridge_dev, vid, &info);
-		if (ret == 0)
-			return -EBUSY;
-	}
+	struct switchdev_obj_port_vlan vlan = {
+		.vid_begin = vid,
+		.vid_end = vid,
+		/* This API only allows programming tagged, non-PVID VIDs */
+		.flags = 0,
+	};
+	int err;
 
 	/* Do not deprogram the CPU port as it may be shared with other user
 	 * ports which can be members of this VLAN as well.
 	 */
-	return dsa_port_vid_del(dp, vid);
+	err = dsa_port_vlan_del(dp, &vlan);
+	if (err)
+		return err;
+
+	vlan_vid_del(master, proto, vid);
+
+	return 0;
 }
 
 struct dsa_hw_port {
@@ -1566,7 +1621,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = {
 #endif
 	.ndo_get_phys_port_name	= dsa_slave_get_phys_port_name,
 	.ndo_setup_tc		= dsa_slave_setup_tc,
-	.ndo_get_stats64	= dsa_slave_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_get_port_parent_id	= dsa_slave_get_port_parent_id,
 	.ndo_vlan_rx_add_vid	= dsa_slave_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= dsa_slave_vlan_rx_kill_vid,
@@ -1756,6 +1811,16 @@ int dsa_slave_create(struct dsa_port *port)
 	slave_dev->netdev_ops = &dsa_slave_netdev_ops;
 	if (ds->ops->port_max_mtu)
 		slave_dev->max_mtu = ds->ops->port_max_mtu(ds, port->index);
+	if (cpu_dp->tag_ops->tail_tag)
+		slave_dev->needed_tailroom = cpu_dp->tag_ops->overhead;
+	else
+		slave_dev->needed_headroom = cpu_dp->tag_ops->overhead;
+	/* Try to save one extra realloc later in the TX path (in the master)
+	 * by also inheriting the master's needed headroom and tailroom.
+	 * The 8021q driver also does this.
+	 */
+	slave_dev->needed_headroom += master->needed_headroom;
+	slave_dev->needed_tailroom += master->needed_tailroom;
 	SET_NETDEV_DEVTYPE(slave_dev, &dsa_type);
 
 	netdev_for_each_tx_queue(slave_dev, dsa_slave_set_lockdep_class_one,
@@ -1766,8 +1831,8 @@ int dsa_slave_create(struct dsa_port *port)
 	slave_dev->vlan_features = master->vlan_features;
 
 	p = netdev_priv(slave_dev);
-	p->stats64 = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
-	if (!p->stats64) {
+	slave_dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!slave_dev->tstats) {
 		free_netdev(slave_dev);
 		return -ENOMEM;
 	}
@@ -1784,16 +1849,17 @@ int dsa_slave_create(struct dsa_port *port)
 	rtnl_lock();
 	ret = dsa_slave_change_mtu(slave_dev, ETH_DATA_LEN);
 	rtnl_unlock();
-	if (ret)
-		dev_warn(ds->dev, "nonfatal error %d setting MTU on port %d\n",
-			 ret, port->index);
+	if (ret && ret != -EOPNOTSUPP)
+		dev_warn(ds->dev, "nonfatal error %d setting MTU to %d on port %d\n",
+			 ret, ETH_DATA_LEN, port->index);
 
 	netif_carrier_off(slave_dev);
 
 	ret = dsa_slave_phy_setup(slave_dev);
 	if (ret) {
-		netdev_err(master, "error %d setting up slave PHY for %s\n",
-			   ret, slave_dev->name);
+		netdev_err(slave_dev,
+			   "error %d setting up PHY for tree %d, switch %d, port %d\n",
+			   ret, ds->dst->index, ds->index, port->index);
 		goto out_gcells;
 	}
 
@@ -1828,7 +1894,7 @@ out_phy:
 out_gcells:
 	gro_cells_destroy(&p->gcells);
 out_free:
-	free_percpu(p->stats64);
+	free_percpu(slave_dev->tstats);
 	free_netdev(slave_dev);
 	port->slave = NULL;
 	return ret;
@@ -1850,7 +1916,7 @@ void dsa_slave_destroy(struct net_device *slave_dev)
 	dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER);
 	phylink_destroy(dp->pl);
 	gro_cells_destroy(&p->gcells);
-	free_percpu(p->stats64);
+	free_percpu(slave_dev->tstats);
 	free_netdev(slave_dev);
 }
 
@@ -1880,9 +1946,9 @@ static int dsa_slave_changeupper(struct net_device *dev,
 	return err;
 }
 
-static int dsa_slave_upper_vlan_check(struct net_device *dev,
-				      struct netdev_notifier_changeupper_info *
-				      info)
+static int
+dsa_prevent_bridging_8021q_upper(struct net_device *dev,
+				 struct netdev_notifier_changeupper_info *info)
 {
 	struct netlink_ext_ack *ext_ack;
 	struct net_device *slave;
@@ -1912,14 +1978,68 @@ static int dsa_slave_upper_vlan_check(struct net_device *dev,
 	return NOTIFY_DONE;
 }
 
+static int
+dsa_slave_check_8021q_upper(struct net_device *dev,
+			    struct netdev_notifier_changeupper_info *info)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	struct net_device *br = dp->bridge_dev;
+	struct bridge_vlan_info br_info;
+	struct netlink_ext_ack *extack;
+	int err = NOTIFY_DONE;
+	u16 vid;
+
+	if (!br || !br_vlan_enabled(br))
+		return NOTIFY_DONE;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+	vid = vlan_dev_vlan_id(info->upper_dev);
+
+	/* br_vlan_get_info() returns -EINVAL or -ENOENT if the
+	 * device, respectively the VID is not found, returning
+	 * 0 means success, which is a failure for us here.
+	 */
+	err = br_vlan_get_info(br, vid, &br_info);
+	if (err == 0) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "This VLAN is already configured by the bridge");
+		return notifier_from_errno(-EBUSY);
+	}
+
+	return NOTIFY_DONE;
+}
+
 static int dsa_slave_netdevice_event(struct notifier_block *nb,
 				     unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (event == NETDEV_CHANGEUPPER) {
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER: {
+		struct netdev_notifier_changeupper_info *info = ptr;
+		struct dsa_switch *ds;
+		struct dsa_port *dp;
+		int err;
+
+		if (!dsa_slave_dev_check(dev))
+			return dsa_prevent_bridging_8021q_upper(dev, ptr);
+
+		dp = dsa_slave_to_port(dev);
+		ds = dp->ds;
+
+		if (ds->ops->port_prechangeupper) {
+			err = ds->ops->port_prechangeupper(ds, dp->index, info);
+			if (err)
+				return notifier_from_errno(err);
+		}
+
+		if (is_vlan_dev(info->upper_dev))
+			return dsa_slave_check_8021q_upper(dev, ptr);
+		break;
+	}
+	case NETDEV_CHANGEUPPER:
 		if (!dsa_slave_dev_check(dev))
-			return dsa_slave_upper_vlan_check(dev, ptr);
+			return NOTIFY_DONE;
 
 		return dsa_slave_changeupper(dev, ptr);
 	}
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index 86c8dc5c32a0..3fb362b6874e 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -139,8 +139,15 @@ static int dsa_switch_bridge_leave(struct dsa_switch *ds,
 		}
 	}
 	if (unset_vlan_filtering) {
-		struct switchdev_trans trans = {0};
+		struct switchdev_trans trans;
 
+		trans.ph_prepare = true;
+		err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port),
+					      false, &trans);
+		if (err && err != EOPNOTSUPP)
+			return err;
+
+		trans.ph_prepare = false;
 		err = dsa_port_vlan_filtering(dsa_to_port(ds, info->port),
 					      false, &trans);
 		if (err && err != EOPNOTSUPP)
@@ -232,43 +239,6 @@ static int dsa_switch_mdb_del(struct dsa_switch *ds,
 	return 0;
 }
 
-static int dsa_port_vlan_device_check(struct net_device *vlan_dev,
-				      int vlan_dev_vid,
-				      void *arg)
-{
-	struct switchdev_obj_port_vlan *vlan = arg;
-	u16 vid;
-
-	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
-		if (vid == vlan_dev_vid)
-			return -EBUSY;
-	}
-
-	return 0;
-}
-
-static int dsa_port_vlan_check(struct dsa_switch *ds, int port,
-			       const struct switchdev_obj_port_vlan *vlan)
-{
-	const struct dsa_port *dp = dsa_to_port(ds, port);
-	int err = 0;
-
-	/* Device is not bridged, let it proceed with the VLAN device
-	 * creation.
-	 */
-	if (!dp->bridge_dev)
-		return err;
-
-	/* dsa_slave_vlan_rx_{add,kill}_vid() cannot use the prepare phase and
-	 * already checks whether there is an overlapping bridge VLAN entry
-	 * with the same VID, so here we only need to check that if we are
-	 * adding a bridge VLAN entry there is not an overlapping VLAN device
-	 * claiming that VID.
-	 */
-	return vlan_for_each(dp->slave, dsa_port_vlan_device_check,
-			     (void *)vlan);
-}
-
 static bool dsa_switch_vlan_match(struct dsa_switch *ds, int port,
 				  struct dsa_notifier_vlan_info *info)
 {
@@ -291,10 +261,6 @@ static int dsa_switch_vlan_prepare(struct dsa_switch *ds,
 
 	for (port = 0; port < ds->num_ports; port++) {
 		if (dsa_switch_vlan_match(ds, port, info)) {
-			err = dsa_port_vlan_check(ds, port, info->vlan);
-			if (err)
-				return err;
-
 			err = ds->ops->port_vlan_prepare(ds, port, info->vlan);
 			if (err)
 				return err;
diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c
index 780b2a15ac9b..8e3e8a5b8559 100644
--- a/net/dsa/tag_8021q.c
+++ b/net/dsa/tag_8021q.c
@@ -146,15 +146,15 @@ EXPORT_SYMBOL_GPL(vid_is_dsa_8021q);
  * user explicitly configured this @vid through the bridge core, then the @vid
  * is installed again, but this time with the flags from the bridge layer.
  */
-static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid,
+static int dsa_8021q_vid_apply(struct dsa_8021q_context *ctx, int port, u16 vid,
 			       u16 flags, bool enabled)
 {
-	struct dsa_port *dp = dsa_to_port(ds, port);
+	struct dsa_port *dp = dsa_to_port(ctx->ds, port);
 
 	if (enabled)
-		return dsa_port_vid_add(dp, vid, flags);
+		return ctx->ops->vlan_add(ctx->ds, dp->index, vid, flags);
 
-	return dsa_port_vid_del(dp, vid);
+	return ctx->ops->vlan_del(ctx->ds, dp->index, vid);
 }
 
 /* RX VLAN tagging (left) and TX VLAN tagging (right) setup shown for a single
@@ -209,25 +209,29 @@ static int dsa_8021q_vid_apply(struct dsa_switch *ds, int port, u16 vid,
  * +-+-----+-+-----+-+-----+-+-----+-+    +-+-----+-+-----+-+-----+-+-----+-+
  *   swp0    swp1    swp2    swp3           swp0    swp1    swp2    swp3
  */
-int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled)
+static int dsa_8021q_setup_port(struct dsa_8021q_context *ctx, int port,
+				bool enabled)
 {
-	int upstream = dsa_upstream_port(ds, port);
-	u16 rx_vid = dsa_8021q_rx_vid(ds, port);
-	u16 tx_vid = dsa_8021q_tx_vid(ds, port);
-	int i, err;
+	int upstream = dsa_upstream_port(ctx->ds, port);
+	u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port);
+	u16 tx_vid = dsa_8021q_tx_vid(ctx->ds, port);
+	struct net_device *master;
+	int i, err, subvlan;
 
 	/* The CPU port is implicitly configured by
 	 * configuring the front-panel ports
 	 */
-	if (!dsa_is_user_port(ds, port))
+	if (!dsa_is_user_port(ctx->ds, port))
 		return 0;
 
+	master = dsa_to_port(ctx->ds, port)->cpu_dp->master;
+
 	/* Add this user port's RX VID to the membership list of all others
 	 * (including itself). This is so that bridging will not be hindered.
 	 * L2 forwarding rules still take precedence when there are no VLAN
 	 * restrictions, so there are no concerns about leaking traffic.
 	 */
-	for (i = 0; i < ds->num_ports; i++) {
+	for (i = 0; i < ctx->ds->num_ports; i++) {
 		u16 flags;
 
 		if (i == upstream)
@@ -240,9 +244,10 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled)
 			/* The RX VID is a regular VLAN on all others */
 			flags = BRIDGE_VLAN_INFO_UNTAGGED;
 
-		err = dsa_8021q_vid_apply(ds, i, rx_vid, flags, enabled);
+		err = dsa_8021q_vid_apply(ctx, i, rx_vid, flags, enabled);
 		if (err) {
-			dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n",
+			dev_err(ctx->ds->dev,
+				"Failed to apply RX VID %d to port %d: %d\n",
 				rx_vid, port, err);
 			return err;
 		}
@@ -251,80 +256,115 @@ int dsa_port_setup_8021q_tagging(struct dsa_switch *ds, int port, bool enabled)
 	/* CPU port needs to see this port's RX VID
 	 * as tagged egress.
 	 */
-	err = dsa_8021q_vid_apply(ds, upstream, rx_vid, 0, enabled);
+	err = dsa_8021q_vid_apply(ctx, upstream, rx_vid, 0, enabled);
 	if (err) {
-		dev_err(ds->dev, "Failed to apply RX VID %d to port %d: %d\n",
+		dev_err(ctx->ds->dev,
+			"Failed to apply RX VID %d to port %d: %d\n",
 			rx_vid, port, err);
 		return err;
 	}
 
+	/* Add to the master's RX filter not only @rx_vid, but in fact
+	 * the entire subvlan range, just in case this DSA switch might
+	 * want to use sub-VLANs.
+	 */
+	for (subvlan = 0; subvlan < DSA_8021Q_N_SUBVLAN; subvlan++) {
+		u16 vid = dsa_8021q_rx_vid_subvlan(ctx->ds, port, subvlan);
+
+		if (enabled)
+			vlan_vid_add(master, ctx->proto, vid);
+		else
+			vlan_vid_del(master, ctx->proto, vid);
+	}
+
 	/* Finally apply the TX VID on this port and on the CPU port */
-	err = dsa_8021q_vid_apply(ds, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED,
+	err = dsa_8021q_vid_apply(ctx, port, tx_vid, BRIDGE_VLAN_INFO_UNTAGGED,
 				  enabled);
 	if (err) {
-		dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n",
+		dev_err(ctx->ds->dev,
+			"Failed to apply TX VID %d on port %d: %d\n",
 			tx_vid, port, err);
 		return err;
 	}
-	err = dsa_8021q_vid_apply(ds, upstream, tx_vid, 0, enabled);
+	err = dsa_8021q_vid_apply(ctx, upstream, tx_vid, 0, enabled);
 	if (err) {
-		dev_err(ds->dev, "Failed to apply TX VID %d on port %d: %d\n",
+		dev_err(ctx->ds->dev,
+			"Failed to apply TX VID %d on port %d: %d\n",
 			tx_vid, upstream, err);
 		return err;
 	}
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(dsa_port_setup_8021q_tagging);
 
-static int dsa_8021q_crosschip_link_apply(struct dsa_switch *ds, int port,
-					  struct dsa_switch *other_ds,
+int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled)
+{
+	int rc, port;
+
+	ASSERT_RTNL();
+
+	for (port = 0; port < ctx->ds->num_ports; port++) {
+		rc = dsa_8021q_setup_port(ctx, port, enabled);
+		if (rc < 0) {
+			dev_err(ctx->ds->dev,
+				"Failed to setup VLAN tagging for port %d: %d\n",
+				port, rc);
+			return rc;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(dsa_8021q_setup);
+
+static int dsa_8021q_crosschip_link_apply(struct dsa_8021q_context *ctx,
+					  int port,
+					  struct dsa_8021q_context *other_ctx,
 					  int other_port, bool enabled)
 {
-	u16 rx_vid = dsa_8021q_rx_vid(ds, port);
+	u16 rx_vid = dsa_8021q_rx_vid(ctx->ds, port);
 
 	/* @rx_vid of local @ds port @port goes to @other_port of
 	 * @other_ds
 	 */
-	return dsa_8021q_vid_apply(other_ds, other_port, rx_vid,
+	return dsa_8021q_vid_apply(other_ctx, other_port, rx_vid,
 				   BRIDGE_VLAN_INFO_UNTAGGED, enabled);
 }
 
-static int dsa_8021q_crosschip_link_add(struct dsa_switch *ds, int port,
-					struct dsa_switch *other_ds,
-					int other_port,
-					struct list_head *crosschip_links)
+static int dsa_8021q_crosschip_link_add(struct dsa_8021q_context *ctx, int port,
+					struct dsa_8021q_context *other_ctx,
+					int other_port)
 {
 	struct dsa_8021q_crosschip_link *c;
 
-	list_for_each_entry(c, crosschip_links, list) {
-		if (c->port == port && c->other_ds == other_ds &&
+	list_for_each_entry(c, &ctx->crosschip_links, list) {
+		if (c->port == port && c->other_ctx == other_ctx &&
 		    c->other_port == other_port) {
 			refcount_inc(&c->refcount);
 			return 0;
 		}
 	}
 
-	dev_dbg(ds->dev, "adding crosschip link from port %d to %s port %d\n",
-		port, dev_name(other_ds->dev), other_port);
+	dev_dbg(ctx->ds->dev,
+		"adding crosschip link from port %d to %s port %d\n",
+		port, dev_name(other_ctx->ds->dev), other_port);
 
 	c = kzalloc(sizeof(*c), GFP_KERNEL);
 	if (!c)
 		return -ENOMEM;
 
 	c->port = port;
-	c->other_ds = other_ds;
+	c->other_ctx = other_ctx;
 	c->other_port = other_port;
 	refcount_set(&c->refcount, 1);
 
-	list_add(&c->list, crosschip_links);
+	list_add(&c->list, &ctx->crosschip_links);
 
 	return 0;
 }
 
-static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds,
+static void dsa_8021q_crosschip_link_del(struct dsa_8021q_context *ctx,
 					 struct dsa_8021q_crosschip_link *c,
-					 struct list_head *crosschip_links,
 					 bool *keep)
 {
 	*keep = !refcount_dec_and_test(&c->refcount);
@@ -332,9 +372,9 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds,
 	if (*keep)
 		return;
 
-	dev_dbg(ds->dev,
+	dev_dbg(ctx->ds->dev,
 		"deleting crosschip link from port %d to %s port %d\n",
-		c->port, dev_name(c->other_ds->dev), c->other_port);
+		c->port, dev_name(c->other_ctx->ds->dev), c->other_port);
 
 	list_del(&c->list);
 	kfree(c);
@@ -347,64 +387,58 @@ static void dsa_8021q_crosschip_link_del(struct dsa_switch *ds,
  * or untagged: it doesn't matter, since it should never egress a frame having
  * our @rx_vid.
  */
-int dsa_8021q_crosschip_bridge_join(struct dsa_switch *ds, int port,
-				    struct dsa_switch *other_ds,
-				    int other_port,
-				    struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port,
+				    struct dsa_8021q_context *other_ctx,
+				    int other_port)
 {
 	/* @other_upstream is how @other_ds reaches us. If we are part
 	 * of disjoint trees, then we are probably connected through
 	 * our CPU ports. If we're part of the same tree though, we should
 	 * probably use dsa_towards_port.
 	 */
-	int other_upstream = dsa_upstream_port(other_ds, other_port);
+	int other_upstream = dsa_upstream_port(other_ctx->ds, other_port);
 	int rc;
 
-	rc = dsa_8021q_crosschip_link_add(ds, port, other_ds,
-					  other_port, crosschip_links);
+	rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_port);
 	if (rc)
 		return rc;
 
-	rc = dsa_8021q_crosschip_link_apply(ds, port, other_ds,
+	rc = dsa_8021q_crosschip_link_apply(ctx, port, other_ctx,
 					    other_port, true);
 	if (rc)
 		return rc;
 
-	rc = dsa_8021q_crosschip_link_add(ds, port, other_ds,
-					  other_upstream,
-					  crosschip_links);
+	rc = dsa_8021q_crosschip_link_add(ctx, port, other_ctx, other_upstream);
 	if (rc)
 		return rc;
 
-	return dsa_8021q_crosschip_link_apply(ds, port, other_ds,
+	return dsa_8021q_crosschip_link_apply(ctx, port, other_ctx,
 					      other_upstream, true);
 }
 EXPORT_SYMBOL_GPL(dsa_8021q_crosschip_bridge_join);
 
-int dsa_8021q_crosschip_bridge_leave(struct dsa_switch *ds, int port,
-				     struct dsa_switch *other_ds,
-				     int other_port,
-				     struct list_head *crosschip_links)
+int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port,
+				     struct dsa_8021q_context *other_ctx,
+				     int other_port)
 {
-	int other_upstream = dsa_upstream_port(other_ds, other_port);
+	int other_upstream = dsa_upstream_port(other_ctx->ds, other_port);
 	struct dsa_8021q_crosschip_link *c, *n;
 
-	list_for_each_entry_safe(c, n, crosschip_links, list) {
-		if (c->port == port && c->other_ds == other_ds &&
+	list_for_each_entry_safe(c, n, &ctx->crosschip_links, list) {
+		if (c->port == port && c->other_ctx == other_ctx &&
 		    (c->other_port == other_port ||
 		     c->other_port == other_upstream)) {
-			struct dsa_switch *other_ds = c->other_ds;
+			struct dsa_8021q_context *other_ctx = c->other_ctx;
 			int other_port = c->other_port;
 			bool keep;
 			int rc;
 
-			dsa_8021q_crosschip_link_del(ds, c, crosschip_links,
-						     &keep);
+			dsa_8021q_crosschip_link_del(ctx, c, &keep);
 			if (keep)
 				continue;
 
-			rc = dsa_8021q_crosschip_link_apply(ds, port,
-							    other_ds,
+			rc = dsa_8021q_crosschip_link_apply(ctx, port,
+							    other_ctx,
 							    other_port,
 							    false);
 			if (rc)
diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c
index 55b00694cdba..002cf7f952e2 100644
--- a/net/dsa/tag_ar9331.c
+++ b/net/dsa/tag_ar9331.c
@@ -31,9 +31,6 @@ static struct sk_buff *ar9331_tag_xmit(struct sk_buff *skb,
 	__le16 *phdr;
 	u16 hdr;
 
-	if (skb_cow_head(skb, AR9331_HDR_LEN) < 0)
-		return NULL;
-
 	phdr = skb_push(skb, AR9331_HDR_LEN);
 
 	hdr = FIELD_PREP(AR9331_HDR_VERSION_MASK, AR9331_HDR_VERSION);
diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c
index cc8512b5f9e2..e934dace3922 100644
--- a/net/dsa/tag_brcm.c
+++ b/net/dsa/tag_brcm.c
@@ -66,9 +66,6 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb,
 	u16 queue = skb_get_queue_mapping(skb);
 	u8 *brcm_tag;
 
-	if (skb_cow_head(skb, BRCM_TAG_LEN) < 0)
-		return NULL;
-
 	/* The Ethernet switch we are interfaced with needs packets to be at
 	 * least 64 bytes (including FCS) otherwise they will be discarded when
 	 * they enter the switch port logic. When Broadcom tags are enabled, we
@@ -107,6 +104,18 @@ static struct sk_buff *brcm_tag_xmit_ll(struct sk_buff *skb,
 	return skb;
 }
 
+/* Frames with this tag have one of these two layouts:
+ * -----------------------------------
+ * | MAC DA | MAC SA | 4b tag | Type | DSA_TAG_PROTO_BRCM
+ * -----------------------------------
+ * -----------------------------------
+ * | 4b tag | MAC DA | MAC SA | Type | DSA_TAG_PROTO_BRCM_PREPEND
+ * -----------------------------------
+ * In both cases, at receive time, skb->data points 2 bytes before the actual
+ * Ethernet type field and we have an offset of 4bytes between where skb->data
+ * and where the payload starts. So the same low-level receive function can be
+ * used.
+ */
 static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb,
 				       struct net_device *dev,
 				       struct packet_type *pt,
@@ -144,27 +153,6 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb,
 
 	return skb;
 }
-
-static int brcm_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				 int *offset)
-{
-	/* We have been called on the DSA master network device after
-	 * eth_type_trans() which pulled the Ethernet header already.
-	 * Frames have one of these two layouts:
-	 * -----------------------------------
-	 * | MAC DA | MAC SA | 4b tag | Type | DSA_TAG_PROTO_BRCM
-	 * -----------------------------------
-	 * -----------------------------------
-	 * | 4b tag | MAC DA | MAC SA | Type | DSA_TAG_PROTO_BRCM_PREPEND
-	 * -----------------------------------
-	 * skb->data points 2 bytes before the actual Ethernet type field and
-	 * we have an offset of 4bytes between where skb->data and where the
-	 * payload starts.
-	 */
-	*offset = BRCM_TAG_LEN;
-	*proto = ((__be16 *)skb->data)[1];
-	return 0;
-}
 #endif
 
 #if IS_ENABLED(CONFIG_NET_DSA_TAG_BRCM)
@@ -200,7 +188,6 @@ static const struct dsa_device_ops brcm_netdev_ops = {
 	.xmit	= brcm_tag_xmit,
 	.rcv	= brcm_tag_rcv,
 	.overhead = BRCM_TAG_LEN,
-	.flow_dissect = brcm_tag_flow_dissect,
 };
 
 DSA_TAG_DRIVER(brcm_netdev_ops);
@@ -229,7 +216,6 @@ static const struct dsa_device_ops brcm_prepend_netdev_ops = {
 	.xmit	= brcm_tag_xmit_prepend,
 	.rcv	= brcm_tag_rcv_prepend,
 	.overhead = BRCM_TAG_LEN,
-	.flow_dissect = brcm_tag_flow_dissect,
 };
 
 DSA_TAG_DRIVER(brcm_prepend_netdev_ops);
diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c
index 7ddec9794477..112c7c6dd568 100644
--- a/net/dsa/tag_dsa.c
+++ b/net/dsa/tag_dsa.c
@@ -1,7 +1,48 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * net/dsa/tag_dsa.c - (Non-ethertype) DSA tagging
+ * Regular and Ethertype DSA tagging
  * Copyright (c) 2008-2009 Marvell Semiconductor
+ *
+ * Regular DSA
+ * -----------
+
+ * For untagged (in 802.1Q terms) packets, the switch will splice in
+ * the tag between the SA and the ethertype of the original
+ * packet. Tagged frames will instead have their outermost .1Q tag
+ * converted to a DSA tag. It expects the same layout when receiving
+ * packets from the CPU.
+ *
+ * Example:
+ *
+ *     .----.----.----.---------
+ * Pu: | DA | SA | ET | Payload ...
+ *     '----'----'----'---------
+ *       6    6    2       N
+ *     .----.----.--------.-----.----.---------
+ * Pt: | DA | SA | 0x8100 | TCI | ET | Payload ...
+ *     '----'----'--------'-----'----'---------
+ *       6    6       2      2    2       N
+ *     .----.----.-----.----.---------
+ * Pd: | DA | SA | DSA | ET | Payload ...
+ *     '----'----'-----'----'---------
+ *       6    6     4    2       N
+ *
+ * No matter if a packet is received untagged (Pu) or tagged (Pt),
+ * they will both have the same layout (Pd) when they are sent to the
+ * CPU. This is done by ignoring 802.3, replacing the ethertype field
+ * with more metadata, among which is a bit to signal if the original
+ * packet was tagged or not.
+ *
+ * Ethertype DSA
+ * -------------
+ * Uses the exact same tag format as regular DSA, but also includes a
+ * proper ethertype field (which the mv88e6xxx driver sets to
+ * ETH_P_EDSA/0xdada) followed by two zero bytes:
+ *
+ * .----.----.--------.--------.-----.----.---------
+ * | DA | SA | 0xdada | 0x0000 | DSA | ET | Payload ...
+ * '----'----'--------'--------'-----'----'---------
+ *   6    6       2        2      4    2       N
  */
 
 #include <linux/etherdevice.h>
@@ -12,46 +53,104 @@
 
 #define DSA_HLEN	4
 
-static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
+/**
+ * enum dsa_cmd - DSA Command
+ * @DSA_CMD_TO_CPU: Set on packets that were trapped or mirrored to
+ *     the CPU port. This is needed to implement control protocols,
+ *     e.g. STP and LLDP, that must not allow those control packets to
+ *     be switched according to the normal rules.
+ * @DSA_CMD_FROM_CPU: Used by the CPU to send a packet to a specific
+ *     port, ignoring all the barriers that the switch normally
+ *     enforces (VLANs, STP port states etc.). No source address
+ *     learning takes place. "sudo send packet"
+ * @DSA_CMD_TO_SNIFFER: Set on the copies of packets that matched some
+ *     user configured ingress or egress monitor criteria. These are
+ *     forwarded by the switch tree to the user configured ingress or
+ *     egress monitor port, which can be set to the CPU port or a
+ *     regular port. If the destination is a regular port, the tag
+ *     will be removed before egressing the port. If the destination
+ *     is the CPU port, the tag will not be removed.
+ * @DSA_CMD_FORWARD: This tag is used on all bulk traffic passing
+ *     through the switch tree, including the flows that are directed
+ *     towards the CPU. Its device/port tuple encodes the original
+ *     source port on which the packet ingressed. It can also be used
+ *     on transmit by the CPU to defer the forwarding decision to the
+ *     hardware, based on the current config of PVT/VTU/ATU
+ *     etc. Source address learning takes places if enabled on the
+ *     receiving DSA/CPU port.
+ */
+enum dsa_cmd {
+	DSA_CMD_TO_CPU     = 0,
+	DSA_CMD_FROM_CPU   = 1,
+	DSA_CMD_TO_SNIFFER = 2,
+	DSA_CMD_FORWARD    = 3
+};
+
+/**
+ * enum dsa_code - TO_CPU Code
+ *
+ * @DSA_CODE_MGMT_TRAP: DA was classified as a management
+ *     address. Typical examples include STP BPDUs and LLDP.
+ * @DSA_CODE_FRAME2REG: Response to a "remote management" request.
+ * @DSA_CODE_IGMP_MLD_TRAP: IGMP/MLD signaling.
+ * @DSA_CODE_POLICY_TRAP: Frame matched some policy configuration on
+ *     the device. Typical examples are matching on DA/SA/VID and DHCP
+ *     snooping.
+ * @DSA_CODE_ARP_MIRROR: The name says it all really.
+ * @DSA_CODE_POLICY_MIRROR: Same as @DSA_CODE_POLICY_TRAP, but the
+ *     particular policy was set to trigger a mirror instead of a
+ *     trap.
+ * @DSA_CODE_RESERVED_6: Unused on all devices up to at least 6393X.
+ * @DSA_CODE_RESERVED_7: Unused on all devices up to at least 6393X.
+ *
+ * A 3-bit code is used to relay why a particular frame was sent to
+ * the CPU. We only use this to determine if the packet was mirrored
+ * or trapped, i.e. whether the packet has been forwarded by hardware
+ * or not.
+ *
+ * This is the superset of all possible codes. Any particular device
+ * may only implement a subset.
+ */
+enum dsa_code {
+	DSA_CODE_MGMT_TRAP     = 0,
+	DSA_CODE_FRAME2REG     = 1,
+	DSA_CODE_IGMP_MLD_TRAP = 2,
+	DSA_CODE_POLICY_TRAP   = 3,
+	DSA_CODE_ARP_MIRROR    = 4,
+	DSA_CODE_POLICY_MIRROR = 5,
+	DSA_CODE_RESERVED_6    = 6,
+	DSA_CODE_RESERVED_7    = 7
+};
+
+static struct sk_buff *dsa_xmit_ll(struct sk_buff *skb, struct net_device *dev,
+				   u8 extra)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
 	u8 *dsa_header;
 
-	/*
-	 * Convert the outermost 802.1q tag to a DSA tag for tagged
-	 * packets, or insert a DSA tag between the addresses and
-	 * the ethertype field for untagged packets.
-	 */
 	if (skb->protocol == htons(ETH_P_8021Q)) {
-		if (skb_cow_head(skb, 0) < 0)
-			return NULL;
+		if (extra) {
+			skb_push(skb, extra);
+			memmove(skb->data, skb->data + extra, 2 * ETH_ALEN);
+		}
 
-		/*
-		 * Construct tagged FROM_CPU DSA tag from 802.1q tag.
-		 */
-		dsa_header = skb->data + 2 * ETH_ALEN;
-		dsa_header[0] = 0x60 | dp->ds->index;
+		/* Construct tagged FROM_CPU DSA tag from 802.1Q tag. */
+		dsa_header = skb->data + 2 * ETH_ALEN + extra;
+		dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | 0x20 | dp->ds->index;
 		dsa_header[1] = dp->index << 3;
 
-		/*
-		 * Move CFI field from byte 2 to byte 1.
-		 */
+		/* Move CFI field from byte 2 to byte 1. */
 		if (dsa_header[2] & 0x10) {
 			dsa_header[1] |= 0x01;
 			dsa_header[2] &= ~0x10;
 		}
 	} else {
-		if (skb_cow_head(skb, DSA_HLEN) < 0)
-			return NULL;
-		skb_push(skb, DSA_HLEN);
+		skb_push(skb, DSA_HLEN + extra);
+		memmove(skb->data, skb->data + DSA_HLEN + extra, 2 * ETH_ALEN);
 
-		memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN);
-
-		/*
-		 * Construct untagged FROM_CPU DSA tag.
-		 */
-		dsa_header = skb->data + 2 * ETH_ALEN;
-		dsa_header[0] = 0x40 | dp->ds->index;
+		/* Construct untagged FROM_CPU DSA tag. */
+		dsa_header = skb->data + 2 * ETH_ALEN + extra;
+		dsa_header[0] = (DSA_CMD_FROM_CPU << 6) | dp->ds->index;
 		dsa_header[1] = dp->index << 3;
 		dsa_header[2] = 0x00;
 		dsa_header[3] = 0x00;
@@ -60,30 +159,60 @@ static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
 	return skb;
 }
 
-static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
-			       struct packet_type *pt)
+static struct sk_buff *dsa_rcv_ll(struct sk_buff *skb, struct net_device *dev,
+				  u8 extra)
 {
+	int source_device, source_port;
+	enum dsa_code code;
+	enum dsa_cmd cmd;
 	u8 *dsa_header;
-	int source_device;
-	int source_port;
 
-	if (unlikely(!pskb_may_pull(skb, DSA_HLEN)))
-		return NULL;
-
-	/*
-	 * The ethertype field is part of the DSA header.
-	 */
+	/* The ethertype field is part of the DSA header. */
 	dsa_header = skb->data - 2;
 
-	/*
-	 * Check that frame type is either TO_CPU or FORWARD.
-	 */
-	if ((dsa_header[0] & 0xc0) != 0x00 && (dsa_header[0] & 0xc0) != 0xc0)
+	cmd = dsa_header[0] >> 6;
+	switch (cmd) {
+	case DSA_CMD_FORWARD:
+		skb->offload_fwd_mark = 1;
+		break;
+
+	case DSA_CMD_TO_CPU:
+		code = (dsa_header[1] & 0x6) | ((dsa_header[2] >> 4) & 1);
+
+		switch (code) {
+		case DSA_CODE_FRAME2REG:
+			/* Remote management is not implemented yet,
+			 * drop.
+			 */
+			return NULL;
+		case DSA_CODE_ARP_MIRROR:
+		case DSA_CODE_POLICY_MIRROR:
+			/* Mark mirrored packets to notify any upper
+			 * device (like a bridge) that forwarding has
+			 * already been done by hardware.
+			 */
+			skb->offload_fwd_mark = 1;
+			break;
+		case DSA_CODE_MGMT_TRAP:
+		case DSA_CODE_IGMP_MLD_TRAP:
+		case DSA_CODE_POLICY_TRAP:
+			/* Traps have, by definition, not been
+			 * forwarded by hardware, so don't mark them.
+			 */
+			break;
+		default:
+			/* Reserved code, this could be anything. Drop
+			 * seems like the safest option.
+			 */
+			return NULL;
+		}
+
+		break;
+
+	default:
 		return NULL;
+	}
 
-	/*
-	 * Determine source device and port.
-	 */
 	source_device = dsa_header[0] & 0x1f;
 	source_port = (dsa_header[1] >> 3) & 0x1f;
 
@@ -91,16 +220,15 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!skb->dev)
 		return NULL;
 
-	/*
-	 * Convert the DSA header to an 802.1q header if the 'tagged'
-	 * bit in the DSA header is set.  If the 'tagged' bit is clear,
-	 * delete the DSA header entirely.
+	/* If the 'tagged' bit is set; convert the DSA tag to a 802.1Q
+	 * tag, and delete the ethertype (extra) if applicable. If the
+	 * 'tagged' bit is cleared; delete the DSA tag, and ethertype
+	 * if applicable.
 	 */
 	if (dsa_header[0] & 0x20) {
 		u8 new_header[4];
 
-		/*
-		 * Insert 802.1q ethertype and copy the VLAN-related
+		/* Insert 802.1Q ethertype and copy the VLAN-related
 		 * fields, but clear the bit that will hold CFI (since
 		 * DSA uses that bit location for another purpose).
 		 */
@@ -109,16 +237,13 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 		new_header[2] = dsa_header[2] & ~0x10;
 		new_header[3] = dsa_header[3];
 
-		/*
-		 * Move CFI bit from its place in the DSA header to
-		 * its 802.1q-designated place.
+		/* Move CFI bit from its place in the DSA header to
+		 * its 802.1Q-designated place.
 		 */
 		if (dsa_header[1] & 0x01)
 			new_header[2] |= 0x10;
 
-		/*
-		 * Update packet checksum if skb is CHECKSUM_COMPLETE.
-		 */
+		/* Update packet checksum if skb is CHECKSUM_COMPLETE. */
 		if (skb->ip_summed == CHECKSUM_COMPLETE) {
 			__wsum c = skb->csum;
 			c = csum_add(c, csum_partial(new_header + 2, 2, 0));
@@ -127,39 +252,101 @@ static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
 		}
 
 		memcpy(dsa_header, new_header, DSA_HLEN);
+
+		if (extra)
+			memmove(skb->data - ETH_HLEN,
+				skb->data - ETH_HLEN - extra,
+				2 * ETH_ALEN);
 	} else {
-		/*
-		 * Remove DSA tag and update checksum.
-		 */
 		skb_pull_rcsum(skb, DSA_HLEN);
 		memmove(skb->data - ETH_HLEN,
-			skb->data - ETH_HLEN - DSA_HLEN,
+			skb->data - ETH_HLEN - DSA_HLEN - extra,
 			2 * ETH_ALEN);
 	}
 
-	skb->offload_fwd_mark = 1;
-
 	return skb;
 }
 
-static int dsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				int *offset)
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_DSA)
+
+static struct sk_buff *dsa_xmit(struct sk_buff *skb, struct net_device *dev)
 {
-	*offset = 4;
-	*proto = ((__be16 *)skb->data)[1];
-	return 0;
+	return dsa_xmit_ll(skb, dev, 0);
+}
+
+static struct sk_buff *dsa_rcv(struct sk_buff *skb, struct net_device *dev,
+			       struct packet_type *pt)
+{
+	if (unlikely(!pskb_may_pull(skb, DSA_HLEN)))
+		return NULL;
+
+	return dsa_rcv_ll(skb, dev, 0);
 }
 
 static const struct dsa_device_ops dsa_netdev_ops = {
-	.name	= "dsa",
-	.proto	= DSA_TAG_PROTO_DSA,
-	.xmit	= dsa_xmit,
-	.rcv	= dsa_rcv,
-	.flow_dissect   = dsa_tag_flow_dissect,
+	.name	  = "dsa",
+	.proto	  = DSA_TAG_PROTO_DSA,
+	.xmit	  = dsa_xmit,
+	.rcv	  = dsa_rcv,
 	.overhead = DSA_HLEN,
 };
 
-MODULE_LICENSE("GPL");
+DSA_TAG_DRIVER(dsa_netdev_ops);
 MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_DSA);
+#endif	/* CONFIG_NET_DSA_TAG_DSA */
+
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA)
+
+#define EDSA_HLEN 8
+
+static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	u8 *edsa_header;
+
+	skb = dsa_xmit_ll(skb, dev, EDSA_HLEN - DSA_HLEN);
+	if (!skb)
+		return NULL;
 
-module_dsa_tag_driver(dsa_netdev_ops);
+	edsa_header = skb->data + 2 * ETH_ALEN;
+	edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff;
+	edsa_header[1] = ETH_P_EDSA & 0xff;
+	edsa_header[2] = 0x00;
+	edsa_header[3] = 0x00;
+	return skb;
+}
+
+static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
+				struct packet_type *pt)
+{
+	if (unlikely(!pskb_may_pull(skb, EDSA_HLEN)))
+		return NULL;
+
+	skb_pull_rcsum(skb, EDSA_HLEN - DSA_HLEN);
+
+	return dsa_rcv_ll(skb, dev, EDSA_HLEN - DSA_HLEN);
+}
+
+static const struct dsa_device_ops edsa_netdev_ops = {
+	.name	  = "edsa",
+	.proto	  = DSA_TAG_PROTO_EDSA,
+	.xmit	  = edsa_xmit,
+	.rcv	  = edsa_rcv,
+	.overhead = EDSA_HLEN,
+};
+
+DSA_TAG_DRIVER(edsa_netdev_ops);
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA);
+#endif	/* CONFIG_NET_DSA_TAG_EDSA */
+
+static struct dsa_tag_driver *dsa_tag_drivers[] = {
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_DSA)
+	&DSA_TAG_DRIVER_NAME(dsa_netdev_ops),
+#endif
+#if IS_ENABLED(CONFIG_NET_DSA_TAG_EDSA)
+	&DSA_TAG_DRIVER_NAME(edsa_netdev_ops),
+#endif
+};
+
+module_dsa_tag_drivers(dsa_tag_drivers);
+
+MODULE_LICENSE("GPL");
diff --git a/net/dsa/tag_edsa.c b/net/dsa/tag_edsa.c
deleted file mode 100644
index d6200ff98200..000000000000
--- a/net/dsa/tag_edsa.c
+++ /dev/null
@@ -1,215 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * net/dsa/tag_edsa.c - Ethertype DSA tagging
- * Copyright (c) 2008-2009 Marvell Semiconductor
- */
-
-#include <linux/etherdevice.h>
-#include <linux/list.h>
-#include <linux/slab.h>
-
-#include "dsa_priv.h"
-
-#define DSA_HLEN	4
-#define EDSA_HLEN	8
-
-#define FRAME_TYPE_TO_CPU	0x00
-#define FRAME_TYPE_FORWARD	0x03
-
-#define TO_CPU_CODE_MGMT_TRAP		0x00
-#define TO_CPU_CODE_FRAME2REG		0x01
-#define TO_CPU_CODE_IGMP_MLD_TRAP	0x02
-#define TO_CPU_CODE_POLICY_TRAP		0x03
-#define TO_CPU_CODE_ARP_MIRROR		0x04
-#define TO_CPU_CODE_POLICY_MIRROR	0x05
-
-static struct sk_buff *edsa_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct dsa_port *dp = dsa_slave_to_port(dev);
-	u8 *edsa_header;
-
-	/*
-	 * Convert the outermost 802.1q tag to a DSA tag and prepend
-	 * a DSA ethertype field is the packet is tagged, or insert
-	 * a DSA ethertype plus DSA tag between the addresses and the
-	 * current ethertype field if the packet is untagged.
-	 */
-	if (skb->protocol == htons(ETH_P_8021Q)) {
-		if (skb_cow_head(skb, DSA_HLEN) < 0)
-			return NULL;
-		skb_push(skb, DSA_HLEN);
-
-		memmove(skb->data, skb->data + DSA_HLEN, 2 * ETH_ALEN);
-
-		/*
-		 * Construct tagged FROM_CPU DSA tag from 802.1q tag.
-		 */
-		edsa_header = skb->data + 2 * ETH_ALEN;
-		edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff;
-		edsa_header[1] = ETH_P_EDSA & 0xff;
-		edsa_header[2] = 0x00;
-		edsa_header[3] = 0x00;
-		edsa_header[4] = 0x60 | dp->ds->index;
-		edsa_header[5] = dp->index << 3;
-
-		/*
-		 * Move CFI field from byte 6 to byte 5.
-		 */
-		if (edsa_header[6] & 0x10) {
-			edsa_header[5] |= 0x01;
-			edsa_header[6] &= ~0x10;
-		}
-	} else {
-		if (skb_cow_head(skb, EDSA_HLEN) < 0)
-			return NULL;
-		skb_push(skb, EDSA_HLEN);
-
-		memmove(skb->data, skb->data + EDSA_HLEN, 2 * ETH_ALEN);
-
-		/*
-		 * Construct untagged FROM_CPU DSA tag.
-		 */
-		edsa_header = skb->data + 2 * ETH_ALEN;
-		edsa_header[0] = (ETH_P_EDSA >> 8) & 0xff;
-		edsa_header[1] = ETH_P_EDSA & 0xff;
-		edsa_header[2] = 0x00;
-		edsa_header[3] = 0x00;
-		edsa_header[4] = 0x40 | dp->ds->index;
-		edsa_header[5] = dp->index << 3;
-		edsa_header[6] = 0x00;
-		edsa_header[7] = 0x00;
-	}
-
-	return skb;
-}
-
-static struct sk_buff *edsa_rcv(struct sk_buff *skb, struct net_device *dev,
-				struct packet_type *pt)
-{
-	u8 *edsa_header;
-	int frame_type;
-	int code;
-	int source_device;
-	int source_port;
-
-	if (unlikely(!pskb_may_pull(skb, EDSA_HLEN)))
-		return NULL;
-
-	/*
-	 * Skip the two null bytes after the ethertype.
-	 */
-	edsa_header = skb->data + 2;
-
-	/*
-	 * Check that frame type is either TO_CPU or FORWARD.
-	 */
-	frame_type = edsa_header[0] >> 6;
-
-	switch (frame_type) {
-	case FRAME_TYPE_TO_CPU:
-		code = (edsa_header[1] & 0x6) | ((edsa_header[2] >> 4) & 1);
-
-		/*
-		 * Mark the frame to never egress on any port of the same switch
-		 * unless it's a trapped IGMP/MLD packet, in which case the
-		 * bridge might want to forward it.
-		 */
-		if (code != TO_CPU_CODE_IGMP_MLD_TRAP)
-			skb->offload_fwd_mark = 1;
-
-		break;
-
-	case FRAME_TYPE_FORWARD:
-		skb->offload_fwd_mark = 1;
-		break;
-
-	default:
-		return NULL;
-	}
-
-	/*
-	 * Determine source device and port.
-	 */
-	source_device = edsa_header[0] & 0x1f;
-	source_port = (edsa_header[1] >> 3) & 0x1f;
-
-	skb->dev = dsa_master_find_slave(dev, source_device, source_port);
-	if (!skb->dev)
-		return NULL;
-
-	/*
-	 * If the 'tagged' bit is set, convert the DSA tag to a 802.1q
-	 * tag and delete the ethertype part.  If the 'tagged' bit is
-	 * clear, delete the ethertype and the DSA tag parts.
-	 */
-	if (edsa_header[0] & 0x20) {
-		u8 new_header[4];
-
-		/*
-		 * Insert 802.1q ethertype and copy the VLAN-related
-		 * fields, but clear the bit that will hold CFI (since
-		 * DSA uses that bit location for another purpose).
-		 */
-		new_header[0] = (ETH_P_8021Q >> 8) & 0xff;
-		new_header[1] = ETH_P_8021Q & 0xff;
-		new_header[2] = edsa_header[2] & ~0x10;
-		new_header[3] = edsa_header[3];
-
-		/*
-		 * Move CFI bit from its place in the DSA header to
-		 * its 802.1q-designated place.
-		 */
-		if (edsa_header[1] & 0x01)
-			new_header[2] |= 0x10;
-
-		skb_pull_rcsum(skb, DSA_HLEN);
-
-		/*
-		 * Update packet checksum if skb is CHECKSUM_COMPLETE.
-		 */
-		if (skb->ip_summed == CHECKSUM_COMPLETE) {
-			__wsum c = skb->csum;
-			c = csum_add(c, csum_partial(new_header + 2, 2, 0));
-			c = csum_sub(c, csum_partial(edsa_header + 2, 2, 0));
-			skb->csum = c;
-		}
-
-		memcpy(edsa_header, new_header, DSA_HLEN);
-
-		memmove(skb->data - ETH_HLEN,
-			skb->data - ETH_HLEN - DSA_HLEN,
-			2 * ETH_ALEN);
-	} else {
-		/*
-		 * Remove DSA tag and update checksum.
-		 */
-		skb_pull_rcsum(skb, EDSA_HLEN);
-		memmove(skb->data - ETH_HLEN,
-			skb->data - ETH_HLEN - EDSA_HLEN,
-			2 * ETH_ALEN);
-	}
-
-	return skb;
-}
-
-static int edsa_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				 int *offset)
-{
-	*offset = 8;
-	*proto = ((__be16 *)skb->data)[3];
-	return 0;
-}
-
-static const struct dsa_device_ops edsa_netdev_ops = {
-	.name	= "edsa",
-	.proto	= DSA_TAG_PROTO_EDSA,
-	.xmit	= edsa_xmit,
-	.rcv	= edsa_rcv,
-	.flow_dissect   = edsa_tag_flow_dissect,
-	.overhead = EDSA_HLEN,
-};
-
-MODULE_LICENSE("GPL");
-MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_EDSA);
-
-module_dsa_tag_driver(edsa_netdev_ops);
diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c
index 408d4af390a0..2f5bd5e338ab 100644
--- a/net/dsa/tag_gswip.c
+++ b/net/dsa/tag_gswip.c
@@ -60,13 +60,8 @@ static struct sk_buff *gswip_tag_xmit(struct sk_buff *skb,
 				      struct net_device *dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
-	int err;
 	u8 *gswip_tag;
 
-	err = skb_cow_head(skb, GSWIP_TX_HEADER_LEN);
-	if (err)
-		return NULL;
-
 	skb_push(skb, GSWIP_TX_HEADER_LEN);
 
 	gswip_tag = skb->data;
diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c
new file mode 100644
index 000000000000..a09805c8e1ab
--- /dev/null
+++ b/net/dsa/tag_hellcreek.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * net/dsa/tag_hellcreek.c - Hirschmann Hellcreek switch tag format handling
+ *
+ * Copyright (C) 2019,2020 Linutronix GmbH
+ * Author Kurt Kanzenbach <kurt@linutronix.de>
+ *
+ * Based on tag_ksz.c.
+ */
+
+#include <linux/skbuff.h>
+#include <net/dsa.h>
+
+#include "dsa_priv.h"
+
+#define HELLCREEK_TAG_LEN	1
+
+static struct sk_buff *hellcreek_xmit(struct sk_buff *skb,
+				      struct net_device *dev)
+{
+	struct dsa_port *dp = dsa_slave_to_port(dev);
+	u8 *tag;
+
+	/* Tag encoding */
+	tag  = skb_put(skb, HELLCREEK_TAG_LEN);
+	*tag = BIT(dp->index);
+
+	return skb;
+}
+
+static struct sk_buff *hellcreek_rcv(struct sk_buff *skb,
+				     struct net_device *dev,
+				     struct packet_type *pt)
+{
+	/* Tag decoding */
+	u8 *tag = skb_tail_pointer(skb) - HELLCREEK_TAG_LEN;
+	unsigned int port = tag[0] & 0x03;
+
+	skb->dev = dsa_master_find_slave(dev, 0, port);
+	if (!skb->dev) {
+		netdev_warn(dev, "Failed to get source port: %d\n", port);
+		return NULL;
+	}
+
+	pskb_trim_rcsum(skb, skb->len - HELLCREEK_TAG_LEN);
+
+	skb->offload_fwd_mark = true;
+
+	return skb;
+}
+
+static const struct dsa_device_ops hellcreek_netdev_ops = {
+	.name	  = "hellcreek",
+	.proto	  = DSA_TAG_PROTO_HELLCREEK,
+	.xmit	  = hellcreek_xmit,
+	.rcv	  = hellcreek_rcv,
+	.overhead = HELLCREEK_TAG_LEN,
+	.tail_tag = true,
+};
+
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_HELLCREEK);
+
+module_dsa_tag_driver(hellcreek_netdev_ops);
diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c
index bd1a3158d79a..4820dbcedfa2 100644
--- a/net/dsa/tag_ksz.c
+++ b/net/dsa/tag_ksz.c
@@ -14,46 +14,6 @@
 #define KSZ_EGRESS_TAG_LEN		1
 #define KSZ_INGRESS_TAG_LEN		1
 
-static struct sk_buff *ksz_common_xmit(struct sk_buff *skb,
-				       struct net_device *dev, int len)
-{
-	struct sk_buff *nskb;
-	int padlen;
-
-	padlen = (skb->len >= ETH_ZLEN) ? 0 : ETH_ZLEN - skb->len;
-
-	if (skb_tailroom(skb) >= padlen + len) {
-		/* Let dsa_slave_xmit() free skb */
-		if (__skb_put_padto(skb, skb->len + padlen, false))
-			return NULL;
-
-		nskb = skb;
-	} else {
-		nskb = alloc_skb(NET_IP_ALIGN + skb->len +
-				 padlen + len, GFP_ATOMIC);
-		if (!nskb)
-			return NULL;
-		skb_reserve(nskb, NET_IP_ALIGN);
-
-		skb_reset_mac_header(nskb);
-		skb_set_network_header(nskb,
-				       skb_network_header(skb) - skb->head);
-		skb_set_transport_header(nskb,
-					 skb_transport_header(skb) - skb->head);
-		skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len));
-
-		/* Let skb_put_padto() free nskb, and let dsa_slave_xmit() free
-		 * skb
-		 */
-		if (skb_put_padto(nskb, nskb->len + padlen))
-			return NULL;
-
-		consume_skb(skb);
-	}
-
-	return nskb;
-}
-
 static struct sk_buff *ksz_common_rcv(struct sk_buff *skb,
 				      struct net_device *dev,
 				      unsigned int port, unsigned int len)
@@ -90,23 +50,18 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb,
 static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
-	struct sk_buff *nskb;
 	u8 *tag;
 	u8 *addr;
 
-	nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN);
-	if (!nskb)
-		return NULL;
-
 	/* Tag encoding */
-	tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
-	addr = skb_mac_header(nskb);
+	tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
+	addr = skb_mac_header(skb);
 
 	*tag = 1 << dp->index;
 	if (is_link_local_ether_addr(addr))
 		*tag |= KSZ8795_TAIL_TAG_OVERRIDE;
 
-	return nskb;
+	return skb;
 }
 
 static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev,
@@ -123,6 +78,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = {
 	.xmit	= ksz8795_xmit,
 	.rcv	= ksz8795_rcv,
 	.overhead = KSZ_INGRESS_TAG_LEN,
+	.tail_tag = true,
 };
 
 DSA_TAG_DRIVER(ksz8795_netdev_ops);
@@ -155,18 +111,13 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
-	struct sk_buff *nskb;
 	__be16 *tag;
 	u8 *addr;
 	u16 val;
 
-	nskb = ksz_common_xmit(skb, dev, KSZ9477_INGRESS_TAG_LEN);
-	if (!nskb)
-		return NULL;
-
 	/* Tag encoding */
-	tag = skb_put(nskb, KSZ9477_INGRESS_TAG_LEN);
-	addr = skb_mac_header(nskb);
+	tag = skb_put(skb, KSZ9477_INGRESS_TAG_LEN);
+	addr = skb_mac_header(skb);
 
 	val = BIT(dp->index);
 
@@ -175,7 +126,7 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb,
 
 	*tag = cpu_to_be16(val);
 
-	return nskb;
+	return skb;
 }
 
 static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev,
@@ -199,6 +150,7 @@ static const struct dsa_device_ops ksz9477_netdev_ops = {
 	.xmit	= ksz9477_xmit,
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ9477_INGRESS_TAG_LEN,
+	.tail_tag = true,
 };
 
 DSA_TAG_DRIVER(ksz9477_netdev_ops);
@@ -211,24 +163,19 @@ static struct sk_buff *ksz9893_xmit(struct sk_buff *skb,
 				    struct net_device *dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
-	struct sk_buff *nskb;
 	u8 *addr;
 	u8 *tag;
 
-	nskb = ksz_common_xmit(skb, dev, KSZ_INGRESS_TAG_LEN);
-	if (!nskb)
-		return NULL;
-
 	/* Tag encoding */
-	tag = skb_put(nskb, KSZ_INGRESS_TAG_LEN);
-	addr = skb_mac_header(nskb);
+	tag = skb_put(skb, KSZ_INGRESS_TAG_LEN);
+	addr = skb_mac_header(skb);
 
 	*tag = BIT(dp->index);
 
 	if (is_link_local_ether_addr(addr))
 		*tag |= KSZ9893_TAIL_TAG_OVERRIDE;
 
-	return nskb;
+	return skb;
 }
 
 static const struct dsa_device_ops ksz9893_netdev_ops = {
@@ -237,6 +184,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = {
 	.xmit	= ksz9893_xmit,
 	.rcv	= ksz9477_rcv,
 	.overhead = KSZ_INGRESS_TAG_LEN,
+	.tail_tag = true,
 };
 
 DSA_TAG_DRIVER(ksz9893_netdev_ops);
diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c
index ccfb6f641bbf..aa1318dccaf0 100644
--- a/net/dsa/tag_lan9303.c
+++ b/net/dsa/tag_lan9303.c
@@ -58,15 +58,6 @@ static struct sk_buff *lan9303_xmit(struct sk_buff *skb, struct net_device *dev)
 	__be16 *lan9303_tag;
 	u16 tag;
 
-	/* insert a special VLAN tag between the MAC addresses
-	 * and the current ethertype field.
-	 */
-	if (skb_cow_head(skb, LAN9303_TAG_LEN) < 0) {
-		dev_dbg(&dev->dev,
-			"Cannot make room for the special tag. Dropping packet\n");
-		return NULL;
-	}
-
 	/* provide 'LAN9303_TAG_LEN' bytes additional space */
 	skb_push(skb, LAN9303_TAG_LEN);
 
diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c
index f602fc758d68..38dcdded74c0 100644
--- a/net/dsa/tag_mtk.c
+++ b/net/dsa/tag_mtk.c
@@ -34,9 +34,6 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb,
 	 * table with VID.
 	 */
 	if (!skb_vlan_tagged(skb)) {
-		if (skb_cow_head(skb, MTK_HDR_LEN) < 0)
-			return NULL;
-
 		skb_push(skb, MTK_HDR_LEN);
 		memmove(skb->data, skb->data + MTK_HDR_LEN, 2 * ETH_ALEN);
 		is_vlan_skb = false;
@@ -105,21 +102,11 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int mtk_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				int *offset)
-{
-	*offset = 4;
-	*proto = ((__be16 *)skb->data)[1];
-
-	return 0;
-}
-
 static const struct dsa_device_ops mtk_netdev_ops = {
 	.name		= "mtk",
 	.proto		= DSA_TAG_PROTO_MTK,
 	.xmit		= mtk_tag_xmit,
 	.rcv		= mtk_tag_rcv,
-	.flow_dissect	= mtk_tag_flow_dissect,
 	.overhead	= MTK_HDR_LEN,
 };
 
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index b4fc05cafaa6..16a1afd5b8e1 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -137,31 +137,29 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb,
 				   struct net_device *netdev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(netdev);
+	struct sk_buff *clone = DSA_SKB_CB(skb)->clone;
 	struct dsa_switch *ds = dp->ds;
 	struct ocelot *ocelot = ds->priv;
 	struct ocelot_port *ocelot_port;
+	u8 *prefix, *injection;
 	u64 qos_class, rew_op;
-	u8 *injection;
-
-	if (unlikely(skb_cow_head(skb, OCELOT_TAG_LEN) < 0)) {
-		netdev_err(netdev, "Cannot make room for tag.\n");
-		return NULL;
-	}
 
 	ocelot_port = ocelot->ports[dp->index];
 
 	injection = skb_push(skb, OCELOT_TAG_LEN);
 
-	memcpy(injection, ocelot_port->xmit_template, OCELOT_TAG_LEN);
+	prefix = skb_push(skb, OCELOT_SHORT_PREFIX_LEN);
+
+	memcpy(prefix, ocelot_port->xmit_template, OCELOT_TOTAL_TAG_LEN);
+
 	/* Fix up the fields which are not statically determined
 	 * in the template
 	 */
 	qos_class = skb->priority;
 	packing(injection, &qos_class, 19,  17, OCELOT_TAG_LEN, PACK, 0);
 
-	if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) {
-		struct sk_buff *clone = DSA_SKB_CB(skb)->clone;
-
+	/* TX timestamping was requested */
+	if (clone) {
 		rew_op = ocelot_port->ptp_cmd;
 		/* Retrieve timestamp ID populated inside skb->cb[0] of the
 		 * clone by ocelot_port_add_txtstamp_skb
@@ -179,19 +177,24 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb,
 				  struct net_device *netdev,
 				  struct packet_type *pt)
 {
+	struct dsa_port *cpu_dp = netdev->dsa_ptr;
+	struct dsa_switch *ds = cpu_dp->ds;
+	struct ocelot *ocelot = ds->priv;
 	u64 src_port, qos_class;
+	u64 vlan_tci, tag_type;
 	u8 *start = skb->data;
 	u8 *extraction;
+	u16 vlan_tpid;
 
 	/* Revert skb->data by the amount consumed by the DSA master,
 	 * so it points to the beginning of the frame.
 	 */
 	skb_push(skb, ETH_HLEN);
-	/* We don't care about the long prefix, it is just for easy entrance
+	/* We don't care about the short prefix, it is just for easy entrance
 	 * into the DSA master's RX filter. Discard it now by moving it into
 	 * the headroom.
 	 */
-	skb_pull(skb, OCELOT_LONG_PREFIX_LEN);
+	skb_pull(skb, OCELOT_SHORT_PREFIX_LEN);
 	/* And skb->data now points to the extraction frame header.
 	 * Keep a pointer to it.
 	 */
@@ -205,10 +208,12 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb,
 	skb_pull(skb, ETH_HLEN);
 
 	/* Remove from inet csum the extraction header */
-	skb_postpull_rcsum(skb, start, OCELOT_LONG_PREFIX_LEN + OCELOT_TAG_LEN);
+	skb_postpull_rcsum(skb, start, OCELOT_TOTAL_TAG_LEN);
 
 	packing(extraction, &src_port,  46, 43, OCELOT_TAG_LEN, UNPACK, 0);
 	packing(extraction, &qos_class, 19, 17, OCELOT_TAG_LEN, UNPACK, 0);
+	packing(extraction, &tag_type,  16, 16, OCELOT_TAG_LEN, UNPACK, 0);
+	packing(extraction, &vlan_tci,  15,  0, OCELOT_TAG_LEN, UNPACK, 0);
 
 	skb->dev = dsa_master_find_slave(netdev, 0, src_port);
 	if (!skb->dev)
@@ -223,6 +228,33 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb,
 	skb->offload_fwd_mark = 1;
 	skb->priority = qos_class;
 
+	/* Ocelot switches copy frames unmodified to the CPU. However, it is
+	 * possible for the user to request a VLAN modification through
+	 * VCAP_IS1_ACT_VID_REPLACE_ENA. In this case, what will happen is that
+	 * the VLAN ID field from the Extraction Header gets updated, but the
+	 * 802.1Q header does not (the classified VLAN only becomes visible on
+	 * egress through the "port tag" of front-panel ports).
+	 * So, for traffic extracted by the CPU, we want to pick up the
+	 * classified VLAN and manually replace the existing 802.1Q header from
+	 * the packet with it, so that the operating system is always up to
+	 * date with the result of tc-vlan actions.
+	 * NOTE: In VLAN-unaware mode, we don't want to do that, we want the
+	 * frame to remain unmodified, because the classified VLAN is always
+	 * equal to the pvid of the ingress port and should not be used for
+	 * processing.
+	 */
+	vlan_tpid = tag_type ? ETH_P_8021AD : ETH_P_8021Q;
+
+	if (ocelot->ports[src_port]->vlan_aware &&
+	    eth_hdr(skb)->h_proto == htons(vlan_tpid)) {
+		u16 dummy_vlan_tci;
+
+		skb_push_rcsum(skb, ETH_HLEN);
+		__skb_vlan_pop(skb, &dummy_vlan_tci);
+		skb_pull_rcsum(skb, ETH_HLEN);
+		__vlan_hwaccel_put_tag(skb, htons(vlan_tpid), vlan_tci);
+	}
+
 	return skb;
 }
 
@@ -231,7 +263,8 @@ static const struct dsa_device_ops ocelot_netdev_ops = {
 	.proto			= DSA_TAG_PROTO_OCELOT,
 	.xmit			= ocelot_xmit,
 	.rcv			= ocelot_rcv,
-	.overhead		= OCELOT_TAG_LEN + OCELOT_LONG_PREFIX_LEN,
+	.overhead		= OCELOT_TOTAL_TAG_LEN,
+	.promisc_on_master	= true,
 };
 
 MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c
index 7066f5e697d7..88181b52f480 100644
--- a/net/dsa/tag_qca.c
+++ b/net/dsa/tag_qca.c
@@ -34,9 +34,6 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev)
 	__be16 *phdr;
 	u16 hdr;
 
-	if (skb_cow_head(skb, QCA_HDR_LEN) < 0)
-		return NULL;
-
 	skb_push(skb, QCA_HDR_LEN);
 
 	memmove(skb->data, skb->data + QCA_HDR_LEN, 2 * ETH_ALEN);
@@ -89,21 +86,11 @@ static struct sk_buff *qca_tag_rcv(struct sk_buff *skb, struct net_device *dev,
 	return skb;
 }
 
-static int qca_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-                                int *offset)
-{
-	*offset = QCA_HDR_LEN;
-	*proto = ((__be16 *)skb->data)[0];
-
-	return 0;
-}
-
 static const struct dsa_device_ops qca_netdev_ops = {
 	.name	= "qca",
 	.proto	= DSA_TAG_PROTO_QCA,
 	.xmit	= qca_tag_xmit,
 	.rcv	= qca_tag_rcv,
-	.flow_dissect = qca_tag_flow_dissect,
 	.overhead = QCA_HDR_LEN,
 };
 
diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c
index 7b63010fa87b..2646abe5a69e 100644
--- a/net/dsa/tag_rtl4_a.c
+++ b/net/dsa/tag_rtl4_a.c
@@ -106,22 +106,11 @@ static struct sk_buff *rtl4a_tag_rcv(struct sk_buff *skb,
 	return skb;
 }
 
-static int rtl4a_tag_flow_dissect(const struct sk_buff *skb, __be16 *proto,
-				  int *offset)
-{
-	*offset = RTL4_A_HDR_LEN;
-	/* Skip past the tag and fetch the encapsulated Ethertype */
-	*proto = ((__be16 *)skb->data)[1];
-
-	return 0;
-}
-
 static const struct dsa_device_ops rtl4a_netdev_ops = {
 	.name	= "rtl4a",
 	.proto	= DSA_TAG_PROTO_RTL4_A,
 	.xmit	= rtl4a_tag_xmit,
 	.rcv	= rtl4a_tag_rcv,
-	.flow_dissect = rtl4a_tag_flow_dissect,
 	.overhead = RTL4_A_HDR_LEN,
 };
 module_dsa_tag_driver(rtl4a_netdev_ops);
diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c
index 9b4a4d719291..50496013cdb7 100644
--- a/net/dsa/tag_sja1105.c
+++ b/net/dsa/tag_sja1105.c
@@ -72,14 +72,21 @@ static inline bool sja1105_is_meta_frame(const struct sk_buff *skb)
 static bool sja1105_can_use_vlan_as_tags(const struct sk_buff *skb)
 {
 	struct vlan_ethhdr *hdr = vlan_eth_hdr(skb);
+	u16 vlan_tci;
 
 	if (hdr->h_vlan_proto == htons(ETH_P_SJA1105))
 		return true;
 
-	if (hdr->h_vlan_proto != htons(ETH_P_8021Q))
+	if (hdr->h_vlan_proto != htons(ETH_P_8021Q) &&
+	    !skb_vlan_tag_present(skb))
 		return false;
 
-	return vid_is_dsa_8021q(ntohs(hdr->h_vlan_TCI) & VLAN_VID_MASK);
+	if (skb_vlan_tag_present(skb))
+		vlan_tci = skb_vlan_tag_get(skb);
+	else
+		vlan_tci = ntohs(hdr->h_vlan_TCI);
+
+	return vid_is_dsa_8021q(vlan_tci & VLAN_VID_MASK);
 }
 
 /* This is the first time the tagger sees the frame on RX.
@@ -283,7 +290,8 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 
 	hdr = eth_hdr(skb);
 	tpid = ntohs(hdr->h_proto);
-	is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q);
+	is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q ||
+		     skb_vlan_tag_present(skb));
 	is_link_local = sja1105_is_link_local(skb);
 	is_meta = sja1105_is_meta_frame(skb);
 
@@ -292,7 +300,12 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 	if (is_tagged) {
 		/* Normal traffic path. */
 		skb_push_rcsum(skb, ETH_HLEN);
-		__skb_vlan_pop(skb, &tci);
+		if (skb_vlan_tag_present(skb)) {
+			tci = skb_vlan_tag_get(skb);
+			__vlan_hwaccel_clear_tag(skb);
+		} else {
+			__skb_vlan_pop(skb, &tci);
+		}
 		skb_pull_rcsum(skb, ETH_HLEN);
 		skb_reset_network_header(skb);
 		skb_reset_transport_header(skb);
@@ -333,6 +346,16 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb,
 					      is_meta);
 }
 
+static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto,
+				 int *offset)
+{
+	/* No tag added for management frames, all ok */
+	if (unlikely(sja1105_is_link_local(skb)))
+		return;
+
+	dsa_tag_generic_flow_dissect(skb, proto, offset);
+}
+
 static const struct dsa_device_ops sja1105_netdev_ops = {
 	.name = "sja1105",
 	.proto = DSA_TAG_PROTO_SJA1105,
@@ -340,6 +363,8 @@ static const struct dsa_device_ops sja1105_netdev_ops = {
 	.rcv = sja1105_rcv,
 	.filter = sja1105_filter,
 	.overhead = VLAN_HLEN,
+	.flow_dissect = sja1105_flow_dissect,
+	.promisc_on_master = true,
 };
 
 MODULE_LICENSE("GPL v2");
diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c
index 4f8ab62f0208..5b97ede56a0f 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -13,42 +13,15 @@
 static struct sk_buff *trailer_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct dsa_port *dp = dsa_slave_to_port(dev);
-	struct sk_buff *nskb;
-	int padlen;
 	u8 *trailer;
 
-	/*
-	 * We have to make sure that the trailer ends up as the very
-	 * last 4 bytes of the packet.  This means that we have to pad
-	 * the packet to the minimum ethernet frame size, if necessary,
-	 * before adding the trailer.
-	 */
-	padlen = 0;
-	if (skb->len < 60)
-		padlen = 60 - skb->len;
-
-	nskb = alloc_skb(NET_IP_ALIGN + skb->len + padlen + 4, GFP_ATOMIC);
-	if (!nskb)
-		return NULL;
-	skb_reserve(nskb, NET_IP_ALIGN);
-
-	skb_reset_mac_header(nskb);
-	skb_set_network_header(nskb, skb_network_header(skb) - skb->head);
-	skb_set_transport_header(nskb, skb_transport_header(skb) - skb->head);
-	skb_copy_and_csum_dev(skb, skb_put(nskb, skb->len));
-	consume_skb(skb);
-
-	if (padlen) {
-		skb_put_zero(nskb, padlen);
-	}
-
-	trailer = skb_put(nskb, 4);
+	trailer = skb_put(skb, 4);
 	trailer[0] = 0x80;
 	trailer[1] = 1 << dp->index;
 	trailer[2] = 0x10;
 	trailer[3] = 0x00;
 
-	return nskb;
+	return skb;
 }
 
 static struct sk_buff *trailer_rcv(struct sk_buff *skb, struct net_device *dev,
@@ -83,6 +56,7 @@ static const struct dsa_device_ops trailer_netdev_ops = {
 	.xmit	= trailer_xmit,
 	.rcv	= trailer_rcv,
 	.overhead = 4,
+	.tail_tag = true,
 };
 
 MODULE_LICENSE("GPL");
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index dac65180c4ef..4106373180c6 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -272,7 +272,7 @@ void eth_header_cache_update(struct hh_cache *hh,
 EXPORT_SYMBOL(eth_header_cache_update);
 
 /**
- * eth_header_parser_protocol - extract protocol from L2 header
+ * eth_header_parse_protocol - extract protocol from L2 header
  * @skb: packet to extract protocol from
  */
 __be16 eth_header_parse_protocol(const struct sk_buff *skb)
@@ -523,8 +523,8 @@ int eth_platform_get_mac_address(struct device *dev, u8 *mac_addr)
 EXPORT_SYMBOL(eth_platform_get_mac_address);
 
 /**
- * Obtain the MAC address from an nvmem cell named 'mac-address' associated
- * with given device.
+ * nvmem_get_mac_address - Obtain the MAC address from an nvmem cell named
+ * 'mac-address' associated with given device.
  *
  * @dev:	Device with which the mac-address cell is associated.
  * @addrbuf:	Buffer to which the MAC address will be copied on success.
diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c
index dae7402eaca3..0515d6604b3b 100644
--- a/net/ethtool/bitset.c
+++ b/net/ethtool/bitset.c
@@ -302,8 +302,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = {
-	[ETHTOOL_A_BITSET_UNSPEC]	= { .type = NLA_REJECT },
+static const struct nla_policy bitset_policy[] = {
 	[ETHTOOL_A_BITSET_NOMASK]	= { .type = NLA_FLAG },
 	[ETHTOOL_A_BITSET_SIZE]		= NLA_POLICY_MAX(NLA_U32,
 							 ETHNL_MAX_BITSET_SIZE),
@@ -312,8 +311,7 @@ static const struct nla_policy bitset_policy[ETHTOOL_A_BITSET_MAX + 1] = {
 	[ETHTOOL_A_BITSET_MASK]		= { .type = NLA_BINARY },
 };
 
-static const struct nla_policy bit_policy[ETHTOOL_A_BITSET_BIT_MAX + 1] = {
-	[ETHTOOL_A_BITSET_BIT_UNSPEC]	= { .type = NLA_REJECT },
+static const struct nla_policy bit_policy[] = {
 	[ETHTOOL_A_BITSET_BIT_INDEX]	= { .type = NLA_U32 },
 	[ETHTOOL_A_BITSET_BIT_NAME]	= { .type = NLA_NUL_STRING },
 	[ETHTOOL_A_BITSET_BIT_VALUE]	= { .type = NLA_FLAG },
@@ -329,10 +327,10 @@ static const struct nla_policy bit_policy[ETHTOOL_A_BITSET_BIT_MAX + 1] = {
  */
 int ethnl_bitset_is_compact(const struct nlattr *bitset, bool *compact)
 {
-	struct nlattr *tb[ETHTOOL_A_BITSET_MAX + 1];
+	struct nlattr *tb[ARRAY_SIZE(bitset_policy)];
 	int ret;
 
-	ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_MAX, bitset,
+	ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, bitset,
 			       bitset_policy, NULL);
 	if (ret < 0)
 		return ret;
@@ -381,10 +379,10 @@ static int ethnl_parse_bit(unsigned int *index, bool *val, unsigned int nbits,
 			   ethnl_string_array_t names,
 			   struct netlink_ext_ack *extack)
 {
-	struct nlattr *tb[ETHTOOL_A_BITSET_BIT_MAX + 1];
+	struct nlattr *tb[ARRAY_SIZE(bit_policy)];
 	int ret, idx;
 
-	ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_BIT_MAX, bit_attr,
+	ret = nla_parse_nested(tb, ARRAY_SIZE(bit_policy) - 1, bit_attr,
 			       bit_policy, extack);
 	if (ret < 0)
 		return ret;
@@ -555,15 +553,15 @@ int ethnl_update_bitset32(u32 *bitmap, unsigned int nbits,
 			  const struct nlattr *attr, ethnl_string_array_t names,
 			  struct netlink_ext_ack *extack, bool *mod)
 {
-	struct nlattr *tb[ETHTOOL_A_BITSET_MAX + 1];
+	struct nlattr *tb[ARRAY_SIZE(bitset_policy)];
 	unsigned int change_bits;
 	bool no_mask;
 	int ret;
 
 	if (!attr)
 		return 0;
-	ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_MAX, attr, bitset_policy,
-			       extack);
+	ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, attr,
+			       bitset_policy, extack);
 	if (ret < 0)
 		return ret;
 
@@ -608,7 +606,7 @@ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask,
 		       ethnl_string_array_t names,
 		       struct netlink_ext_ack *extack)
 {
-	struct nlattr *tb[ETHTOOL_A_BITSET_MAX + 1];
+	struct nlattr *tb[ARRAY_SIZE(bitset_policy)];
 	const struct nlattr *bit_attr;
 	bool no_mask;
 	int rem;
@@ -616,8 +614,8 @@ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask,
 
 	if (!attr)
 		return 0;
-	ret = nla_parse_nested(tb, ETHTOOL_A_BITSET_MAX, attr, bitset_policy,
-			       extack);
+	ret = nla_parse_nested(tb, ARRAY_SIZE(bitset_policy) - 1, attr,
+			       bitset_policy, extack);
 	if (ret < 0)
 		return ret;
 	no_mask = tb[ETHTOOL_A_BITSET_NOMASK];
@@ -630,6 +628,8 @@ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask,
 			return ret;
 
 		change_bits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]);
+		if (change_bits > nbits)
+			change_bits = nbits;
 		bitmap_from_arr32(val, nla_data(tb[ETHTOOL_A_BITSET_VALUE]),
 				  change_bits);
 		if (change_bits < nbits)
diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index 888f6e101f34..63560bbb7d1f 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -11,10 +11,9 @@
  */
 #define MAX_CABLE_LENGTH_CM (150 * 100)
 
-static const struct nla_policy
-cable_test_act_policy[ETHTOOL_A_CABLE_TEST_MAX + 1] = {
-	[ETHTOOL_A_CABLE_TEST_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CABLE_TEST_HEADER]		= { .type = NLA_NESTED },
+const struct nla_policy ethnl_cable_test_act_policy[] = {
+	[ETHTOOL_A_CABLE_TEST_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int ethnl_cable_test_started(struct phy_device *phydev, u8 cmd)
@@ -56,18 +55,12 @@ out:
 
 int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_CABLE_TEST_MAX + 1];
 	struct ethnl_req_info req_info = {};
 	const struct ethtool_phy_ops *ops;
+	struct nlattr **tb = info->attrs;
 	struct net_device *dev;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_CABLE_TEST_MAX,
-			  cable_test_act_policy, info->extack);
-	if (ret < 0)
-		return ret;
-
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_CABLE_TEST_HEADER],
 					 genl_info_net(info), info->extack,
@@ -218,18 +211,16 @@ struct cable_test_tdr_req_info {
 	struct ethnl_req_info		base;
 };
 
-static const struct nla_policy
-cable_test_tdr_act_cfg_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1] = {
+static const struct nla_policy cable_test_tdr_act_cfg_policy[] = {
 	[ETHTOOL_A_CABLE_TEST_TDR_CFG_FIRST]	= { .type = NLA_U32 },
 	[ETHTOOL_A_CABLE_TEST_TDR_CFG_LAST]	= { .type = NLA_U32 },
 	[ETHTOOL_A_CABLE_TEST_TDR_CFG_STEP]	= { .type = NLA_U32 },
 	[ETHTOOL_A_CABLE_TEST_TDR_CFG_PAIR]	= { .type = NLA_U8 },
 };
 
-static const struct nla_policy
-cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_MAX + 1] = {
-	[ETHTOOL_A_CABLE_TEST_TDR_UNSPEC]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_CABLE_TEST_TDR_HEADER]	= { .type = NLA_NESTED },
+const struct nla_policy ethnl_cable_test_tdr_act_policy[] = {
+	[ETHTOOL_A_CABLE_TEST_TDR_HEADER]	=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_CABLE_TEST_TDR_CFG]		= { .type = NLA_NESTED },
 };
 
@@ -238,7 +229,7 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest,
 					struct genl_info *info,
 					struct phy_tdr_config *cfg)
 {
-	struct nlattr *tb[ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX + 1];
+	struct nlattr *tb[ARRAY_SIZE(cable_test_tdr_act_cfg_policy)];
 	int ret;
 
 	cfg->first = 100;
@@ -249,8 +240,10 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest,
 	if (!nest)
 		return 0;
 
-	ret = nla_parse_nested(tb, ETHTOOL_A_CABLE_TEST_TDR_CFG_MAX, nest,
-			       cable_test_tdr_act_cfg_policy, info->extack);
+	ret = nla_parse_nested(tb,
+			       ARRAY_SIZE(cable_test_tdr_act_cfg_policy) - 1,
+			       nest, cable_test_tdr_act_cfg_policy,
+			       info->extack);
 	if (ret < 0)
 		return ret;
 
@@ -313,19 +306,13 @@ static int ethnl_act_cable_test_tdr_cfg(const struct nlattr *nest,
 
 int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_CABLE_TEST_TDR_MAX + 1];
 	struct ethnl_req_info req_info = {};
 	const struct ethtool_phy_ops *ops;
+	struct nlattr **tb = info->attrs;
 	struct phy_tdr_config cfg;
 	struct net_device *dev;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_CABLE_TEST_TDR_MAX,
-			  cable_test_tdr_act_policy, info->extack);
-	if (ret < 0)
-		return ret;
-
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER],
 					 genl_info_net(info), info->extack,
diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
index 9ef54cdcf662..25a9e566ef5c 100644
--- a/net/ethtool/channels.c
+++ b/net/ethtool/channels.c
@@ -17,18 +17,9 @@ struct channels_reply_data {
 #define CHANNELS_REPDATA(__reply_base) \
 	container_of(__reply_base, struct channels_reply_data, base)
 
-static const struct nla_policy
-channels_get_policy[ETHTOOL_A_CHANNELS_MAX + 1] = {
-	[ETHTOOL_A_CHANNELS_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_CHANNELS_RX_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_TX_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_OTHER_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_COMBINED_MAX]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_RX_COUNT]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_TX_COUNT]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_OTHER_COUNT]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_COMBINED_COUNT]	= { .type = NLA_REJECT },
+const struct nla_policy ethnl_channels_get_policy[] = {
+	[ETHTOOL_A_CHANNELS_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int channels_prepare_data(const struct ethnl_req_info *req_base,
@@ -99,10 +90,8 @@ const struct ethnl_request_ops ethnl_channels_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_CHANNELS_GET,
 	.reply_cmd		= ETHTOOL_MSG_CHANNELS_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_CHANNELS_HEADER,
-	.max_attr		= ETHTOOL_A_CHANNELS_MAX,
 	.req_info_size		= sizeof(struct channels_req_info),
 	.reply_data_size	= sizeof(struct channels_reply_data),
-	.request_policy		= channels_get_policy,
 
 	.prepare_data		= channels_prepare_data,
 	.reply_size		= channels_reply_size,
@@ -111,14 +100,9 @@ const struct ethnl_request_ops ethnl_channels_request_ops = {
 
 /* CHANNELS_SET */
 
-static const struct nla_policy
-channels_set_policy[ETHTOOL_A_CHANNELS_MAX + 1] = {
-	[ETHTOOL_A_CHANNELS_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_CHANNELS_RX_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_TX_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_OTHER_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_CHANNELS_COMBINED_MAX]	= { .type = NLA_REJECT },
+const struct nla_policy ethnl_channels_set_policy[] = {
+	[ETHTOOL_A_CHANNELS_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_CHANNELS_RX_COUNT]		= { .type = NLA_U32 },
 	[ETHTOOL_A_CHANNELS_TX_COUNT]		= { .type = NLA_U32 },
 	[ETHTOOL_A_CHANNELS_OTHER_COUNT]	= { .type = NLA_U32 },
@@ -127,22 +111,17 @@ channels_set_policy[ETHTOOL_A_CHANNELS_MAX + 1] = {
 
 int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_CHANNELS_MAX + 1];
 	unsigned int from_channel, old_total, i;
 	bool mod = false, mod_combined = false;
 	struct ethtool_channels channels = {};
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	const struct nlattr *err_attr;
 	const struct ethtool_ops *ops;
 	struct net_device *dev;
 	u32 max_rx_in_use = 0;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_CHANNELS_MAX, channels_set_policy,
-			  info->extack);
-	if (ret < 0)
-		return ret;
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_CHANNELS_HEADER],
 					 genl_info_net(info), info->extack,
@@ -215,17 +194,19 @@ int ethnl_set_channels(struct sk_buff *skb, struct genl_info *info)
 	if (netif_is_rxfh_configured(dev) &&
 	    !ethtool_get_max_rxfh_channel(dev, &max_rx_in_use) &&
 	    (channels.combined_count + channels.rx_count) <= max_rx_in_use) {
+		ret = -EINVAL;
 		GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing indirection table settings");
-		return -EINVAL;
+		goto out_ops;
 	}
 
 	/* Disabling channels, query zero-copy AF_XDP sockets */
 	from_channel = channels.combined_count +
 		       min(channels.rx_count, channels.tx_count);
 	for (i = from_channel; i < old_total; i++)
-		if (xdp_get_umem_from_qid(dev, i)) {
+		if (xsk_get_pool_from_qid(dev, i)) {
+			ret = -EINVAL;
 			GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing zerocopy AF_XDP sockets");
-			return -EINVAL;
+			goto out_ops;
 		}
 
 	ret = dev->ethtool_ops->set_channels(dev, &channels);
diff --git a/net/ethtool/coalesce.c b/net/ethtool/coalesce.c
index 6afd99042d67..1d6bc132aa4d 100644
--- a/net/ethtool/coalesce.c
+++ b/net/ethtool/coalesce.c
@@ -51,32 +51,9 @@ __CHECK_SUPPORTED_OFFSET(COALESCE_TX_USECS_HIGH);
 __CHECK_SUPPORTED_OFFSET(COALESCE_TX_MAX_FRAMES_HIGH);
 __CHECK_SUPPORTED_OFFSET(COALESCE_RATE_SAMPLE_INTERVAL);
 
-static const struct nla_policy
-coalesce_get_policy[ETHTOOL_A_COALESCE_MAX + 1] = {
-	[ETHTOOL_A_COALESCE_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_COALESCE_RX_USECS]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_RX_MAX_FRAMES]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_RX_USECS_IRQ]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_IRQ]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_TX_USECS]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_TX_MAX_FRAMES]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_TX_USECS_IRQ]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_IRQ]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_STATS_BLOCK_USECS]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_USE_ADAPTIVE_RX]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_USE_ADAPTIVE_TX]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_PKT_RATE_LOW]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_RX_USECS_LOW]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_LOW]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_TX_USECS_LOW]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_LOW]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_PKT_RATE_HIGH]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_RX_USECS_HIGH]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_RX_MAX_FRAMES_HIGH]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_TX_USECS_HIGH]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_TX_MAX_FRAMES_HIGH]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL] = { .type = NLA_REJECT },
+const struct nla_policy ethnl_coalesce_get_policy[] = {
+	[ETHTOOL_A_COALESCE_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int coalesce_prepare_data(const struct ethnl_req_info *req_base,
@@ -203,10 +180,8 @@ const struct ethnl_request_ops ethnl_coalesce_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_COALESCE_GET,
 	.reply_cmd		= ETHTOOL_MSG_COALESCE_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_COALESCE_HEADER,
-	.max_attr		= ETHTOOL_A_COALESCE_MAX,
 	.req_info_size		= sizeof(struct coalesce_req_info),
 	.reply_data_size	= sizeof(struct coalesce_reply_data),
-	.request_policy		= coalesce_get_policy,
 
 	.prepare_data		= coalesce_prepare_data,
 	.reply_size		= coalesce_reply_size,
@@ -215,10 +190,9 @@ const struct ethnl_request_ops ethnl_coalesce_request_ops = {
 
 /* COALESCE_SET */
 
-static const struct nla_policy
-coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1] = {
-	[ETHTOOL_A_COALESCE_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_COALESCE_HEADER]		= { .type = NLA_NESTED },
+const struct nla_policy ethnl_coalesce_set_policy[] = {
+	[ETHTOOL_A_COALESCE_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_COALESCE_RX_USECS]		= { .type = NLA_U32 },
 	[ETHTOOL_A_COALESCE_RX_MAX_FRAMES]	= { .type = NLA_U32 },
 	[ETHTOOL_A_COALESCE_RX_USECS_IRQ]	= { .type = NLA_U32 },
@@ -245,9 +219,9 @@ coalesce_set_policy[ETHTOOL_A_COALESCE_MAX + 1] = {
 
 int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_COALESCE_MAX + 1];
 	struct ethtool_coalesce coalesce = {};
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	const struct ethtool_ops *ops;
 	struct net_device *dev;
 	u32 supported_params;
@@ -255,11 +229,6 @@ int ethnl_set_coalesce(struct sk_buff *skb, struct genl_info *info)
 	int ret;
 	u16 a;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_COALESCE_MAX, coalesce_set_policy,
-			  info->extack);
-	if (ret < 0)
-		return ret;
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_COALESCE_HEADER],
 					 genl_info_net(info), info->extack,
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index ed19573fccd7..24036e3055a1 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -192,6 +192,8 @@ const char link_mode_names[][ETH_GSTRING_LEN] = {
 	__DEFINE_LINK_MODE_NAME(400000, LR4_ER4_FR4, Full),
 	__DEFINE_LINK_MODE_NAME(400000, DR4, Full),
 	__DEFINE_LINK_MODE_NAME(400000, CR4, Full),
+	__DEFINE_LINK_MODE_NAME(100, FX, Half),
+	__DEFINE_LINK_MODE_NAME(100, FX, Full),
 };
 static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 
diff --git a/net/ethtool/debug.c b/net/ethtool/debug.c
index 1bd026a29f3f..f99912d7957e 100644
--- a/net/ethtool/debug.c
+++ b/net/ethtool/debug.c
@@ -16,11 +16,9 @@ struct debug_reply_data {
 #define DEBUG_REPDATA(__reply_base) \
 	container_of(__reply_base, struct debug_reply_data, base)
 
-static const struct nla_policy
-debug_get_policy[ETHTOOL_A_DEBUG_MAX + 1] = {
-	[ETHTOOL_A_DEBUG_UNSPEC]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_DEBUG_HEADER]	= { .type = NLA_NESTED },
-	[ETHTOOL_A_DEBUG_MSGMASK]	= { .type = NLA_REJECT },
+const struct nla_policy ethnl_debug_get_policy[] = {
+	[ETHTOOL_A_DEBUG_HEADER]	=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int debug_prepare_data(const struct ethnl_req_info *req_base,
@@ -69,10 +67,8 @@ const struct ethnl_request_ops ethnl_debug_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_DEBUG_GET,
 	.reply_cmd		= ETHTOOL_MSG_DEBUG_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_DEBUG_HEADER,
-	.max_attr		= ETHTOOL_A_DEBUG_MAX,
 	.req_info_size		= sizeof(struct debug_req_info),
 	.reply_data_size	= sizeof(struct debug_reply_data),
-	.request_policy		= debug_get_policy,
 
 	.prepare_data		= debug_prepare_data,
 	.reply_size		= debug_reply_size,
@@ -81,27 +77,21 @@ const struct ethnl_request_ops ethnl_debug_request_ops = {
 
 /* DEBUG_SET */
 
-static const struct nla_policy
-debug_set_policy[ETHTOOL_A_DEBUG_MAX + 1] = {
-	[ETHTOOL_A_DEBUG_UNSPEC]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_DEBUG_HEADER]	= { .type = NLA_NESTED },
+const struct nla_policy ethnl_debug_set_policy[] = {
+	[ETHTOOL_A_DEBUG_HEADER]	=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_DEBUG_MSGMASK]	= { .type = NLA_NESTED },
 };
 
 int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_DEBUG_MAX + 1];
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	struct net_device *dev;
 	bool mod = false;
 	u32 msg_mask;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_DEBUG_MAX, debug_set_policy,
-			  info->extack);
-	if (ret < 0)
-		return ret;
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_DEBUG_HEADER],
 					 genl_info_net(info), info->extack,
diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c
index 94aa19cff22f..901b7de941ab 100644
--- a/net/ethtool/eee.c
+++ b/net/ethtool/eee.c
@@ -19,16 +19,9 @@ struct eee_reply_data {
 #define EEE_REPDATA(__reply_base) \
 	container_of(__reply_base, struct eee_reply_data, base)
 
-static const struct nla_policy
-eee_get_policy[ETHTOOL_A_EEE_MAX + 1] = {
-	[ETHTOOL_A_EEE_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_EEE_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_EEE_MODES_OURS]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_EEE_MODES_PEER]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_EEE_ACTIVE]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_EEE_ENABLED]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_EEE_TX_LPI_ENABLED]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_EEE_TX_LPI_TIMER]	= { .type = NLA_REJECT },
+const struct nla_policy ethnl_eee_get_policy[] = {
+	[ETHTOOL_A_EEE_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int eee_prepare_data(const struct ethnl_req_info *req_base,
@@ -119,10 +112,8 @@ const struct ethnl_request_ops ethnl_eee_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_EEE_GET,
 	.reply_cmd		= ETHTOOL_MSG_EEE_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_EEE_HEADER,
-	.max_attr		= ETHTOOL_A_EEE_MAX,
 	.req_info_size		= sizeof(struct eee_req_info),
 	.reply_data_size	= sizeof(struct eee_reply_data),
-	.request_policy		= eee_get_policy,
 
 	.prepare_data		= eee_prepare_data,
 	.reply_size		= eee_reply_size,
@@ -131,13 +122,10 @@ const struct ethnl_request_ops ethnl_eee_request_ops = {
 
 /* EEE_SET */
 
-static const struct nla_policy
-eee_set_policy[ETHTOOL_A_EEE_MAX + 1] = {
-	[ETHTOOL_A_EEE_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_EEE_HEADER]		= { .type = NLA_NESTED },
+const struct nla_policy ethnl_eee_set_policy[] = {
+	[ETHTOOL_A_EEE_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_EEE_MODES_OURS]	= { .type = NLA_NESTED },
-	[ETHTOOL_A_EEE_MODES_PEER]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_EEE_ACTIVE]		= { .type = NLA_REJECT },
 	[ETHTOOL_A_EEE_ENABLED]		= { .type = NLA_U8 },
 	[ETHTOOL_A_EEE_TX_LPI_ENABLED]	= { .type = NLA_U8 },
 	[ETHTOOL_A_EEE_TX_LPI_TIMER]	= { .type = NLA_U32 },
@@ -145,18 +133,14 @@ eee_set_policy[ETHTOOL_A_EEE_MAX + 1] = {
 
 int ethnl_set_eee(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_EEE_MAX + 1];
-	struct ethtool_eee eee = {};
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	const struct ethtool_ops *ops;
+	struct ethtool_eee eee = {};
 	struct net_device *dev;
 	bool mod = false;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_EEE_MAX,
-			  eee_set_policy, info->extack);
-	if (ret < 0)
-		return ret;
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_EEE_HEADER],
 					 genl_info_net(info), info->extack,
diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index 495635f152ba..1c9f4df273bd 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -20,14 +20,9 @@ struct features_reply_data {
 #define FEATURES_REPDATA(__reply_base) \
 	container_of(__reply_base, struct features_reply_data, base)
 
-static const struct nla_policy
-features_get_policy[ETHTOOL_A_FEATURES_MAX + 1] = {
-	[ETHTOOL_A_FEATURES_UNSPEC]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_FEATURES_HEADER]	= { .type = NLA_NESTED },
-	[ETHTOOL_A_FEATURES_HW]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_FEATURES_WANTED]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_FEATURES_ACTIVE]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_FEATURES_NOCHANGE]	= { .type = NLA_REJECT },
+const struct nla_policy ethnl_features_get_policy[] = {
+	[ETHTOOL_A_FEATURES_HEADER]	=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static void ethnl_features_to_bitmap32(u32 *dest, netdev_features_t src)
@@ -120,10 +115,8 @@ const struct ethnl_request_ops ethnl_features_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_FEATURES_GET,
 	.reply_cmd		= ETHTOOL_MSG_FEATURES_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_FEATURES_HEADER,
-	.max_attr		= ETHTOOL_A_FEATURES_MAX,
 	.req_info_size		= sizeof(struct features_req_info),
 	.reply_data_size	= sizeof(struct features_reply_data),
-	.request_policy		= features_get_policy,
 
 	.prepare_data		= features_prepare_data,
 	.reply_size		= features_reply_size,
@@ -132,14 +125,10 @@ const struct ethnl_request_ops ethnl_features_request_ops = {
 
 /* FEATURES_SET */
 
-static const struct nla_policy
-features_set_policy[ETHTOOL_A_FEATURES_MAX + 1] = {
-	[ETHTOOL_A_FEATURES_UNSPEC]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_FEATURES_HEADER]	= { .type = NLA_NESTED },
-	[ETHTOOL_A_FEATURES_HW]		= { .type = NLA_REJECT },
+const struct nla_policy ethnl_features_set_policy[] = {
+	[ETHTOOL_A_FEATURES_HEADER]	=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_FEATURES_WANTED]	= { .type = NLA_NESTED },
-	[ETHTOOL_A_FEATURES_ACTIVE]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_FEATURES_NOCHANGE]	= { .type = NLA_REJECT },
 };
 
 static void ethnl_features_to_bitmap(unsigned long *dest, netdev_features_t val)
@@ -229,17 +218,12 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	DECLARE_BITMAP(new_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(req_wanted, NETDEV_FEATURE_COUNT);
 	DECLARE_BITMAP(req_mask, NETDEV_FEATURE_COUNT);
-	struct nlattr *tb[ETHTOOL_A_FEATURES_MAX + 1];
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	struct net_device *dev;
 	bool mod;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_FEATURES_MAX, features_set_policy,
-			  info->extack);
-	if (ret < 0)
-		return ret;
 	if (!tb[ETHTOOL_A_FEATURES_WANTED])
 		return -EINVAL;
 	ret = ethnl_parse_header_dev_get(&req_info,
@@ -296,7 +280,7 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 					  active_diff_mask, compact);
 	}
 	if (mod)
-		ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL);
+		netdev_features_change(dev);
 
 out_rtnl:
 	rtnl_unlock();
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 441794e0034f..771688e1b0da 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1706,7 +1706,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
 		min(channels.rx_count, channels.tx_count);
 	to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count);
 	for (i = from_channel; i < to_channel; i++)
-		if (xdp_get_umem_from_qid(dev, i))
+		if (xsk_get_pool_from_qid(dev, i))
 			return -EINVAL;
 
 	ret = dev->ethtool_ops->set_channels(dev, &channels);
@@ -1861,23 +1861,18 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
 			id.data ? (id.data * HZ) : MAX_SCHEDULE_TIMEOUT);
 	} else {
 		/* Driver expects to be called at twice the frequency in rc */
-		int n = rc * 2, i, interval = HZ / n;
+		int n = rc * 2, interval = HZ / n;
+		u64 count = n * id.data, i = 0;
 
-		/* Count down seconds */
 		do {
-			/* Count down iterations per second */
-			i = n;
-			do {
-				rtnl_lock();
-				rc = ops->set_phys_id(dev,
-				    (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON);
-				rtnl_unlock();
-				if (rc)
-					break;
-				schedule_timeout_interruptible(interval);
-			} while (!signal_pending(current) && --i != 0);
-		} while (!signal_pending(current) &&
-			 (id.data == 0 || --id.data != 0));
+			rtnl_lock();
+			rc = ops->set_phys_id(dev,
+				    (i++ & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON);
+			rtnl_unlock();
+			if (rc)
+				break;
+			schedule_timeout_interruptible(interval);
+		} while (!signal_pending(current) && (!id.data || i < count));
 	}
 
 	rtnl_lock();
@@ -2438,7 +2433,7 @@ static int noinline_for_stack ethtool_set_per_queue(struct net_device *dev,
 		return ethtool_set_per_queue_coalesce(dev, useraddr, &per_queue_opt);
 	default:
 		return -EOPNOTSUPP;
-	};
+	}
 }
 
 static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna)
@@ -2464,14 +2459,15 @@ static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna)
 
 static int get_phy_tunable(struct net_device *dev, void __user *useraddr)
 {
-	int ret;
-	struct ethtool_tunable tuna;
 	struct phy_device *phydev = dev->phydev;
+	struct ethtool_tunable tuna;
+	bool phy_drv_tunable;
 	void *data;
+	int ret;
 
-	if (!(phydev && phydev->drv && phydev->drv->get_tunable))
+	phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable;
+	if (!phy_drv_tunable && !dev->ethtool_ops->get_phy_tunable)
 		return -EOPNOTSUPP;
-
 	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
 		return -EFAULT;
 	ret = ethtool_phy_tunable_valid(&tuna);
@@ -2480,9 +2476,13 @@ static int get_phy_tunable(struct net_device *dev, void __user *useraddr)
 	data = kmalloc(tuna.len, GFP_USER);
 	if (!data)
 		return -ENOMEM;
-	mutex_lock(&phydev->lock);
-	ret = phydev->drv->get_tunable(phydev, &tuna, data);
-	mutex_unlock(&phydev->lock);
+	if (phy_drv_tunable) {
+		mutex_lock(&phydev->lock);
+		ret = phydev->drv->get_tunable(phydev, &tuna, data);
+		mutex_unlock(&phydev->lock);
+	} else {
+		ret = dev->ethtool_ops->get_phy_tunable(dev, &tuna, data);
+	}
 	if (ret)
 		goto out;
 	useraddr += sizeof(tuna);
@@ -2498,12 +2498,14 @@ out:
 
 static int set_phy_tunable(struct net_device *dev, void __user *useraddr)
 {
-	int ret;
-	struct ethtool_tunable tuna;
 	struct phy_device *phydev = dev->phydev;
+	struct ethtool_tunable tuna;
+	bool phy_drv_tunable;
 	void *data;
+	int ret;
 
-	if (!(phydev && phydev->drv && phydev->drv->set_tunable))
+	phy_drv_tunable = phydev && phydev->drv && phydev->drv->get_tunable;
+	if (!phy_drv_tunable && !dev->ethtool_ops->set_phy_tunable)
 		return -EOPNOTSUPP;
 	if (copy_from_user(&tuna, useraddr, sizeof(tuna)))
 		return -EFAULT;
@@ -2514,9 +2516,13 @@ static int set_phy_tunable(struct net_device *dev, void __user *useraddr)
 	data = memdup_user(useraddr, tuna.len);
 	if (IS_ERR(data))
 		return PTR_ERR(data);
-	mutex_lock(&phydev->lock);
-	ret = phydev->drv->set_tunable(phydev, &tuna, data);
-	mutex_unlock(&phydev->lock);
+	if (phy_drv_tunable) {
+		mutex_lock(&phydev->lock);
+		ret = phydev->drv->set_tunable(phydev, &tuna, data);
+		mutex_unlock(&phydev->lock);
+	} else {
+		ret = dev->ethtool_ops->set_phy_tunable(dev, &tuna, data);
+	}
 
 	kfree(data);
 	return ret;
@@ -3025,13 +3031,14 @@ ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input)
 	case TCP_V4_FLOW:
 	case TCP_V6_FLOW:
 		match->key.basic.ip_proto = IPPROTO_TCP;
+		match->mask.basic.ip_proto = 0xff;
 		break;
 	case UDP_V4_FLOW:
 	case UDP_V6_FLOW:
 		match->key.basic.ip_proto = IPPROTO_UDP;
+		match->mask.basic.ip_proto = 0xff;
 		break;
 	}
-	match->mask.basic.ip_proto = 0xff;
 
 	match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC);
 	match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] =
diff --git a/net/ethtool/linkinfo.c b/net/ethtool/linkinfo.c
index 5eaf173eaaca..b91839870efc 100644
--- a/net/ethtool/linkinfo.c
+++ b/net/ethtool/linkinfo.c
@@ -16,15 +16,9 @@ struct linkinfo_reply_data {
 #define LINKINFO_REPDATA(__reply_base) \
 	container_of(__reply_base, struct linkinfo_reply_data, base)
 
-static const struct nla_policy
-linkinfo_get_policy[ETHTOOL_A_LINKINFO_MAX + 1] = {
-	[ETHTOOL_A_LINKINFO_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKINFO_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_LINKINFO_PORT]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKINFO_PHYADDR]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKINFO_TP_MDIX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKINFO_TRANSCEIVER]	= { .type = NLA_REJECT },
+const struct nla_policy ethnl_linkinfo_get_policy[] = {
+	[ETHTOOL_A_LINKINFO_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int linkinfo_prepare_data(const struct ethnl_req_info *req_base,
@@ -83,10 +77,8 @@ const struct ethnl_request_ops ethnl_linkinfo_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_LINKINFO_GET,
 	.reply_cmd		= ETHTOOL_MSG_LINKINFO_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_LINKINFO_HEADER,
-	.max_attr		= ETHTOOL_A_LINKINFO_MAX,
 	.req_info_size		= sizeof(struct linkinfo_req_info),
 	.reply_data_size	= sizeof(struct linkinfo_reply_data),
-	.request_policy		= linkinfo_get_policy,
 
 	.prepare_data		= linkinfo_prepare_data,
 	.reply_size		= linkinfo_reply_size,
@@ -95,32 +87,24 @@ const struct ethnl_request_ops ethnl_linkinfo_request_ops = {
 
 /* LINKINFO_SET */
 
-static const struct nla_policy
-linkinfo_set_policy[ETHTOOL_A_LINKINFO_MAX + 1] = {
-	[ETHTOOL_A_LINKINFO_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKINFO_HEADER]		= { .type = NLA_NESTED },
+const struct nla_policy ethnl_linkinfo_set_policy[] = {
+	[ETHTOOL_A_LINKINFO_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_LINKINFO_PORT]		= { .type = NLA_U8 },
 	[ETHTOOL_A_LINKINFO_PHYADDR]		= { .type = NLA_U8 },
-	[ETHTOOL_A_LINKINFO_TP_MDIX]		= { .type = NLA_REJECT },
 	[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL]	= { .type = NLA_U8 },
-	[ETHTOOL_A_LINKINFO_TRANSCEIVER]	= { .type = NLA_REJECT },
 };
 
 int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_LINKINFO_MAX + 1];
 	struct ethtool_link_ksettings ksettings = {};
 	struct ethtool_link_settings *lsettings;
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	struct net_device *dev;
 	bool mod = false;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_LINKINFO_MAX, linkinfo_set_policy,
-			  info->extack);
-	if (ret < 0)
-		return ret;
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_LINKINFO_HEADER],
 					 genl_info_net(info), info->extack,
diff --git a/net/ethtool/linkmodes.c b/net/ethtool/linkmodes.c
index 7044a2853886..c5bcb9abc8b9 100644
--- a/net/ethtool/linkmodes.c
+++ b/net/ethtool/linkmodes.c
@@ -18,17 +18,9 @@ struct linkmodes_reply_data {
 #define LINKMODES_REPDATA(__reply_base) \
 	container_of(__reply_base, struct linkmodes_reply_data, base)
 
-static const struct nla_policy
-linkmodes_get_policy[ETHTOOL_A_LINKMODES_MAX + 1] = {
-	[ETHTOOL_A_LINKMODES_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKMODES_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_LINKMODES_AUTONEG]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKMODES_OURS]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKMODES_PEER]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKMODES_SPEED]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKMODES_DUPLEX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE]	= { .type = NLA_REJECT },
+const struct nla_policy ethnl_linkmodes_get_policy[] = {
+	[ETHTOOL_A_LINKMODES_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int linkmodes_prepare_data(const struct ethnl_req_info *req_base,
@@ -148,10 +140,8 @@ const struct ethnl_request_ops ethnl_linkmodes_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_LINKMODES_GET,
 	.reply_cmd		= ETHTOOL_MSG_LINKMODES_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_LINKMODES_HEADER,
-	.max_attr		= ETHTOOL_A_LINKMODES_MAX,
 	.req_info_size		= sizeof(struct linkmodes_req_info),
 	.reply_data_size	= sizeof(struct linkmodes_reply_data),
-	.request_policy		= linkmodes_get_policy,
 
 	.prepare_data		= linkmodes_prepare_data,
 	.reply_size		= linkmodes_reply_size,
@@ -272,19 +262,18 @@ static const struct link_mode_info link_mode_params[] = {
 	__DEFINE_LINK_MODE_PARAMS(400000, LR4_ER4_FR4, Full),
 	__DEFINE_LINK_MODE_PARAMS(400000, DR4, Full),
 	__DEFINE_LINK_MODE_PARAMS(400000, CR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(100, FX, Half),
+	__DEFINE_LINK_MODE_PARAMS(100, FX, Full),
 };
 
-static const struct nla_policy
-linkmodes_set_policy[ETHTOOL_A_LINKMODES_MAX + 1] = {
-	[ETHTOOL_A_LINKMODES_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKMODES_HEADER]		= { .type = NLA_NESTED },
+const struct nla_policy ethnl_linkmodes_set_policy[] = {
+	[ETHTOOL_A_LINKMODES_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_LINKMODES_AUTONEG]		= { .type = NLA_U8 },
 	[ETHTOOL_A_LINKMODES_OURS]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_LINKMODES_PEER]		= { .type = NLA_REJECT },
 	[ETHTOOL_A_LINKMODES_SPEED]		= { .type = NLA_U32 },
 	[ETHTOOL_A_LINKMODES_DUPLEX]		= { .type = NLA_U8 },
 	[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG]	= { .type = NLA_U8 },
-	[ETHTOOL_A_LINKMODES_MASTER_SLAVE_STATE]	= { .type = NLA_REJECT },
 };
 
 /* Set advertised link modes to all supported modes matching requested speed
@@ -390,18 +379,13 @@ static int ethnl_update_linkmodes(struct genl_info *info, struct nlattr **tb,
 
 int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_LINKMODES_MAX + 1];
 	struct ethtool_link_ksettings ksettings = {};
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	struct net_device *dev;
 	bool mod = false;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_LINKMODES_MAX, linkmodes_set_policy,
-			  info->extack);
-	if (ret < 0)
-		return ret;
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_LINKMODES_HEADER],
 					 genl_info_net(info), info->extack,
diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c
index 4834091ec24c..fb676f349455 100644
--- a/net/ethtool/linkstate.c
+++ b/net/ethtool/linkstate.c
@@ -20,15 +20,9 @@ struct linkstate_reply_data {
 #define LINKSTATE_REPDATA(__reply_base) \
 	container_of(__reply_base, struct linkstate_reply_data, base)
 
-static const struct nla_policy
-linkstate_get_policy[ETHTOOL_A_LINKSTATE_MAX + 1] = {
-	[ETHTOOL_A_LINKSTATE_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKSTATE_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_LINKSTATE_LINK]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKSTATE_SQI]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKSTATE_SQI_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKSTATE_EXT_STATE]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_LINKSTATE_EXT_SUBSTATE]	= { .type = NLA_REJECT },
+const struct nla_policy ethnl_linkstate_get_policy[] = {
+	[ETHTOOL_A_LINKSTATE_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int linkstate_get_sqi(struct net_device *dev)
@@ -179,10 +173,8 @@ const struct ethnl_request_ops ethnl_linkstate_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_LINKSTATE_GET,
 	.reply_cmd		= ETHTOOL_MSG_LINKSTATE_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_LINKSTATE_HEADER,
-	.max_attr		= ETHTOOL_A_LINKSTATE_MAX,
 	.req_info_size		= sizeof(struct linkstate_req_info),
 	.reply_data_size	= sizeof(struct linkstate_reply_data),
-	.request_policy		= linkstate_get_policy,
 
 	.prepare_data		= linkstate_prepare_data,
 	.reply_size		= linkstate_reply_size,
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 0c3f54baec4e..50d3c8896f91 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -9,12 +9,24 @@ static struct genl_family ethtool_genl_family;
 static bool ethnl_ok __read_mostly;
 static u32 ethnl_bcast_seq;
 
-static const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_MAX + 1] = {
-	[ETHTOOL_A_HEADER_UNSPEC]	= { .type = NLA_REJECT },
+#define ETHTOOL_FLAGS_BASIC (ETHTOOL_FLAG_COMPACT_BITSETS |	\
+			     ETHTOOL_FLAG_OMIT_REPLY)
+#define ETHTOOL_FLAGS_STATS (ETHTOOL_FLAGS_BASIC | ETHTOOL_FLAG_STATS)
+
+const struct nla_policy ethnl_header_policy[] = {
 	[ETHTOOL_A_HEADER_DEV_INDEX]	= { .type = NLA_U32 },
 	[ETHTOOL_A_HEADER_DEV_NAME]	= { .type = NLA_NUL_STRING,
 					    .len = ALTIFNAMSIZ - 1 },
-	[ETHTOOL_A_HEADER_FLAGS]	= { .type = NLA_U32 },
+	[ETHTOOL_A_HEADER_FLAGS]	= NLA_POLICY_MASK(NLA_U32,
+							  ETHTOOL_FLAGS_BASIC),
+};
+
+const struct nla_policy ethnl_header_policy_stats[] = {
+	[ETHTOOL_A_HEADER_DEV_INDEX]	= { .type = NLA_U32 },
+	[ETHTOOL_A_HEADER_DEV_NAME]	= { .type = NLA_NUL_STRING,
+					    .len = ALTIFNAMSIZ - 1 },
+	[ETHTOOL_A_HEADER_FLAGS]	= NLA_POLICY_MASK(NLA_U32,
+							  ETHTOOL_FLAGS_STATS),
 };
 
 /**
@@ -37,7 +49,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 			       const struct nlattr *header, struct net *net,
 			       struct netlink_ext_ack *extack, bool require_dev)
 {
-	struct nlattr *tb[ETHTOOL_A_HEADER_MAX + 1];
+	struct nlattr *tb[ARRAY_SIZE(ethnl_header_policy)];
 	const struct nlattr *devname_attr;
 	struct net_device *dev = NULL;
 	u32 flags = 0;
@@ -47,19 +59,15 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 		NL_SET_ERR_MSG(extack, "request header missing");
 		return -EINVAL;
 	}
-	ret = nla_parse_nested(tb, ETHTOOL_A_HEADER_MAX, header,
-			       ethnl_header_policy, extack);
+	/* No validation here, command policy should have a nested policy set
+	 * for the header, therefore validation should have already been done.
+	 */
+	ret = nla_parse_nested(tb, ARRAY_SIZE(ethnl_header_policy) - 1, header,
+			       NULL, extack);
 	if (ret < 0)
 		return ret;
-	if (tb[ETHTOOL_A_HEADER_FLAGS]) {
+	if (tb[ETHTOOL_A_HEADER_FLAGS])
 		flags = nla_get_u32(tb[ETHTOOL_A_HEADER_FLAGS]);
-		if (flags & ~ETHTOOL_FLAG_ALL) {
-			NL_SET_ERR_MSG_ATTR(extack, tb[ETHTOOL_A_HEADER_FLAGS],
-					    "unrecognized request flags");
-			nl_set_extack_cookie_u32(extack, ETHTOOL_FLAG_ALL);
-			return -EOPNOTSUPP;
-		}
-	}
 
 	devname_attr = tb[ETHTOOL_A_HEADER_DEV_NAME];
 	if (tb[ETHTOOL_A_HEADER_DEV_INDEX]) {
@@ -247,7 +255,7 @@ static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
 /**
  * ethnl_default_parse() - Parse request message
  * @req_info:    pointer to structure to put data into
- * @nlhdr:       pointer to request message header
+ * @tb:		 parsed attributes
  * @net:         request netns
  * @request_ops: struct request_ops for request type
  * @extack:      netlink extack for error reporting
@@ -259,37 +267,24 @@ static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
  * Return: 0 on success or negative error code
  */
 static int ethnl_default_parse(struct ethnl_req_info *req_info,
-			       const struct nlmsghdr *nlhdr, struct net *net,
+			       struct nlattr **tb, struct net *net,
 			       const struct ethnl_request_ops *request_ops,
 			       struct netlink_ext_ack *extack, bool require_dev)
 {
-	struct nlattr **tb;
 	int ret;
 
-	tb = kmalloc_array(request_ops->max_attr + 1, sizeof(tb[0]),
-			   GFP_KERNEL);
-	if (!tb)
-		return -ENOMEM;
-
-	ret = nlmsg_parse(nlhdr, GENL_HDRLEN, tb, request_ops->max_attr,
-			  request_ops->request_policy, extack);
-	if (ret < 0)
-		goto out;
 	ret = ethnl_parse_header_dev_get(req_info, tb[request_ops->hdr_attr],
 					 net, extack, require_dev);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	if (request_ops->parse_request) {
 		ret = request_ops->parse_request(req_info, tb, extack);
 		if (ret < 0)
-			goto out;
+			return ret;
 	}
 
-	ret = 0;
-out:
-	kfree(tb);
-	return ret;
+	return 0;
 }
 
 /**
@@ -334,8 +329,8 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 		return -ENOMEM;
 	}
 
-	ret = ethnl_default_parse(req_info, info->nlhdr, genl_info_net(info), ops,
-				  info->extack, !ops->allow_nodev_do);
+	ret = ethnl_default_parse(req_info, info->attrs, genl_info_net(info),
+				  ops, info->extack, !ops->allow_nodev_do);
 	if (ret < 0)
 		goto err_dev;
 	ethnl_init_reply_data(reply_data, ops, req_info->dev);
@@ -480,6 +475,7 @@ out:
 /* generic ->start() handler for GET requests */
 static int ethnl_default_start(struct netlink_callback *cb)
 {
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
 	struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb);
 	struct ethnl_reply_data *reply_data;
 	const struct ethnl_request_ops *ops;
@@ -502,8 +498,8 @@ static int ethnl_default_start(struct netlink_callback *cb)
 		goto free_req_info;
 	}
 
-	ret = ethnl_default_parse(req_info, cb->nlh, sock_net(cb->skb->sk), ops,
-				  cb->extack, false);
+	ret = ethnl_default_parse(req_info, info->attrs, sock_net(cb->skb->sk),
+				  ops, cb->extack, false);
 	if (req_info->dev) {
 		/* We ignore device specification in dump requests but as the
 		 * same parser as for non-dump (doit) requests is used, it
@@ -696,6 +692,8 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_strset_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_strset_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_LINKINFO_GET,
@@ -703,11 +701,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_linkinfo_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_linkinfo_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_LINKINFO_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_linkinfo,
+		.policy = ethnl_linkinfo_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_linkinfo_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_LINKMODES_GET,
@@ -715,11 +717,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_linkmodes_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_linkmodes_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_LINKMODES_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_linkmodes,
+		.policy = ethnl_linkmodes_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_linkmodes_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_LINKSTATE_GET,
@@ -727,6 +733,8 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_linkstate_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_linkstate_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_DEBUG_GET,
@@ -734,11 +742,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_debug_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_debug_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_DEBUG_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_debug,
+		.policy = ethnl_debug_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_debug_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_WOL_GET,
@@ -747,11 +759,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_wol_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_wol_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_WOL_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_wol,
+		.policy = ethnl_wol_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_wol_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_FEATURES_GET,
@@ -759,11 +775,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_features_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_features_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_FEATURES_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_features,
+		.policy = ethnl_features_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_features_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_PRIVFLAGS_GET,
@@ -771,11 +791,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_privflags_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_privflags_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_PRIVFLAGS_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_privflags,
+		.policy = ethnl_privflags_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_privflags_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_RINGS_GET,
@@ -783,11 +807,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_rings_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_rings_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_RINGS_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_rings,
+		.policy = ethnl_rings_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_rings_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_CHANNELS_GET,
@@ -795,11 +823,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_channels_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_channels_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_CHANNELS_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_channels,
+		.policy = ethnl_channels_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_channels_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_COALESCE_GET,
@@ -807,11 +839,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_coalesce_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_coalesce_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_COALESCE_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_coalesce,
+		.policy = ethnl_coalesce_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_coalesce_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_PAUSE_GET,
@@ -819,11 +855,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_pause_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_pause_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_PAUSE_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_pause,
+		.policy = ethnl_pause_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_pause_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_EEE_GET,
@@ -831,11 +871,15 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_eee_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_eee_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_EEE_SET,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_set_eee,
+		.policy = ethnl_eee_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_eee_set_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_TSINFO_GET,
@@ -843,22 +887,30 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.start	= ethnl_default_start,
 		.dumpit	= ethnl_default_dumpit,
 		.done	= ethnl_default_done,
+		.policy = ethnl_tsinfo_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_tsinfo_get_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_CABLE_TEST_ACT,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_act_cable_test,
+		.policy = ethnl_cable_test_act_policy,
+		.maxattr = ARRAY_SIZE(ethnl_cable_test_act_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_CABLE_TEST_TDR_ACT,
 		.flags	= GENL_UNS_ADMIN_PERM,
 		.doit	= ethnl_act_cable_test_tdr,
+		.policy = ethnl_cable_test_tdr_act_policy,
+		.maxattr = ARRAY_SIZE(ethnl_cable_test_tdr_act_policy) - 1,
 	},
 	{
 		.cmd	= ETHTOOL_MSG_TUNNEL_INFO_GET,
 		.doit	= ethnl_tunnel_info_doit,
 		.start	= ethnl_tunnel_info_start,
 		.dumpit	= ethnl_tunnel_info_dumpit,
+		.policy = ethnl_tunnel_info_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_tunnel_info_get_policy) - 1,
 	},
 };
 
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index e2085005caac..d8efec516d86 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -266,10 +266,8 @@ static inline void ethnl_ops_complete(struct net_device *dev)
  * @request_cmd:      command id for request (GET)
  * @reply_cmd:        command id for reply (GET_REPLY)
  * @hdr_attr:         attribute type for request header
- * @max_attr:         maximum (top level) attribute type
  * @req_info_size:    size of request info
  * @reply_data_size:  size of reply data
- * @request_policy:   netlink policy for message contents
  * @allow_nodev_do:   allow non-dump request with no device identification
  * @parse_request:
  *	Parse request except common header (struct ethnl_req_info). Common
@@ -312,10 +310,8 @@ struct ethnl_request_ops {
 	u8			request_cmd;
 	u8			reply_cmd;
 	u16			hdr_attr;
-	unsigned int		max_attr;
 	unsigned int		req_info_size;
 	unsigned int		reply_data_size;
-	const struct nla_policy *request_policy;
 	bool			allow_nodev_do;
 
 	int (*parse_request)(struct ethnl_req_info *req_info,
@@ -349,6 +345,37 @@ extern const struct ethnl_request_ops ethnl_pause_request_ops;
 extern const struct ethnl_request_ops ethnl_eee_request_ops;
 extern const struct ethnl_request_ops ethnl_tsinfo_request_ops;
 
+extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
+extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
+extern const struct nla_policy ethnl_strset_get_policy[ETHTOOL_A_STRSET_COUNTS_ONLY + 1];
+extern const struct nla_policy ethnl_linkinfo_get_policy[ETHTOOL_A_LINKINFO_HEADER + 1];
+extern const struct nla_policy ethnl_linkinfo_set_policy[ETHTOOL_A_LINKINFO_TP_MDIX_CTRL + 1];
+extern const struct nla_policy ethnl_linkmodes_get_policy[ETHTOOL_A_LINKMODES_HEADER + 1];
+extern const struct nla_policy ethnl_linkmodes_set_policy[ETHTOOL_A_LINKMODES_MASTER_SLAVE_CFG + 1];
+extern const struct nla_policy ethnl_linkstate_get_policy[ETHTOOL_A_LINKSTATE_HEADER + 1];
+extern const struct nla_policy ethnl_debug_get_policy[ETHTOOL_A_DEBUG_HEADER + 1];
+extern const struct nla_policy ethnl_debug_set_policy[ETHTOOL_A_DEBUG_MSGMASK + 1];
+extern const struct nla_policy ethnl_wol_get_policy[ETHTOOL_A_WOL_HEADER + 1];
+extern const struct nla_policy ethnl_wol_set_policy[ETHTOOL_A_WOL_SOPASS + 1];
+extern const struct nla_policy ethnl_features_get_policy[ETHTOOL_A_FEATURES_HEADER + 1];
+extern const struct nla_policy ethnl_features_set_policy[ETHTOOL_A_FEATURES_WANTED + 1];
+extern const struct nla_policy ethnl_privflags_get_policy[ETHTOOL_A_PRIVFLAGS_HEADER + 1];
+extern const struct nla_policy ethnl_privflags_set_policy[ETHTOOL_A_PRIVFLAGS_FLAGS + 1];
+extern const struct nla_policy ethnl_rings_get_policy[ETHTOOL_A_RINGS_HEADER + 1];
+extern const struct nla_policy ethnl_rings_set_policy[ETHTOOL_A_RINGS_TX + 1];
+extern const struct nla_policy ethnl_channels_get_policy[ETHTOOL_A_CHANNELS_HEADER + 1];
+extern const struct nla_policy ethnl_channels_set_policy[ETHTOOL_A_CHANNELS_COMBINED_COUNT + 1];
+extern const struct nla_policy ethnl_coalesce_get_policy[ETHTOOL_A_COALESCE_HEADER + 1];
+extern const struct nla_policy ethnl_coalesce_set_policy[ETHTOOL_A_COALESCE_RATE_SAMPLE_INTERVAL + 1];
+extern const struct nla_policy ethnl_pause_get_policy[ETHTOOL_A_PAUSE_HEADER + 1];
+extern const struct nla_policy ethnl_pause_set_policy[ETHTOOL_A_PAUSE_TX + 1];
+extern const struct nla_policy ethnl_eee_get_policy[ETHTOOL_A_EEE_HEADER + 1];
+extern const struct nla_policy ethnl_eee_set_policy[ETHTOOL_A_EEE_TX_LPI_TIMER + 1];
+extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_HEADER + 1];
+extern const struct nla_policy ethnl_cable_test_act_policy[ETHTOOL_A_CABLE_TEST_HEADER + 1];
+extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG + 1];
+extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1];
+
 int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info);
 int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info);
 int ethnl_set_debug(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c
index 7aea35d1e8a5..09998dc5c185 100644
--- a/net/ethtool/pause.c
+++ b/net/ethtool/pause.c
@@ -10,20 +10,23 @@ struct pause_req_info {
 struct pause_reply_data {
 	struct ethnl_reply_data		base;
 	struct ethtool_pauseparam	pauseparam;
+	struct ethtool_pause_stats	pausestat;
 };
 
 #define PAUSE_REPDATA(__reply_base) \
 	container_of(__reply_base, struct pause_reply_data, base)
 
-static const struct nla_policy
-pause_get_policy[ETHTOOL_A_PAUSE_MAX + 1] = {
-	[ETHTOOL_A_PAUSE_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_PAUSE_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_PAUSE_AUTONEG]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_PAUSE_RX]			= { .type = NLA_REJECT },
-	[ETHTOOL_A_PAUSE_TX]			= { .type = NLA_REJECT },
+const struct nla_policy ethnl_pause_get_policy[] = {
+	[ETHTOOL_A_PAUSE_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy_stats),
 };
 
+static void ethtool_stats_init(u64 *stats, unsigned int n)
+{
+	while (n--)
+		stats[n] = ETHTOOL_STAT_NOT_SET;
+}
+
 static int pause_prepare_data(const struct ethnl_req_info *req_base,
 			      struct ethnl_reply_data *reply_base,
 			      struct genl_info *info)
@@ -34,10 +37,17 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base,
 
 	if (!dev->ethtool_ops->get_pauseparam)
 		return -EOPNOTSUPP;
+
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
 		return ret;
 	dev->ethtool_ops->get_pauseparam(dev, &data->pauseparam);
+	if (req_base->flags & ETHTOOL_FLAG_STATS &&
+	    dev->ethtool_ops->get_pause_stats) {
+		ethtool_stats_init((u64 *)&data->pausestat,
+				   sizeof(data->pausestat) / 8);
+		dev->ethtool_ops->get_pause_stats(dev, &data->pausestat);
+	}
 	ethnl_ops_complete(dev);
 
 	return 0;
@@ -46,9 +56,50 @@ static int pause_prepare_data(const struct ethnl_req_info *req_base,
 static int pause_reply_size(const struct ethnl_req_info *req_base,
 			    const struct ethnl_reply_data *reply_base)
 {
-	return nla_total_size(sizeof(u8)) +	/* _PAUSE_AUTONEG */
+	int n = nla_total_size(sizeof(u8)) +	/* _PAUSE_AUTONEG */
 		nla_total_size(sizeof(u8)) +	/* _PAUSE_RX */
 		nla_total_size(sizeof(u8));	/* _PAUSE_TX */
+
+	if (req_base->flags & ETHTOOL_FLAG_STATS)
+		n += nla_total_size(0) +	/* _PAUSE_STATS */
+			nla_total_size_64bit(sizeof(u64)) *
+				(ETHTOOL_A_PAUSE_STAT_MAX - 2);
+	return n;
+}
+
+static int ethtool_put_stat(struct sk_buff *skb, u64 val, u16 attrtype,
+			    u16 padtype)
+{
+	if (val == ETHTOOL_STAT_NOT_SET)
+		return 0;
+	if (nla_put_u64_64bit(skb, attrtype, val, padtype))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int pause_put_stats(struct sk_buff *skb,
+			   const struct ethtool_pause_stats *pause_stats)
+{
+	const u16 pad = ETHTOOL_A_PAUSE_STAT_PAD;
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, ETHTOOL_A_PAUSE_STATS);
+	if (!nest)
+		return -EMSGSIZE;
+
+	if (ethtool_put_stat(skb, pause_stats->tx_pause_frames,
+			     ETHTOOL_A_PAUSE_STAT_TX_FRAMES, pad) ||
+	    ethtool_put_stat(skb, pause_stats->rx_pause_frames,
+			     ETHTOOL_A_PAUSE_STAT_RX_FRAMES, pad))
+		goto err_cancel;
+
+	nla_nest_end(skb, nest);
+	return 0;
+
+err_cancel:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
 }
 
 static int pause_fill_reply(struct sk_buff *skb,
@@ -63,6 +114,10 @@ static int pause_fill_reply(struct sk_buff *skb,
 	    nla_put_u8(skb, ETHTOOL_A_PAUSE_TX, !!pauseparam->tx_pause))
 		return -EMSGSIZE;
 
+	if (req_base->flags & ETHTOOL_FLAG_STATS &&
+	    pause_put_stats(skb, &data->pausestat))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
@@ -70,10 +125,8 @@ const struct ethnl_request_ops ethnl_pause_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_PAUSE_GET,
 	.reply_cmd		= ETHTOOL_MSG_PAUSE_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_PAUSE_HEADER,
-	.max_attr		= ETHTOOL_A_PAUSE_MAX,
 	.req_info_size		= sizeof(struct pause_req_info),
 	.reply_data_size	= sizeof(struct pause_reply_data),
-	.request_policy		= pause_get_policy,
 
 	.prepare_data		= pause_prepare_data,
 	.reply_size		= pause_reply_size,
@@ -82,10 +135,9 @@ const struct ethnl_request_ops ethnl_pause_request_ops = {
 
 /* PAUSE_SET */
 
-static const struct nla_policy
-pause_set_policy[ETHTOOL_A_PAUSE_MAX + 1] = {
-	[ETHTOOL_A_PAUSE_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_PAUSE_HEADER]		= { .type = NLA_NESTED },
+const struct nla_policy ethnl_pause_set_policy[] = {
+	[ETHTOOL_A_PAUSE_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_PAUSE_AUTONEG]		= { .type = NLA_U8 },
 	[ETHTOOL_A_PAUSE_RX]			= { .type = NLA_U8 },
 	[ETHTOOL_A_PAUSE_TX]			= { .type = NLA_U8 },
@@ -93,18 +145,14 @@ pause_set_policy[ETHTOOL_A_PAUSE_MAX + 1] = {
 
 int ethnl_set_pause(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_PAUSE_MAX + 1];
 	struct ethtool_pauseparam params = {};
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	const struct ethtool_ops *ops;
 	struct net_device *dev;
 	bool mod = false;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_PAUSE_MAX,
-			  pause_set_policy, info->extack);
-	if (ret < 0)
-		return ret;
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_PAUSE_HEADER],
 					 genl_info_net(info), info->extack,
diff --git a/net/ethtool/privflags.c b/net/ethtool/privflags.c
index 77447dceb109..fc9f3be23a19 100644
--- a/net/ethtool/privflags.c
+++ b/net/ethtool/privflags.c
@@ -18,11 +18,9 @@ struct privflags_reply_data {
 #define PRIVFLAGS_REPDATA(__reply_base) \
 	container_of(__reply_base, struct privflags_reply_data, base)
 
-static const struct nla_policy
-privflags_get_policy[ETHTOOL_A_PRIVFLAGS_MAX + 1] = {
-	[ETHTOOL_A_PRIVFLAGS_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_PRIVFLAGS_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_PRIVFLAGS_FLAGS]		= { .type = NLA_REJECT },
+const struct nla_policy ethnl_privflags_get_policy[] = {
+	[ETHTOOL_A_PRIVFLAGS_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int ethnl_get_priv_flags_info(struct net_device *dev,
@@ -124,10 +122,8 @@ const struct ethnl_request_ops ethnl_privflags_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_PRIVFLAGS_GET,
 	.reply_cmd		= ETHTOOL_MSG_PRIVFLAGS_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_PRIVFLAGS_HEADER,
-	.max_attr		= ETHTOOL_A_PRIVFLAGS_MAX,
 	.req_info_size		= sizeof(struct privflags_req_info),
 	.reply_data_size	= sizeof(struct privflags_reply_data),
-	.request_policy		= privflags_get_policy,
 
 	.prepare_data		= privflags_prepare_data,
 	.reply_size		= privflags_reply_size,
@@ -137,18 +133,17 @@ const struct ethnl_request_ops ethnl_privflags_request_ops = {
 
 /* PRIVFLAGS_SET */
 
-static const struct nla_policy
-privflags_set_policy[ETHTOOL_A_PRIVFLAGS_MAX + 1] = {
-	[ETHTOOL_A_PRIVFLAGS_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_PRIVFLAGS_HEADER]		= { .type = NLA_NESTED },
+const struct nla_policy ethnl_privflags_set_policy[] = {
+	[ETHTOOL_A_PRIVFLAGS_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_PRIVFLAGS_FLAGS]		= { .type = NLA_NESTED },
 };
 
 int ethnl_set_privflags(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_PRIVFLAGS_MAX + 1];
 	const char (*names)[ETH_GSTRING_LEN] = NULL;
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	const struct ethtool_ops *ops;
 	struct net_device *dev;
 	unsigned int nflags;
@@ -157,11 +152,6 @@ int ethnl_set_privflags(struct sk_buff *skb, struct genl_info *info)
 	u32 flags;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_PRIVFLAGS_MAX, privflags_set_policy,
-			  info->extack);
-	if (ret < 0)
-		return ret;
 	if (!tb[ETHTOOL_A_PRIVFLAGS_FLAGS])
 		return -EINVAL;
 	ret = ethnl_bitset_is_compact(tb[ETHTOOL_A_PRIVFLAGS_FLAGS], &compact);
diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c
index 5422526f4eef..4e097812a967 100644
--- a/net/ethtool/rings.c
+++ b/net/ethtool/rings.c
@@ -15,18 +15,9 @@ struct rings_reply_data {
 #define RINGS_REPDATA(__reply_base) \
 	container_of(__reply_base, struct rings_reply_data, base)
 
-static const struct nla_policy
-rings_get_policy[ETHTOOL_A_RINGS_MAX + 1] = {
-	[ETHTOOL_A_RINGS_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_RINGS_RX_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_RX_MINI_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_RX_JUMBO_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_TX_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_RX]			= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_RX_MINI]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_RX_JUMBO]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_TX]			= { .type = NLA_REJECT },
+const struct nla_policy ethnl_rings_get_policy[] = {
+	[ETHTOOL_A_RINGS_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int rings_prepare_data(const struct ethnl_req_info *req_base,
@@ -97,10 +88,8 @@ const struct ethnl_request_ops ethnl_rings_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_RINGS_GET,
 	.reply_cmd		= ETHTOOL_MSG_RINGS_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_RINGS_HEADER,
-	.max_attr		= ETHTOOL_A_RINGS_MAX,
 	.req_info_size		= sizeof(struct rings_req_info),
 	.reply_data_size	= sizeof(struct rings_reply_data),
-	.request_policy		= rings_get_policy,
 
 	.prepare_data		= rings_prepare_data,
 	.reply_size		= rings_reply_size,
@@ -109,14 +98,9 @@ const struct ethnl_request_ops ethnl_rings_request_ops = {
 
 /* RINGS_SET */
 
-static const struct nla_policy
-rings_set_policy[ETHTOOL_A_RINGS_MAX + 1] = {
-	[ETHTOOL_A_RINGS_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_RINGS_RX_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_RX_MINI_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_RX_JUMBO_MAX]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_RINGS_TX_MAX]		= { .type = NLA_REJECT },
+const struct nla_policy ethnl_rings_set_policy[] = {
+	[ETHTOOL_A_RINGS_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_RINGS_RX]			= { .type = NLA_U32 },
 	[ETHTOOL_A_RINGS_RX_MINI]		= { .type = NLA_U32 },
 	[ETHTOOL_A_RINGS_RX_JUMBO]		= { .type = NLA_U32 },
@@ -125,20 +109,15 @@ rings_set_policy[ETHTOOL_A_RINGS_MAX + 1] = {
 
 int ethnl_set_rings(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *tb[ETHTOOL_A_RINGS_MAX + 1];
 	struct ethtool_ringparam ringparam = {};
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	const struct nlattr *err_attr;
 	const struct ethtool_ops *ops;
 	struct net_device *dev;
 	bool mod = false;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb,
-			  ETHTOOL_A_RINGS_MAX, rings_set_policy,
-			  info->extack);
-	if (ret < 0)
-		return ret;
 	ret = ethnl_parse_header_dev_get(&req_info,
 					 tb[ETHTOOL_A_RINGS_HEADER],
 					 genl_info_net(info), info->extack,
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 82707b662fe4..c3a5489964cd 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -99,18 +99,15 @@ struct strset_reply_data {
 #define STRSET_REPDATA(__reply_base) \
 	container_of(__reply_base, struct strset_reply_data, base)
 
-static const struct nla_policy strset_get_policy[ETHTOOL_A_STRSET_MAX + 1] = {
-	[ETHTOOL_A_STRSET_UNSPEC]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_STRSET_HEADER]	= { .type = NLA_NESTED },
+const struct nla_policy ethnl_strset_get_policy[] = {
+	[ETHTOOL_A_STRSET_HEADER]	=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_STRSET_STRINGSETS]	= { .type = NLA_NESTED },
+	[ETHTOOL_A_STRSET_COUNTS_ONLY]	= { .type = NLA_FLAG },
 };
 
-static const struct nla_policy
-get_stringset_policy[ETHTOOL_A_STRINGSET_MAX + 1] = {
-	[ETHTOOL_A_STRINGSET_UNSPEC]	= { .type = NLA_REJECT },
+static const struct nla_policy get_stringset_policy[] = {
 	[ETHTOOL_A_STRINGSET_ID]	= { .type = NLA_U32 },
-	[ETHTOOL_A_STRINGSET_COUNT]	= { .type = NLA_REJECT },
-	[ETHTOOL_A_STRINGSET_STRINGS]	= { .type = NLA_REJECT },
 };
 
 /**
@@ -138,10 +135,10 @@ static bool strset_include(const struct strset_req_info *info,
 static int strset_get_id(const struct nlattr *nest, u32 *val,
 			 struct netlink_ext_ack *extack)
 {
-	struct nlattr *tb[ETHTOOL_A_STRINGSET_MAX + 1];
+	struct nlattr *tb[ARRAY_SIZE(get_stringset_policy)];
 	int ret;
 
-	ret = nla_parse_nested(tb, ETHTOOL_A_STRINGSET_MAX, nest,
+	ret = nla_parse_nested(tb, ARRAY_SIZE(get_stringset_policy) - 1, nest,
 			       get_stringset_policy, extack);
 	if (ret < 0)
 		return ret;
@@ -152,9 +149,7 @@ static int strset_get_id(const struct nlattr *nest, u32 *val,
 	return 0;
 }
 
-static const struct nla_policy
-strset_stringsets_policy[ETHTOOL_A_STRINGSETS_MAX + 1] = {
-	[ETHTOOL_A_STRINGSETS_UNSPEC]		= { .type = NLA_REJECT },
+static const struct nla_policy strset_stringsets_policy[] = {
 	[ETHTOOL_A_STRINGSETS_STRINGSET]	= { .type = NLA_NESTED },
 };
 
@@ -169,7 +164,8 @@ static int strset_parse_request(struct ethnl_req_info *req_base,
 
 	if (!nest)
 		return 0;
-	ret = nla_validate_nested(nest, ETHTOOL_A_STRINGSETS_MAX,
+	ret = nla_validate_nested(nest,
+				  ARRAY_SIZE(strset_stringsets_policy) - 1,
 				  strset_stringsets_policy, extack);
 	if (ret < 0)
 		return ret;
@@ -186,7 +182,7 @@ static int strset_parse_request(struct ethnl_req_info *req_base,
 		ret = strset_get_id(attr, &id, extack);
 		if (ret < 0)
 			return ret;
-		if (ret >= ETH_SS_COUNT) {
+		if (id >= ETH_SS_COUNT) {
 			NL_SET_ERR_MSG_ATTR(extack, attr,
 					    "unknown string set id");
 			return -EOPNOTSUPP;
@@ -445,10 +441,8 @@ const struct ethnl_request_ops ethnl_strset_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_STRSET_GET,
 	.reply_cmd		= ETHTOOL_MSG_STRSET_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_STRSET_HEADER,
-	.max_attr		= ETHTOOL_A_STRSET_MAX,
 	.req_info_size		= sizeof(struct strset_req_info),
 	.reply_data_size	= sizeof(struct strset_reply_data),
-	.request_policy		= strset_get_policy,
 	.allow_nodev_do		= true,
 
 	.parse_request		= strset_parse_request,
diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c
index 7cb5b512b77c..63b5814bd460 100644
--- a/net/ethtool/tsinfo.c
+++ b/net/ethtool/tsinfo.c
@@ -18,14 +18,9 @@ struct tsinfo_reply_data {
 #define TSINFO_REPDATA(__reply_base) \
 	container_of(__reply_base, struct tsinfo_reply_data, base)
 
-static const struct nla_policy
-tsinfo_get_policy[ETHTOOL_A_TSINFO_MAX + 1] = {
-	[ETHTOOL_A_TSINFO_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_TSINFO_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_TSINFO_TIMESTAMPING]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_TSINFO_TX_TYPES]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_TSINFO_RX_FILTERS]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_TSINFO_PHC_INDEX]		= { .type = NLA_REJECT },
+const struct nla_policy ethnl_tsinfo_get_policy[] = {
+	[ETHTOOL_A_TSINFO_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int tsinfo_prepare_data(const struct ethnl_req_info *req_base,
@@ -132,10 +127,8 @@ const struct ethnl_request_ops ethnl_tsinfo_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_TSINFO_GET,
 	.reply_cmd		= ETHTOOL_MSG_TSINFO_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_TSINFO_HEADER,
-	.max_attr		= ETHTOOL_A_TSINFO_MAX,
 	.req_info_size		= sizeof(struct tsinfo_req_info),
 	.reply_data_size	= sizeof(struct tsinfo_reply_data),
-	.request_policy		= tsinfo_get_policy,
 
 	.prepare_data		= tsinfo_prepare_data,
 	.reply_size		= tsinfo_reply_size,
diff --git a/net/ethtool/tunnels.c b/net/ethtool/tunnels.c
index d93bf2da0f34..e7f2ee0d2471 100644
--- a/net/ethtool/tunnels.c
+++ b/net/ethtool/tunnels.c
@@ -8,10 +8,9 @@
 #include "common.h"
 #include "netlink.h"
 
-static const struct nla_policy
-ethtool_tunnel_info_policy[ETHTOOL_A_TUNNEL_INFO_MAX + 1] = {
-	[ETHTOOL_A_TUNNEL_INFO_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_TUNNEL_INFO_HEADER]		= { .type = NLA_NESTED },
+const struct nla_policy ethnl_tunnel_info_get_policy[] = {
+	[ETHTOOL_A_TUNNEL_INFO_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static_assert(ETHTOOL_UDP_TUNNEL_TYPE_VXLAN == ilog2(UDP_TUNNEL_TYPE_VXLAN));
@@ -161,35 +160,19 @@ err_cancel_ports:
 	return -EMSGSIZE;
 }
 
-static int
-ethnl_tunnel_info_req_parse(struct ethnl_req_info *req_info,
-			    const struct nlmsghdr *nlhdr, struct net *net,
-			    struct netlink_ext_ack *extack, bool require_dev)
-{
-	struct nlattr *tb[ETHTOOL_A_TUNNEL_INFO_MAX + 1];
-	int ret;
-
-	ret = nlmsg_parse(nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_TUNNEL_INFO_MAX,
-			  ethtool_tunnel_info_policy, extack);
-	if (ret < 0)
-		return ret;
-
-	return ethnl_parse_header_dev_get(req_info,
-					  tb[ETHTOOL_A_TUNNEL_INFO_HEADER],
-					  net, extack, require_dev);
-}
-
 int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	struct sk_buff *rskb;
 	void *reply_payload;
 	int reply_len;
 	int ret;
 
-	ret = ethnl_tunnel_info_req_parse(&req_info, info->nlhdr,
-					  genl_info_net(info), info->extack,
-					  true);
+	ret = ethnl_parse_header_dev_get(&req_info,
+					 tb[ETHTOOL_A_TUNNEL_INFO_HEADER],
+					 genl_info_net(info), info->extack,
+					 true);
 	if (ret < 0)
 		return ret;
 
@@ -233,16 +216,19 @@ struct ethnl_tunnel_info_dump_ctx {
 
 int ethnl_tunnel_info_start(struct netlink_callback *cb)
 {
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
 	struct ethnl_tunnel_info_dump_ctx *ctx = (void *)cb->ctx;
+	struct nlattr **tb = info->attrs;
 	int ret;
 
 	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
 
 	memset(ctx, 0, sizeof(*ctx));
 
-	ret = ethnl_tunnel_info_req_parse(&ctx->req_info, cb->nlh,
-					  sock_net(cb->skb->sk), cb->extack,
-					  false);
+	ret = ethnl_parse_header_dev_get(&ctx->req_info,
+					 tb[ETHTOOL_A_TUNNEL_INFO_HEADER],
+					 sock_net(cb->skb->sk), cb->extack,
+					 false);
 	if (ctx->req_info.dev) {
 		dev_put(ctx->req_info.dev);
 		ctx->req_info.dev = NULL;
diff --git a/net/ethtool/wol.c b/net/ethtool/wol.c
index 1798421e9f1c..ada7df2331d2 100644
--- a/net/ethtool/wol.c
+++ b/net/ethtool/wol.c
@@ -17,12 +17,9 @@ struct wol_reply_data {
 #define WOL_REPDATA(__reply_base) \
 	container_of(__reply_base, struct wol_reply_data, base)
 
-static const struct nla_policy
-wol_get_policy[ETHTOOL_A_WOL_MAX + 1] = {
-	[ETHTOOL_A_WOL_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_WOL_HEADER]		= { .type = NLA_NESTED },
-	[ETHTOOL_A_WOL_MODES]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_WOL_SOPASS]		= { .type = NLA_REJECT },
+const struct nla_policy ethnl_wol_get_policy[] = {
+	[ETHTOOL_A_WOL_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
 static int wol_prepare_data(const struct ethnl_req_info *req_base,
@@ -89,10 +86,8 @@ const struct ethnl_request_ops ethnl_wol_request_ops = {
 	.request_cmd		= ETHTOOL_MSG_WOL_GET,
 	.reply_cmd		= ETHTOOL_MSG_WOL_GET_REPLY,
 	.hdr_attr		= ETHTOOL_A_WOL_HEADER,
-	.max_attr		= ETHTOOL_A_WOL_MAX,
 	.req_info_size		= sizeof(struct wol_req_info),
 	.reply_data_size	= sizeof(struct wol_reply_data),
-	.request_policy		= wol_get_policy,
 
 	.prepare_data		= wol_prepare_data,
 	.reply_size		= wol_reply_size,
@@ -101,10 +96,9 @@ const struct ethnl_request_ops ethnl_wol_request_ops = {
 
 /* WOL_SET */
 
-static const struct nla_policy
-wol_set_policy[ETHTOOL_A_WOL_MAX + 1] = {
-	[ETHTOOL_A_WOL_UNSPEC]		= { .type = NLA_REJECT },
-	[ETHTOOL_A_WOL_HEADER]		= { .type = NLA_NESTED },
+const struct nla_policy ethnl_wol_set_policy[] = {
+	[ETHTOOL_A_WOL_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
 	[ETHTOOL_A_WOL_MODES]		= { .type = NLA_NESTED },
 	[ETHTOOL_A_WOL_SOPASS]		= { .type = NLA_BINARY,
 					    .len = SOPASS_MAX },
@@ -113,16 +107,12 @@ wol_set_policy[ETHTOOL_A_WOL_MAX + 1] = {
 int ethnl_set_wol(struct sk_buff *skb, struct genl_info *info)
 {
 	struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
-	struct nlattr *tb[ETHTOOL_A_WOL_MAX + 1];
 	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
 	struct net_device *dev;
 	bool mod = false;
 	int ret;
 
-	ret = nlmsg_parse(info->nlhdr, GENL_HDRLEN, tb, ETHTOOL_A_WOL_MAX,
-			  wol_set_policy, info->extack);
-	if (ret < 0)
-		return ret;
 	ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_WOL_HEADER],
 					 genl_info_net(info), info->extack,
 					 true);
diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c
index 7e11a6c35bc3..4cfd9e829c7b 100644
--- a/net/hsr/hsr_debugfs.c
+++ b/net/hsr/hsr_debugfs.c
@@ -60,17 +60,7 @@ hsr_node_table_show(struct seq_file *sfp, void *data)
 	return 0;
 }
 
-/* hsr_node_table_open - Open the node_table file
- *
- * Description:
- * This routine opens a debugfs file node_table of specific hsr
- * or prp device
- */
-static int
-hsr_node_table_open(struct inode *inode, struct file *filp)
-{
-	return single_open(filp, hsr_node_table_show, inode->i_private);
-}
+DEFINE_SHOW_ATTRIBUTE(hsr_node_table);
 
 void hsr_debugfs_rename(struct net_device *dev)
 {
@@ -85,13 +75,6 @@ void hsr_debugfs_rename(struct net_device *dev)
 		priv->node_tbl_root = d;
 }
 
-static const struct file_operations hsr_fops = {
-	.open	= hsr_node_table_open,
-	.read	= seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-};
-
 /* hsr_debugfs_init - create hsr node_table file for dumping
  * the node table
  *
@@ -113,7 +96,7 @@ void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev)
 
 	de = debugfs_create_file("node_table", S_IFREG | 0444,
 				 priv->node_tbl_root, priv,
-				 &hsr_fops);
+				 &hsr_node_table_fops);
 	if (IS_ERR(de)) {
 		pr_err("Cannot create hsr node_table file\n");
 		debugfs_remove(priv->node_tbl_root);
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 7dc92ce5a134..a9c30a608e35 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -217,7 +217,10 @@ struct hsr_priv {
 	u8 net_id;		/* for PRP, it occupies most significant 3 bits
 				 * of lan_id
 				 */
-	unsigned char		sup_multicast_addr[ETH_ALEN];
+	unsigned char		sup_multicast_addr[ETH_ALEN] __aligned(sizeof(u16));
+				/* Align to u16 boundary to avoid unaligned access
+				 * in ether_addr_equal
+				 */
 #ifdef	CONFIG_DEBUG_FS
 	struct dentry *node_tbl_root;
 #endif
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 0e4681cf71db..f3c8f91dbe2c 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -493,7 +493,7 @@ fail:
 	return res;
 }
 
-static const struct genl_ops hsr_ops[] = {
+static const struct genl_small_ops hsr_ops[] = {
 	{
 		.cmd = HSR_C_GET_NODE_STATUS,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -518,8 +518,8 @@ static struct genl_family hsr_genl_family __ro_after_init = {
 	.policy = hsr_genl_policy,
 	.netnsok = true,
 	.module = THIS_MODULE,
-	.ops = hsr_ops,
-	.n_ops = ARRAY_SIZE(hsr_ops),
+	.small_ops = hsr_ops,
+	.n_small_ops = ARRAY_SIZE(hsr_ops),
 	.mcgrps = hsr_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(hsr_mcgrps),
 };
diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
index 7fe3b6b6c495..b07abc38b4b3 100644
--- a/net/ieee802154/netlink.c
+++ b/net/ieee802154/netlink.c
@@ -81,7 +81,7 @@ int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info)
 	return genlmsg_reply(msg, info);
 }
 
-static const struct genl_ops ieee802154_ops[] = {
+static const struct genl_small_ops ieee802154_ops[] = {
 	/* see nl-phy.c */
 	IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy,
 			ieee802154_dump_phy),
@@ -130,8 +130,8 @@ struct genl_family nl802154_family __ro_after_init = {
 	.maxattr	= IEEE802154_ATTR_MAX,
 	.policy		= ieee802154_policy,
 	.module		= THIS_MODULE,
-	.ops		= ieee802154_ops,
-	.n_ops		= ARRAY_SIZE(ieee802154_ops),
+	.small_ops	= ieee802154_ops,
+	.n_small_ops	= ARRAY_SIZE(ieee802154_ops),
 	.mcgrps		= ieee802154_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(ieee802154_mcgrps),
 };
diff --git a/net/ieee802154/nl-mac.c b/net/ieee802154/nl-mac.c
index 6d091e419d3e..9c640d670ffe 100644
--- a/net/ieee802154/nl-mac.c
+++ b/net/ieee802154/nl-mac.c
@@ -149,7 +149,7 @@ static struct net_device *ieee802154_nl_get_dev(struct genl_info *info)
 	if (info->attrs[IEEE802154_ATTR_DEV_NAME]) {
 		char name[IFNAMSIZ + 1];
 
-		nla_strlcpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME],
+		nla_strscpy(name, info->attrs[IEEE802154_ATTR_DEV_NAME],
 			    sizeof(name));
 		dev = dev_get_by_name(&init_net, name);
 	} else if (info->attrs[IEEE802154_ATTR_DEV_INDEX]) {
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 4307503a6f0b..b94fa8eb831b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -450,7 +450,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	/* BPF prog is run before any checks are done so that if the prog
 	 * changes context in a wrong way it will be caught.
 	 */
-	err = BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr);
+	err = BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr);
 	if (err)
 		return err;
 
@@ -1017,6 +1017,7 @@ static int inet_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon
 
 const struct proto_ops inet_stream_ops = {
 	.family		   = PF_INET,
+	.flags		   = PROTO_CMSG_DATA_ONLY,
 	.owner		   = THIS_MODULE,
 	.release	   = inet_release,
 	.bind		   = inet_bind,
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 687971d83b4e..922dd73e5740 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -125,6 +125,7 @@ static int arp_constructor(struct neighbour *neigh);
 static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb);
 static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb);
 static void parp_redo(struct sk_buff *skb);
+static int arp_is_multicast(const void *pkey);
 
 static const struct neigh_ops arp_generic_ops = {
 	.family =		AF_INET,
@@ -156,6 +157,7 @@ struct neigh_table arp_tbl = {
 	.key_eq		= arp_key_eq,
 	.constructor	= arp_constructor,
 	.proxy_redo	= parp_redo,
+	.is_multicast	= arp_is_multicast,
 	.id		= "arp_cache",
 	.parms		= {
 		.tbl			= &arp_tbl,
@@ -928,6 +930,10 @@ static void parp_redo(struct sk_buff *skb)
 	arp_process(dev_net(skb->dev), NULL, skb);
 }
 
+static int arp_is_multicast(const void *pkey)
+{
+	return ipv4_is_multicast(*((__be32 *)pkey));
+}
 
 /*
  *	Receive an arp request from the device layer.
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index e3939f76b024..d520e61649c8 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -28,27 +28,6 @@ static u32 unsupported_ops[] = {
 static const struct btf_type *tcp_sock_type;
 static u32 tcp_sock_id, sock_id;
 
-static int btf_sk_storage_get_ids[5];
-static struct bpf_func_proto btf_sk_storage_get_proto __read_mostly;
-
-static int btf_sk_storage_delete_ids[5];
-static struct bpf_func_proto btf_sk_storage_delete_proto __read_mostly;
-
-static void convert_sk_func_proto(struct bpf_func_proto *to, int *to_btf_ids,
-				  const struct bpf_func_proto *from)
-{
-	int i;
-
-	*to = *from;
-	to->btf_id = to_btf_ids;
-	for (i = 0; i < ARRAY_SIZE(to->arg_type); i++) {
-		if (to->arg_type[i] == ARG_PTR_TO_SOCKET) {
-			to->arg_type[i] = ARG_PTR_TO_BTF_ID;
-			to->btf_id[i] = tcp_sock_id;
-		}
-	}
-}
-
 static int bpf_tcp_ca_init(struct btf *btf)
 {
 	s32 type_id;
@@ -64,13 +43,6 @@ static int bpf_tcp_ca_init(struct btf *btf)
 	tcp_sock_id = type_id;
 	tcp_sock_type = btf_type_by_id(btf, tcp_sock_id);
 
-	convert_sk_func_proto(&btf_sk_storage_get_proto,
-			      btf_sk_storage_get_ids,
-			      &bpf_sk_storage_get_proto);
-	convert_sk_func_proto(&btf_sk_storage_delete_proto,
-			      btf_sk_storage_delete_ids,
-			      &bpf_sk_storage_delete_proto);
-
 	return 0;
 }
 
@@ -123,6 +95,7 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size,
 }
 
 static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
+					const struct btf *btf,
 					const struct btf_type *t, int off,
 					int size, enum bpf_access_type atype,
 					u32 *next_btf_id)
@@ -130,7 +103,7 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
 	size_t end;
 
 	if (atype == BPF_READ)
-		return btf_struct_access(log, t, off, size, atype, next_btf_id);
+		return btf_struct_access(log, btf, t, off, size, atype, next_btf_id);
 
 	if (t != tcp_sock_type) {
 		bpf_log(log, "only read is supported\n");
@@ -185,8 +158,8 @@ static const struct bpf_func_proto bpf_tcp_send_ack_proto = {
 	/* In case we want to report error later */
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_PTR_TO_BTF_ID,
+	.arg1_btf_id	= &tcp_sock_id,
 	.arg2_type	= ARG_ANYTHING,
-	.btf_id		= &tcp_sock_id,
 };
 
 static const struct bpf_func_proto *
@@ -197,9 +170,9 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id,
 	case BPF_FUNC_tcp_send_ack:
 		return &bpf_tcp_send_ack_proto;
 	case BPF_FUNC_sk_storage_get:
-		return &btf_sk_storage_get_proto;
+		return &bpf_sk_storage_get_proto;
 	case BPF_FUNC_sk_storage_delete:
-		return &btf_sk_storage_delete_proto;
+		return &bpf_sk_storage_delete_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 2eb71579f4d2..471d33a0d095 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -498,7 +498,7 @@ static void cipso_v4_doi_free_rcu(struct rcu_head *entry)
 /**
  * cipso_v4_doi_remove - Remove an existing DOI from the CIPSO protocol engine
  * @doi: the DOI value
- * @audit_secid: the LSM secid to use in the audit message
+ * @audit_info: NetLabel audit information
  *
  * Description:
  * Removes a DOI definition from the CIPSO engine.  The NetLabel routines will
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 123a6d39438f..75f67994fc85 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -650,8 +650,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct in_device *in_dev;
 	struct ifaddrmsg *ifm;
 	struct in_ifaddr *ifa;
-
-	int err = -EINVAL;
+	int err;
 
 	ASSERT_RTNL();
 
@@ -881,7 +880,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
 		ifa->ifa_broadcast = nla_get_in_addr(tb[IFA_BROADCAST]);
 
 	if (tb[IFA_LABEL])
-		nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
+		nla_strscpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ);
 	else
 		memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
 
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 8b07f3a4f2db..a3271ec3e162 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -443,7 +443,6 @@ static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb,
 int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
 	u8 *tail;
-	u8 *vaddr;
 	int nfrags;
 	int esph_offset;
 	struct page *page;
@@ -485,14 +484,10 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *
 			page = pfrag->page;
 			get_page(page);
 
-			vaddr = kmap_atomic(page);
-
-			tail = vaddr + pfrag->offset;
+			tail = page_address(page) + pfrag->offset;
 
 			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
-			kunmap_atomic(vaddr);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 86a23e4a6a50..84bb707bd88d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -292,7 +292,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
 			.flowi4_iif = LOOPBACK_IFINDEX,
 			.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
 			.daddr = ip_hdr(skb)->saddr,
-			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
+			.flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK,
 			.flowi4_scope = scope,
 			.flowi4_mark = vmark ? skb->mark : 0,
 		};
@@ -696,7 +696,7 @@ int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
 		cfg->fc_gw4 = *((__be32 *)via->rtvia_addr);
 		break;
 	case AF_INET6:
-#ifdef CONFIG_IPV6
+#if IS_ENABLED(CONFIG_IPV6)
 		if (alen != sizeof(struct in6_addr)) {
 			NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA");
 			return -EINVAL;
@@ -825,7 +825,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 	if (has_gw && has_via) {
 		NL_SET_ERR_MSG(extack,
 			       "Nexthop configuration can not contain both GATEWAY and VIA");
-		goto errout;
+		return -EINVAL;
 	}
 
 	return 0;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 1f75dc686b6b..b5400cec4f69 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -973,7 +973,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
 			char tmp[TCP_CA_NAME_MAX];
 			bool ecn_ca = false;
 
-			nla_strlcpy(tmp, nla, sizeof(tmp));
+			nla_strscpy(tmp, nla, sizeof(tmp));
 			val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
 		} else {
 			if (nla_len(nla) != sizeof(u32))
@@ -1641,9 +1641,8 @@ int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nhc,
 		break;
 	}
 
-	*flags |= (nhc->nhc_flags & RTNH_F_ONLINK);
-	if (nhc->nhc_flags & RTNH_F_OFFLOAD)
-		*flags |= RTNH_F_OFFLOAD;
+	*flags |= (nhc->nhc_flags &
+		   (RTNH_F_ONLINK | RTNH_F_OFFLOAD | RTNH_F_TRAP));
 
 	if (!skip_oif && nhc->nhc_dev &&
 	    nla_put_u32(skb, RTA_OIF, nhc->nhc_dev->ifindex))
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index ffc5332f1390..28117c05dc35 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2100,15 +2100,6 @@ static void __fib_info_notify_update(struct net *net, struct fib_table *tb,
 			rtmsg_fib(RTM_NEWROUTE, htonl(n->key), fa,
 				  KEYLENGTH - fa->fa_slen, tb->tb_id,
 				  info, NLM_F_REPLACE);
-
-			/* call_fib_entry_notifiers will be removed when
-			 * in-kernel notifier is implemented and supported
-			 * for nexthop objects
-			 */
-			call_fib_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
-						 n->key,
-						 KEYLENGTH - fa->fa_slen, fa,
-						 NULL);
 		}
 	}
 }
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index abd083415f89..e5f69b0bf3df 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -237,7 +237,7 @@ static struct sk_buff *fou_gro_receive(struct sock *sk,
 
 	/* We can clear the encap_mark for FOU as we are essentially doing
 	 * one of two possible things.  We are either adding an L4 tunnel
-	 * header to the outer L3 tunnel header, or we are are simply
+	 * header to the outer L3 tunnel header, or we are simply
 	 * treating the GRE tunnel header as though it is a UDP protocol
 	 * specific header such as VXLAN or GENEVE.
 	 */
@@ -429,7 +429,7 @@ next_proto:
 
 	/* We can clear the encap_mark for GUE as we are essentially doing
 	 * one of two possible things.  We are either adding an L4 tunnel
-	 * header to the outer L3 tunnel header, or we are are simply
+	 * header to the outer L3 tunnel header, or we are simply
 	 * treating the GRE tunnel header as though it is a UDP protocol
 	 * specific header such as VXLAN or GENEVE.
 	 */
@@ -911,7 +911,7 @@ static int fou_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-static const struct genl_ops fou_nl_ops[] = {
+static const struct genl_small_ops fou_nl_ops[] = {
 	{
 		.cmd = FOU_CMD_ADD,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -940,8 +940,8 @@ static struct genl_family fou_nl_family __ro_after_init = {
 	.policy = fou_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= fou_nl_ops,
-	.n_ops		= ARRAY_SIZE(fou_nl_ops),
+	.small_ops	= fou_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(fou_nl_ops),
 };
 
 size_t fou_encap_hlen(struct ip_tunnel_encap *e)
diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c
index 66fdbfe5447c..5d1e6fe9d838 100644
--- a/net/ipv4/gre_demux.c
+++ b/net/ipv4/gre_demux.c
@@ -128,7 +128,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
 	 * to 0 and sets the configured key in the
 	 * inner erspan header field
 	 */
-	if (greh->protocol == htons(ETH_P_ERSPAN) ||
+	if ((greh->protocol == htons(ETH_P_ERSPAN) && hdr_len != 4) ||
 	    greh->protocol == htons(ETH_P_ERSPAN2)) {
 		struct erspan_base_hdr *ershdr;
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index cf36f955bfe6..396b492c804f 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -239,7 +239,7 @@ static struct {
 /**
  * icmp_global_allow - Are we allowed to send one more ICMP message ?
  *
- * Uses a token bucket to limit our ICMP messages to sysctl_icmp_msgs_per_sec.
+ * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec.
  * Returns false if we reached the limit and can not send another packet.
  * Note: called with BH disabled
  */
@@ -267,7 +267,10 @@ bool icmp_global_allow(void)
 	}
 	credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
 	if (credit) {
-		credit--;
+		/* We want to use a credit of one in average, but need to randomize
+		 * it for security reasons.
+		 */
+		credit = max_t(int, credit - prandom_u32_max(3), 0);
 		rc = true;
 	}
 	WRITE_ONCE(icmp_global.credit, credit);
@@ -352,7 +355,7 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
 
 	csum = skb_copy_and_csum_bits(icmp_param->skb,
 				      icmp_param->offset + offset,
-				      to, len, 0);
+				      to, len);
 
 	skb->csum = csum_block_add(skb->csum, csum, odd);
 	if (icmp_pointers[icmp_param->data.icmph.type].error)
@@ -376,15 +379,15 @@ static void icmp_push_reply(struct icmp_bxm *icmp_param,
 		ip_flush_pending_frames(sk);
 	} else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
 		struct icmphdr *icmph = icmp_hdr(skb);
-		__wsum csum = 0;
+		__wsum csum;
 		struct sk_buff *skb1;
 
+		csum = csum_partial_copy_nocheck((void *)&icmp_param->data,
+						 (char *)icmph,
+						 icmp_param->head_len);
 		skb_queue_walk(&sk->sk_write_queue, skb1) {
 			csum = csum_add(csum, skb1->csum);
 		}
-		csum = csum_partial_copy_nocheck((void *)&icmp_param->data,
-						 (char *)icmph,
-						 icmp_param->head_len, csum);
 		icmph->checksum = csum_fold(csum);
 		skb->ip_summed = CHECKSUM_NONE;
 		ip_push_pending_frames(sk, fl4);
@@ -444,7 +447,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
 	fl4.flowi4_proto = IPPROTO_ICMP;
 	fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
-	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		goto out_unlock;
@@ -457,6 +460,23 @@ out_bh_enable:
 	local_bh_enable();
 }
 
+/*
+ * The device used for looking up which routing table to use for sending an ICMP
+ * error is preferably the source whenever it is set, which should ensure the
+ * icmp error can be sent to the source host, else lookup using the routing
+ * table of the destination device, else use the main routing table (index 0).
+ */
+static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb)
+{
+	struct net_device *route_lookup_dev = NULL;
+
+	if (skb->dev)
+		route_lookup_dev = skb->dev;
+	else if (skb_dst(skb))
+		route_lookup_dev = skb_dst(skb)->dev;
+	return route_lookup_dev;
+}
+
 static struct rtable *icmp_route_lookup(struct net *net,
 					struct flowi4 *fl4,
 					struct sk_buff *skb_in,
@@ -465,6 +485,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 					int type, int code,
 					struct icmp_bxm *param)
 {
+	struct net_device *route_lookup_dev;
 	struct rtable *rt, *rt2;
 	struct flowi4 fl4_dec;
 	int err;
@@ -479,9 +500,10 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	fl4->flowi4_proto = IPPROTO_ICMP;
 	fl4->fl4_icmp_type = type;
 	fl4->fl4_icmp_code = code;
-	fl4->flowi4_oif = l3mdev_master_ifindex(skb_dst(skb_in)->dev);
+	route_lookup_dev = icmp_get_route_lookup_dev(skb_in);
+	fl4->flowi4_oif = l3mdev_master_ifindex(route_lookup_dev);
 
-	security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
+	security_skb_classify_flow(skb_in, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_key_hash(net, fl4, skb_in);
 	if (IS_ERR(rt))
 		return rt;
@@ -503,7 +525,7 @@ static struct rtable *icmp_route_lookup(struct net *net,
 	if (err)
 		goto relookup_failed;
 
-	if (inet_addr_type_dev_table(net, skb_dst(skb_in)->dev,
+	if (inet_addr_type_dev_table(net, route_lookup_dev,
 				     fl4_dec.saddr) == RTN_LOCAL) {
 		rt2 = __ip_route_output_key(net, &fl4_dec);
 		if (IS_ERR(rt2))
@@ -690,9 +712,9 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 		rcu_read_unlock();
 	}
 
-	tos = icmp_pointers[type].error ? ((iph->tos & IPTOS_TOS_MASK) |
+	tos = icmp_pointers[type].error ? (RT_TOS(iph->tos) |
 					   IPTOS_PREC_INTERNETCONTROL) :
-					  iph->tos;
+					   iph->tos;
 	mark = IP4_REPLY_MARK(net, skb_in->mark);
 
 	if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt))
@@ -784,7 +806,7 @@ EXPORT_SYMBOL(icmp_ndo_send);
 
 static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	const struct net_protocol *ipprot;
 	int protocol = iph->protocol;
 
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b457dd2d6c75..6bd7ca09af03 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -564,7 +564,7 @@ void inet_csk_clear_xmit_timers(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	icsk->icsk_pending = icsk->icsk_ack.pending = icsk->icsk_ack.blocked = 0;
+	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
 
 	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
 	sk_stop_timer(sk, &icsk->icsk_delack_timer);
@@ -602,7 +602,7 @@ struct dst_entry *inet_csk_route_req(const struct sock *sk,
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
 			   htons(ireq->ir_num), sk->sk_uid);
-	security_req_classify_flow(req, flowi4_to_flowi(fl4));
+	security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
@@ -640,7 +640,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
 			   (opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, ireq->ir_rmt_port,
 			   htons(ireq->ir_num), sk->sk_uid);
-	security_req_classify_flow(req, flowi4_to_flowi(fl4));
+	security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
@@ -787,7 +787,7 @@ static void reqsk_queue_hash_req(struct request_sock *req,
 	timer_setup(&req->rsk_timer, reqsk_timer_handler, TIMER_PINNED);
 	mod_timer(&req->rsk_timer, jiffies + timeout);
 
-	inet_ehash_insert(req_to_sk(req), NULL);
+	inet_ehash_insert(req_to_sk(req), NULL, NULL);
 	/* before letting lookups find us, make sure all req fields
 	 * are committed to memory and refcnt initialized.
 	 */
@@ -851,6 +851,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		newicsk->icsk_retransmits = 0;
 		newicsk->icsk_backoff	  = 0;
 		newicsk->icsk_probes_out  = 0;
+		newicsk->icsk_probes_tstamp = 0;
 
 		/* Deinitialize accept_queue to trap illegal accesses. */
 		memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index f1bd95f243b3..93474b1bea4e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -125,6 +125,7 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 			     bool net_admin)
 {
 	const struct inet_sock *inet = inet_sk(sk);
+	struct inet_diag_sockopt inet_sockopt;
 
 	if (nla_put_u8(skb, INET_DIAG_SHUTDOWN, sk->sk_shutdown))
 		goto errout;
@@ -180,6 +181,22 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb,
 	r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk));
 	r->idiag_inode = sock_i_ino(sk);
 
+	memset(&inet_sockopt, 0, sizeof(inet_sockopt));
+	inet_sockopt.recverr	= inet->recverr;
+	inet_sockopt.is_icsk	= inet->is_icsk;
+	inet_sockopt.freebind	= inet->freebind;
+	inet_sockopt.hdrincl	= inet->hdrincl;
+	inet_sockopt.mc_loop	= inet->mc_loop;
+	inet_sockopt.transparent = inet->transparent;
+	inet_sockopt.mc_all	= inet->mc_all;
+	inet_sockopt.nodefrag	= inet->nodefrag;
+	inet_sockopt.bind_address_no_port = inet->bind_address_no_port;
+	inet_sockopt.recverr_rfc4884 = inet->recverr_rfc4884;
+	inet_sockopt.defer_connect = inet->defer_connect;
+	if (nla_put(skb, INET_DIAG_SOCKOPT, sizeof(inet_sockopt),
+		    &inet_sockopt))
+		goto errout;
+
 	return 0;
 errout:
 	return 1;
@@ -462,8 +479,10 @@ static int inet_req_diag_fill(struct sock *sk, struct sk_buff *skb,
 	r->idiag_inode	= 0;
 
 	if (net_admin && nla_put_u32(skb, INET_DIAG_MARK,
-				     inet_rsk(reqsk)->ir_mark))
+				     inet_rsk(reqsk)->ir_mark)) {
+		nlmsg_cancel(skb, nlh);
 		return -EMSGSIZE;
+	}
 
 	nlmsg_end(skb, nlh);
 	return 0;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 10d31733297d..05cd198d7a6b 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -145,12 +145,16 @@ static void inet_frags_free_cb(void *ptr, void *arg)
 		inet_frag_destroy(fq);
 }
 
-static void fqdir_work_fn(struct work_struct *work)
+static LLIST_HEAD(fqdir_free_list);
+
+static void fqdir_free_fn(struct work_struct *work)
 {
-	struct fqdir *fqdir = container_of(work, struct fqdir, destroy_work);
-	struct inet_frags *f = fqdir->f;
+	struct llist_node *kill_list;
+	struct fqdir *fqdir, *tmp;
+	struct inet_frags *f;
 
-	rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL);
+	/* Atomically snapshot the list of fqdirs to free */
+	kill_list = llist_del_all(&fqdir_free_list);
 
 	/* We need to make sure all ongoing call_rcu(..., inet_frag_destroy_rcu)
 	 * have completed, since they need to dereference fqdir.
@@ -158,10 +162,25 @@ static void fqdir_work_fn(struct work_struct *work)
 	 */
 	rcu_barrier();
 
-	if (refcount_dec_and_test(&f->refcnt))
-		complete(&f->completion);
+	llist_for_each_entry_safe(fqdir, tmp, kill_list, free_list) {
+		f = fqdir->f;
+		if (refcount_dec_and_test(&f->refcnt))
+			complete(&f->completion);
 
-	kfree(fqdir);
+		kfree(fqdir);
+	}
+}
+
+static DECLARE_WORK(fqdir_free_work, fqdir_free_fn);
+
+static void fqdir_work_fn(struct work_struct *work)
+{
+	struct fqdir *fqdir = container_of(work, struct fqdir, destroy_work);
+
+	rhashtable_free_and_destroy(&fqdir->rhashtable, inet_frags_free_cb, NULL);
+
+	if (llist_add(&fqdir->free_list, &fqdir_free_list))
+		queue_work(system_wq, &fqdir_free_work);
 }
 
 int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net)
@@ -184,10 +203,22 @@ int fqdir_init(struct fqdir **fqdirp, struct inet_frags *f, struct net *net)
 }
 EXPORT_SYMBOL(fqdir_init);
 
+static struct workqueue_struct *inet_frag_wq;
+
+static int __init inet_frag_wq_init(void)
+{
+	inet_frag_wq = create_workqueue("inet_frag_wq");
+	if (!inet_frag_wq)
+		panic("Could not create inet frag workq");
+	return 0;
+}
+
+pure_initcall(inet_frag_wq_init);
+
 void fqdir_exit(struct fqdir *fqdir)
 {
 	INIT_WORK(&fqdir->destroy_work, fqdir_work_fn);
-	queue_work(system_wq, &fqdir->destroy_work);
+	queue_work(inet_frag_wq, &fqdir->destroy_work);
 }
 EXPORT_SYMBOL(fqdir_exit);
 
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 239e54474b65..45fb450b4522 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -20,6 +20,9 @@
 #include <net/addrconf.h>
 #include <net/inet_connection_sock.h>
 #include <net/inet_hashtables.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <net/inet6_hashtables.h>
+#endif
 #include <net/secure_seq.h>
 #include <net/ip.h>
 #include <net/tcp.h>
@@ -228,7 +231,7 @@ static void inet_unhash2(struct inet_hashinfo *h, struct sock *sk)
 
 static inline int compute_score(struct sock *sk, struct net *net,
 				const unsigned short hnum, const __be32 daddr,
-				const int dif, const int sdif, bool exact_dif)
+				const int dif, const int sdif)
 {
 	int score = -1;
 
@@ -277,15 +280,13 @@ static struct sock *inet_lhash2_lookup(struct net *net,
 				const __be32 daddr, const unsigned short hnum,
 				const int dif, const int sdif)
 {
-	bool exact_dif = inet_exact_dif_match(net, skb);
 	struct inet_connection_sock *icsk;
 	struct sock *sk, *result = NULL;
 	int score, hiscore = 0;
 
 	inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
 		sk = (struct sock *)icsk;
-		score = compute_score(sk, net, hnum, daddr,
-				      dif, sdif, exact_dif);
+		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
 			result = lookup_reuseport(net, sk, skb, doff,
 						  saddr, sport, daddr, hnum);
@@ -510,10 +511,52 @@ static u32 inet_sk_port_offset(const struct sock *sk)
 					  inet->inet_dport);
 }
 
-/* insert a socket into ehash, and eventually remove another one
- * (The another one can be a SYN_RECV or TIMEWAIT
+/* Searches for an exsiting socket in the ehash bucket list.
+ * Returns true if found, false otherwise.
+ */
+static bool inet_ehash_lookup_by_sk(struct sock *sk,
+				    struct hlist_nulls_head *list)
+{
+	const __portpair ports = INET_COMBINED_PORTS(sk->sk_dport, sk->sk_num);
+	const int sdif = sk->sk_bound_dev_if;
+	const int dif = sk->sk_bound_dev_if;
+	const struct hlist_nulls_node *node;
+	struct net *net = sock_net(sk);
+	struct sock *esk;
+
+	INET_ADDR_COOKIE(acookie, sk->sk_daddr, sk->sk_rcv_saddr);
+
+	sk_nulls_for_each_rcu(esk, node, list) {
+		if (esk->sk_hash != sk->sk_hash)
+			continue;
+		if (sk->sk_family == AF_INET) {
+			if (unlikely(INET_MATCH(esk, net, acookie,
+						sk->sk_daddr,
+						sk->sk_rcv_saddr,
+						ports, dif, sdif))) {
+				return true;
+			}
+		}
+#if IS_ENABLED(CONFIG_IPV6)
+		else if (sk->sk_family == AF_INET6) {
+			if (unlikely(INET6_MATCH(esk, net,
+						 &sk->sk_v6_daddr,
+						 &sk->sk_v6_rcv_saddr,
+						 ports, dif, sdif))) {
+				return true;
+			}
+		}
+#endif
+	}
+	return false;
+}
+
+/* Insert a socket into ehash, and eventually remove another one
+ * (The another one can be a SYN_RECV or TIMEWAIT)
+ * If an existing socket already exists, socket sk is not inserted,
+ * and sets found_dup_sk parameter to true.
  */
-bool inet_ehash_insert(struct sock *sk, struct sock *osk)
+bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 {
 	struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
 	struct hlist_nulls_head *list;
@@ -532,16 +575,23 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk)
 	if (osk) {
 		WARN_ON_ONCE(sk->sk_hash != osk->sk_hash);
 		ret = sk_nulls_del_node_init_rcu(osk);
+	} else if (found_dup_sk) {
+		*found_dup_sk = inet_ehash_lookup_by_sk(sk, list);
+		if (*found_dup_sk)
+			ret = false;
 	}
+
 	if (ret)
 		__sk_nulls_add_node_rcu(sk, list);
+
 	spin_unlock(lock);
+
 	return ret;
 }
 
-bool inet_ehash_nolisten(struct sock *sk, struct sock *osk)
+bool inet_ehash_nolisten(struct sock *sk, struct sock *osk, bool *found_dup_sk)
 {
-	bool ok = inet_ehash_insert(sk, osk);
+	bool ok = inet_ehash_insert(sk, osk, found_dup_sk);
 
 	if (ok) {
 		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
@@ -585,7 +635,7 @@ int __inet_hash(struct sock *sk, struct sock *osk)
 	int err = 0;
 
 	if (sk->sk_state != TCP_LISTEN) {
-		inet_ehash_nolisten(sk, osk);
+		inet_ehash_nolisten(sk, osk, NULL);
 		return 0;
 	}
 	WARN_ON(!sk_unhashed(sk));
@@ -681,7 +731,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		tb = inet_csk(sk)->icsk_bind_hash;
 		spin_lock_bh(&head->lock);
 		if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
-			inet_ehash_nolisten(sk, NULL);
+			inet_ehash_nolisten(sk, NULL, NULL);
 			spin_unlock_bh(&head->lock);
 			return 0;
 		}
@@ -760,7 +810,7 @@ ok:
 	inet_bind_hash(sk, tb, port);
 	if (sk_unhashed(sk)) {
 		inet_sk(sk)->inet_sport = htons(port);
-		inet_ehash_nolisten(sk, (struct sock *)tw);
+		inet_ehash_nolisten(sk, (struct sock *)tw, NULL);
 	}
 	if (tw)
 		inet_twsk_bind_unhash(tw, hinfo);
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index c411c87ae865..437afe392e66 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -272,14 +272,14 @@ restart:
 				continue;
 			tw = inet_twsk(sk);
 			if ((tw->tw_family != family) ||
-				refcount_read(&twsk_net(tw)->count))
+				refcount_read(&twsk_net(tw)->ns.count))
 				continue;
 
 			if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt)))
 				continue;
 
 			if (unlikely((tw->tw_family != family) ||
-				     refcount_read(&twsk_net(tw)->count))) {
+				     refcount_read(&twsk_net(tw)->ns.count))) {
 				inet_twsk_put(tw);
 				goto restart;
 			}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 4e31f23e4117..a68bf4c6fe9b 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -625,9 +625,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 	}
 
 	if (dev->header_ops) {
-		/* Need space for new headers */
-		if (skb_cow_head(skb, dev->needed_headroom -
-				      (tunnel->hlen + sizeof(struct iphdr))))
+		if (skb_cow_head(skb, 0))
 			goto free_skb;
 
 		tnl_params = (const struct iphdr *)skb->data;
@@ -748,7 +746,11 @@ static void ipgre_link_update(struct net_device *dev, bool set_mtu)
 	len = tunnel->tun_hlen - len;
 	tunnel->hlen = tunnel->hlen + len;
 
-	dev->needed_headroom = dev->needed_headroom + len;
+	if (dev->header_ops)
+		dev->hard_header_len += len;
+	else
+		dev->needed_headroom += len;
+
 	if (set_mtu)
 		dev->mtu = max_t(int, dev->mtu - len, 68);
 
@@ -918,7 +920,7 @@ static const struct net_device_ops ipgre_netdev_ops = {
 	.ndo_start_xmit		= ipgre_xmit,
 	.ndo_do_ioctl		= ip_tunnel_ioctl,
 	.ndo_change_mtu		= ip_tunnel_change_mtu,
-	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_get_iflink		= ip_tunnel_get_iflink,
 	.ndo_tunnel_ctl		= ipgre_tunnel_ctl,
 };
@@ -944,6 +946,7 @@ static void __gre_tunnel_init(struct net_device *dev)
 	tunnel->parms.iph.protocol = IPPROTO_GRE;
 
 	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
+	dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph);
 
 	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
@@ -987,10 +990,14 @@ static int ipgre_tunnel_init(struct net_device *dev)
 				return -EINVAL;
 			dev->flags = IFF_BROADCAST;
 			dev->header_ops = &ipgre_header_ops;
+			dev->hard_header_len = tunnel->hlen + sizeof(*iph);
+			dev->needed_headroom = 0;
 		}
 #endif
 	} else if (!tunnel->collect_md) {
 		dev->header_ops = &ipgre_header_ops;
+		dev->hard_header_len = tunnel->hlen + sizeof(*iph);
+		dev->needed_headroom = 0;
 	}
 
 	return ip_tunnel_init(dev);
@@ -1268,7 +1275,7 @@ static const struct net_device_ops gre_tap_netdev_ops = {
 	.ndo_set_mac_address 	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= ip_tunnel_change_mtu,
-	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_get_iflink		= ip_tunnel_get_iflink,
 	.ndo_fill_metadata_dst	= gre_fill_metadata_dst,
 };
@@ -1301,7 +1308,7 @@ static const struct net_device_ops erspan_netdev_ops = {
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= ip_tunnel_change_mtu,
-	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_get_iflink		= ip_tunnel_get_iflink,
 	.ndo_fill_metadata_dst	= gre_fill_metadata_dst,
 };
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 948747aac4e2..da1b5038bdfd 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -47,32 +47,32 @@ void ip_options_build(struct sk_buff *skb, struct ip_options *opt,
 	unsigned char *iph = skb_network_header(skb);
 
 	memcpy(&(IPCB(skb)->opt), opt, sizeof(struct ip_options));
-	memcpy(iph+sizeof(struct iphdr), opt->__data, opt->optlen);
+	memcpy(iph + sizeof(struct iphdr), opt->__data, opt->optlen);
 	opt = &(IPCB(skb)->opt);
 
 	if (opt->srr)
-		memcpy(iph+opt->srr+iph[opt->srr+1]-4, &daddr, 4);
+		memcpy(iph + opt->srr + iph[opt->srr + 1] - 4, &daddr, 4);
 
 	if (!is_frag) {
 		if (opt->rr_needaddr)
-			ip_rt_get_source(iph+opt->rr+iph[opt->rr+2]-5, skb, rt);
+			ip_rt_get_source(iph + opt->rr + iph[opt->rr + 2] - 5, skb, rt);
 		if (opt->ts_needaddr)
-			ip_rt_get_source(iph+opt->ts+iph[opt->ts+2]-9, skb, rt);
+			ip_rt_get_source(iph + opt->ts + iph[opt->ts + 2] - 9, skb, rt);
 		if (opt->ts_needtime) {
 			__be32 midtime;
 
 			midtime = inet_current_timestamp();
-			memcpy(iph+opt->ts+iph[opt->ts+2]-5, &midtime, 4);
+			memcpy(iph + opt->ts + iph[opt->ts + 2] - 5, &midtime, 4);
 		}
 		return;
 	}
 	if (opt->rr) {
-		memset(iph+opt->rr, IPOPT_NOP, iph[opt->rr+1]);
+		memset(iph + opt->rr, IPOPT_NOP, iph[opt->rr + 1]);
 		opt->rr = 0;
 		opt->rr_needaddr = 0;
 	}
 	if (opt->ts) {
-		memset(iph+opt->ts, IPOPT_NOP, iph[opt->ts+1]);
+		memset(iph + opt->ts, IPOPT_NOP, iph[opt->ts + 1]);
 		opt->ts = 0;
 		opt->ts_needaddr = opt->ts_needtime = 0;
 	}
@@ -495,26 +495,29 @@ EXPORT_SYMBOL(ip_options_compile);
 void ip_options_undo(struct ip_options *opt)
 {
 	if (opt->srr) {
-		unsigned  char *optptr = opt->__data+opt->srr-sizeof(struct  iphdr);
-		memmove(optptr+7, optptr+3, optptr[1]-7);
-		memcpy(optptr+3, &opt->faddr, 4);
+		unsigned char *optptr = opt->__data + opt->srr - sizeof(struct iphdr);
+
+		memmove(optptr + 7, optptr + 3, optptr[1] - 7);
+		memcpy(optptr + 3, &opt->faddr, 4);
 	}
 	if (opt->rr_needaddr) {
-		unsigned  char *optptr = opt->__data+opt->rr-sizeof(struct  iphdr);
+		unsigned char *optptr = opt->__data + opt->rr - sizeof(struct iphdr);
+
 		optptr[2] -= 4;
-		memset(&optptr[optptr[2]-1], 0, 4);
+		memset(&optptr[optptr[2] - 1], 0, 4);
 	}
 	if (opt->ts) {
-		unsigned  char *optptr = opt->__data+opt->ts-sizeof(struct  iphdr);
+		unsigned char *optptr = opt->__data + opt->ts - sizeof(struct iphdr);
+
 		if (opt->ts_needtime) {
 			optptr[2] -= 4;
-			memset(&optptr[optptr[2]-1], 0, 4);
-			if ((optptr[3]&0xF) == IPOPT_TS_PRESPEC)
+			memset(&optptr[optptr[2] - 1], 0, 4);
+			if ((optptr[3] & 0xF) == IPOPT_TS_PRESPEC)
 				optptr[2] -= 4;
 		}
 		if (opt->ts_needaddr) {
 			optptr[2] -= 4;
-			memset(&optptr[optptr[2]-1], 0, 4);
+			memset(&optptr[optptr[2] - 1], 0, 4);
 		}
 	}
 }
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e6f2ada9e7d5..2ed0b01f72f0 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -143,7 +143,8 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
  *
  */
 int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
-			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt)
+			  __be32 saddr, __be32 daddr, struct ip_options_rcu *opt,
+			  u8 tos)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct rtable *rt = skb_rtable(skb);
@@ -156,7 +157,7 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 	iph = ip_hdr(skb);
 	iph->version  = 4;
 	iph->ihl      = 5;
-	iph->tos      = inet->tos;
+	iph->tos      = tos;
 	iph->ttl      = ip_select_ttl(inet, &rt->dst);
 	iph->daddr    = (opt && opt->opt.srr ? opt->opt.faddr : daddr);
 	iph->saddr    = saddr;
@@ -301,7 +302,7 @@ static int __ip_finish_output(struct net *net, struct sock *sk, struct sk_buff *
 	if (skb_is_gso(skb))
 		return ip_finish_output_gso(net, sk, skb, mtu);
 
-	if (skb->len > mtu || (IPCB(skb)->flags & IPSKB_FRAG_PMTU))
+	if (skb->len > mtu || IPCB(skb)->frag_max_size)
 		return ip_fragment(net, sk, skb, mtu, ip_finish_output2);
 
 	return ip_finish_output2(net, sk, skb);
@@ -997,7 +998,7 @@ static int __ip_append_data(struct sock *sk,
 
 	fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0);
 	maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen;
-	maxnonfragsize = ip_sk_ignore_df(sk) ? 0xFFFF : mtu;
+	maxnonfragsize = ip_sk_ignore_df(sk) ? IP_MAX_MTU : mtu;
 
 	if (cork->length + length > maxnonfragsize - fragheaderlen) {
 		ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport,
@@ -1127,7 +1128,7 @@ alloc_new_skb:
 			if (fraggap) {
 				skb->csum = skb_copy_and_csum_bits(
 					skb_prev, maxfraglen,
-					data + transhdrlen, fraggap, 0);
+					data + transhdrlen, fraggap);
 				skb_prev->csum = csum_sub(skb_prev->csum,
 							  skb->csum);
 				data += fraggap;
@@ -1352,7 +1353,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 	if (cork->flags & IPCORK_OPT)
 		opt = cork->opt;
 
-	if (!(rt->dst.dev->features&NETIF_F_SG))
+	if (!(rt->dst.dev->features & NETIF_F_SG))
 		return -EOPNOTSUPP;
 
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
@@ -1412,7 +1413,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 				skb->csum = skb_copy_and_csum_bits(skb_prev,
 								   maxfraglen,
 						    skb_transport_header(skb),
-								   fraggap, 0);
+								   fraggap);
 				skb_prev->csum = csum_sub(skb_prev->csum,
 							  skb->csum);
 				pskb_trim_unique(skb_prev, maxfraglen);
@@ -1537,7 +1538,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 	ip_select_ident(net, skb, sk);
 
 	if (opt) {
-		iph->ihl += opt->optlen>>2;
+		iph->ihl += opt->optlen >> 2;
 		ip_options_build(skb, opt, cork->addr, rt, 0);
 	}
 
@@ -1649,7 +1650,7 @@ static int ip_reply_glue_bits(void *dptr, char *to, int offset,
 {
 	__wsum csum;
 
-	csum = csum_partial_copy_nocheck(dptr+offset, to, len, 0);
+	csum = csum_partial_copy_nocheck(dptr+offset, to, len);
 	skb->csum = csum_block_add(skb->csum, csum, odd);
 	return 0;
 }
@@ -1699,7 +1700,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   daddr, saddr,
 			   tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
 			   arg->uid);
-	security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+	security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_key(net, &fl4);
 	if (IS_ERR(rt))
 		return;
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index d2c223554ff7..ec6036713e2c 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1124,8 +1124,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		dev_put(dev);
 
 		err = -EINVAL;
-		if (sk->sk_bound_dev_if &&
-		    (!midx || midx != sk->sk_bound_dev_if))
+		if (sk->sk_bound_dev_if && midx != sk->sk_bound_dev_if)
 			break;
 
 		inet->uc_index = ifindex;
@@ -1189,7 +1188,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
 		err = -EINVAL;
 		if (sk->sk_bound_dev_if &&
 		    mreq.imr_ifindex != sk->sk_bound_dev_if &&
-		    (!midx || midx != sk->sk_bound_dev_if))
+		    midx != sk->sk_bound_dev_if)
 			break;
 
 		inet->mc_index = mreq.imr_ifindex;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0c1f36404471..76a420c76f16 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -317,7 +317,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 	}
 
 	dev->needed_headroom = t_hlen + hlen;
-	mtu -= (dev->hard_header_len + t_hlen);
+	mtu -= t_hlen;
 
 	if (mtu < IPV4_MIN_MTU)
 		mtu = IPV4_MIN_MTU;
@@ -347,7 +347,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
 	nt = netdev_priv(dev);
 	t_hlen = nt->hlen + sizeof(struct iphdr);
 	dev->min_mtu = ETH_MIN_MTU;
-	dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
+	dev->max_mtu = IP_MAX_MTU - t_hlen;
 	ip_tunnel_add(itn, nt);
 	return nt;
 
@@ -360,7 +360,6 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
 		  bool log_ecn_error)
 {
-	struct pcpu_sw_netstats *tstats;
 	const struct iphdr *iph = ip_hdr(skb);
 	int err;
 
@@ -402,12 +401,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		}
 	}
 
-	tstats = this_cpu_ptr(tunnel->dev->tstats);
-	u64_stats_update_begin(&tstats->syncp);
-	tstats->rx_packets++;
-	tstats->rx_bytes += skb->len;
-	u64_stats_update_end(&tstats->syncp);
-
+	dev_sw_netstats_rx_add(tunnel->dev, skb->len);
 	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev)));
 
 	if (tunnel->dev->type == ARPHRD_ETHER) {
@@ -494,11 +488,10 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
 	int mtu;
 
 	tunnel_hlen = md ? tunnel_hlen : tunnel->hlen;
-	pkt_size = skb->len - tunnel_hlen - dev->hard_header_len;
+	pkt_size = skb->len - tunnel_hlen;
 
 	if (df)
-		mtu = dst_mtu(&rt->dst) - dev->hard_header_len
-					- sizeof(struct iphdr) - tunnel_hlen;
+		mtu = dst_mtu(&rt->dst) - (sizeof(struct iphdr) + tunnel_hlen);
 	else
 		mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
@@ -614,9 +607,6 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	if (!df && skb->protocol == htons(ETH_P_IP))
-		df = inner_iph->frag_off & htons(IP_DF);
-
 	headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len;
 	if (headroom > dev->needed_headroom)
 		dev->needed_headroom = headroom;
@@ -768,8 +758,11 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph,
-			    0, 0, false)) {
+	df = tnl_params->frag_off;
+	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
+		df |= (inner_iph->frag_off & htons(IP_DF));
+
+	if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, 0, 0, false)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
@@ -797,10 +790,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 			ttl = ip4_dst_hoplimit(&rt->dst);
 	}
 
-	df = tnl_params->frag_off;
-	if (skb->protocol == htons(ETH_P_IP) && !tunnel->ignore_df)
-		df |= (inner_iph->frag_off&htons(IP_DF));
-
 	max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr)
 			+ rt->dst.header_len + ip_encap_hlen(&tunnel->encap);
 	if (max_headroom > dev->needed_headroom)
@@ -982,7 +971,7 @@ int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
-	int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
+	int max_mtu = IP_MAX_MTU - t_hlen;
 
 	if (new_mtu < ETH_MIN_MTU)
 		return -EINVAL;
@@ -1159,10 +1148,9 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 
 	mtu = ip_tunnel_bind_dev(dev);
 	if (tb[IFLA_MTU]) {
-		unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen;
+		unsigned int max = IP_MAX_MTU - (nt->hlen + sizeof(struct iphdr));
 
-		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU,
-			    (unsigned int)(max - sizeof(struct iphdr)));
+		mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU, max);
 	}
 
 	err = dev_set_mtu(dev, mtu);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index b2ea1a8c5fd6..7ca338fbe8ba 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -263,7 +263,7 @@ static int iptunnel_pmtud_check_icmp(struct sk_buff *skb, int mtu)
 	const struct icmphdr *icmph = icmp_hdr(skb);
 	const struct iphdr *iph = ip_hdr(skb);
 
-	if (mtu <= 576 || iph->frag_off != htons(IP_DF))
+	if (mtu < 576 || iph->frag_off != htons(IP_DF))
 		return 0;
 
 	if (ipv4_is_lbcast(iph->daddr)  || ipv4_is_multicast(iph->daddr) ||
@@ -359,7 +359,7 @@ static int iptunnel_pmtud_check_icmpv6(struct sk_buff *skb, int mtu)
 	__be16 frag_off;
 	int offset;
 
-	if (mtu <= IPV6_MIN_MTU)
+	if (mtu < IPV6_MIN_MTU)
 		return 0;
 
 	if (stype == IPV6_ADDR_ANY || stype == IPV6_ADDR_MULTICAST ||
@@ -429,36 +429,6 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst,
 }
 EXPORT_SYMBOL(skb_tunnel_check_pmtu);
 
-/* Often modified stats are per cpu, other are shared (netdev->stats) */
-void ip_tunnel_get_stats64(struct net_device *dev,
-			   struct rtnl_link_stats64 *tot)
-{
-	int i;
-
-	netdev_stats_to_stats64(tot, &dev->stats);
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_sw_netstats *tstats =
-						   per_cpu_ptr(dev->tstats, i);
-		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
-		unsigned int start;
-
-		do {
-			start = u64_stats_fetch_begin_irq(&tstats->syncp);
-			rx_packets = tstats->rx_packets;
-			tx_packets = tstats->tx_packets;
-			rx_bytes = tstats->rx_bytes;
-			tx_bytes = tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
-
-		tot->rx_packets += rx_packets;
-		tot->tx_packets += tx_packets;
-		tot->rx_bytes   += rx_bytes;
-		tot->tx_bytes   += tx_bytes;
-	}
-}
-EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64);
-
 static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = {
 	[LWTUNNEL_IP_UNSPEC]	= { .strict_start_type = LWTUNNEL_IP_OPTS },
 	[LWTUNNEL_IP_ID]	= { .type = NLA_U64 },
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index f687abb069fa..abc171e79d3e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -95,7 +95,6 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 {
 	unsigned short family;
 	struct net_device *dev;
-	struct pcpu_sw_netstats *tstats;
 	struct xfrm_state *x;
 	const struct xfrm_mode *inner_mode;
 	struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
@@ -138,13 +137,7 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
 
 	skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
 	skb->dev = dev;
-
-	tstats = this_cpu_ptr(dev->tstats);
-
-	u64_stats_update_begin(&tstats->syncp);
-	tstats->rx_packets++;
-	tstats->rx_bytes += skb->len;
-	u64_stats_update_end(&tstats->syncp);
+	dev_sw_netstats_rx_add(dev, skb->len);
 
 	return 0;
 }
@@ -411,7 +404,7 @@ static const struct net_device_ops vti_netdev_ops = {
 	.ndo_start_xmit	= vti_tunnel_xmit,
 	.ndo_do_ioctl	= ip_tunnel_ioctl,
 	.ndo_change_mtu	= ip_tunnel_change_mtu,
-	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_stats64 = dev_get_tstats64,
 	.ndo_get_iflink = ip_tunnel_get_iflink,
 	.ndo_tunnel_ctl	= vti_tunnel_ctl,
 };
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 561f15b5a944..3cd13e1bc6a7 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1441,7 +1441,7 @@ static int __init ip_auto_config(void)
 	int retries = CONF_OPEN_RETRIES;
 #endif
 	int err;
-	unsigned int i;
+	unsigned int i, count;
 
 	/* Initialise all name servers and NTP servers to NONE (but only if the
 	 * "ip=" or "nfsaddrs=" kernel command line parameters weren't decoded,
@@ -1575,7 +1575,7 @@ static int __init ip_auto_config(void)
 	if (ic_dev_mtu)
 		pr_cont(", mtu=%d", ic_dev_mtu);
 	/* Name servers (if any): */
-	for (i = 0; i < CONF_NAMESERVERS_MAX; i++) {
+	for (i = 0, count = 0; i < CONF_NAMESERVERS_MAX; i++) {
 		if (ic_nameservers[i] != NONE) {
 			if (i == 0)
 				pr_info("     nameserver%u=%pI4",
@@ -1583,12 +1583,14 @@ static int __init ip_auto_config(void)
 			else
 				pr_cont(", nameserver%u=%pI4",
 					i, &ic_nameservers[i]);
+
+			count++;
 		}
-		if (i + 1 == CONF_NAMESERVERS_MAX)
+		if ((i + 1 == CONF_NAMESERVERS_MAX) && count > 0)
 			pr_cont("\n");
 	}
 	/* NTP servers (if any): */
-	for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) {
+	for (i = 0, count = 0; i < CONF_NTP_SERVERS_MAX; i++) {
 		if (ic_ntp_servers[i] != NONE) {
 			if (i == 0)
 				pr_info("     ntpserver%u=%pI4",
@@ -1596,8 +1598,10 @@ static int __init ip_auto_config(void)
 			else
 				pr_cont(", ntpserver%u=%pI4",
 					i, &ic_ntp_servers[i]);
+
+			count++;
 		}
-		if (i + 1 == CONF_NTP_SERVERS_MAX)
+		if ((i + 1 == CONF_NTP_SERVERS_MAX) && count > 0)
 			pr_cont("\n");
 	}
 #endif /* !SILENT */
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 75d35e76bec2..d5bfa087c23a 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -347,7 +347,7 @@ static const struct net_device_ops ipip_netdev_ops = {
 	.ndo_start_xmit	= ipip_tunnel_xmit,
 	.ndo_do_ioctl	= ip_tunnel_ioctl,
 	.ndo_change_mtu = ip_tunnel_change_mtu,
-	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_stats64 = dev_get_tstats64,
 	.ndo_get_iflink = ip_tunnel_get_iflink,
 	.ndo_tunnel_ctl	= ipip_tunnel_ctl,
 };
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 876fd6ff1ff9..939792a38814 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1038,10 +1038,13 @@ static int ipmr_cache_report(struct mr_table *mrt,
 		memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr));
 		msg->im_msgtype = assert;
 		msg->im_mbz = 0;
-		if (assert == IGMPMSG_WRVIFWHOLE)
+		if (assert == IGMPMSG_WRVIFWHOLE) {
 			msg->im_vif = vifi;
-		else
+			msg->im_vif_hi = vifi >> 8;
+		} else {
 			msg->im_vif = mrt->mroute_reg_vif_num;
+			msg->im_vif_hi = mrt->mroute_reg_vif_num >> 8;
+		}
 		ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2;
 		ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) +
 					     sizeof(struct iphdr));
@@ -1054,6 +1057,7 @@ static int ipmr_cache_report(struct mr_table *mrt,
 		ip_hdr(skb)->protocol = 0;
 		msg = (struct igmpmsg *)skb_network_header(skb);
 		msg->im_vif = vifi;
+		msg->im_vif_hi = vifi >> 8;
 		skb_dst_set(skb, dst_clone(skb_dst(pkt)));
 		/* Add our header */
 		igmp = skb_put(skb, sizeof(struct igmphdr));
@@ -2396,6 +2400,7 @@ static size_t igmpmsg_netlink_msgsize(size_t payloadlen)
 		+ nla_total_size(4)	/* IPMRA_CREPORT_VIF_ID */
 		+ nla_total_size(4)	/* IPMRA_CREPORT_SRC_ADDR */
 		+ nla_total_size(4)	/* IPMRA_CREPORT_DST_ADDR */
+		+ nla_total_size(4)	/* IPMRA_CREPORT_TABLE */
 					/* IPMRA_CREPORT_PKT */
 		+ nla_total_size(payloadlen)
 		;
@@ -2427,11 +2432,12 @@ static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt)
 	rtgenm = nlmsg_data(nlh);
 	rtgenm->rtgen_family = RTNL_FAMILY_IPMR;
 	if (nla_put_u8(skb, IPMRA_CREPORT_MSGTYPE, msg->im_msgtype) ||
-	    nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif) ||
+	    nla_put_u32(skb, IPMRA_CREPORT_VIF_ID, msg->im_vif | (msg->im_vif_hi << 8)) ||
 	    nla_put_in_addr(skb, IPMRA_CREPORT_SRC_ADDR,
 			    msg->im_src.s_addr) ||
 	    nla_put_in_addr(skb, IPMRA_CREPORT_DST_ADDR,
-			    msg->im_dst.s_addr))
+			    msg->im_dst.s_addr) ||
+	    nla_put_u32(skb, IPMRA_CREPORT_TABLE, mrt->id))
 		goto nla_put_failure;
 
 	nla = nla_reserve(skb, IPMRA_CREPORT_PKT, payloadlen);
diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
index 3205d5f7c8c9..25ea6ac44db9 100644
--- a/net/ipv4/metrics.c
+++ b/net/ipv4/metrics.c
@@ -31,7 +31,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
 		if (type == RTAX_CC_ALGO) {
 			char tmp[TCP_CA_NAME_MAX];
 
-			nla_strlcpy(tmp, nla, sizeof(tmp));
+			nla_strscpy(tmp, nla, sizeof(tmp));
 			val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
 			if (val == TCP_CA_UNSPEC) {
 				NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm");
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index a058213b77a7..7c841037c533 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -17,17 +17,19 @@
 #include <net/netfilter/nf_queue.h>
 
 /* route_me_harder function, used by iptable_nat, iptable_mangle + ip_queue */
-int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_type)
+int ip_route_me_harder(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int addr_type)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 	struct flowi4 fl4 = {};
 	__be32 saddr = iph->saddr;
-	const struct sock *sk = skb_to_full_sk(skb);
-	__u8 flags = sk ? inet_sk_flowi_flags(sk) : 0;
+	__u8 flags;
 	struct net_device *dev = skb_dst(skb)->dev;
 	unsigned int hh_len;
 
+	sk = sk_to_full_sk(sk);
+	flags = sk ? inet_sk_flowi_flags(sk) : 0;
+
 	if (addr_type == RTN_UNSPEC)
 		addr_type = inet_addr_type_dev_table(net, dev, saddr);
 	if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST)
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index d1e04d2b5170..c576a63d09db 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -203,7 +203,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = READ_ONCE(table->private); /* Address dependency. */
+	private = rcu_access_pointer(table->private);
 	cpu     = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct arpt_entry **)private->jumpstack[cpu];
@@ -649,7 +649,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	 * (other than comefrom, which userspace doesn't care
@@ -673,7 +673,7 @@ static int copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	const struct arpt_entry *e;
 	struct xt_counters *counters;
-	struct xt_table_info *private = table->private;
+	struct xt_table_info *private = xt_table_get_private_protected(table);
 	int ret = 0;
 	void *loc_cpu_entry;
 
@@ -807,7 +807,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 	t = xt_request_find_table_lock(net, NFPROTO_ARP, name);
 	if (!IS_ERR(t)) {
 		struct arpt_getinfo info;
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
@@ -860,7 +860,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr,
 
 	t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
@@ -1017,7 +1017,7 @@ static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 	}
 
 	local_bh_disable();
-	private = t->private;
+	private = xt_table_get_private_protected(t);
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
@@ -1330,7 +1330,7 @@ static int compat_copy_entries_to_user(unsigned int total_size,
 				       void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
@@ -1379,7 +1379,7 @@ static int compat_get_entries(struct net *net,
 	xt_compat_lock(NFPROTO_ARP);
 	t = xt_find_table_lock(net, NFPROTO_ARP, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 		struct xt_table_info info;
 
 		ret = compat_table_info(private, &info);
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index f15bc21d7301..e8f6f9d86237 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -258,7 +258,7 @@ ipt_do_table(struct sk_buff *skb,
 	WARN_ON(!(table->valid_hooks & (1 << hook)));
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = READ_ONCE(table->private); /* Address dependency. */
+	private = rcu_access_pointer(table->private);
 	cpu        = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct ipt_entry **)private->jumpstack[cpu];
@@ -791,7 +791,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
@@ -815,7 +815,7 @@ copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	const struct ipt_entry *e;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	int ret = 0;
 	const void *loc_cpu_entry;
 
@@ -964,7 +964,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 	t = xt_request_find_table_lock(net, AF_INET, name);
 	if (!IS_ERR(t)) {
 		struct ipt_getinfo info;
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
@@ -1018,7 +1018,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr,
 
 	t = xt_find_table_lock(net, AF_INET, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
 						   t, uptr->entrytable);
@@ -1173,7 +1173,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 	}
 
 	local_bh_disable();
-	private = t->private;
+	private = xt_table_get_private_protected(t);
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
@@ -1543,7 +1543,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
 			    void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
@@ -1589,7 +1589,7 @@ compat_get_entries(struct net *net, struct compat_ipt_get_entries __user *uptr,
 	xt_compat_lock(AF_INET);
 	t = xt_find_table_lock(net, AF_INET, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 		struct xt_table_info info;
 		ret = compat_table_info(private, &info);
 		if (!ret && get.size == info.size)
diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c
index e16b98ee6266..4b8840734762 100644
--- a/net/ipv4/netfilter/ipt_REJECT.c
+++ b/net/ipv4/netfilter/ipt_REJECT.c
@@ -56,7 +56,8 @@ reject_tg(struct sk_buff *skb, const struct xt_action_param *par)
 		nf_send_unreach(skb, ICMP_PKT_FILTERED, hook);
 		break;
 	case IPT_TCP_RESET:
-		nf_send_reset(xt_net(par), skb, hook);
+		nf_send_reset(xt_net(par), par->state->sk, skb, hook);
+		break;
 	case IPT_ICMP_ECHOREPLY:
 		/* Doesn't happen. */
 		break;
diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c
index cc23f1ce239c..8cd3224d913e 100644
--- a/net/ipv4/netfilter/ipt_rpfilter.c
+++ b/net/ipv4/netfilter/ipt_rpfilter.c
@@ -76,7 +76,7 @@ static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	flow.daddr = iph->saddr;
 	flow.saddr = rpfilter_get_saddr(iph->daddr);
 	flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
-	flow.flowi4_tos = RT_TOS(iph->tos);
+	flow.flowi4_tos = iph->tos & IPTOS_RT_MASK;
 	flow.flowi4_scope = RT_SCOPE_UNIVERSE;
 	flow.flowi4_oif = l3mdev_master_ifindex_rcu(xt_in(par));
 
diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c
index f703a717ab1d..833079589273 100644
--- a/net/ipv4/netfilter/iptable_mangle.c
+++ b/net/ipv4/netfilter/iptable_mangle.c
@@ -62,7 +62,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
 		    iph->daddr != daddr ||
 		    skb->mark != mark ||
 		    iph->tos != tos) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
diff --git a/net/ipv4/netfilter/nf_log_arp.c b/net/ipv4/netfilter/nf_log_arp.c
index 7a83f881efa9..136030ad2e54 100644
--- a/net/ipv4/netfilter/nf_log_arp.c
+++ b/net/ipv4/netfilter/nf_log_arp.c
@@ -43,16 +43,31 @@ static void dump_arp_packet(struct nf_log_buf *m,
 			    const struct nf_loginfo *info,
 			    const struct sk_buff *skb, unsigned int nhoff)
 {
-	const struct arphdr *ah;
-	struct arphdr _arph;
 	const struct arppayload *ap;
 	struct arppayload _arpp;
+	const struct arphdr *ah;
+	unsigned int logflags;
+	struct arphdr _arph;
 
 	ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph);
 	if (ah == NULL) {
 		nf_log_buf_add(m, "TRUNCATED");
 		return;
 	}
+
+	if (info->type == NF_LOG_TYPE_LOG)
+		logflags = info->u.log.logflags;
+	else
+		logflags = NF_LOG_DEFAULT_MASK;
+
+	if (logflags & NF_LOG_MACDECODE) {
+		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ",
+			       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest);
+		nf_log_dump_vlan(m, skb);
+		nf_log_buf_add(m, "MACPROTO=%04x ",
+			       ntohs(eth_hdr(skb)->h_proto));
+	}
+
 	nf_log_buf_add(m, "ARP HTYPE=%d PTYPE=0x%04x OPCODE=%d",
 		       ntohs(ah->ar_hrd), ntohs(ah->ar_pro), ntohs(ah->ar_op));
 
diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index 0c72156130b6..d07583fac8f8 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/net/ipv4/netfilter/nf_log_ipv4.c
@@ -284,8 +284,10 @@ static void dump_ipv4_mac_header(struct nf_log_buf *m,
 
 	switch (dev->type) {
 	case ARPHRD_ETHER:
-		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ",
-			       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
+		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ",
+			       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest);
+		nf_log_dump_vlan(m, skb);
+		nf_log_buf_add(m, "MACPROTO=%04x ",
 			       ntohs(eth_hdr(skb)->h_proto));
 		return;
 	default:
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 9dcfa4e461b6..4eed5afca392 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -12,6 +12,128 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_bridge.h>
 
+static int nf_reject_iphdr_validate(struct sk_buff *skb)
+{
+	struct iphdr *iph;
+	u32 len;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		return 0;
+
+	iph = ip_hdr(skb);
+	if (iph->ihl < 5 || iph->version != 4)
+		return 0;
+
+	len = ntohs(iph->tot_len);
+	if (skb->len < len)
+		return 0;
+	else if (len < (iph->ihl*4))
+		return 0;
+
+	if (!pskb_may_pull(skb, iph->ihl*4))
+		return 0;
+
+	return 1;
+}
+
+struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net,
+					   struct sk_buff *oldskb,
+					   const struct net_device *dev,
+					   int hook)
+{
+	const struct tcphdr *oth;
+	struct sk_buff *nskb;
+	struct iphdr *niph;
+	struct tcphdr _oth;
+
+	if (!nf_reject_iphdr_validate(oldskb))
+		return NULL;
+
+	oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
+	if (!oth)
+		return NULL;
+
+	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
+			 LL_MAX_HEADER, GFP_ATOMIC);
+	if (!nskb)
+		return NULL;
+
+	nskb->dev = (struct net_device *)dev;
+
+	skb_reserve(nskb, LL_MAX_HEADER);
+	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
+				   net->ipv4.sysctl_ip_default_ttl);
+	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
+	niph->tot_len = htons(nskb->len);
+	ip_send_check(niph);
+
+	return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v4_tcp_reset);
+
+struct sk_buff *nf_reject_skb_v4_unreach(struct net *net,
+					 struct sk_buff *oldskb,
+					 const struct net_device *dev,
+					 int hook, u8 code)
+{
+	struct sk_buff *nskb;
+	struct iphdr *niph;
+	struct icmphdr *icmph;
+	unsigned int len;
+	__wsum csum;
+	u8 proto;
+
+	if (!nf_reject_iphdr_validate(oldskb))
+		return NULL;
+
+	/* IP header checks: fragment. */
+	if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET))
+		return NULL;
+
+	/* RFC says return as much as we can without exceeding 576 bytes. */
+	len = min_t(unsigned int, 536, oldskb->len);
+
+	if (!pskb_may_pull(oldskb, len))
+		return NULL;
+
+	if (pskb_trim_rcsum(oldskb, ntohs(ip_hdr(oldskb)->tot_len)))
+		return NULL;
+
+	proto = ip_hdr(oldskb)->protocol;
+
+	if (!skb_csum_unnecessary(oldskb) &&
+	    nf_reject_verify_csum(proto) &&
+	    nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), proto))
+		return NULL;
+
+	nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct icmphdr) +
+			 LL_MAX_HEADER + len, GFP_ATOMIC);
+	if (!nskb)
+		return NULL;
+
+	nskb->dev = (struct net_device *)dev;
+
+	skb_reserve(nskb, LL_MAX_HEADER);
+	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP,
+				   net->ipv4.sysctl_ip_default_ttl);
+
+	skb_reset_transport_header(nskb);
+	icmph = skb_put_zero(nskb, sizeof(struct icmphdr));
+	icmph->type     = ICMP_DEST_UNREACH;
+	icmph->code	= code;
+
+	skb_put_data(nskb, skb_network_header(oldskb), len);
+
+	csum = csum_partial((void *)icmph, len + sizeof(struct icmphdr), 0);
+	icmph->checksum = csum_fold(csum);
+
+	niph->tot_len	= htons(nskb->len);
+	ip_send_check(niph);
+
+	return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v4_unreach);
+
 const struct tcphdr *nf_reject_ip_tcphdr_get(struct sk_buff *oldskb,
 					     struct tcphdr *_oth, int hook)
 {
@@ -112,7 +234,8 @@ static int nf_reject_fill_skb_dst(struct sk_buff *skb_in)
 }
 
 /* Send RST reply */
-void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
+void nf_send_reset(struct net *net, struct sock *sk, struct sk_buff *oldskb,
+		   int hook)
 {
 	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
@@ -124,7 +247,8 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	if (!oth)
 		return;
 
-	if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(oldskb))
+	if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
+	    nf_reject_fill_skb_dst(oldskb) < 0)
 		return;
 
 	if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
@@ -144,8 +268,7 @@ void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
 				   ip4_dst_hoplimit(skb_dst(nskb)));
 	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
-
-	if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+	if (ip_route_me_harder(net, sk, nskb, RTN_UNSPEC))
 		goto free_nskb;
 
 	niph = ip_hdr(nskb);
@@ -193,7 +316,8 @@ void nf_send_unreach(struct sk_buff *skb_in, int code, int hook)
 	if (iph->frag_off & htons(IP_OFFSET))
 		return;
 
-	if (hook == NF_INET_PRE_ROUTING && nf_reject_fill_skb_dst(skb_in))
+	if ((hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) &&
+	    nf_reject_fill_skb_dst(skb_in) < 0)
 		return;
 
 	if (skb_csum_unnecessary(skb_in) || !nf_reject_verify_csum(proto)) {
diff --git a/net/ipv4/netfilter/nft_reject_ipv4.c b/net/ipv4/netfilter/nft_reject_ipv4.c
index e408f813f5d8..ff437e4ed6db 100644
--- a/net/ipv4/netfilter/nft_reject_ipv4.c
+++ b/net/ipv4/netfilter/nft_reject_ipv4.c
@@ -27,7 +27,8 @@ static void nft_reject_ipv4_eval(const struct nft_expr *expr,
 		nf_send_unreach(pkt->skb, priv->icmp_code, nft_hook(pkt));
 		break;
 	case NFT_REJECT_TCP_RST:
-		nf_send_reset(nft_net(pkt), pkt->skb, nft_hook(pkt));
+		nf_send_reset(nft_net(pkt), pkt->xt.state->sk, pkt->skb,
+			      nft_hook(pkt));
 		break;
 	default:
 		break;
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 134e92382275..e53e43aef785 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -36,14 +36,145 @@ static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = {
 	[NHA_FDB]		= { .type = NLA_FLAG },
 };
 
+static bool nexthop_notifiers_is_empty(struct net *net)
+{
+	return !net->nexthop.notifier_chain.head;
+}
+
+static void
+__nh_notifier_single_info_init(struct nh_notifier_single_info *nh_info,
+			       const struct nexthop *nh)
+{
+	struct nh_info *nhi = rtnl_dereference(nh->nh_info);
+
+	nh_info->dev = nhi->fib_nhc.nhc_dev;
+	nh_info->gw_family = nhi->fib_nhc.nhc_gw_family;
+	if (nh_info->gw_family == AF_INET)
+		nh_info->ipv4 = nhi->fib_nhc.nhc_gw.ipv4;
+	else if (nh_info->gw_family == AF_INET6)
+		nh_info->ipv6 = nhi->fib_nhc.nhc_gw.ipv6;
+
+	nh_info->is_reject = nhi->reject_nh;
+	nh_info->is_fdb = nhi->fdb_nh;
+	nh_info->has_encap = !!nhi->fib_nhc.nhc_lwtstate;
+}
+
+static int nh_notifier_single_info_init(struct nh_notifier_info *info,
+					const struct nexthop *nh)
+{
+	info->nh = kzalloc(sizeof(*info->nh), GFP_KERNEL);
+	if (!info->nh)
+		return -ENOMEM;
+
+	__nh_notifier_single_info_init(info->nh, nh);
+
+	return 0;
+}
+
+static void nh_notifier_single_info_fini(struct nh_notifier_info *info)
+{
+	kfree(info->nh);
+}
+
+static int nh_notifier_grp_info_init(struct nh_notifier_info *info,
+				     const struct nexthop *nh)
+{
+	struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
+	u16 num_nh = nhg->num_nh;
+	int i;
+
+	info->nh_grp = kzalloc(struct_size(info->nh_grp, nh_entries, num_nh),
+			       GFP_KERNEL);
+	if (!info->nh_grp)
+		return -ENOMEM;
+
+	info->nh_grp->num_nh = num_nh;
+	info->nh_grp->is_fdb = nhg->fdb_nh;
+
+	for (i = 0; i < num_nh; i++) {
+		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
+
+		info->nh_grp->nh_entries[i].id = nhge->nh->id;
+		info->nh_grp->nh_entries[i].weight = nhge->weight;
+		__nh_notifier_single_info_init(&info->nh_grp->nh_entries[i].nh,
+					       nhge->nh);
+	}
+
+	return 0;
+}
+
+static void nh_notifier_grp_info_fini(struct nh_notifier_info *info)
+{
+	kfree(info->nh_grp);
+}
+
+static int nh_notifier_info_init(struct nh_notifier_info *info,
+				 const struct nexthop *nh)
+{
+	info->id = nh->id;
+	info->is_grp = nh->is_group;
+
+	if (info->is_grp)
+		return nh_notifier_grp_info_init(info, nh);
+	else
+		return nh_notifier_single_info_init(info, nh);
+}
+
+static void nh_notifier_info_fini(struct nh_notifier_info *info)
+{
+	if (info->is_grp)
+		nh_notifier_grp_info_fini(info);
+	else
+		nh_notifier_single_info_fini(info);
+}
+
 static int call_nexthop_notifiers(struct net *net,
 				  enum nexthop_event_type event_type,
-				  struct nexthop *nh)
+				  struct nexthop *nh,
+				  struct netlink_ext_ack *extack)
+{
+	struct nh_notifier_info info = {
+		.net = net,
+		.extack = extack,
+	};
+	int err;
+
+	ASSERT_RTNL();
+
+	if (nexthop_notifiers_is_empty(net))
+		return 0;
+
+	err = nh_notifier_info_init(&info, nh);
+	if (err) {
+		NL_SET_ERR_MSG(extack, "Failed to initialize nexthop notifier info");
+		return err;
+	}
+
+	err = blocking_notifier_call_chain(&net->nexthop.notifier_chain,
+					   event_type, &info);
+	nh_notifier_info_fini(&info);
+
+	return notifier_to_errno(err);
+}
+
+static int call_nexthop_notifier(struct notifier_block *nb, struct net *net,
+				 enum nexthop_event_type event_type,
+				 struct nexthop *nh,
+				 struct netlink_ext_ack *extack)
 {
+	struct nh_notifier_info info = {
+		.net = net,
+		.extack = extack,
+	};
 	int err;
 
-	err = atomic_notifier_call_chain(&net->nexthop.notifier_chain,
-					 event_type, nh);
+	err = nh_notifier_info_init(&info, nh);
+	if (err)
+		return err;
+
+	err = nb->notifier_call(nb, event_type, &info);
+	nh_notifier_info_fini(&info);
+
 	return notifier_to_errno(err);
 }
 
@@ -133,12 +264,9 @@ static struct nexthop *nexthop_alloc(void)
 
 static struct nh_group *nexthop_grp_alloc(u16 num_nh)
 {
-	size_t sz = offsetof(struct nexthop, nh_grp)
-		    + sizeof(struct nh_group)
-		    + sizeof(struct nh_grp_entry) * num_nh;
 	struct nh_group *nhg;
 
-	nhg = kzalloc(sz, GFP_KERNEL);
+	nhg = kzalloc(struct_size(nhg, nh_entries, num_nh), GFP_KERNEL);
 	if (nhg)
 		nhg->num_nh = num_nh;
 
@@ -279,7 +407,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh,
 	case AF_INET:
 		fib_nh = &nhi->fib_nh;
 		if (fib_nh->fib_nh_gw_family &&
-		    nla_put_u32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4))
+		    nla_put_be32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4))
 			goto nla_put_failure;
 		break;
 
@@ -499,7 +627,7 @@ static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
 	for (i = NHA_GROUP_TYPE + 1; i < __NHA_MAX; ++i) {
 		if (!tb[i])
 			continue;
-		if (tb[NHA_FDB])
+		if (i == NHA_FDB)
 			continue;
 		NL_SET_ERR_MSG(extack,
 			       "No other attributes can be set in nexthop groups");
@@ -785,9 +913,10 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
 {
 	struct nh_grp_entry *nhges, *new_nhges;
 	struct nexthop *nhp = nhge->nh_parent;
+	struct netlink_ext_ack extack;
 	struct nexthop *nh = nhge->nh;
 	struct nh_group *nhg, *newg;
-	int i, j;
+	int i, j, err;
 
 	WARN_ON(!nh);
 
@@ -800,7 +929,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
 		return;
 	}
 
-	newg->has_v4 = nhg->has_v4;
+	newg->has_v4 = false;
 	newg->mpath = nhg->mpath;
 	newg->fdb_nh = nhg->fdb_nh;
 	newg->num_nh = nhg->num_nh;
@@ -809,12 +938,18 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
 	nhges = nhg->nh_entries;
 	new_nhges = newg->nh_entries;
 	for (i = 0, j = 0; i < nhg->num_nh; ++i) {
+		struct nh_info *nhi;
+
 		/* current nexthop getting removed */
 		if (nhg->nh_entries[i].nh == nh) {
 			newg->num_nh--;
 			continue;
 		}
 
+		nhi = rtnl_dereference(nhges[i].nh->nh_info);
+		if (nhi->family == AF_INET)
+			newg->has_v4 = true;
+
 		list_del(&nhges[i].nh_list);
 		new_nhges[j].nh_parent = nhges[i].nh_parent;
 		new_nhges[j].nh = nhges[i].nh;
@@ -829,6 +964,10 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
 	list_del(&nhge->nh_list);
 	nexthop_put(nhge->nh);
 
+	err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, &extack);
+	if (err)
+		pr_err("%s\n", extack._msg);
+
 	if (nlinfo)
 		nexthop_notify(RTM_NEWNEXTHOP, nhp, nlinfo);
 }
@@ -842,7 +981,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
 		remove_nh_grp_entry(net, nhge, nlinfo);
 
 	/* make sure all see the newly published array before releasing rtnl */
-	synchronize_rcu();
+	synchronize_net();
 }
 
 static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
@@ -867,8 +1006,6 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 	bool do_flush = false;
 	struct fib_info *fi;
 
-	call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh);
-
 	list_for_each_entry(fi, &nh->fi_list, nh_list) {
 		fi->fib_flags |= RTNH_F_DEAD;
 		do_flush = true;
@@ -906,6 +1043,8 @@ static void __remove_nexthop(struct net *net, struct nexthop *nh,
 static void remove_nexthop(struct net *net, struct nexthop *nh,
 			   struct nl_info *nlinfo)
 {
+	call_nexthop_notifiers(net, NEXTHOP_EVENT_DEL, nh, NULL);
+
 	/* remove from the tree */
 	rb_erase(&nh->rb_node, &net->nexthop.rb_root);
 
@@ -937,13 +1076,17 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old,
 			       struct netlink_ext_ack *extack)
 {
 	struct nh_group *oldg, *newg;
-	int i;
+	int i, err;
 
 	if (!new->is_group) {
 		NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop.");
 		return -EINVAL;
 	}
 
+	err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack);
+	if (err)
+		return err;
+
 	oldg = rtnl_dereference(old->nh_grp);
 	newg = rtnl_dereference(new->nh_grp);
 
@@ -961,30 +1104,100 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old,
 	return 0;
 }
 
+static void nh_group_v4_update(struct nh_group *nhg)
+{
+	struct nh_grp_entry *nhges;
+	bool has_v4 = false;
+	int i;
+
+	nhges = nhg->nh_entries;
+	for (i = 0; i < nhg->num_nh; i++) {
+		struct nh_info *nhi;
+
+		nhi = rtnl_dereference(nhges[i].nh->nh_info);
+		if (nhi->family == AF_INET)
+			has_v4 = true;
+	}
+	nhg->has_v4 = has_v4;
+}
+
 static int replace_nexthop_single(struct net *net, struct nexthop *old,
 				  struct nexthop *new,
 				  struct netlink_ext_ack *extack)
 {
+	u8 old_protocol, old_nh_flags;
 	struct nh_info *oldi, *newi;
+	struct nh_grp_entry *nhge;
+	int err;
 
 	if (new->is_group) {
 		NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group.");
 		return -EINVAL;
 	}
 
+	err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new, extack);
+	if (err)
+		return err;
+
+	/* Hardware flags were set on 'old' as 'new' is not in the red-black
+	 * tree. Therefore, inherit the flags from 'old' to 'new'.
+	 */
+	new->nh_flags |= old->nh_flags & (RTNH_F_OFFLOAD | RTNH_F_TRAP);
+
 	oldi = rtnl_dereference(old->nh_info);
 	newi = rtnl_dereference(new->nh_info);
 
 	newi->nh_parent = old;
 	oldi->nh_parent = new;
 
+	old_protocol = old->protocol;
+	old_nh_flags = old->nh_flags;
+
 	old->protocol = new->protocol;
 	old->nh_flags = new->nh_flags;
 
 	rcu_assign_pointer(old->nh_info, newi);
 	rcu_assign_pointer(new->nh_info, oldi);
 
+	/* Send a replace notification for all the groups using the nexthop. */
+	list_for_each_entry(nhge, &old->grp_list, nh_list) {
+		struct nexthop *nhp = nhge->nh_parent;
+
+		err = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp,
+					     extack);
+		if (err)
+			goto err_notify;
+	}
+
+	/* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially
+	 * update IPv4 indication in all the groups using the nexthop.
+	 */
+	if (oldi->family == AF_INET && newi->family == AF_INET6) {
+		list_for_each_entry(nhge, &old->grp_list, nh_list) {
+			struct nexthop *nhp = nhge->nh_parent;
+			struct nh_group *nhg;
+
+			nhg = rtnl_dereference(nhp->nh_grp);
+			nh_group_v4_update(nhg);
+		}
+	}
+
 	return 0;
+
+err_notify:
+	rcu_assign_pointer(new->nh_info, newi);
+	rcu_assign_pointer(old->nh_info, oldi);
+	old->nh_flags = old_nh_flags;
+	old->protocol = old_protocol;
+	oldi->nh_parent = old;
+	newi->nh_parent = new;
+	list_for_each_entry_continue_reverse(nhge, &old->grp_list, nh_list) {
+		struct nexthop *nhp = nhge->nh_parent;
+
+		call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, nhp, extack);
+	}
+	call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, old, extack);
+	return err;
 }
 
 static void __nexthop_replace_notify(struct net *net, struct nexthop *nh,
@@ -1101,7 +1314,7 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh,
 	while (1) {
 		struct nexthop *nh;
 
-		next = rtnl_dereference(*pp);
+		next = *pp;
 		if (!next)
 			break;
 
@@ -1133,7 +1346,11 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh,
 
 	rb_link_node_rcu(&new_nh->rb_node, parent, pp);
 	rb_insert_color(&new_nh->rb_node, root);
-	rc = 0;
+
+	rc = call_nexthop_notifiers(net, NEXTHOP_EVENT_REPLACE, new_nh, extack);
+	if (rc)
+		rb_erase(&new_nh->rb_node, &net->nexthop.rb_root);
+
 out:
 	if (!rc) {
 		nh_base_seq_inc(net);
@@ -1242,8 +1459,10 @@ static struct nexthop *nexthop_create_group(struct net *net,
 	return nh;
 
 out_no_nh:
-	for (; i >= 0; --i)
+	for (i--; i >= 0; --i) {
+		list_del(&nhg->nh_entries[i].nh_list);
 		nexthop_put(nhg->nh_entries[i].nh);
+	}
 
 	kfree(nhg->spare);
 	kfree(nhg);
@@ -1922,19 +2141,71 @@ static struct notifier_block nh_netdev_notifier = {
 	.notifier_call = nh_netdev_event,
 };
 
-int register_nexthop_notifier(struct net *net, struct notifier_block *nb)
+static int nexthops_dump(struct net *net, struct notifier_block *nb,
+			 struct netlink_ext_ack *extack)
+{
+	struct rb_root *root = &net->nexthop.rb_root;
+	struct rb_node *node;
+	int err = 0;
+
+	for (node = rb_first(root); node; node = rb_next(node)) {
+		struct nexthop *nh;
+
+		nh = rb_entry(node, struct nexthop, rb_node);
+		err = call_nexthop_notifier(nb, net, NEXTHOP_EVENT_REPLACE, nh,
+					    extack);
+		if (err)
+			break;
+	}
+
+	return err;
+}
+
+int register_nexthop_notifier(struct net *net, struct notifier_block *nb,
+			      struct netlink_ext_ack *extack)
 {
-	return atomic_notifier_chain_register(&net->nexthop.notifier_chain, nb);
+	int err;
+
+	rtnl_lock();
+	err = nexthops_dump(net, nb, extack);
+	if (err)
+		goto unlock;
+	err = blocking_notifier_chain_register(&net->nexthop.notifier_chain,
+					       nb);
+unlock:
+	rtnl_unlock();
+	return err;
 }
 EXPORT_SYMBOL(register_nexthop_notifier);
 
 int unregister_nexthop_notifier(struct net *net, struct notifier_block *nb)
 {
-	return atomic_notifier_chain_unregister(&net->nexthop.notifier_chain,
-						nb);
+	return blocking_notifier_chain_unregister(&net->nexthop.notifier_chain,
+						  nb);
 }
 EXPORT_SYMBOL(unregister_nexthop_notifier);
 
+void nexthop_set_hw_flags(struct net *net, u32 id, bool offload, bool trap)
+{
+	struct nexthop *nexthop;
+
+	rcu_read_lock();
+
+	nexthop = nexthop_find_by_id(net, id);
+	if (!nexthop)
+		goto out;
+
+	nexthop->nh_flags &= ~(RTNH_F_OFFLOAD | RTNH_F_TRAP);
+	if (offload)
+		nexthop->nh_flags |= RTNH_F_OFFLOAD;
+	if (trap)
+		nexthop->nh_flags |= RTNH_F_TRAP;
+
+out:
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(nexthop_set_hw_flags);
+
 static void __net_exit nexthop_net_exit(struct net *net)
 {
 	rtnl_lock();
@@ -1951,7 +2222,7 @@ static int __net_init nexthop_net_init(struct net *net)
 	net->nexthop.devhash = kzalloc(sz, GFP_KERNEL);
 	if (!net->nexthop.devhash)
 		return -ENOMEM;
-	ATOMIC_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain);
+	BLOCKING_INIT_NOTIFIER_HEAD(&net->nexthop.notifier_chain);
 
 	return 0;
 }
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index df6fbefe44d4..8b943f85fff9 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -293,7 +293,8 @@ EXPORT_SYMBOL_GPL(ping_close);
 
 /* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */
 static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
-				struct sockaddr *uaddr, int addr_len) {
+				struct sockaddr *uaddr, int addr_len)
+{
 	struct net *net = sock_net(sk);
 	if (sk->sk_family == AF_INET) {
 		struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
@@ -310,10 +311,10 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
 			 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
 
-		chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
-
 		if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
 			chk_addr_ret = RTN_LOCAL;
+		else
+			chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
 
 		if ((!inet_can_nonlocal_bind(net, isk) &&
 		     chk_addr_ret != RTN_LOCAL) ||
@@ -383,20 +384,6 @@ static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
 	}
 }
 
-static void ping_clear_saddr(struct sock *sk, int dif)
-{
-	sk->sk_bound_dev_if = dif;
-	if (sk->sk_family == AF_INET) {
-		struct inet_sock *isk = inet_sk(sk);
-		isk->inet_rcv_saddr = isk->inet_saddr = 0;
-#if IS_ENABLED(CONFIG_IPV6)
-	} else if (sk->sk_family == AF_INET6) {
-		struct ipv6_pinfo *np = inet6_sk(sk);
-		memset(&sk->sk_v6_rcv_saddr, 0, sizeof(sk->sk_v6_rcv_saddr));
-		memset(&np->saddr, 0, sizeof(np->saddr));
-#endif
-	}
-}
 /*
  * We need our own bind because there are no privileged id's == local ports.
  * Moreover, we don't allow binding to multi- and broadcast addresses.
@@ -420,12 +407,13 @@ int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		goto out;
 
 	err = -EADDRINUSE;
-	ping_set_saddr(sk, uaddr);
 	snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port);
 	if (ping_get_port(sk, snum) != 0) {
-		ping_clear_saddr(sk, dif);
+		/* Restore possibly modified sk->sk_bound_dev_if by ping_check_bind_addr(). */
+		sk->sk_bound_dev_if = dif;
 		goto out;
 	}
+	ping_set_saddr(sk, uaddr);
 
 	pr_debug("after bind(): num = %hu, dif = %d\n",
 		 isk->inet_num,
@@ -647,7 +635,8 @@ static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
 }
 
 int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
-			void *user_icmph, size_t icmph_len) {
+			void *user_icmph, size_t icmph_len)
+{
 	u8 type, code;
 
 	if (len > 0xFFFF)
@@ -789,7 +778,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl4.fl4_icmp_type = user_icmph.type;
 	fl4.fl4_icmp_code = user_icmph.code;
 
-	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+	security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8d5e1695b9aa..63cd370ea29d 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -167,6 +167,7 @@ static const struct snmp_mib snmp4_udp_list[] = {
 	SNMP_MIB_ITEM("SndbufErrors", UDP_MIB_SNDBUFERRORS),
 	SNMP_MIB_ITEM("InCsumErrors", UDP_MIB_CSUMERRORS),
 	SNMP_MIB_ITEM("IgnoredMulti", UDP_MIB_IGNOREDMULTI),
+	SNMP_MIB_ITEM("MemErrors", UDP_MIB_MEMERRORS),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 407956be7deb..50a73178d63a 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -260,11 +260,12 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info)
 		err = EHOSTUNREACH;
 		if (code > NR_ICMP_UNREACH)
 			break;
-		err = icmp_err_convert[code].errno;
-		harderr = icmp_err_convert[code].fatal;
 		if (code == ICMP_FRAG_NEEDED) {
 			harderr = inet->pmtudisc != IP_PMTUDISC_DONT;
 			err = EMSGSIZE;
+		} else {
+			err = icmp_err_convert[code].errno;
+			harderr = icmp_err_convert[code].fatal;
 		}
 	}
 
@@ -478,7 +479,7 @@ static int raw_getfrag(void *from, char *to, int offset, int len, int odd,
 			skb->csum = csum_block_add(
 				skb->csum,
 				csum_partial_copy_nocheck(rfv->hdr.c + offset,
-							  to, copy, 0),
+							  to, copy),
 				odd);
 
 		odd = 0;
@@ -639,7 +640,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			goto done;
 	}
 
-	security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+	security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_flow(net, &fl4, sk);
 	if (IS_ERR(rt)) {
 		err = PTR_ERR(rt);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 58642b29a499..e26652ff7059 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -623,7 +623,7 @@ static inline u32 fnhe_hashfun(__be32 daddr)
 	u32 hval;
 
 	net_get_random_once(&fnhe_hashrnd, sizeof(fnhe_hashrnd));
-	hval = jhash_1word((__force u32) daddr, fnhe_hashrnd);
+	hval = jhash_1word((__force u32)daddr, fnhe_hashrnd);
 	return hash_32(hval, FNHE_HASH_SHIFT);
 }
 
@@ -1016,13 +1016,14 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 {
 	struct dst_entry *dst = &rt->dst;
 	struct net *net = dev_net(dst->dev);
-	u32 old_mtu = ipv4_mtu(dst);
 	struct fib_result res;
 	bool lock = false;
+	u32 old_mtu;
 
 	if (ip_mtu_locked(dst))
 		return;
 
+	old_mtu = ipv4_mtu(dst);
 	if (old_mtu < mtu)
 		return;
 
@@ -1066,7 +1067,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
 		      int oif, u8 protocol)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 	u32 mark = IP4_REPLY_MARK(net, skb->mark);
@@ -1083,7 +1084,7 @@ EXPORT_SYMBOL_GPL(ipv4_update_pmtu);
 
 static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
@@ -1101,7 +1102,7 @@ static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 
 void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 	struct dst_entry *odst = NULL;
@@ -1131,7 +1132,7 @@ void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu)
 		new = true;
 	}
 
-	__ip_rt_update_pmtu((struct rtable *) xfrm_dst_path(&rt->dst), &fl4, mtu);
+	__ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu);
 
 	if (!dst_check(&rt->dst, 0)) {
 		if (new)
@@ -1156,7 +1157,7 @@ EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu);
 void ipv4_redirect(struct sk_buff *skb, struct net *net,
 		   int oif, u8 protocol)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 
@@ -1172,7 +1173,7 @@ EXPORT_SYMBOL_GPL(ipv4_redirect);
 
 void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
 {
-	const struct iphdr *iph = (const struct iphdr *) skb->data;
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct flowi4 fl4;
 	struct rtable *rt;
 	struct net *net = sock_net(sk);
@@ -1312,7 +1313,7 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 
 static unsigned int ipv4_mtu(const struct dst_entry *dst)
 {
-	const struct rtable *rt = (const struct rtable *) dst;
+	const struct rtable *rt = (const struct rtable *)dst;
 	unsigned int mtu = rt->rt_pmtu;
 
 	if (!mtu || time_after_eq(jiffies, rt->dst.expires))
@@ -1740,7 +1741,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		flags |= RTCF_LOCAL;
 
 	rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
-			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+			   IN_DEV_ORCONF(in_dev, NOPOLICY), false);
 	if (!rth)
 		return -ENOBUFS;
 
@@ -1856,8 +1857,8 @@ static int __mkroute_input(struct sk_buff *skb,
 	}
 
 	rth = rt_dst_alloc(out_dev->dev, 0, res->type,
-			   IN_DEV_CONF_GET(in_dev, NOPOLICY),
-			   IN_DEV_CONF_GET(out_dev, NOXFRM));
+			   IN_DEV_ORCONF(in_dev, NOPOLICY),
+			   IN_DEV_ORCONF(out_dev, NOXFRM));
 	if (!rth) {
 		err = -ENOBUFS;
 		goto cleanup;
@@ -2226,7 +2227,7 @@ local_input:
 
 	rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev,
 			   flags | RTCF_LOCAL, res->type,
-			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+			   IN_DEV_ORCONF(in_dev, NOPOLICY), false);
 	if (!rth)
 		goto e_nobufs;
 
@@ -2449,8 +2450,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 
 add:
 	rth = rt_dst_alloc(dev_out, flags, type,
-			   IN_DEV_CONF_GET(in_dev, NOPOLICY),
-			   IN_DEV_CONF_GET(in_dev, NOXFRM));
+			   IN_DEV_ORCONF(in_dev, NOPOLICY),
+			   IN_DEV_ORCONF(in_dev, NOXFRM));
 	if (!rth)
 		return ERR_PTR(-ENOBUFS);
 
@@ -2769,10 +2770,12 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 	if (IS_ERR(rt))
 		return rt;
 
-	if (flp4->flowi4_proto)
+	if (flp4->flowi4_proto) {
+		flp4->flowi4_oif = rt->dst.dev->ifindex;
 		rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst,
 							flowi4_to_flowi(flp4),
 							sk, 0);
+	}
 
 	return rt;
 }
@@ -2869,6 +2872,9 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
 	if (rt->dst.dev &&
 	    nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
 		goto nla_put_failure;
+	if (rt->dst.lwtstate &&
+	    lwtunnel_fill_encap(skb, rt->dst.lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
+		goto nla_put_failure;
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (rt->dst.tclassid &&
 	    nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid))
@@ -3219,7 +3225,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 
 	fl4.daddr = dst;
 	fl4.saddr = src;
-	fl4.flowi4_tos = rtm->rtm_tos;
+	fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK;
 	fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_uid = uid;
@@ -3243,8 +3249,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		fl4.flowi4_iif = iif; /* for rt_fill_info */
 		skb->dev	= dev;
 		skb->mark	= mark;
-		err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos,
-					 dev, &res);
+		err = ip_route_input_rcu(skb, dst, src,
+					 rtm->rtm_tos & IPTOS_RT_MASK, dev,
+					 &res);
 
 		rt = skb_rtable(skb);
 		if (err == 0 && rt->dst.error)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index e03756631541..33792cf55a79 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -286,11 +286,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 					    struct sock *sk,
 					    struct sk_buff *skb)
 {
+	struct tcp_request_sock *treq;
 	struct request_sock *req;
 
 #ifdef CONFIG_MPTCP
-	struct tcp_request_sock *treq;
-
 	if (sk_is_mptcp(sk))
 		ops = &mptcp_subflow_request_sock_ops;
 #endif
@@ -299,8 +298,9 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 	if (!req)
 		return NULL;
 
-#if IS_ENABLED(CONFIG_MPTCP)
 	treq = tcp_rsk(req);
+	treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
+#if IS_ENABLED(CONFIG_MPTCP)
 	treq->is_mptcp = sk_is_mptcp(sk);
 	if (treq->is_mptcp) {
 		int err = mptcp_subflow_init_cookie_req(req, sk, skb);
@@ -331,7 +331,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	__u32 cookie = ntohl(th->ack_seq) - 1;
 	struct sock *ret = sk;
 	struct request_sock *req;
-	int mss;
+	int full_space, mss;
 	struct rtable *rt;
 	__u8 rcv_wscale;
 	struct flowi4 fl4;
@@ -418,7 +418,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 			   inet_sk_flowi_flags(sk),
 			   opt->srr ? opt->faddr : ireq->ir_rmt_addr,
 			   ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
-	security_req_classify_flow(req, flowi4_to_flowi(&fl4));
+	security_req_classify_flow(req, flowi4_to_flowi_common(&fl4));
 	rt = ip_route_output_key(sock_net(sk), &fl4);
 	if (IS_ERR(rt)) {
 		reqsk_free(req);
@@ -427,8 +427,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 
 	/* Try to redo what tcp_v4_send_synack did. */
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(&rt->dst, RTAX_WINDOW);
+	/* limit the window selection if the user enforce a smaller rx buffer */
+	full_space = tcp_full_space(sk);
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+	    (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+		req->rsk_window_clamp = full_space;
 
-	tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+	tcp_select_initial_window(sk, full_space, req->mss,
 				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 54023a46db04..3e5f4f2e705e 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1330,6 +1330,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra2		= &comp_sack_nr_max,
 	},
 	{
+		.procname       = "tcp_reflect_tos",
+		.data           = &init_net.ipv4.sysctl_tcp_reflect_tos,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{
 		.procname	= "udp_rmem_min",
 		.data		= &init_net.ipv4.sysctl_udp_rmem_min,
 		.maxlen		= sizeof(init_net.ipv4.sysctl_udp_rmem_min),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2135ee7c806d..32545ecf2ab1 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -418,6 +418,8 @@ void tcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
+	icsk->icsk_rto_min = TCP_RTO_MIN;
+	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
 
@@ -483,6 +485,8 @@ static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,
 			return true;
 		if (tcp_rmem_pressure(sk))
 			return true;
+		if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss)
+			return true;
 	}
 	if (sk->sk_prot->stream_memory_read)
 		return sk->sk_prot->stream_memory_read(sk);
@@ -562,7 +566,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 			mask |= EPOLLIN | EPOLLRDNORM;
 
 		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
-			if (sk_stream_is_writeable(sk)) {
+			if (__sk_stream_is_writeable(sk, 1)) {
 				mask |= EPOLLOUT | EPOLLWRNORM;
 			} else {  /* send SIGIO later */
 				sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -574,7 +578,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 				 * pairs with the input side.
 				 */
 				smp_mb__after_atomic();
-				if (sk_stream_is_writeable(sk))
+				if (__sk_stream_is_writeable(sk, 1))
 					mask |= EPOLLOUT | EPOLLWRNORM;
 			}
 		} else
@@ -950,7 +954,7 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
  * importantly be able to generate EPOLLOUT for Edge Trigger epoll()
  * users.
  */
-static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
+void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
 {
 	if (skb && !skb->len) {
 		tcp_unlink_write_queue(skb, sk);
@@ -960,6 +964,68 @@ static void tcp_remove_empty_skb(struct sock *sk, struct sk_buff *skb)
 	}
 }
 
+struct sk_buff *tcp_build_frag(struct sock *sk, int size_goal, int flags,
+			       struct page *page, int offset, size_t *size)
+{
+	struct sk_buff *skb = tcp_write_queue_tail(sk);
+	struct tcp_sock *tp = tcp_sk(sk);
+	bool can_coalesce;
+	int copy, i;
+
+	if (!skb || (copy = size_goal - skb->len) <= 0 ||
+	    !tcp_skb_can_collapse_to(skb)) {
+new_segment:
+		if (!sk_stream_memory_free(sk))
+			return NULL;
+
+		skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
+					  tcp_rtx_and_write_queues_empty(sk));
+		if (!skb)
+			return NULL;
+
+#ifdef CONFIG_TLS_DEVICE
+		skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
+		skb_entail(sk, skb);
+		copy = size_goal;
+	}
+
+	if (copy > *size)
+		copy = *size;
+
+	i = skb_shinfo(skb)->nr_frags;
+	can_coalesce = skb_can_coalesce(skb, i, page, offset);
+	if (!can_coalesce && i >= sysctl_max_skb_frags) {
+		tcp_mark_push(tp, skb);
+		goto new_segment;
+	}
+	if (!sk_wmem_schedule(sk, copy))
+		return NULL;
+
+	if (can_coalesce) {
+		skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+	} else {
+		get_page(page);
+		skb_fill_page_desc(skb, i, page, offset, copy);
+	}
+
+	if (!(flags & MSG_NO_SHARED_FRAGS))
+		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
+
+	skb->len += copy;
+	skb->data_len += copy;
+	skb->truesize += copy;
+	sk_wmem_queued_add(sk, copy);
+	sk_mem_charge(sk, copy);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+	WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
+	TCP_SKB_CB(skb)->end_seq += copy;
+	tcp_skb_pcount_set(skb, 0);
+
+	*size = copy;
+	return skb;
+}
+
 ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 			 size_t size, int flags)
 {
@@ -995,59 +1061,12 @@ ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
 		goto out_err;
 
 	while (size > 0) {
-		struct sk_buff *skb = tcp_write_queue_tail(sk);
-		int copy, i;
-		bool can_coalesce;
-
-		if (!skb || (copy = size_goal - skb->len) <= 0 ||
-		    !tcp_skb_can_collapse_to(skb)) {
-new_segment:
-			if (!sk_stream_memory_free(sk))
-				goto wait_for_sndbuf;
-
-			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
-					tcp_rtx_and_write_queues_empty(sk));
-			if (!skb)
-				goto wait_for_memory;
-
-#ifdef CONFIG_TLS_DEVICE
-			skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
-#endif
-			skb_entail(sk, skb);
-			copy = size_goal;
-		}
-
-		if (copy > size)
-			copy = size;
-
-		i = skb_shinfo(skb)->nr_frags;
-		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= sysctl_max_skb_frags) {
-			tcp_mark_push(tp, skb);
-			goto new_segment;
-		}
-		if (!sk_wmem_schedule(sk, copy))
-			goto wait_for_memory;
-
-		if (can_coalesce) {
-			skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
-		} else {
-			get_page(page);
-			skb_fill_page_desc(skb, i, page, offset, copy);
-		}
+		struct sk_buff *skb;
+		size_t copy = size;
 
-		if (!(flags & MSG_NO_SHARED_FRAGS))
-			skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
-
-		skb->len += copy;
-		skb->data_len += copy;
-		skb->truesize += copy;
-		sk_wmem_queued_add(sk, copy);
-		sk_mem_charge(sk, copy);
-		skb->ip_summed = CHECKSUM_PARTIAL;
-		WRITE_ONCE(tp->write_seq, tp->write_seq + copy);
-		TCP_SKB_CB(skb)->end_seq += copy;
-		tcp_skb_pcount_set(skb, 0);
+		skb = tcp_build_frag(sk, size_goal, flags, page, offset, &copy);
+		if (!skb)
+			goto wait_for_space;
 
 		if (!copied)
 			TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
@@ -1068,9 +1087,8 @@ new_segment:
 			tcp_push_one(sk, mss_now);
 		continue;
 
-wait_for_sndbuf:
+wait_for_space:
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-wait_for_memory:
 		tcp_push(sk, flags & ~MSG_MORE, mss_now,
 			 TCP_NAGLE_PUSH, size_goal);
 
@@ -1281,7 +1299,7 @@ restart:
 
 new_segment:
 			if (!sk_stream_memory_free(sk))
-				goto wait_for_sndbuf;
+				goto wait_for_space;
 
 			if (unlikely(process_backlog >= 16)) {
 				process_backlog = 0;
@@ -1292,7 +1310,7 @@ new_segment:
 			skb = sk_stream_alloc_skb(sk, 0, sk->sk_allocation,
 						  first_skb);
 			if (!skb)
-				goto wait_for_memory;
+				goto wait_for_space;
 
 			process_backlog++;
 			skb->ip_summed = CHECKSUM_PARTIAL;
@@ -1325,7 +1343,7 @@ new_segment:
 			struct page_frag *pfrag = sk_page_frag(sk);
 
 			if (!sk_page_frag_refill(sk, pfrag))
-				goto wait_for_memory;
+				goto wait_for_space;
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
@@ -1339,7 +1357,7 @@ new_segment:
 			copy = min_t(int, copy, pfrag->size - pfrag->offset);
 
 			if (!sk_wmem_schedule(sk, copy))
-				goto wait_for_memory;
+				goto wait_for_space;
 
 			err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
 						       pfrag->page,
@@ -1392,9 +1410,8 @@ new_segment:
 			tcp_push_one(sk, mss_now);
 		continue;
 
-wait_for_sndbuf:
+wait_for_space:
 		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-wait_for_memory:
 		if (copied)
 			tcp_push(sk, flags & ~MSG_MORE, mss_now,
 				 TCP_NAGLE_PUSH, size_goal);
@@ -1526,7 +1543,7 @@ static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
  * calculation of whether or not we must ACK for the sake of
  * a window update.
  */
-static void tcp_cleanup_rbuf(struct sock *sk, int copied)
+void tcp_cleanup_rbuf(struct sock *sk, int copied)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool time_to_ack = false;
@@ -1539,10 +1556,8 @@ static void tcp_cleanup_rbuf(struct sock *sk, int copied)
 
 	if (inet_csk_ack_scheduled(sk)) {
 		const struct inet_connection_sock *icsk = inet_csk(sk);
-		   /* Delayed ACKs frequently hit locked sockets during bulk
-		    * receive. */
-		if (icsk->icsk_ack.blocked ||
-		    /* Once-per-two-segments ACK was not sent by tcp_input.c */
+
+		if (/* Once-per-two-segments ACK was not sent by tcp_input.c */
 		    tp->rcv_nxt - tp->rcv_wup > icsk->icsk_ack.rcv_mss ||
 		    /*
 		     * If this read emptied read buffer, we send ACK, if
@@ -1743,52 +1758,272 @@ int tcp_mmap(struct file *file, struct socket *sock,
 }
 EXPORT_SYMBOL(tcp_mmap);
 
+static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb,
+				       u32 *offset_frag)
+{
+	skb_frag_t *frag;
+
+	offset_skb -= skb_headlen(skb);
+	if ((int)offset_skb < 0 || skb_has_frag_list(skb))
+		return NULL;
+
+	frag = skb_shinfo(skb)->frags;
+	while (offset_skb) {
+		if (skb_frag_size(frag) > offset_skb) {
+			*offset_frag = offset_skb;
+			return frag;
+		}
+		offset_skb -= skb_frag_size(frag);
+		++frag;
+	}
+	*offset_frag = 0;
+	return frag;
+}
+
+static bool can_map_frag(const skb_frag_t *frag)
+{
+	return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag);
+}
+
+static int find_next_mappable_frag(const skb_frag_t *frag,
+				   int remaining_in_skb)
+{
+	int offset = 0;
+
+	if (likely(can_map_frag(frag)))
+		return 0;
+
+	while (offset < remaining_in_skb && !can_map_frag(frag)) {
+		offset += skb_frag_size(frag);
+		++frag;
+	}
+	return offset;
+}
+
+static void tcp_zerocopy_set_hint_for_skb(struct sock *sk,
+					  struct tcp_zerocopy_receive *zc,
+					  struct sk_buff *skb, u32 offset)
+{
+	u32 frag_offset, partial_frag_remainder = 0;
+	int mappable_offset;
+	skb_frag_t *frag;
+
+	/* worst case: skip to next skb. try to improve on this case below */
+	zc->recv_skip_hint = skb->len - offset;
+
+	/* Find the frag containing this offset (and how far into that frag) */
+	frag = skb_advance_to_frag(skb, offset, &frag_offset);
+	if (!frag)
+		return;
+
+	if (frag_offset) {
+		struct skb_shared_info *info = skb_shinfo(skb);
+
+		/* We read part of the last frag, must recvmsg() rest of skb. */
+		if (frag == &info->frags[info->nr_frags - 1])
+			return;
+
+		/* Else, we must at least read the remainder in this frag. */
+		partial_frag_remainder = skb_frag_size(frag) - frag_offset;
+		zc->recv_skip_hint -= partial_frag_remainder;
+		++frag;
+	}
+
+	/* partial_frag_remainder: If part way through a frag, must read rest.
+	 * mappable_offset: Bytes till next mappable frag, *not* counting bytes
+	 * in partial_frag_remainder.
+	 */
+	mappable_offset = find_next_mappable_frag(frag, zc->recv_skip_hint);
+	zc->recv_skip_hint = mappable_offset + partial_frag_remainder;
+}
+
+static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
+			      int nonblock, int flags,
+			      struct scm_timestamping_internal *tss,
+			      int *cmsg_flags);
+static int receive_fallback_to_copy(struct sock *sk,
+				    struct tcp_zerocopy_receive *zc, int inq)
+{
+	unsigned long copy_address = (unsigned long)zc->copybuf_address;
+	struct scm_timestamping_internal tss_unused;
+	int err, cmsg_flags_unused;
+	struct msghdr msg = {};
+	struct iovec iov;
+
+	zc->length = 0;
+	zc->recv_skip_hint = 0;
+
+	if (copy_address != zc->copybuf_address)
+		return -EINVAL;
+
+	err = import_single_range(READ, (void __user *)copy_address,
+				  inq, &iov, &msg.msg_iter);
+	if (err)
+		return err;
+
+	err = tcp_recvmsg_locked(sk, &msg, inq, /*nonblock=*/1, /*flags=*/0,
+				 &tss_unused, &cmsg_flags_unused);
+	if (err < 0)
+		return err;
+
+	zc->copybuf_len = err;
+	if (likely(zc->copybuf_len)) {
+		struct sk_buff *skb;
+		u32 offset;
+
+		skb = tcp_recv_skb(sk, tcp_sk(sk)->copied_seq, &offset);
+		if (skb)
+			tcp_zerocopy_set_hint_for_skb(sk, zc, skb, offset);
+	}
+	return 0;
+}
+
+static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc,
+				   struct sk_buff *skb, u32 copylen,
+				   u32 *offset, u32 *seq)
+{
+	unsigned long copy_address = (unsigned long)zc->copybuf_address;
+	struct msghdr msg = {};
+	struct iovec iov;
+	int err;
+
+	if (copy_address != zc->copybuf_address)
+		return -EINVAL;
+
+	err = import_single_range(READ, (void __user *)copy_address,
+				  copylen, &iov, &msg.msg_iter);
+	if (err)
+		return err;
+	err = skb_copy_datagram_msg(skb, *offset, &msg, copylen);
+	if (err)
+		return err;
+	zc->recv_skip_hint -= copylen;
+	*offset += copylen;
+	*seq += copylen;
+	return (__s32)copylen;
+}
+
+static int tcp_zerocopy_handle_leftover_data(struct tcp_zerocopy_receive *zc,
+					     struct sock *sk,
+					     struct sk_buff *skb,
+					     u32 *seq,
+					     s32 copybuf_len)
+{
+	u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint);
+
+	if (!copylen)
+		return 0;
+	/* skb is null if inq < PAGE_SIZE. */
+	if (skb)
+		offset = *seq - TCP_SKB_CB(skb)->seq;
+	else
+		skb = tcp_recv_skb(sk, *seq, &offset);
+
+	zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset,
+						  seq);
+	return zc->copybuf_len < 0 ? 0 : copylen;
+}
+
+static int tcp_zerocopy_vm_insert_batch_error(struct vm_area_struct *vma,
+					      struct page **pending_pages,
+					      unsigned long pages_remaining,
+					      unsigned long *address,
+					      u32 *length,
+					      u32 *seq,
+					      struct tcp_zerocopy_receive *zc,
+					      u32 total_bytes_to_map,
+					      int err)
+{
+	/* At least one page did not map. Try zapping if we skipped earlier. */
+	if (err == -EBUSY &&
+	    zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT) {
+		u32 maybe_zap_len;
+
+		maybe_zap_len = total_bytes_to_map -  /* All bytes to map */
+				*length + /* Mapped or pending */
+				(pages_remaining * PAGE_SIZE); /* Failed map. */
+		zap_page_range(vma, *address, maybe_zap_len);
+		err = 0;
+	}
+
+	if (!err) {
+		unsigned long leftover_pages = pages_remaining;
+		int bytes_mapped;
+
+		/* We called zap_page_range, try to reinsert. */
+		err = vm_insert_pages(vma, *address,
+				      pending_pages,
+				      &pages_remaining);
+		bytes_mapped = PAGE_SIZE * (leftover_pages - pages_remaining);
+		*seq += bytes_mapped;
+		*address += bytes_mapped;
+	}
+	if (err) {
+		/* Either we were unable to zap, OR we zapped, retried an
+		 * insert, and still had an issue. Either ways, pages_remaining
+		 * is the number of pages we were unable to map, and we unroll
+		 * some state we speculatively touched before.
+		 */
+		const int bytes_not_mapped = PAGE_SIZE * pages_remaining;
+
+		*length -= bytes_not_mapped;
+		zc->recv_skip_hint += bytes_not_mapped;
+	}
+	return err;
+}
+
 static int tcp_zerocopy_vm_insert_batch(struct vm_area_struct *vma,
 					struct page **pages,
-					unsigned long pages_to_map,
-					unsigned long *insert_addr,
-					u32 *length_with_pending,
+					unsigned int pages_to_map,
+					unsigned long *address,
+					u32 *length,
 					u32 *seq,
-					struct tcp_zerocopy_receive *zc)
+					struct tcp_zerocopy_receive *zc,
+					u32 total_bytes_to_map)
 {
 	unsigned long pages_remaining = pages_to_map;
-	int bytes_mapped;
-	int ret;
+	unsigned int pages_mapped;
+	unsigned int bytes_mapped;
+	int err;
 
-	ret = vm_insert_pages(vma, *insert_addr, pages, &pages_remaining);
-	bytes_mapped = PAGE_SIZE * (pages_to_map - pages_remaining);
+	err = vm_insert_pages(vma, *address, pages, &pages_remaining);
+	pages_mapped = pages_to_map - (unsigned int)pages_remaining;
+	bytes_mapped = PAGE_SIZE * pages_mapped;
 	/* Even if vm_insert_pages fails, it may have partially succeeded in
 	 * mapping (some but not all of the pages).
 	 */
 	*seq += bytes_mapped;
-	*insert_addr += bytes_mapped;
-	if (ret) {
-		/* But if vm_insert_pages did fail, we have to unroll some state
-		 * we speculatively touched before.
-		 */
-		const int bytes_not_mapped = PAGE_SIZE * pages_remaining;
-		*length_with_pending -= bytes_not_mapped;
-		zc->recv_skip_hint += bytes_not_mapped;
-	}
-	return ret;
+	*address += bytes_mapped;
+
+	if (likely(!err))
+		return 0;
+
+	/* Error: maybe zap and retry + rollback state for failed inserts. */
+	return tcp_zerocopy_vm_insert_batch_error(vma, pages + pages_mapped,
+		pages_remaining, address, length, seq, zc, total_bytes_to_map,
+		err);
 }
 
+#define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32
 static int tcp_zerocopy_receive(struct sock *sk,
 				struct tcp_zerocopy_receive *zc)
 {
+	u32 length = 0, offset, vma_len, avail_len, copylen = 0;
 	unsigned long address = (unsigned long)zc->address;
-	u32 length = 0, seq, offset, zap_len;
-	#define PAGE_BATCH_SIZE 8
-	struct page *pages[PAGE_BATCH_SIZE];
+	struct page *pages[TCP_ZEROCOPY_PAGE_BATCH_SIZE];
+	s32 copybuf_len = zc->copybuf_len;
+	struct tcp_sock *tp = tcp_sk(sk);
 	const skb_frag_t *frags = NULL;
+	unsigned int pages_to_map = 0;
 	struct vm_area_struct *vma;
 	struct sk_buff *skb = NULL;
-	unsigned long pg_idx = 0;
-	unsigned long curr_addr;
-	struct tcp_sock *tp;
-	int inq;
+	u32 seq = tp->copied_seq;
+	u32 total_bytes_to_map;
+	int inq = tcp_inq(sk);
 	int ret;
 
+	zc->copybuf_len = 0;
+
 	if (address & (PAGE_SIZE - 1) || address != zc->address)
 		return -EINVAL;
 
@@ -1797,7 +2032,16 @@ static int tcp_zerocopy_receive(struct sock *sk,
 
 	sock_rps_record_flow(sk);
 
-	tp = tcp_sk(sk);
+	if (inq && inq <= copybuf_len)
+		return receive_fallback_to_copy(sk, zc, inq);
+
+	if (inq < PAGE_SIZE) {
+		zc->length = 0;
+		zc->recv_skip_hint = inq;
+		if (!inq && sock_flag(sk, SOCK_DONE))
+			return -EIO;
+		return 0;
+	}
 
 	mmap_read_lock(current->mm);
 
@@ -1806,33 +2050,26 @@ static int tcp_zerocopy_receive(struct sock *sk,
 		mmap_read_unlock(current->mm);
 		return -EINVAL;
 	}
-	zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
-
-	seq = tp->copied_seq;
-	inq = tcp_inq(sk);
-	zc->length = min_t(u32, zc->length, inq);
-	zap_len = zc->length & ~(PAGE_SIZE - 1);
-	if (zap_len) {
-		zap_page_range(vma, address, zap_len);
+	vma_len = min_t(unsigned long, zc->length, vma->vm_end - address);
+	avail_len = min_t(u32, vma_len, inq);
+	total_bytes_to_map = avail_len & ~(PAGE_SIZE - 1);
+	if (total_bytes_to_map) {
+		if (!(zc->flags & TCP_RECEIVE_ZEROCOPY_FLAG_TLB_CLEAN_HINT))
+			zap_page_range(vma, address, total_bytes_to_map);
+		zc->length = total_bytes_to_map;
 		zc->recv_skip_hint = 0;
 	} else {
-		zc->recv_skip_hint = zc->length;
+		zc->length = avail_len;
+		zc->recv_skip_hint = avail_len;
 	}
 	ret = 0;
-	curr_addr = address;
 	while (length + PAGE_SIZE <= zc->length) {
+		int mappable_offset;
+		struct page *page;
+
 		if (zc->recv_skip_hint < PAGE_SIZE) {
-			/* If we're here, finish the current batch. */
-			if (pg_idx) {
-				ret = tcp_zerocopy_vm_insert_batch(vma, pages,
-								   pg_idx,
-								   &curr_addr,
-								   &length,
-								   &seq, zc);
-				if (ret)
-					goto out;
-				pg_idx = 0;
-			}
+			u32 offset_frag;
+
 			if (skb) {
 				if (zc->recv_skip_hint > 0)
 					break;
@@ -1842,56 +2079,57 @@ static int tcp_zerocopy_receive(struct sock *sk,
 				skb = tcp_recv_skb(sk, seq, &offset);
 			}
 			zc->recv_skip_hint = skb->len - offset;
-			offset -= skb_headlen(skb);
-			if ((int)offset < 0 || skb_has_frag_list(skb))
+			frags = skb_advance_to_frag(skb, offset, &offset_frag);
+			if (!frags || offset_frag)
 				break;
-			frags = skb_shinfo(skb)->frags;
-			while (offset) {
-				if (skb_frag_size(frags) > offset)
-					goto out;
-				offset -= skb_frag_size(frags);
-				frags++;
-			}
 		}
-		if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) {
-			int remaining = zc->recv_skip_hint;
 
-			while (remaining && (skb_frag_size(frags) != PAGE_SIZE ||
-					     skb_frag_off(frags))) {
-				remaining -= skb_frag_size(frags);
-				frags++;
-			}
-			zc->recv_skip_hint -= remaining;
+		mappable_offset = find_next_mappable_frag(frags,
+							  zc->recv_skip_hint);
+		if (mappable_offset) {
+			zc->recv_skip_hint = mappable_offset;
 			break;
 		}
-		pages[pg_idx] = skb_frag_page(frags);
-		pg_idx++;
+		page = skb_frag_page(frags);
+		prefetchw(page);
+		pages[pages_to_map++] = page;
 		length += PAGE_SIZE;
 		zc->recv_skip_hint -= PAGE_SIZE;
 		frags++;
-		if (pg_idx == PAGE_BATCH_SIZE) {
-			ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx,
-							   &curr_addr, &length,
-							   &seq, zc);
+		if (pages_to_map == TCP_ZEROCOPY_PAGE_BATCH_SIZE ||
+		    zc->recv_skip_hint < PAGE_SIZE) {
+			/* Either full batch, or we're about to go to next skb
+			 * (and we cannot unroll failed ops across skbs).
+			 */
+			ret = tcp_zerocopy_vm_insert_batch(vma, pages,
+							   pages_to_map,
+							   &address, &length,
+							   &seq, zc,
+							   total_bytes_to_map);
 			if (ret)
 				goto out;
-			pg_idx = 0;
+			pages_to_map = 0;
 		}
 	}
-	if (pg_idx) {
-		ret = tcp_zerocopy_vm_insert_batch(vma, pages, pg_idx,
-						   &curr_addr, &length, &seq,
-						   zc);
+	if (pages_to_map) {
+		ret = tcp_zerocopy_vm_insert_batch(vma, pages, pages_to_map,
+						   &address, &length, &seq,
+						   zc, total_bytes_to_map);
 	}
 out:
 	mmap_read_unlock(current->mm);
-	if (length) {
+	/* Try to copy straggler data. */
+	if (!ret)
+		copylen = tcp_zerocopy_handle_leftover_data(zc, sk, skb, &seq,
+							    copybuf_len);
+
+	if (length + copylen) {
 		WRITE_ONCE(tp->copied_seq, seq);
 		tcp_rcv_space_adjust(sk);
 
 		/* Clean up data we have read: This will do ACK frames. */
 		tcp_recv_skb(sk, seq, &offset);
-		tcp_cleanup_rbuf(sk, length);
+		tcp_cleanup_rbuf(sk, length + copylen);
 		ret = 0;
 		if (length == zc->length)
 			zc->recv_skip_hint = 0;
@@ -2013,36 +2251,28 @@ static int tcp_inq_hint(struct sock *sk)
  *	Probably, code can be easily improved even more.
  */
 
-int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
-		int flags, int *addr_len)
+static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
+			      int nonblock, int flags,
+			      struct scm_timestamping_internal *tss,
+			      int *cmsg_flags)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int copied = 0;
 	u32 peek_seq;
 	u32 *seq;
 	unsigned long used;
-	int err, inq;
+	int err;
 	int target;		/* Read at least this many bytes */
 	long timeo;
 	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
-	struct scm_timestamping_internal tss;
-	int cmsg_flags;
-
-	if (unlikely(flags & MSG_ERRQUEUE))
-		return inet_recv_error(sk, msg, len, addr_len);
-
-	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) &&
-	    (sk->sk_state == TCP_ESTABLISHED))
-		sk_busy_loop(sk, nonblock);
-
-	lock_sock(sk);
 
 	err = -ENOTCONN;
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
 
-	cmsg_flags = tp->recvmsg_inq ? 1 : 0;
+	if (tp->recvmsg_inq)
+		*cmsg_flags = 1;
 	timeo = sock_rcvtimeo(sk, nonblock);
 
 	/* Urgent data needs to be handled specially. */
@@ -2222,8 +2452,8 @@ skip_copy:
 		}
 
 		if (TCP_SKB_CB(skb)->has_rxtstamp) {
-			tcp_update_recv_tstamps(skb, &tss);
-			cmsg_flags |= 2;
+			tcp_update_recv_tstamps(skb, tss);
+			*cmsg_flags |= 2;
 		}
 
 		if (used + offset < skb->len)
@@ -2249,22 +2479,9 @@ found_fin_ok:
 
 	/* Clean up data we have read: This will do ACK frames. */
 	tcp_cleanup_rbuf(sk, copied);
-
-	release_sock(sk);
-
-	if (cmsg_flags) {
-		if (cmsg_flags & 2)
-			tcp_recv_timestamp(msg, sk, &tss);
-		if (cmsg_flags & 1) {
-			inq = tcp_inq_hint(sk);
-			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
-		}
-	}
-
 	return copied;
 
 out:
-	release_sock(sk);
 	return err;
 
 recv_urg:
@@ -2275,6 +2492,36 @@ recv_sndq:
 	err = tcp_peek_sndq(sk, msg, len);
 	goto out;
 }
+
+int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
+		int flags, int *addr_len)
+{
+	int cmsg_flags = 0, ret, inq;
+	struct scm_timestamping_internal tss;
+
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return inet_recv_error(sk, msg, len, addr_len);
+
+	if (sk_can_busy_loop(sk) &&
+	    skb_queue_empty_lockless(&sk->sk_receive_queue) &&
+	    sk->sk_state == TCP_ESTABLISHED)
+		sk_busy_loop(sk, nonblock);
+
+	lock_sock(sk);
+	ret = tcp_recvmsg_locked(sk, msg, len, nonblock, flags, &tss,
+				 &cmsg_flags);
+	release_sock(sk);
+
+	if (cmsg_flags && ret >= 0) {
+		if (cmsg_flags & 2)
+			tcp_recv_timestamp(msg, sk, &tss);
+		if (cmsg_flags & 1) {
+			inq = tcp_inq_hint(sk);
+			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
+		}
+	}
+	return ret;
+}
 EXPORT_SYMBOL(tcp_recvmsg);
 
 void tcp_set_state(struct sock *sk, int state)
@@ -2405,13 +2652,12 @@ bool tcp_check_oom(struct sock *sk, int shift)
 	return too_many_orphans || out_of_socket_memory;
 }
 
-void tcp_close(struct sock *sk, long timeout)
+void __tcp_close(struct sock *sk, long timeout)
 {
 	struct sk_buff *skb;
 	int data_was_unread = 0;
 	int state;
 
-	lock_sock(sk);
 	sk->sk_shutdown = SHUTDOWN_MASK;
 
 	if (sk->sk_state == TCP_LISTEN) {
@@ -2575,6 +2821,12 @@ adjudge_to_death:
 out:
 	bh_unlock_sock(sk);
 	local_bh_enable();
+}
+
+void tcp_close(struct sock *sk, long timeout)
+{
+	lock_sock(sk);
+	__tcp_close(sk, timeout);
 	release_sock(sk);
 	sock_put(sk);
 }
@@ -2685,7 +2937,10 @@ int tcp_disconnect(struct sock *sk, int flags)
 
 	icsk->icsk_backoff = 0;
 	icsk->icsk_probes_out = 0;
+	icsk->icsk_probes_tstamp = 0;
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
+	icsk->icsk_rto_min = TCP_RTO_MIN;
+	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tp->snd_cwnd = TCP_INIT_CWND;
 	tp->snd_cwnd_cnt = 0;
@@ -2695,6 +2950,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	if (icsk->icsk_ca_ops->release)
 		icsk->icsk_ca_ops->release(sk);
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
+	icsk->icsk_ca_initialized = 0;
 	tcp_set_ca_state(sk, TCP_CA_Open);
 	tp->is_sack_reneg = 0;
 	tcp_clear_retrans(tp);
@@ -3019,6 +3275,21 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val)
 }
 EXPORT_SYMBOL(tcp_sock_set_keepcnt);
 
+int tcp_set_window_clamp(struct sock *sk, int val)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	if (!val) {
+		if (sk->sk_state != TCP_CLOSE)
+			return -EINVAL;
+		tp->window_clamp = 0;
+	} else {
+		tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
+			SOCK_MIN_RCVBUF / 2 : val;
+	}
+	return 0;
+}
+
 /*
  *	Socket option code for TCP.
  */
@@ -3046,7 +3317,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		name[val] = 0;
 
 		lock_sock(sk);
-		err = tcp_set_congestion_control(sk, name, true, true,
+		err = tcp_set_congestion_control(sk, name, true,
 						 ns_capable(sock_net(sk)->user_ns,
 							    CAP_NET_ADMIN));
 		release_sock(sk);
@@ -3208,7 +3479,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case TCP_SAVE_SYN:
-		if (val < 0 || val > 1)
+		/* 0: disable, 1: enable, 2: start from ether_header */
+		if (val < 0 || val > 2)
 			err = -EINVAL;
 		else
 			tp->save_syn = val;
@@ -3231,15 +3503,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		break;
 
 	case TCP_WINDOW_CLAMP:
-		if (!val) {
-			if (sk->sk_state != TCP_CLOSE) {
-				err = -EINVAL;
-				break;
-			}
-			tp->window_clamp = 0;
-		} else
-			tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
-						SOCK_MIN_RCVBUF / 2 : val;
+		err = tcp_set_window_clamp(sk, val);
 		break;
 
 	case TCP_QUICKACK:
@@ -3789,20 +4053,21 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 
 		lock_sock(sk);
 		if (tp->saved_syn) {
-			if (len < tp->saved_syn[0]) {
-				if (put_user(tp->saved_syn[0], optlen)) {
+			if (len < tcp_saved_syn_len(tp->saved_syn)) {
+				if (put_user(tcp_saved_syn_len(tp->saved_syn),
+					     optlen)) {
 					release_sock(sk);
 					return -EFAULT;
 				}
 				release_sock(sk);
 				return -EINVAL;
 			}
-			len = tp->saved_syn[0];
+			len = tcp_saved_syn_len(tp->saved_syn);
 			if (put_user(len, optlen)) {
 				release_sock(sk);
 				return -EFAULT;
 			}
-			if (copy_to_user(optval, tp->saved_syn + 1, len)) {
+			if (copy_to_user(optval, tp->saved_syn->data, len)) {
 				release_sock(sk);
 				return -EFAULT;
 			}
@@ -3818,7 +4083,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 	}
 #ifdef CONFIG_MMU
 	case TCP_ZEROCOPY_RECEIVE: {
-		struct tcp_zerocopy_receive zc;
+		struct tcp_zerocopy_receive zc = {};
 		int err;
 
 		if (get_user(len, optlen))
@@ -3835,7 +4100,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		lock_sock(sk);
 		err = tcp_zerocopy_receive(sk, &zc);
 		release_sock(sk);
-		if (len == sizeof(zc))
+		if (len >= offsetofend(struct tcp_zerocopy_receive, err))
 			goto zerocopy_rcv_sk_err;
 		switch (len) {
 		case offsetofend(struct tcp_zerocopy_receive, err):
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 6c4d79baff26..6ea3dc2e4219 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -945,7 +945,7 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
 	filter_expired = after(tcp_jiffies32,
 			       bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
 	if (rs->rtt_us >= 0 &&
-	    (rs->rtt_us <= bbr->min_rtt_us ||
+	    (rs->rtt_us < bbr->min_rtt_us ||
 	     (filter_expired && !rs->is_ack_delayed))) {
 		bbr->min_rtt_us = rs->rtt_us;
 		bbr->min_rtt_stamp = tcp_jiffies32;
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 7aa68f4aae6c..bc7d2a586e18 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -15,8 +15,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 {
 	struct iov_iter *iter = &msg->msg_iter;
 	int peek = flags & MSG_PEEK;
-	int i, ret, copied = 0;
 	struct sk_msg *msg_rx;
+	int i, copied = 0;
 
 	msg_rx = list_first_entry_or_null(&psock->ingress_msg,
 					  struct sk_msg, list);
@@ -37,17 +37,16 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 			page = sg_page(sge);
 			if (copied + copy > len)
 				copy = len - copied;
-			ret = copy_page_to_iter(page, sge->offset, copy, iter);
-			if (ret != copy) {
-				msg_rx->sg.start = i;
-				return -EFAULT;
-			}
+			copy = copy_page_to_iter(page, sge->offset, copy, iter);
+			if (!copy)
+				return copied ? copied : -EFAULT;
 
 			copied += copy;
 			if (likely(!peek)) {
 				sge->offset += copy;
 				sge->length -= copy;
-				sk_mem_uncharge(sk, copy);
+				if (!msg_rx->skb)
+					sk_mem_uncharge(sk, copy);
 				msg_rx->sg.size -= copy;
 
 				if (!sge->length) {
@@ -56,6 +55,11 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock,
 						put_page(page);
 				}
 			} else {
+				/* Lets not optimize peek case if copy_page_to_iter
+				 * didn't copy the entire length lets just break.
+				 */
+				if (copy != sge->length)
+					return copied;
 				sk_msg_iter_var_next(i);
 			}
 
@@ -567,10 +571,9 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS],
 	prot[TCP_BPF_TX].sendpage		= tcp_bpf_sendpage;
 }
 
-static void tcp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops)
+static void tcp_bpf_check_v6_needs_rebuild(struct proto *ops)
 {
-	if (sk->sk_family == AF_INET6 &&
-	    unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) {
+	if (unlikely(ops != smp_load_acquire(&tcpv6_prot_saved))) {
 		spin_lock_bh(&tcpv6_prot_lock);
 		if (likely(ops != tcpv6_prot_saved)) {
 			tcp_bpf_rebuild_protos(tcp_bpf_prots[TCP_BPF_IPV6], ops);
@@ -603,13 +606,11 @@ struct proto *tcp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
 	int family = sk->sk_family == AF_INET6 ? TCP_BPF_IPV6 : TCP_BPF_IPV4;
 	int config = psock->progs.msg_parser   ? TCP_BPF_TX   : TCP_BPF_BASE;
 
-	if (!psock->sk_proto) {
-		struct proto *ops = READ_ONCE(sk->sk_prot);
-
-		if (tcp_bpf_assert_proto_ops(ops))
+	if (sk->sk_family == AF_INET6) {
+		if (tcp_bpf_assert_proto_ops(psock->sk_proto))
 			return ERR_PTR(-EINVAL);
 
-		tcp_bpf_check_v6_needs_rebuild(sk, ops);
+		tcp_bpf_check_v6_needs_rebuild(psock->sk_proto);
 	}
 
 	return &tcp_bpf_prots[family][config];
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 62878cf26d9c..563d016e7478 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -176,7 +176,7 @@ void tcp_assign_congestion_control(struct sock *sk)
 
 void tcp_init_congestion_control(struct sock *sk)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct inet_connection_sock *icsk = inet_csk(sk);
 
 	tcp_sk(sk)->prior_ssthresh = 0;
 	if (icsk->icsk_ca_ops->init)
@@ -185,6 +185,7 @@ void tcp_init_congestion_control(struct sock *sk)
 		INET_ECN_xmit(sk);
 	else
 		INET_ECN_dontxmit(sk);
+	icsk->icsk_ca_initialized = 1;
 }
 
 static void tcp_reinit_congestion_control(struct sock *sk,
@@ -197,6 +198,11 @@ static void tcp_reinit_congestion_control(struct sock *sk,
 	icsk->icsk_ca_setsockopt = 1;
 	memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv));
 
+	if (ca->flags & TCP_CONG_NEEDS_ECN)
+		INET_ECN_xmit(sk);
+	else
+		INET_ECN_dontxmit(sk);
+
 	if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 		tcp_init_congestion_control(sk);
 }
@@ -340,7 +346,7 @@ out:
  * already initialized.
  */
 int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
-			       bool reinit, bool cap_net_admin)
+			       bool cap_net_admin)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_congestion_ops *ca;
@@ -361,28 +367,14 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
 		goto out;
 	}
 
-	if (!ca) {
+	if (!ca)
 		err = -ENOENT;
-	} else if (!load) {
-		const struct tcp_congestion_ops *old_ca = icsk->icsk_ca_ops;
-
-		if (bpf_try_module_get(ca, ca->owner)) {
-			if (reinit) {
-				tcp_reinit_congestion_control(sk, ca);
-			} else {
-				icsk->icsk_ca_ops = ca;
-				bpf_module_put(old_ca, old_ca->owner);
-			}
-		} else {
-			err = -EBUSY;
-		}
-	} else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin)) {
+	else if (!((ca->flags & TCP_CONG_NON_RESTRICTED) || cap_net_admin))
 		err = -EPERM;
-	} else if (!bpf_try_module_get(ca, ca->owner)) {
+	else if (!bpf_try_module_get(ca, ca->owner))
 		err = -EBUSY;
-	} else {
+	else
 		tcp_reinit_congestion_control(sk, ca);
-	}
  out:
 	rcu_read_unlock();
 	return err;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 09b62de04eea..af2814c9342a 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -295,7 +295,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	refcount_set(&req->rsk_refcnt, 2);
 
 	/* Now finish processing the fastopen child socket. */
-	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
+	tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB, skb);
 
 	tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b1ce2054291d..9b44caa4b956 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -138,6 +138,69 @@ void clean_acked_data_flush(void)
 EXPORT_SYMBOL_GPL(clean_acked_data_flush);
 #endif
 
+#ifdef CONFIG_CGROUP_BPF
+static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
+{
+	bool unknown_opt = tcp_sk(sk)->rx_opt.saw_unknown &&
+		BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+				       BPF_SOCK_OPS_PARSE_UNKNOWN_HDR_OPT_CB_FLAG);
+	bool parse_all_opt = BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+						    BPF_SOCK_OPS_PARSE_ALL_HDR_OPT_CB_FLAG);
+	struct bpf_sock_ops_kern sock_ops;
+
+	if (likely(!unknown_opt && !parse_all_opt))
+		return;
+
+	/* The skb will be handled in the
+	 * bpf_skops_established() or
+	 * bpf_skops_write_hdr_opt().
+	 */
+	switch (sk->sk_state) {
+	case TCP_SYN_RECV:
+	case TCP_SYN_SENT:
+	case TCP_LISTEN:
+		return;
+	}
+
+	sock_owned_by_me(sk);
+
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+	sock_ops.op = BPF_SOCK_OPS_PARSE_HDR_OPT_CB;
+	sock_ops.is_fullsock = 1;
+	sock_ops.sk = sk;
+	bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
+
+	BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
+}
+
+static void bpf_skops_established(struct sock *sk, int bpf_op,
+				  struct sk_buff *skb)
+{
+	struct bpf_sock_ops_kern sock_ops;
+
+	sock_owned_by_me(sk);
+
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+	sock_ops.op = bpf_op;
+	sock_ops.is_fullsock = 1;
+	sock_ops.sk = sk;
+	/* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */
+	if (skb)
+		bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
+
+	BPF_CGROUP_RUN_PROG_SOCK_OPS(&sock_ops);
+}
+#else
+static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
+{
+}
+
+static void bpf_skops_established(struct sock *sk, int bpf_op,
+				  struct sk_buff *skb)
+{
+}
+#endif
+
 static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb,
 			     unsigned int len)
 {
@@ -447,7 +510,6 @@ static void tcp_init_buffer_space(struct sock *sk)
 	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK))
 		tcp_sndbuf_expand(sk);
 
-	tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss);
 	tcp_mstamp_refresh(tp);
 	tp->rcvq_space.time = tp->tcp_mstamp;
 	tp->rcvq_space.seq = tp->copied_seq;
@@ -471,6 +533,8 @@ static void tcp_init_buffer_space(struct sock *sk)
 
 	tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp);
 	tp->snd_cwnd_stamp = tcp_jiffies32;
+	tp->rcvq_space.space = min3(tp->rcv_ssthresh, tp->rcv_wnd,
+				    (u32)TCP_INIT_CWND * tp->advmss);
 }
 
 /* 4. Recalculate window clamp after socket hit its memory bounds. */
@@ -956,7 +1020,11 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 		      ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
 }
 
-/* This must be called before lost_out is incremented */
+ /* This must be called before lost_out or retrans_out are updated
+  * on a new loss, because we want to know if all skbs previously
+  * known to be lost have already been retransmitted, indicating
+  * that this newly lost skb is our next skb to retransmit.
+  */
 static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 {
 	if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) ||
@@ -966,41 +1034,36 @@ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb)
 		tp->retransmit_skb_hint = skb;
 }
 
-/* Sum the number of packets on the wire we have marked as lost.
- * There are two cases we care about here:
- * a) Packet hasn't been marked lost (nor retransmitted),
- *    and this is the first loss.
- * b) Packet has been marked both lost and retransmitted,
- *    and this means we think it was lost again.
+/* Sum the number of packets on the wire we have marked as lost, and
+ * notify the congestion control module that the given skb was marked lost.
  */
-static void tcp_sum_lost(struct tcp_sock *tp, struct sk_buff *skb)
+static void tcp_notify_skb_loss_event(struct tcp_sock *tp, const struct sk_buff *skb)
 {
-	__u8 sacked = TCP_SKB_CB(skb)->sacked;
-
-	if (!(sacked & TCPCB_LOST) ||
-	    ((sacked & TCPCB_LOST) && (sacked & TCPCB_SACKED_RETRANS)))
-		tp->lost += tcp_skb_pcount(skb);
+	tp->lost += tcp_skb_pcount(skb);
 }
 
-static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb)
+void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
 {
-	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
-		tcp_verify_retransmit_hint(tp, skb);
+	__u8 sacked = TCP_SKB_CB(skb)->sacked;
+	struct tcp_sock *tp = tcp_sk(sk);
 
-		tp->lost_out += tcp_skb_pcount(skb);
-		tcp_sum_lost(tp, skb);
-		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
-	}
-}
+	if (sacked & TCPCB_SACKED_ACKED)
+		return;
 
-void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb)
-{
 	tcp_verify_retransmit_hint(tp, skb);
-
-	tcp_sum_lost(tp, skb);
-	if (!(TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_ACKED))) {
+	if (sacked & TCPCB_LOST) {
+		if (sacked & TCPCB_SACKED_RETRANS) {
+			/* Account for retransmits that are lost again */
+			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
+			tp->retrans_out -= tcp_skb_pcount(skb);
+			NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
+				      tcp_skb_pcount(skb));
+			tcp_notify_skb_loss_event(tp, skb);
+		}
+	} else {
 		tp->lost_out += tcp_skb_pcount(skb);
 		TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
+		tcp_notify_skb_loss_event(tp, skb);
 	}
 }
 
@@ -2263,7 +2326,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 		if (cnt > packets)
 			break;
 
-		tcp_skb_mark_lost(tp, skb);
+		if (!(TCP_SKB_CB(skb)->sacked & TCPCB_LOST))
+			tcp_mark_skb_lost(sk, skb);
 
 		if (mark_head)
 			break;
@@ -2483,7 +2547,7 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
  *   1) If the packets in flight is larger than ssthresh, PRR spreads the
  *	cwnd reductions across a full RTT.
  *   2) Otherwise PRR uses packet conservation to send as much as delivered.
- *      But when the retransmits are acked without further losses, PRR
+ *      But when SND_UNA is acked without further losses,
  *      slow starts cwnd up to ssthresh to speed up the recovery.
  */
 static void tcp_init_cwnd_reduction(struct sock *sk)
@@ -2500,7 +2564,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk)
 	tcp_ecn_queue_cwr(tp);
 }
 
-void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)
+void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost, int flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	int sndcnt = 0;
@@ -2514,8 +2578,7 @@ void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int flag)
 		u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +
 			       tp->prior_cwnd - 1;
 		sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out;
-	} else if ((flag & (FLAG_RETRANS_DATA_ACKED | FLAG_LOST_RETRANS)) ==
-		   FLAG_RETRANS_DATA_ACKED) {
+	} else if (flag & FLAG_SND_UNA_ADVANCED && !newly_lost) {
 		sndcnt = min_t(int, delta,
 			       max_t(int, tp->prr_delivered - tp->prr_out,
 				     newly_acked_sacked) + 1);
@@ -2626,17 +2689,26 @@ void tcp_simple_retransmit(struct sock *sk)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	unsigned int mss = tcp_current_mss(sk);
+	int mss;
+
+	/* A fastopen SYN request is stored as two separate packets within
+	 * the retransmit queue, this is done by tcp_send_syn_data().
+	 * As a result simply checking the MSS of the frames in the queue
+	 * will not work for the SYN packet.
+	 *
+	 * Us being here is an indication of a path MTU issue so we can
+	 * assume that the fastopen SYN was lost and just mark all the
+	 * frames in the retransmit queue as lost. We will use an MSS of
+	 * -1 to mark all frames as lost, otherwise compute the current MSS.
+	 */
+	if (tp->syn_data && sk->sk_state == TCP_SYN_SENT)
+		mss = -1;
+	else
+		mss = tcp_current_mss(sk);
 
 	skb_rbtree_walk(skb, &sk->tcp_rtx_queue) {
-		if (tcp_skb_seglen(skb) > mss &&
-		    !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) {
-			if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
-				TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
-				tp->retrans_out -= tcp_skb_pcount(skb);
-			}
-			tcp_skb_mark_lost_uncond_verify(tp, skb);
-		}
+		if (tcp_skb_seglen(skb) > mss)
+			tcp_mark_skb_lost(sk, skb);
 	}
 
 	tcp_clear_retrans_hints_partial(tp);
@@ -2787,7 +2859,8 @@ static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag)
 	} else if (tcp_is_rack(sk)) {
 		u32 prior_retrans = tp->retrans_out;
 
-		tcp_rack_mark_lost(sk);
+		if (tcp_rack_mark_lost(sk))
+			*ack_flag &= ~FLAG_SET_XMIT_TIMER;
 		if (prior_retrans > tp->retrans_out)
 			*ack_flag |= FLAG_LOST_RETRANS;
 	}
@@ -3312,6 +3385,7 @@ static void tcp_ack_probe(struct sock *sk)
 		return;
 	if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) {
 		icsk->icsk_backoff = 0;
+		icsk->icsk_probes_tstamp = 0;
 		inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0);
 		/* Socket must be waked up by subsequent tcp_data_snd_check().
 		 * This function is not for random using!
@@ -3319,8 +3393,8 @@ static void tcp_ack_probe(struct sock *sk)
 	} else {
 		unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
 
-		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-				     when, TCP_RTO_MAX);
+		when = tcp_clamp_probe0_to_user_timeout(sk, when);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, TCP_RTO_MAX);
 	}
 }
 
@@ -3362,7 +3436,7 @@ static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked,
 
 	if (tcp_in_cwnd_reduction(sk)) {
 		/* Reduce cwnd if state mandates */
-		tcp_cwnd_reduction(sk, acked_sacked, flag);
+		tcp_cwnd_reduction(sk, acked_sacked, rs->losses, flag);
 	} else if (tcp_may_raise_cwnd(sk, flag)) {
 		/* Advance cwnd if state allows */
 		tcp_cong_avoid(sk, ack, acked_sacked);
@@ -3743,9 +3817,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	if (tp->tlp_high_seq)
 		tcp_process_tlp_ack(sk, ack, flag);
-	/* If needed, reset TLP/RTO timer; RACK may later override this. */
-	if (flag & FLAG_SET_XMIT_TIMER)
-		tcp_set_xmit_timer(sk);
 
 	if (tcp_ack_is_dubious(sk, flag)) {
 		if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) {
@@ -3758,6 +3829,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 				      &rexmit);
 	}
 
+	/* If needed, reset TLP/RTO timer when RACK doesn't set. */
+	if (flag & FLAG_SET_XMIT_TIMER)
+		tcp_set_xmit_timer(sk);
+
 	if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
 		sk_dst_confirm(sk);
 
@@ -3819,7 +3894,7 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie,
 	foc->exp = exp_opt;
 }
 
-static void smc_parse_options(const struct tcphdr *th,
+static bool smc_parse_options(const struct tcphdr *th,
 			      struct tcp_options_received *opt_rx,
 			      const unsigned char *ptr,
 			      int opsize)
@@ -3828,10 +3903,13 @@ static void smc_parse_options(const struct tcphdr *th,
 	if (static_branch_unlikely(&tcp_have_smc)) {
 		if (th->syn && !(opsize & 1) &&
 		    opsize >= TCPOLEN_EXP_SMC_BASE &&
-		    get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)
+		    get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC) {
 			opt_rx->smc_ok = 1;
+			return true;
+		}
 	}
 #endif
+	return false;
 }
 
 /* Try to parse the MSS option from the TCP header. Return 0 on failure, clamped
@@ -3892,6 +3970,7 @@ void tcp_parse_options(const struct net *net,
 
 	ptr = (const unsigned char *)(th + 1);
 	opt_rx->saw_tstamp = 0;
+	opt_rx->saw_unknown = 0;
 
 	while (length > 0) {
 		int opcode = *ptr++;
@@ -3982,15 +4061,21 @@ void tcp_parse_options(const struct net *net,
 				 */
 				if (opsize >= TCPOLEN_EXP_FASTOPEN_BASE &&
 				    get_unaligned_be16(ptr) ==
-				    TCPOPT_FASTOPEN_MAGIC)
+				    TCPOPT_FASTOPEN_MAGIC) {
 					tcp_parse_fastopen_option(opsize -
 						TCPOLEN_EXP_FASTOPEN_BASE,
 						ptr + 2, th->syn, foc, true);
-				else
-					smc_parse_options(th, opt_rx, ptr,
-							  opsize);
+					break;
+				}
+
+				if (smc_parse_options(th, opt_rx, ptr, opsize))
+					break;
+
+				opt_rx->saw_unknown = 1;
 				break;
 
+			default:
+				opt_rx->saw_unknown = 1;
 			}
 			ptr += opsize-2;
 			length -= opsize;
@@ -4151,10 +4236,13 @@ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
 }
 
 /* When we get a reset we do this. */
-void tcp_reset(struct sock *sk)
+void tcp_reset(struct sock *sk, struct sk_buff *skb)
 {
 	trace_tcp_receive_reset(sk);
 
+	if (sk_is_mptcp(sk))
+		mptcp_incoming_options(sk, skb);
+
 	/* We want the right error as BSD sees it (and indeed as we do). */
 	switch (sk->sk_state) {
 	case TCP_SYN_SENT:
@@ -4311,10 +4399,9 @@ static void tcp_rcv_spurious_retrans(struct sock *sk, const struct sk_buff *skb)
 	 * The receiver remembers and reflects via DSACKs. Leverage the
 	 * DSACK state and change the txhash to re-route speculatively.
 	 */
-	if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq) {
-		sk_rethink_txhash(sk);
+	if (TCP_SKB_CB(skb)->seq == tcp_sk(sk)->duplicate_sack[0].start_seq &&
+	    sk_rethink_txhash(sk))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPDUPLICATEDATAREHASH);
-	}
 }
 
 static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb)
@@ -4363,7 +4450,8 @@ static void tcp_sack_maybe_coalesce(struct tcp_sock *tp)
 				sp[i] = sp[i + 1];
 			continue;
 		}
-		this_sack++, swalk++;
+		this_sack++;
+		swalk++;
 	}
 }
 
@@ -4840,7 +4928,8 @@ void tcp_data_ready(struct sock *sk)
 	int avail = tp->rcv_nxt - tp->copied_seq;
 
 	if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&
-	    !sock_flag(sk, SOCK_DONE))
+	    !sock_flag(sk, SOCK_DONE) &&
+	    tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss)
 		return;
 
 	sk->sk_data_ready(sk);
@@ -4853,7 +4942,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	int eaten;
 
 	if (sk_is_mptcp(sk))
-		mptcp_incoming_options(sk, skb, &tp->rx_opt);
+		mptcp_incoming_options(sk, skb);
 
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		__kfree_skb(skb);
@@ -5277,12 +5366,6 @@ static bool tcp_should_expand_sndbuf(const struct sock *sk)
 	return true;
 }
 
-/* When incoming ACK allowed to free some skb from write_queue,
- * we remember this event in flag SOCK_QUEUE_SHRUNK and wake up socket
- * on the exit from tcp input handler.
- *
- * PROBLEM: sndbuf expansion does not work well with largesend.
- */
 static void tcp_new_space(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -5297,16 +5380,13 @@ static void tcp_new_space(struct sock *sk)
 
 static void tcp_check_space(struct sock *sk)
 {
-	if (sock_flag(sk, SOCK_QUEUE_SHRUNK)) {
-		sock_reset_flag(sk, SOCK_QUEUE_SHRUNK);
-		/* pairs with tcp_poll() */
-		smp_mb();
-		if (sk->sk_socket &&
-		    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
-			tcp_new_space(sk);
-			if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
-				tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
-		}
+	/* pairs with tcp_poll() */
+	smp_mb();
+	if (sk->sk_socket &&
+	    test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
+		tcp_new_space(sk);
+		if (!test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
+			tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
 	}
 }
 
@@ -5544,7 +5624,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 						  &tp->last_oow_ack_time))
 				tcp_send_dupack(sk, skb);
 		} else if (tcp_reset_check(sk, skb)) {
-			tcp_reset(sk);
+			tcp_reset(sk, skb);
 		}
 		goto discard;
 	}
@@ -5580,7 +5660,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		}
 
 		if (rst_seq_match)
-			tcp_reset(sk);
+			tcp_reset(sk, skb);
 		else {
 			/* Disable TFO if RST is out-of-order
 			 * and no data has been received
@@ -5608,6 +5688,8 @@ syn_challenge:
 		goto discard;
 	}
 
+	bpf_skops_parse_hdr(sk, skb);
+
 	return true;
 
 discard:
@@ -5766,6 +5848,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 				tcp_data_snd_check(sk);
 				if (!inet_csk_ack_scheduled(sk))
 					goto no_ack;
+			} else {
+				tcp_update_wl(tp, TCP_SKB_CB(skb)->seq);
 			}
 
 			__tcp_ack_snd_check(sk, 0);
@@ -5816,7 +5900,7 @@ discard:
 }
 EXPORT_SYMBOL(tcp_rcv_established);
 
-void tcp_init_transfer(struct sock *sk, int bpf_op)
+void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -5837,8 +5921,10 @@ void tcp_init_transfer(struct sock *sk, int bpf_op)
 		tp->snd_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk));
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 
-	tcp_call_bpf(sk, bpf_op, 0, NULL);
-	tcp_init_congestion_control(sk);
+	icsk->icsk_ca_initialized = 0;
+	bpf_skops_established(sk, bpf_op, skb);
+	if (!icsk->icsk_ca_initialized)
+		tcp_init_congestion_control(sk);
 	tcp_init_buffer_space(sk);
 }
 
@@ -5856,7 +5942,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 		sk_mark_napi_id(sk, skb);
 	}
 
-	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
+	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB, skb);
 
 	/* Prevent spurious tcp_cwnd_restart() on first data
 	 * packet.
@@ -6011,7 +6097,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		 */
 
 		if (th->rst) {
-			tcp_reset(sk);
+			tcp_reset(sk, skb);
 			goto discard;
 		}
 
@@ -6328,7 +6414,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		} else {
 			tcp_try_undo_spurious_syn(sk);
 			tp->retrans_stamp = 0;
-			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB);
+			tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB,
+					  skb);
 			WRITE_ONCE(tp->copied_seq, tp->rcv_nxt);
 		}
 		smp_mb();
@@ -6438,7 +6525,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_LAST_ACK:
 		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 			if (sk_is_mptcp(sk))
-				mptcp_incoming_options(sk, skb, &tp->rx_opt);
+				mptcp_incoming_options(sk, skb);
 			break;
 		}
 		fallthrough;
@@ -6452,7 +6539,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
 			    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
 				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
-				tcp_reset(sk);
+				tcp_reset(sk, skb);
 				return 1;
 			}
 		}
@@ -6617,13 +6704,27 @@ static void tcp_reqsk_record_syn(const struct sock *sk,
 {
 	if (tcp_sk(sk)->save_syn) {
 		u32 len = skb_network_header_len(skb) + tcp_hdrlen(skb);
-		u32 *copy;
+		struct saved_syn *saved_syn;
+		u32 mac_hdrlen;
+		void *base;
+
+		if (tcp_sk(sk)->save_syn == 2) {  /* Save full header. */
+			base = skb_mac_header(skb);
+			mac_hdrlen = skb_mac_header_len(skb);
+			len += mac_hdrlen;
+		} else {
+			base = skb_network_header(skb);
+			mac_hdrlen = 0;
+		}
 
-		copy = kmalloc(len + sizeof(u32), GFP_ATOMIC);
-		if (copy) {
-			copy[0] = len;
-			memcpy(&copy[1], skb_network_header(skb), len);
-			req->saved_syn = copy;
+		saved_syn = kmalloc(struct_size(saved_syn, data, len),
+				    GFP_ATOMIC);
+		if (saved_syn) {
+			saved_syn->mac_hdrlen = mac_hdrlen;
+			saved_syn->network_hdrlen = skb_network_header_len(skb);
+			saved_syn->tcp_hdrlen = tcp_hdrlen(skb);
+			memcpy(saved_syn->data, base, len);
+			req->saved_syn = saved_syn;
 		}
 	}
 }
@@ -6719,18 +6820,13 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	/* Note: tcp_v6_init_req() might override ir_iif for link locals */
 	inet_rsk(req)->ir_iif = inet_request_bound_dev_if(sk, skb);
 
-	af_ops->init_req(req, sk, skb);
-
-	if (security_inet_conn_request(sk, skb, req))
+	dst = af_ops->route_req(sk, skb, &fl, req);
+	if (!dst)
 		goto drop_and_free;
 
 	if (tmp_opt.tstamp_ok)
 		tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
 
-	dst = af_ops->route_req(sk, &fl, req);
-	if (!dst)
-		goto drop_and_free;
-
 	if (!want_cookie && !isn) {
 		/* Kill the following clause, if you dislike this way. */
 		if (!net->ipv4.sysctl_tcp_syncookies &&
@@ -6762,6 +6858,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 
 	tcp_rsk(req)->snt_isn = isn;
 	tcp_rsk(req)->txhash = net_tx_rndhash();
+	tcp_rsk(req)->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
 	tcp_openreq_init_rwin(req, sk, dst);
 	sk_rx_queue_set(req_to_sk(req), skb);
 	if (!want_cookie) {
@@ -6770,7 +6867,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	}
 	if (fastopen_sk) {
 		af_ops->send_synack(fastopen_sk, dst, &fl, req,
-				    &foc, TCP_SYNACK_FASTOPEN);
+				    &foc, TCP_SYNACK_FASTOPEN, skb);
 		/* Add the child socket directly into the accept queue */
 		if (!inet_csk_reqsk_queue_add(sk, req, fastopen_sk)) {
 			reqsk_fastopen_remove(fastopen_sk, req, false);
@@ -6788,7 +6885,8 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 				tcp_timeout_init((struct sock *)req));
 		af_ops->send_synack(sk, dst, &fl, req, &foc,
 				    !want_cookie ? TCP_SYNACK_NORMAL :
-						   TCP_SYNACK_COOKIE);
+						   TCP_SYNACK_COOKIE,
+				    skb);
 		if (want_cookie) {
 			reqsk_free(req);
 			return 0;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 592c73962723..777306b5bc22 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -575,7 +575,7 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
 	case TCP_SYN_SENT:
 	case TCP_SYN_RECV:
 		/* Only in fast or simultaneous open. If a fast open socket is
-		 * is already accepted it is treated as a connected one below.
+		 * already accepted it is treated as a connected one below.
 		 */
 		if (fastopen && !fastopen->sk)
 			break;
@@ -965,26 +965,38 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 			      struct flowi *fl,
 			      struct request_sock *req,
 			      struct tcp_fastopen_cookie *foc,
-			      enum tcp_synack_type synack_type)
+			      enum tcp_synack_type synack_type,
+			      struct sk_buff *syn_skb)
 {
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct flowi4 fl4;
 	int err = -1;
 	struct sk_buff *skb;
+	u8 tos;
 
 	/* First, grab a route. */
 	if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
 		return -1;
 
-	skb = tcp_make_synack(sk, dst, req, foc, synack_type);
+	skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
 
 	if (skb) {
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
+		tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
+				(inet_sk(sk)->tos & INET_ECN_MASK) :
+				inet_sk(sk)->tos;
+
+		if (!INET_ECN_is_capable(tos) &&
+		    tcp_bpf_ca_needs_ecn((struct sock *)req))
+			tos |= INET_ECN_ECT_0;
+
 		rcu_read_lock();
 		err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr,
 					    ireq->ir_rmt_addr,
-					    rcu_dereference(ireq->ireq_opt));
+					    rcu_dereference(ireq->ireq_opt),
+					    tos);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -1433,9 +1445,15 @@ static void tcp_v4_init_req(struct request_sock *req,
 }
 
 static struct dst_entry *tcp_v4_route_req(const struct sock *sk,
+					  struct sk_buff *skb,
 					  struct flowi *fl,
-					  const struct request_sock *req)
+					  struct request_sock *req)
 {
+	tcp_v4_init_req(req, sk, skb);
+
+	if (security_inet_conn_request(sk, skb, req))
+		return NULL;
+
 	return inet_csk_route_req(sk, &fl->u.ip4, req);
 }
 
@@ -1455,7 +1473,6 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.req_md5_lookup	=	tcp_v4_md5_lookup,
 	.calc_md5_hash	=	tcp_v4_md5_hash_skb,
 #endif
-	.init_req	=	tcp_v4_init_req,
 #ifdef CONFIG_SYN_COOKIES
 	.cookie_init_seq =	cookie_v4_init_sequence,
 #endif
@@ -1492,6 +1509,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 				  bool *own_req)
 {
 	struct inet_request_sock *ireq;
+	bool found_dup_sk = false;
 	struct inet_sock *newinet;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
@@ -1529,6 +1547,12 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 	newinet->inet_id = prandom_u32();
 
+	/* Set ToS of the new socket based upon the value of incoming SYN.
+	 * ECT bits are set later in tcp_init_transfer().
+	 */
+	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+		newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
+
 	if (!dst) {
 		dst = inet_csk_route_child_sock(sk, newsk, req);
 		if (!dst)
@@ -1565,12 +1589,22 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 
 	if (__inet_inherit_port(sk, newsk) < 0)
 		goto put_and_exit;
-	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
+				       &found_dup_sk);
 	if (likely(*own_req)) {
 		tcp_move_syn(newtp, req);
 		ireq->ireq_opt = NULL;
 	} else {
 		newinet->inet_opt = NULL;
+
+		if (!req_unhash && found_dup_sk) {
+			/* This code path should only be executed in the
+			 * syncookie case only
+			 */
+			bh_unlock_sock(newsk);
+			sock_put(newsk);
+			newsk = NULL;
+		}
 	}
 	return newsk;
 
@@ -1726,6 +1760,7 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 {
 	u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf);
+	u32 tail_gso_size, tail_gso_segs;
 	struct skb_shared_info *shinfo;
 	const struct tcphdr *th;
 	struct tcphdr *thtail;
@@ -1733,6 +1768,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	unsigned int hdrlen;
 	bool fragstolen;
 	u32 gso_segs;
+	u32 gso_size;
 	int delta;
 
 	/* In case all data was pulled from skb frags (in __pskb_pull_tail()),
@@ -1758,13 +1794,6 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	 */
 	th = (const struct tcphdr *)skb->data;
 	hdrlen = th->doff * 4;
-	shinfo = skb_shinfo(skb);
-
-	if (!shinfo->gso_size)
-		shinfo->gso_size = skb->len - hdrlen;
-
-	if (!shinfo->gso_segs)
-		shinfo->gso_segs = 1;
 
 	tail = sk->sk_backlog.tail;
 	if (!tail)
@@ -1787,6 +1816,15 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 		goto no_coalesce;
 
 	__skb_pull(skb, hdrlen);
+
+	shinfo = skb_shinfo(skb);
+	gso_size = shinfo->gso_size ?: skb->len;
+	gso_segs = shinfo->gso_segs ?: 1;
+
+	shinfo = skb_shinfo(tail);
+	tail_gso_size = shinfo->gso_size ?: (tail->len - hdrlen);
+	tail_gso_segs = shinfo->gso_segs ?: 1;
+
 	if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) {
 		TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq;
 
@@ -1813,11 +1851,8 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 		}
 
 		/* Not as strict as GRO. We only need to carry mss max value */
-		skb_shinfo(tail)->gso_size = max(shinfo->gso_size,
-						 skb_shinfo(tail)->gso_size);
-
-		gso_segs = skb_shinfo(tail)->gso_segs + shinfo->gso_segs;
-		skb_shinfo(tail)->gso_segs = min_t(u32, gso_segs, 0xFFFF);
+		shinfo->gso_size = max(gso_size, tail_gso_size);
+		shinfo->gso_segs = min_t(u32, gso_segs + tail_gso_segs, 0xFFFF);
 
 		sk->sk_backlog.len += delta;
 		__NET_INC_STATS(sock_net(sk),
@@ -2730,6 +2765,20 @@ void tcp4_proc_exit(void)
 }
 #endif /* CONFIG_PROC_FS */
 
+/* @wake is one when sk_stream_write_space() calls us.
+ * This sends EPOLLOUT only if notsent_bytes is half the limit.
+ * This mimics the strategy used in sock_def_write_space().
+ */
+bool tcp_stream_memory_free(const struct sock *sk, int wake)
+{
+	const struct tcp_sock *tp = tcp_sk(sk);
+	u32 notsent_bytes = READ_ONCE(tp->write_seq) -
+			    READ_ONCE(tp->snd_nxt);
+
+	return (notsent_bytes << wake) < tcp_notsent_lowat(tp);
+}
+EXPORT_SYMBOL(tcp_stream_memory_free);
+
 struct proto tcp_prot = {
 	.name			= "TCP",
 	.owner			= THIS_MODULE,
diff --git a/net/ipv4/tcp_lp.c b/net/ipv4/tcp_lp.c
index 8c643a4ffad1..e6459537d4d2 100644
--- a/net/ipv4/tcp_lp.c
+++ b/net/ipv4/tcp_lp.c
@@ -89,6 +89,7 @@ struct lp {
 
 /**
  * tcp_lp_init
+ * @sk: socket to initialize congestion control algorithm for
  *
  * Init all required variables.
  * Clone the handling from Vegas module implementation.
@@ -111,6 +112,7 @@ static void tcp_lp_init(struct sock *sk)
 
 /**
  * tcp_lp_cong_avoid
+ * @sk: socket to avoid congesting
  *
  * Implementation of cong_avoid.
  * Will only call newReno CA when away from inference.
@@ -126,6 +128,7 @@ static void tcp_lp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 
 /**
  * tcp_lp_remote_hz_estimator
+ * @sk: socket which needs an estimate for the remote HZs
  *
  * Estimate remote HZ.
  * We keep on updating the estimated value, where original TCP-LP
@@ -176,6 +179,7 @@ static u32 tcp_lp_remote_hz_estimator(struct sock *sk)
 
 /**
  * tcp_lp_owd_calculator
+ * @sk: socket to calculate one way delay for
  *
  * Calculate one way delay (in relative format).
  * Original implement OWD as minus of remote time difference to local time
@@ -210,6 +214,8 @@ static u32 tcp_lp_owd_calculator(struct sock *sk)
 
 /**
  * tcp_lp_rtt_sample
+ * @sk: socket to add a rtt sample to
+ * @rtt: round trip time, which is ignored!
  *
  * Implementation or rtt_sample.
  * Will take the following action,
@@ -254,6 +260,7 @@ static void tcp_lp_rtt_sample(struct sock *sk, u32 rtt)
 
 /**
  * tcp_lp_pkts_acked
+ * @sk: socket requiring congestion avoidance calculations
  *
  * Implementation of pkts_acked.
  * Deal with active drop under Early Congestion Indication.
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 279db8822439..0588b004ddac 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -887,7 +887,7 @@ static void tcp_metrics_flush_all(struct net *net)
 		pp = &hb->chain;
 		for (tm = deref_locked(*pp); tm; tm = deref_locked(*pp)) {
 			match = net ? net_eq(tm_net(tm), net) :
-				!refcount_read(&tm_net(tm)->count);
+				!refcount_read(&tm_net(tm)->ns.count);
 			if (match) {
 				*pp = tm->tcpm_next;
 				kfree_rcu(tm, rcu_head);
@@ -943,7 +943,7 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-static const struct genl_ops tcp_metrics_nl_ops[] = {
+static const struct genl_small_ops tcp_metrics_nl_ops[] = {
 	{
 		.cmd = TCP_METRICS_CMD_GET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -966,8 +966,8 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = {
 	.policy = tcp_metrics_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= tcp_metrics_nl_ops,
-	.n_ops		= ARRAY_SIZE(tcp_metrics_nl_ops),
+	.small_ops	= tcp_metrics_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(tcp_metrics_nl_ops),
 };
 
 static unsigned int tcpmhash_entries;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 495dda2449fe..0055ae0a3bf8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -801,7 +801,7 @@ embryonic_reset:
 		req->rsk_ops->send_reset(sk, skb);
 	} else if (fastopen) { /* received a valid RST pkt */
 		reqsk_fastopen_remove(sk, req, true);
-		tcp_reset(sk);
+		tcp_reset(sk, skb);
 	}
 	if (!fastopen) {
 		inet_csk_reqsk_queue_drop(sk, req);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 85ff417bda7f..8478cf749821 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -438,20 +438,161 @@ struct tcp_out_options {
 	u8 ws;			/* window scale, 0 to disable */
 	u8 num_sack_blocks;	/* number of SACK blocks to include */
 	u8 hash_size;		/* bytes in hash_location */
+	u8 bpf_opt_len;		/* length of BPF hdr option */
 	__u8 *hash_location;	/* temporary pointer, overloaded */
 	__u32 tsval, tsecr;	/* need to include OPTION_TS */
 	struct tcp_fastopen_cookie *fastopen_cookie;	/* Fast open cookie */
 	struct mptcp_out_options mptcp;
 };
 
-static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
+static void mptcp_options_write(__be32 *ptr, const struct tcp_sock *tp,
+				struct tcp_out_options *opts)
 {
 #if IS_ENABLED(CONFIG_MPTCP)
 	if (unlikely(OPTION_MPTCP & opts->options))
-		mptcp_write_options(ptr, &opts->mptcp);
+		mptcp_write_options(ptr, tp, &opts->mptcp);
 #endif
 }
 
+#ifdef CONFIG_CGROUP_BPF
+static int bpf_skops_write_hdr_opt_arg0(struct sk_buff *skb,
+					enum tcp_synack_type synack_type)
+{
+	if (unlikely(!skb))
+		return BPF_WRITE_HDR_TCP_CURRENT_MSS;
+
+	if (unlikely(synack_type == TCP_SYNACK_COOKIE))
+		return BPF_WRITE_HDR_TCP_SYNACK_COOKIE;
+
+	return 0;
+}
+
+/* req, syn_skb and synack_type are used when writing synack */
+static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
+				  struct request_sock *req,
+				  struct sk_buff *syn_skb,
+				  enum tcp_synack_type synack_type,
+				  struct tcp_out_options *opts,
+				  unsigned int *remaining)
+{
+	struct bpf_sock_ops_kern sock_ops;
+	int err;
+
+	if (likely(!BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk),
+					   BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG)) ||
+	    !*remaining)
+		return;
+
+	/* *remaining has already been aligned to 4 bytes, so *remaining >= 4 */
+
+	/* init sock_ops */
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+
+	sock_ops.op = BPF_SOCK_OPS_HDR_OPT_LEN_CB;
+
+	if (req) {
+		/* The listen "sk" cannot be passed here because
+		 * it is not locked.  It would not make too much
+		 * sense to do bpf_setsockopt(listen_sk) based
+		 * on individual connection request also.
+		 *
+		 * Thus, "req" is passed here and the cgroup-bpf-progs
+		 * of the listen "sk" will be run.
+		 *
+		 * "req" is also used here for fastopen even the "sk" here is
+		 * a fullsock "child" sk.  It is to keep the behavior
+		 * consistent between fastopen and non-fastopen on
+		 * the bpf programming side.
+		 */
+		sock_ops.sk = (struct sock *)req;
+		sock_ops.syn_skb = syn_skb;
+	} else {
+		sock_owned_by_me(sk);
+
+		sock_ops.is_fullsock = 1;
+		sock_ops.sk = sk;
+	}
+
+	sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
+	sock_ops.remaining_opt_len = *remaining;
+	/* tcp_current_mss() does not pass a skb */
+	if (skb)
+		bpf_skops_init_skb(&sock_ops, skb, 0);
+
+	err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
+
+	if (err || sock_ops.remaining_opt_len == *remaining)
+		return;
+
+	opts->bpf_opt_len = *remaining - sock_ops.remaining_opt_len;
+	/* round up to 4 bytes */
+	opts->bpf_opt_len = (opts->bpf_opt_len + 3) & ~3;
+
+	*remaining -= opts->bpf_opt_len;
+}
+
+static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
+				    struct request_sock *req,
+				    struct sk_buff *syn_skb,
+				    enum tcp_synack_type synack_type,
+				    struct tcp_out_options *opts)
+{
+	u8 first_opt_off, nr_written, max_opt_len = opts->bpf_opt_len;
+	struct bpf_sock_ops_kern sock_ops;
+	int err;
+
+	if (likely(!max_opt_len))
+		return;
+
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+
+	sock_ops.op = BPF_SOCK_OPS_WRITE_HDR_OPT_CB;
+
+	if (req) {
+		sock_ops.sk = (struct sock *)req;
+		sock_ops.syn_skb = syn_skb;
+	} else {
+		sock_owned_by_me(sk);
+
+		sock_ops.is_fullsock = 1;
+		sock_ops.sk = sk;
+	}
+
+	sock_ops.args[0] = bpf_skops_write_hdr_opt_arg0(skb, synack_type);
+	sock_ops.remaining_opt_len = max_opt_len;
+	first_opt_off = tcp_hdrlen(skb) - max_opt_len;
+	bpf_skops_init_skb(&sock_ops, skb, first_opt_off);
+
+	err = BPF_CGROUP_RUN_PROG_SOCK_OPS_SK(&sock_ops, sk);
+
+	if (err)
+		nr_written = 0;
+	else
+		nr_written = max_opt_len - sock_ops.remaining_opt_len;
+
+	if (nr_written < max_opt_len)
+		memset(skb->data + first_opt_off + nr_written, TCPOPT_NOP,
+		       max_opt_len - nr_written);
+}
+#else
+static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
+				  struct request_sock *req,
+				  struct sk_buff *syn_skb,
+				  enum tcp_synack_type synack_type,
+				  struct tcp_out_options *opts,
+				  unsigned int *remaining)
+{
+}
+
+static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
+				    struct request_sock *req,
+				    struct sk_buff *syn_skb,
+				    enum tcp_synack_type synack_type,
+				    struct tcp_out_options *opts)
+{
+}
+#endif
+
 /* Write previously computed TCP options to the packet.
  *
  * Beware: Something in the Internet is very sensitive to the ordering of
@@ -561,7 +702,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 
 	smc_options_write(ptr, &options);
 
-	mptcp_options_write(ptr, opts);
+	mptcp_options_write(ptr, tp, opts);
 }
 
 static void smc_set_option(const struct tcp_sock *tp,
@@ -691,6 +832,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
+	bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -701,7 +844,8 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 				       struct tcp_out_options *opts,
 				       const struct tcp_md5sig_key *md5,
 				       struct tcp_fastopen_cookie *foc,
-				       enum tcp_synack_type synack_type)
+				       enum tcp_synack_type synack_type,
+				       struct sk_buff *syn_skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	unsigned int remaining = MAX_TCP_OPTION_SPACE;
@@ -758,6 +902,9 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 
 	smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
 
+	bpf_skops_hdr_opt_len((struct sock *)sk, skb, req, syn_skb,
+			      synack_type, opts, &remaining);
+
 	return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -826,6 +973,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 			opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
 	}
 
+	if (unlikely(BPF_SOCK_OPS_TEST_FLAG(tp,
+					    BPF_SOCK_OPS_WRITE_HDR_OPT_CB_FLAG))) {
+		unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
+
+		bpf_skops_hdr_opt_len(sk, skb, NULL, NULL, 0, opts, &remaining);
+
+		size = MAX_TCP_OPTION_SPACE - remaining;
+	}
+
 	return size;
 }
 
@@ -883,9 +1039,9 @@ static void tcp_tsq_handler(struct sock *sk)
  * transferring tsq->head because tcp_wfree() might
  * interrupt us (non NAPI drivers)
  */
-static void tcp_tasklet_func(unsigned long data)
+static void tcp_tasklet_func(struct tasklet_struct *t)
 {
-	struct tsq_tasklet *tsq = (struct tsq_tasklet *)data;
+	struct tsq_tasklet *tsq = from_tasklet(tsq,  t, tasklet);
 	LIST_HEAD(list);
 	unsigned long flags;
 	struct list_head *q, *n;
@@ -970,9 +1126,7 @@ void __init tcp_tasklet_init(void)
 		struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i);
 
 		INIT_LIST_HEAD(&tsq->head);
-		tasklet_init(&tsq->tasklet,
-			     tcp_tasklet_func,
-			     (unsigned long)tsq);
+		tasklet_setup(&tsq->tasklet, tcp_tasklet_func);
 	}
 }
 
@@ -1193,7 +1347,6 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		}
 	}
 
-	tcp_options_write((__be32 *)(th + 1), tp, &opts);
 	skb_shinfo(skb)->gso_type = sk->sk_gso_type;
 	if (likely(!(tcb->tcp_flags & TCPHDR_SYN))) {
 		th->window      = htons(tcp_select_window(sk));
@@ -1204,6 +1357,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 		 */
 		th->window	= htons(min(tp->rcv_wnd, 65535U));
 	}
+
+	tcp_options_write((__be32 *)(th + 1), tp, &opts);
+
 #ifdef CONFIG_TCP_MD5SIG
 	/* Calculate the MD5 hash, as we have all we need now */
 	if (md5) {
@@ -1213,6 +1369,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	}
 #endif
 
+	/* BPF prog is the last one writing header option */
+	bpf_skops_write_hdr_opt(sk, skb, NULL, NULL, 0, &opts);
+
 	INDIRECT_CALL_INET(icsk->icsk_af_ops->send_check,
 			   tcp_v6_send_check, tcp_v4_send_check,
 			   sk, skb);
@@ -1411,6 +1570,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	if (!buff)
 		return -ENOMEM; /* We'll just try again later. */
 	skb_copy_decrypted(buff, skb);
+	mptcp_skb_ext_copy(buff, skb);
 
 	sk_wmem_queued_add(sk, buff->truesize);
 	sk_mem_charge(sk, buff->truesize);
@@ -1524,7 +1684,6 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
 		skb->truesize	   -= delta_truesize;
 		sk_wmem_queued_add(sk, -delta_truesize);
 		sk_mem_uncharge(sk, delta_truesize);
-		sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
 	}
 
 	/* Any change of skb->len requires recalculation of tso factor. */
@@ -1723,7 +1882,8 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
 	 * window, and remember whether we were cwnd-limited then.
 	 */
 	if (!before(tp->snd_una, tp->max_packets_seq) ||
-	    tp->packets_out > tp->max_packets_out) {
+	    tp->packets_out > tp->max_packets_out ||
+	    is_cwnd_limited) {
 		tp->max_packets_out = tp->packets_out;
 		tp->max_packets_seq = tp->snd_nxt;
 		tp->is_cwnd_limited = is_cwnd_limited;
@@ -1966,6 +2126,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	if (unlikely(!buff))
 		return -ENOMEM;
 	skb_copy_decrypted(buff, skb);
+	mptcp_skb_ext_copy(buff, skb);
 
 	sk_wmem_queued_add(sk, buff->truesize);
 	sk_mem_charge(sk, buff->truesize);
@@ -2236,6 +2397,7 @@ static int tcp_mtu_probe(struct sock *sk)
 
 	skb = tcp_send_head(sk);
 	skb_copy_decrypted(nskb, skb);
+	mptcp_skb_ext_copy(nskb, skb);
 
 	TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
 	TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
@@ -2545,6 +2707,10 @@ repair:
 	else
 		tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED);
 
+	is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd);
+	if (likely(sent_pkts || is_cwnd_limited))
+		tcp_cwnd_validate(sk, is_cwnd_limited);
+
 	if (likely(sent_pkts)) {
 		if (tcp_in_cwnd_reduction(sk))
 			tp->prr_out += sent_pkts;
@@ -2552,8 +2718,6 @@ repair:
 		/* Send one loss probe per tail loss episode. */
 		if (push_one != 2)
 			tcp_schedule_loss_probe(sk, false);
-		is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd);
-		tcp_cwnd_validate(sk, is_cwnd_limited);
 		return false;
 	}
 	return !tp->packets_out && !tcp_write_queue_empty(sk);
@@ -3336,20 +3500,20 @@ int tcp_send_synack(struct sock *sk)
 }
 
 /**
- * tcp_make_synack - Prepare a SYN-ACK.
- * sk: listener socket
- * dst: dst entry attached to the SYNACK
- * req: request_sock pointer
- * foc: cookie for tcp fast open
- * synack_type: Type of synback to prepare
- *
- * Allocate one skb and build a SYNACK packet.
- * @dst is consumed : Caller should not use it again.
+ * tcp_make_synack - Allocate one skb and build a SYNACK packet.
+ * @sk: listener socket
+ * @dst: dst entry attached to the SYNACK. It is consumed and caller
+ *       should not use it again.
+ * @req: request_sock pointer
+ * @foc: cookie for tcp fast open
+ * @synack_type: Type of synack to prepare
+ * @syn_skb: SYN packet just received.  It could be NULL for rtx case.
  */
 struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 				struct request_sock *req,
 				struct tcp_fastopen_cookie *foc,
-				enum tcp_synack_type synack_type)
+				enum tcp_synack_type synack_type,
+				struct sk_buff *syn_skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -3408,8 +3572,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
 	skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
+	/* bpf program will be interested in the tcp_flags */
+	TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK;
 	tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
-					     foc, synack_type) + sizeof(*th);
+					     foc, synack_type,
+					     syn_skb) + sizeof(*th);
 
 	skb_push(skb, tcp_header_size);
 	skb_reset_transport_header(skb);
@@ -3441,6 +3608,9 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 	rcu_read_unlock();
 #endif
 
+	bpf_skops_write_hdr_opt((struct sock *)sk, skb, req, syn_skb,
+				synack_type, &opts);
+
 	skb->skb_mstamp_ns = now;
 	tcp_add_tx_delay(skb, tp);
 
@@ -3741,16 +3911,15 @@ void tcp_send_delayed_ack(struct sock *sk)
 		ato = min(ato, max_ato);
 	}
 
+	ato = min_t(u32, ato, inet_csk(sk)->icsk_delack_max);
+
 	/* Stay within the limit we were given */
 	timeout = jiffies + ato;
 
 	/* Use new timeout only if there wasn't a older one earlier. */
 	if (icsk->icsk_ack.pending & ICSK_ACK_TIMER) {
-		/* If delack timer was blocked or is about to expire,
-		 * send ACK now.
-		 */
-		if (icsk->icsk_ack.blocked ||
-		    time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
+		/* If delack timer is about to expire, send ACK now. */
+		if (time_before_eq(icsk->icsk_ack.timeout, jiffies + (ato >> 2))) {
 			tcp_send_ack(sk);
 			return;
 		}
@@ -3779,10 +3948,15 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 	buff = alloc_skb(MAX_TCP_HEADER,
 			 sk_gfp_mask(sk, GFP_ATOMIC | __GFP_NOWARN));
 	if (unlikely(!buff)) {
+		struct inet_connection_sock *icsk = inet_csk(sk);
+		unsigned long delay;
+
+		delay = TCP_DELACK_MAX << icsk->icsk_ack.retry;
+		if (delay < TCP_RTO_MAX)
+			icsk->icsk_ack.retry++;
 		inet_csk_schedule_ack(sk);
-		inet_csk(sk)->icsk_ack.ato = TCP_ATO_MIN;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-					  TCP_DELACK_MAX, TCP_RTO_MAX);
+		icsk->icsk_ack.ato = TCP_ATO_MIN;
+		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX);
 		return;
 	}
 
@@ -3910,6 +4084,7 @@ void tcp_send_probe0(struct sock *sk)
 		/* Cancel probe timer, if it is not required. */
 		icsk->icsk_probes_out = 0;
 		icsk->icsk_backoff = 0;
+		icsk->icsk_probes_tstamp = 0;
 		return;
 	}
 
@@ -3924,6 +4099,8 @@ void tcp_send_probe0(struct sock *sk)
 		 */
 		timeout = TCP_RESOURCE_PROBE_INTERVAL;
 	}
+
+	timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout);
 	tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX);
 }
 
@@ -3934,7 +4111,8 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 	int res;
 
 	tcp_rsk(req)->txhash = net_tx_rndhash();
-	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL);
+	res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
+				  NULL);
 	if (!res) {
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index fdb715bdd2d1..6f1b4ac7fe99 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -2,20 +2,6 @@
 #include <linux/tcp.h>
 #include <net/tcp.h>
 
-void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
-{
-	struct tcp_sock *tp = tcp_sk(sk);
-
-	tcp_skb_mark_lost_uncond_verify(tp, skb);
-	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) {
-		/* Account for retransmits that are lost again */
-		TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
-		tp->retrans_out -= tcp_skb_pcount(skb);
-		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT,
-			      tcp_skb_pcount(skb));
-	}
-}
-
 static bool tcp_rack_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2)
 {
 	return t1 > t2 || (t1 == t2 && after(seq1, seq2));
@@ -110,13 +96,13 @@ static void tcp_rack_detect_loss(struct sock *sk, u32 *reo_timeout)
 	}
 }
 
-void tcp_rack_mark_lost(struct sock *sk)
+bool tcp_rack_mark_lost(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 timeout;
 
 	if (!tp->rack.advanced)
-		return;
+		return false;
 
 	/* Reset the advanced flag to avoid unnecessary queue scanning */
 	tp->rack.advanced = 0;
@@ -126,6 +112,7 @@ void tcp_rack_mark_lost(struct sock *sk)
 		inet_csk_reset_xmit_timer(sk, ICSK_TIME_REO_TIMEOUT,
 					  timeout, inet_csk(sk)->icsk_rto);
 	}
+	return !!timeout;
 }
 
 /* Record the most recently (re)sent time among the (s)acked packets
@@ -167,6 +154,7 @@ void tcp_rack_reo_timeout(struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	u32 timeout, prior_inflight;
+	u32 lost = tp->lost;
 
 	prior_inflight = tcp_packets_in_flight(tp);
 	tcp_rack_detect_loss(sk, &timeout);
@@ -174,7 +162,7 @@ void tcp_rack_reo_timeout(struct sock *sk)
 		if (inet_csk(sk)->icsk_ca_state != TCP_CA_Recovery) {
 			tcp_enter_recovery(sk, false);
 			if (!inet_csk(sk)->icsk_ca_ops->cong_control)
-				tcp_cwnd_reduction(sk, 1, 0);
+				tcp_cwnd_reduction(sk, 1, tp->lost - lost, 0);
 		}
 		tcp_xmit_retransmit_queue(sk);
 	}
@@ -246,6 +234,6 @@ void tcp_newreno_mark_lost(struct sock *sk, bool snd_una_advanced)
 			tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb,
 				     mss, mss, GFP_ATOMIC);
 
-		tcp_skb_mark_lost_uncond_verify(tp, skb);
+		tcp_mark_skb_lost(sk, skb);
 	}
 }
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 6cebf412d590..5842081bc8a2 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -10,7 +10,7 @@
 #include <net/tcp.h>
 
 /* These factors derived from the recommended values in the aer:
- * .01 and and 7/8.
+ * .01 and 7/8.
  */
 #define TCP_SCALABLE_AI_CNT	100U
 #define TCP_SCALABLE_MD_SCALE	3
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 0c08c420fbc2..4ef08079ccfa 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -40,6 +40,24 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 	return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));
 }
 
+u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 remaining;
+	s32 elapsed;
+
+	if (!icsk->icsk_user_timeout || !icsk->icsk_probes_tstamp)
+		return when;
+
+	elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp;
+	if (unlikely(elapsed < 0))
+		elapsed = 0;
+	remaining = msecs_to_jiffies(icsk->icsk_user_timeout) - elapsed;
+	remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN);
+
+	return min_t(u32, remaining, when);
+}
+
 /**
  *  tcp_write_err() - close socket and save error info
  *  @sk:  The socket the error has appeared on.
@@ -219,14 +237,8 @@ static int tcp_write_timeout(struct sock *sk)
 	int retry_until;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
-		if (icsk->icsk_retransmits) {
-			dst_negative_advice(sk);
-		} else {
-			sk_rethink_txhash(sk);
-			tp->timeout_rehash++;
-			__NET_INC_STATS(sock_net(sk),
-					LINUX_MIB_TCPTIMEOUTREHASH);
-		}
+		if (icsk->icsk_retransmits)
+			__dst_negative_advice(sk);
 		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
 		expired = icsk->icsk_retransmits >= retry_until;
 	} else {
@@ -234,12 +246,7 @@ static int tcp_write_timeout(struct sock *sk)
 			/* Black hole detection */
 			tcp_mtu_probing(icsk, sk);
 
-			dst_negative_advice(sk);
-		} else {
-			sk_rethink_txhash(sk);
-			tp->timeout_rehash++;
-			__NET_INC_STATS(sock_net(sk),
-					LINUX_MIB_TCPTIMEOUTREHASH);
+			__dst_negative_advice(sk);
 		}
 
 		retry_until = net->ipv4.sysctl_tcp_retries2;
@@ -270,6 +277,11 @@ static int tcp_write_timeout(struct sock *sk)
 		return 1;
 	}
 
+	if (sk_rethink_txhash(sk)) {
+		tp->timeout_rehash++;
+		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH);
+	}
+
 	return 0;
 }
 
@@ -331,7 +343,6 @@ static void tcp_delack_timer(struct timer_list *t)
 	if (!sock_owned_by_user(sk)) {
 		tcp_delack_timer_handler(sk);
 	} else {
-		icsk->icsk_ack.blocked = 1;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
 		/* deleguate our work to tcp_release_cb() */
 		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags))
@@ -350,6 +361,7 @@ static void tcp_probe_timer(struct sock *sk)
 
 	if (tp->packets_out || !skb) {
 		icsk->icsk_probes_out = 0;
+		icsk->icsk_probes_tstamp = 0;
 		return;
 	}
 
@@ -361,13 +373,12 @@ static void tcp_probe_timer(struct sock *sk)
 	 * corresponding system limit. We also implement similar policy when
 	 * we use RTO to probe window in tcp_retransmit_timer().
 	 */
-	if (icsk->icsk_user_timeout) {
-		u32 elapsed = tcp_model_timeout(sk, icsk->icsk_probes_out,
-						tcp_probe0_base(sk));
-
-		if (elapsed >= icsk->icsk_user_timeout)
-			goto abort;
-	}
+	if (!icsk->icsk_probes_tstamp)
+		icsk->icsk_probes_tstamp = tcp_jiffies32;
+	else if (icsk->icsk_user_timeout &&
+		 (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >=
+		 msecs_to_jiffies(icsk->icsk_user_timeout))
+		goto abort;
 
 	max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
 	if (sock_flag(sk, SOCK_DEAD)) {
diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c
index 3f51e781562a..c8003c8aad2c 100644
--- a/net/ipv4/tcp_vegas.c
+++ b/net/ipv4/tcp_vegas.c
@@ -293,10 +293,10 @@ size_t tcp_vegas_get_info(struct sock *sk, u32 ext, int *attr,
 	const struct vegas *ca = inet_csk_ca(sk);
 
 	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
-		info->vegas.tcpv_enabled = ca->doing_vegas_now,
-		info->vegas.tcpv_rttcnt = ca->cntRTT,
-		info->vegas.tcpv_rtt = ca->baseRTT,
-		info->vegas.tcpv_minrtt = ca->minRTT,
+		info->vegas.tcpv_enabled = ca->doing_vegas_now;
+		info->vegas.tcpv_rttcnt = ca->cntRTT;
+		info->vegas.tcpv_rtt = ca->baseRTT;
+		info->vegas.tcpv_minrtt = ca->minRTT;
 
 		*attr = INET_DIAG_VEGASINFO;
 		return sizeof(struct tcpvegas_info);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index e88efba07551..69ea76578abb 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -541,7 +541,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 				 inet_sdif(skb), udptable, skb);
 }
 
-struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
+struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
 				 __be16 sport, __be16 dport)
 {
 	const struct iphdr *iph = ip_hdr(skb);
@@ -550,7 +550,6 @@ struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
 				 iph->daddr, dport, inet_iif(skb),
 				 inet_sdif(skb), &udp_table, NULL);
 }
-EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb);
 
 /* Must be called under rcu_read_lock().
  * Does increment socket refcount.
@@ -702,7 +701,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
 			       iph->saddr, uh->source, skb->dev->ifindex,
 			       inet_sdif(skb), udptable, NULL);
-	if (!sk) {
+	if (!sk || udp_sk(sk)->encap_type) {
 		/* No socket for error: try tunnels before discarding */
 		sk = ERR_PTR(-ENOENT);
 		if (static_branch_unlikely(&udp_encap_needed_key)) {
@@ -874,7 +873,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
 	struct sock *sk = skb->sk;
 	struct inet_sock *inet = inet_sk(sk);
 	struct udphdr *uh;
-	int err = 0;
+	int err;
 	int is_udplite = IS_UDPLITE(sk);
 	int offset = skb_transport_offset(skb);
 	int len = skb->len - offset;
@@ -1170,7 +1169,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		ipc.oif = inet->uc_index;
 	} else if (ipv4_is_lbcast(daddr) && inet->uc_index) {
 		/* oif is set, packet is to local broadcast and
-		 * and uc_index is set. oif is most likely set
+		 * uc_index is set. oif is most likely set
 		 * by sk_bound_dev_if. If uc_index != oif check if the
 		 * oif is an L3 master and uc_index is an L3 slave.
 		 * If so, we want to allow the send using the uc_index.
@@ -1197,7 +1196,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 				   faddr, saddr, dport, inet->inet_sport,
 				   sk->sk_uid);
 
-		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
+		security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
 		rt = ip_route_output_flow(net, fl4, sk);
 		if (IS_ERR(rt)) {
 			err = PTR_ERR(rt);
@@ -2038,6 +2037,9 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		if (rc == -ENOMEM)
 			UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS,
 					is_udplite);
+		else
+			UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS,
+				      is_udplite);
 		UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 		kfree_skb(skb);
 		trace_udp_fail_queue_rcv_skb(rc, sk);
@@ -2173,7 +2175,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		__skb_pull(skb, skb_transport_offset(skb));
 		ret = udp_queue_rcv_one_skb(sk, skb);
 		if (ret > 0)
-			ip_protocol_deliver_rcu(dev_net(skb->dev), skb, -ret);
+			ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret);
 	}
 	return 0;
 }
@@ -2553,7 +2555,8 @@ int udp_v4_early_demux(struct sk_buff *skb)
 		 */
 		if (!inet_sk(sk)->inet_daddr && in_dev)
 			return ip_mc_validate_source(skb, iph->daddr,
-						     iph->saddr, iph->tos,
+						     iph->saddr,
+						     iph->tos & IPTOS_RT_MASK,
 						     skb->dev, in_dev, &itag);
 	}
 	return 0;
diff --git a/net/ipv4/udp_bpf.c b/net/ipv4/udp_bpf.c
index eddd973e6575..7a94791efc1a 100644
--- a/net/ipv4/udp_bpf.c
+++ b/net/ipv4/udp_bpf.c
@@ -22,10 +22,9 @@ static void udp_bpf_rebuild_protos(struct proto *prot, const struct proto *base)
 	prot->close  = sock_map_close;
 }
 
-static void udp_bpf_check_v6_needs_rebuild(struct sock *sk, struct proto *ops)
+static void udp_bpf_check_v6_needs_rebuild(struct proto *ops)
 {
-	if (sk->sk_family == AF_INET6 &&
-	    unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
+	if (unlikely(ops != smp_load_acquire(&udpv6_prot_saved))) {
 		spin_lock_bh(&udpv6_prot_lock);
 		if (likely(ops != udpv6_prot_saved)) {
 			udp_bpf_rebuild_protos(&udp_bpf_prots[UDP_BPF_IPV6], ops);
@@ -46,8 +45,8 @@ struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock)
 {
 	int family = sk->sk_family == AF_INET ? UDP_BPF_IPV4 : UDP_BPF_IPV6;
 
-	if (!psock->sk_proto)
-		udp_bpf_check_v6_needs_rebuild(sk, READ_ONCE(sk->sk_prot));
+	if (sk->sk_family == AF_INET6)
+		udp_bpf_check_v6_needs_rebuild(psock->sk_proto);
 
 	return &udp_bpf_prots[family];
 }
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index 1dbece34496e..b2cee9a307d4 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -30,7 +30,7 @@ static int udp_dump_one(struct udp_table *tbl,
 			const struct inet_diag_req_v2 *req)
 {
 	struct sk_buff *in_skb = cb->skb;
-	int err = -EINVAL;
+	int err;
 	struct sock *sk = NULL;
 	struct sk_buff *rep;
 	struct net *net = sock_net(in_skb->sk);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e67a66fbf27b..cfc872689b99 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -49,6 +49,7 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	__skb_pull(skb, tnl_hlen);
 	skb_reset_mac_header(skb);
 	skb_set_network_header(skb, skb_inner_network_offset(skb));
+	skb_set_transport_header(skb, skb_inner_transport_offset(skb));
 	skb->mac_len = skb_inner_network_offset(skb);
 	skb->protocol = new_protocol;
 
@@ -67,6 +68,8 @@ static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 				      (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM))));
 
 	features &= skb->dev->hw_enc_features;
+	/* CRC checksum can't be handled by HW when it's a UDP tunneling packet. */
+	features &= ~NETIF_F_SCTP_CRC;
 
 	/* The only checksum offload we care about from here on out is the
 	 * outer one so strip the existing checksum feature flags and
@@ -184,8 +187,67 @@ out_unlock:
 }
 EXPORT_SYMBOL(skb_udp_tunnel_segment);
 
+static void __udpv4_gso_segment_csum(struct sk_buff *seg,
+				     __be32 *oldip, __be32 *newip,
+				     __be16 *oldport, __be16 *newport)
+{
+	struct udphdr *uh;
+	struct iphdr *iph;
+
+	if (*oldip == *newip && *oldport == *newport)
+		return;
+
+	uh = udp_hdr(seg);
+	iph = ip_hdr(seg);
+
+	if (uh->check) {
+		inet_proto_csum_replace4(&uh->check, seg, *oldip, *newip,
+					 true);
+		inet_proto_csum_replace2(&uh->check, seg, *oldport, *newport,
+					 false);
+		if (!uh->check)
+			uh->check = CSUM_MANGLED_0;
+	}
+	*oldport = *newport;
+
+	csum_replace4(&iph->check, *oldip, *newip);
+	*oldip = *newip;
+}
+
+static struct sk_buff *__udpv4_gso_segment_list_csum(struct sk_buff *segs)
+{
+	struct sk_buff *seg;
+	struct udphdr *uh, *uh2;
+	struct iphdr *iph, *iph2;
+
+	seg = segs;
+	uh = udp_hdr(seg);
+	iph = ip_hdr(seg);
+
+	if ((udp_hdr(seg)->dest == udp_hdr(seg->next)->dest) &&
+	    (udp_hdr(seg)->source == udp_hdr(seg->next)->source) &&
+	    (ip_hdr(seg)->daddr == ip_hdr(seg->next)->daddr) &&
+	    (ip_hdr(seg)->saddr == ip_hdr(seg->next)->saddr))
+		return segs;
+
+	while ((seg = seg->next)) {
+		uh2 = udp_hdr(seg);
+		iph2 = ip_hdr(seg);
+
+		__udpv4_gso_segment_csum(seg,
+					 &iph2->saddr, &iph->saddr,
+					 &uh2->source, &uh->source);
+		__udpv4_gso_segment_csum(seg,
+					 &iph2->daddr, &iph->daddr,
+					 &uh2->dest, &uh->dest);
+	}
+
+	return segs;
+}
+
 static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
-					      netdev_features_t features)
+					      netdev_features_t features,
+					      bool is_ipv6)
 {
 	unsigned int mss = skb_shinfo(skb)->gso_size;
 
@@ -195,11 +257,11 @@ static struct sk_buff *__udp_gso_segment_list(struct sk_buff *skb,
 
 	udp_hdr(skb)->len = htons(sizeof(struct udphdr) + mss);
 
-	return skb;
+	return is_ipv6 ? skb : __udpv4_gso_segment_list_csum(skb);
 }
 
 struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
-				  netdev_features_t features)
+				  netdev_features_t features, bool is_ipv6)
 {
 	struct sock *sk = gso_skb->sk;
 	unsigned int sum_truesize = 0;
@@ -211,7 +273,7 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 	__be16 newlen;
 
 	if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)
-		return __udp_gso_segment_list(gso_skb, features);
+		return __udp_gso_segment_list(gso_skb, features, is_ipv6);
 
 	mss = skb_shinfo(gso_skb)->gso_size;
 	if (gso_skb->len <= sizeof(*uh) + mss)
@@ -325,7 +387,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
 		goto out;
 
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
-		return __udp_gso_segment(skb, features);
+		return __udp_gso_segment(skb, features, false);
 
 	mss = skb_shinfo(skb)->gso_size;
 	if (unlikely(skb->len <= mss))
@@ -366,7 +428,7 @@ out:
 static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 					       struct sk_buff *skb)
 {
-	struct udphdr *uh = udp_hdr(skb);
+	struct udphdr *uh = udp_gro_udphdr(skb);
 	struct sk_buff *pp = NULL;
 	struct udphdr *uh2;
 	struct sk_buff *p;
@@ -500,12 +562,22 @@ out:
 }
 EXPORT_SYMBOL(udp_gro_receive);
 
+static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+					__be16 dport)
+{
+	const struct iphdr *iph = skb_gro_network_header(skb);
+
+	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+				 iph->daddr, dport, inet_iif(skb),
+				 inet_sdif(skb), &udp_table, NULL);
+}
+
 INDIRECT_CALLABLE_SCOPE
 struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
+	struct sock *sk = NULL;
 	struct sk_buff *pp;
-	struct sock *sk;
 
 	if (unlikely(!uh))
 		goto flush;
@@ -523,7 +595,10 @@ struct sk_buff *udp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 skip:
 	NAPI_GRO_CB(skb)->is_ipv6 = 0;
 	rcu_read_lock();
-	sk = static_branch_unlikely(&udp_encap_needed_key) ? udp4_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+	if (static_branch_unlikely(&udp_encap_needed_key))
+		sk = udp4_gro_lookup_skb(skb, uh->source, uh->dest);
+
 	pp = udp_gro_receive(head, skb, uh, sk);
 	rcu_read_unlock();
 	return pp;
@@ -551,8 +626,8 @@ int udp_gro_complete(struct sk_buff *skb, int nhoff,
 {
 	__be16 newlen = htons(skb->len - nhoff);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
-	int err = -ENOSYS;
 	struct sock *sk;
+	int err;
 
 	uh->len = newlen;
 
diff --git a/net/ipv4/udp_tunnel_nic.c b/net/ipv4/udp_tunnel_nic.c
index 69962165c0e8..0d122edc368d 100644
--- a/net/ipv4/udp_tunnel_nic.c
+++ b/net/ipv4/udp_tunnel_nic.c
@@ -19,8 +19,9 @@ enum udp_tunnel_nic_table_entry_flags {
 struct udp_tunnel_nic_table_entry {
 	__be16 port;
 	u8 type;
-	u8 use_cnt;
 	u8 flags;
+	u16 use_cnt;
+#define UDP_TUNNEL_NIC_USE_CNT_MAX	U16_MAX
 	u8 hw_priv;
 };
 
@@ -370,6 +371,8 @@ udp_tunnel_nic_entry_adj(struct udp_tunnel_nic *utn,
 	bool dodgy = entry->flags & UDP_TUNNEL_NIC_ENTRY_OP_FAIL;
 	unsigned int from, to;
 
+	WARN_ON(entry->use_cnt + (u32)use_cnt_adj > U16_MAX);
+
 	/* If not going from used to unused or vice versa - all done.
 	 * For dodgy entries make sure we try to sync again (queue the entry).
 	 */
@@ -675,6 +678,7 @@ static void
 udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
 {
 	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic_shared_node *node;
 	unsigned int i, j;
 
 	/* Freeze all the ports we are already tracking so that the replay
@@ -686,7 +690,12 @@ udp_tunnel_nic_replay(struct net_device *dev, struct udp_tunnel_nic *utn)
 	utn->missed = 0;
 	utn->need_replay = 0;
 
-	udp_tunnel_get_rx_info(dev);
+	if (!info->shared) {
+		udp_tunnel_get_rx_info(dev);
+	} else {
+		list_for_each_entry(node, &info->shared->devices, list)
+			udp_tunnel_get_rx_info(node->dev);
+	}
 
 	for (i = 0; i < utn->n_tables; i++)
 		for (j = 0; j < info->tables[i].n_entries; j++)
@@ -742,20 +751,39 @@ err_free_utn:
 	return NULL;
 }
 
+static void udp_tunnel_nic_free(struct udp_tunnel_nic *utn)
+{
+	unsigned int i;
+
+	for (i = 0; i < utn->n_tables; i++)
+		kfree(utn->entries[i]);
+	kfree(utn->entries);
+	kfree(utn);
+}
+
 static int udp_tunnel_nic_register(struct net_device *dev)
 {
 	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+	struct udp_tunnel_nic_shared_node *node = NULL;
 	struct udp_tunnel_nic *utn;
 	unsigned int n_tables, i;
 
 	BUILD_BUG_ON(sizeof(utn->missed) * BITS_PER_BYTE <
 		     UDP_TUNNEL_NIC_MAX_TABLES);
+	/* Expect use count of at most 2 (IPv4, IPv6) per device */
+	BUILD_BUG_ON(UDP_TUNNEL_NIC_USE_CNT_MAX <
+		     UDP_TUNNEL_NIC_MAX_SHARING_DEVICES * 2);
 
+	/* Check that the driver info is sane */
 	if (WARN_ON(!info->set_port != !info->unset_port) ||
 	    WARN_ON(!info->set_port == !info->sync_table) ||
 	    WARN_ON(!info->tables[0].n_entries))
 		return -EINVAL;
 
+	if (WARN_ON(info->shared &&
+		    info->flags & UDP_TUNNEL_NIC_INFO_OPEN_ONLY))
+		return -EINVAL;
+
 	n_tables = 1;
 	for (i = 1; i < UDP_TUNNEL_NIC_MAX_TABLES; i++) {
 		if (!info->tables[i].n_entries)
@@ -766,9 +794,33 @@ static int udp_tunnel_nic_register(struct net_device *dev)
 			return -EINVAL;
 	}
 
-	utn = udp_tunnel_nic_alloc(info, n_tables);
-	if (!utn)
-		return -ENOMEM;
+	/* Create UDP tunnel state structures */
+	if (info->shared) {
+		node = kzalloc(sizeof(*node), GFP_KERNEL);
+		if (!node)
+			return -ENOMEM;
+
+		node->dev = dev;
+	}
+
+	if (info->shared && info->shared->udp_tunnel_nic_info) {
+		utn = info->shared->udp_tunnel_nic_info;
+	} else {
+		utn = udp_tunnel_nic_alloc(info, n_tables);
+		if (!utn) {
+			kfree(node);
+			return -ENOMEM;
+		}
+	}
+
+	if (info->shared) {
+		if (!info->shared->udp_tunnel_nic_info) {
+			INIT_LIST_HEAD(&info->shared->devices);
+			info->shared->udp_tunnel_nic_info = utn;
+		}
+
+		list_add_tail(&node->list, &info->shared->devices);
+	}
 
 	utn->dev = dev;
 	dev_hold(dev);
@@ -783,7 +835,33 @@ static int udp_tunnel_nic_register(struct net_device *dev)
 static void
 udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
 {
-	unsigned int i;
+	const struct udp_tunnel_nic_info *info = dev->udp_tunnel_nic_info;
+
+	/* For a shared table remove this dev from the list of sharing devices
+	 * and if there are other devices just detach.
+	 */
+	if (info->shared) {
+		struct udp_tunnel_nic_shared_node *node, *first;
+
+		list_for_each_entry(node, &info->shared->devices, list)
+			if (node->dev == dev)
+				break;
+		if (node->dev != dev)
+			return;
+
+		list_del(&node->list);
+		kfree(node);
+
+		first = list_first_entry_or_null(&info->shared->devices,
+						 typeof(*first), list);
+		if (first) {
+			udp_tunnel_drop_rx_info(dev);
+			utn->dev = first->dev;
+			goto release_dev;
+		}
+
+		info->shared->udp_tunnel_nic_info = NULL;
+	}
 
 	/* Flush before we check work, so we don't waste time adding entries
 	 * from the work which we will boot immediately.
@@ -796,10 +874,8 @@ udp_tunnel_nic_unregister(struct net_device *dev, struct udp_tunnel_nic *utn)
 	if (utn->work_pending)
 		return;
 
-	for (i = 0; i < utn->n_tables; i++)
-		kfree(utn->entries[i]);
-	kfree(utn->entries);
-	kfree(utn);
+	udp_tunnel_nic_free(utn);
+release_dev:
 	dev->udp_tunnel_nic = NULL;
 	dev_put(dev);
 }
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index dc19aff7c2e0..fb0648e7fb32 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -64,14 +64,14 @@ static int xfrm_tunnel_err(struct sk_buff *skb, u32 info)
 static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = {
 	.handler	=	xfrm_tunnel_rcv,
 	.err_handler	=	xfrm_tunnel_err,
-	.priority	=	3,
+	.priority	=	4,
 };
 
 #if IS_ENABLED(CONFIG_IPV6)
 static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = {
 	.handler	=	xfrm_tunnel_rcv,
 	.err_handler	=	xfrm_tunnel_err,
-	.priority	=	2,
+	.priority	=	3,
 };
 #endif
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 01146b66d666..9edc5bb2d531 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -1997,6 +1997,7 @@ EXPORT_SYMBOL(ipv6_chk_prefix);
  * ipv6_dev_find - find the first device with a given source address.
  * @net: the net namespace
  * @addr: the source address
+ * @dev: used to find the L3 domain of interest
  *
  * The caller should be protected by RCU, or RTNL.
  */
@@ -2466,8 +2467,9 @@ static void addrconf_add_mroute(struct net_device *dev)
 		.fc_ifindex = dev->ifindex,
 		.fc_dst_len = 8,
 		.fc_flags = RTF_UP,
-		.fc_type = RTN_UNICAST,
+		.fc_type = RTN_MULTICAST,
 		.fc_nlinfo.nl_net = dev_net(dev),
+		.fc_protocol = RTPROT_KERNEL,
 	};
 
 	ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0);
@@ -5022,8 +5024,10 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca,
 		return -EMSGSIZE;
 
 	if (args->netnsid >= 0 &&
-	    nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+	    nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) {
+		nlmsg_cancel(skb, nlh);
 		return -EMSGSIZE;
+	}
 
 	put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
 	if (nla_put_in6_addr(skb, IFA_MULTICAST, &ifmca->mca_addr) < 0 ||
@@ -5054,8 +5058,10 @@ static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca,
 		return -EMSGSIZE;
 
 	if (args->netnsid >= 0 &&
-	    nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid))
+	    nla_put_s32(skb, IFA_TARGET_NETNSID, args->netnsid)) {
+		nlmsg_cancel(skb, nlh);
 		return -EMSGSIZE;
+	}
 
 	put_ifaddrmsg(nlh, 128, IFA_F_PERMANENT, scope, ifindex);
 	if (nla_put_in6_addr(skb, IFA_ANYCAST, &ifaca->aca_addr) < 0 ||
diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c
index 9ebf3fe0d2b1..c70c192bc91b 100644
--- a/net/ipv6/addrconf_core.c
+++ b/net/ipv6/addrconf_core.c
@@ -191,6 +191,13 @@ static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt,
 	return -EAFNOSUPPORT;
 }
 
+static int eafnosupport_ipv6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb,
+				      int (*output)(struct net *, struct sock *, struct sk_buff *))
+{
+	kfree_skb(skb);
+	return -EAFNOSUPPORT;
+}
+
 const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 	.ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow,
 	.ipv6_route_input  = eafnosupport_ipv6_route_input,
@@ -201,6 +208,7 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 	.ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6,
 	.fib6_nh_init	   = eafnosupport_fib6_nh_init,
 	.ip6_del_rt	   = eafnosupport_ip6_del_rt,
+	.ipv6_fragment	   = eafnosupport_ipv6_fragment,
 };
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 642fc6ac13d2..8a22486cf270 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -306,7 +306,9 @@ static int ip6addrlbl_del(struct net *net,
 /* add default label */
 static int __net_init ip6addrlbl_net_init(struct net *net)
 {
-	int err = 0;
+	struct ip6addrlbl_entry *p = NULL;
+	struct hlist_node *n;
+	int err;
 	int i;
 
 	ADDRLABEL(KERN_DEBUG "%s\n", __func__);
@@ -315,14 +317,20 @@ static int __net_init ip6addrlbl_net_init(struct net *net)
 	INIT_HLIST_HEAD(&net->ipv6.ip6addrlbl_table.head);
 
 	for (i = 0; i < ARRAY_SIZE(ip6addrlbl_init_table); i++) {
-		int ret = ip6addrlbl_add(net,
-					 ip6addrlbl_init_table[i].prefix,
-					 ip6addrlbl_init_table[i].prefixlen,
-					 0,
-					 ip6addrlbl_init_table[i].label, 0);
-		/* XXX: should we free all rules when we catch an error? */
-		if (ret && (!err || err != -ENOMEM))
-			err = ret;
+		err = ip6addrlbl_add(net,
+				     ip6addrlbl_init_table[i].prefix,
+				     ip6addrlbl_init_table[i].prefixlen,
+				     0,
+				     ip6addrlbl_init_table[i].label, 0);
+		if (err)
+			goto err_ip6addrlbl_add;
+	}
+	return 0;
+
+err_ip6addrlbl_add:
+	hlist_for_each_entry_safe(p, n, &net->ipv6.ip6addrlbl_table.head, list) {
+		hlist_del_rcu(&p->list);
+		kfree_rcu(p, rcu);
 	}
 	return err;
 }
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 0306509ab063..8e9c3e9ea36e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -451,7 +451,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	/* BPF prog is run before any checks are done so that if the prog
 	 * changes context in a wrong way it will be caught.
 	 */
-	err = BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr);
+	err = BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr);
 	if (err)
 		return err;
 
@@ -661,6 +661,7 @@ int inet6_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 
 const struct proto_ops inet6_stream_ops = {
 	.family		   = PF_INET6,
+	.flags		   = PROTO_CMSG_DATA_ONLY,
 	.owner		   = THIS_MODULE,
 	.release	   = inet6_release,
 	.bind		   = inet6_bind,
@@ -818,7 +819,7 @@ int inet6_sk_rebuild_header(struct sock *sk)
 		fl6.fl6_dport = inet->inet_dport;
 		fl6.fl6_sport = inet->inet_sport;
 		fl6.flowi6_uid = sk->sk_uid;
-		security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+		security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 		rcu_read_lock();
 		final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt),
@@ -1026,6 +1027,7 @@ static const struct ipv6_stub ipv6_stub_impl = {
 	.xfrm6_rcv_encap = xfrm6_rcv_encap,
 #endif
 	.nd_tbl	= &nd_tbl,
+	.ipv6_fragment = ip6_fragment,
 };
 
 static const struct ipv6_bpf_stub ipv6_bpf_stub_impl = {
diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c
index d88d97617f7e..440080da805b 100644
--- a/net/ipv6/ah6.c
+++ b/net/ipv6/ah6.c
@@ -588,7 +588,8 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb)
 	memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len);
 	memset(ah->auth_data, 0, ahp->icv_trunc_len);
 
-	if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN))
+	err = ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN);
+	if (err)
 		goto out_free;
 
 	ip6h->priority    = 0;
diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c
index 8d3f66c310db..51184a70ac7e 100644
--- a/net/ipv6/calipso.c
+++ b/net/ipv6/calipso.c
@@ -423,7 +423,7 @@ static void calipso_doi_free_rcu(struct rcu_head *entry)
 /**
  * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine
  * @doi: the DOI value
- * @audit_secid: the LSM secid to use in the audit message
+ * @audit_info: NetLabel audit information
  *
  * Description:
  * Removes a DOI definition from the CALIPSO engine.  The NetLabel routines will
@@ -761,7 +761,7 @@ static int calipso_genopt(unsigned char *buf, u32 start, u32 buf_len,
 	calipso[1] = len - 2;
 	*(__be32 *)(calipso + 2) = htonl(doi_def->doi);
 	calipso[6] = (len - CALIPSO_HDR_LEN) / 4;
-	calipso[7] = secattr->attr.mls.lvl,
+	calipso[7] = secattr->attr.mls.lvl;
 	crc = ~crc_ccitt(0xffff, calipso, len);
 	calipso[8] = crc & 0xff;
 	calipso[9] = (crc >> 8) & 0xff;
@@ -1226,7 +1226,7 @@ static int calipso_req_setattr(struct request_sock *req,
 
 /**
  * calipso_req_delattr - Delete the CALIPSO option from a request socket
- * @reg: the request socket
+ * @req: the request socket
  *
  * Description:
  * Removes the CALIPSO option from a request socket, if present.
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index cc8ad7ddecda..206f66310a88 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -60,7 +60,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
 	if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr))
 		fl6->flowi6_oif = np->mcast_oif;
 
-	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
 }
 
 int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
index 52c2f063529f..2b804fcebcc6 100644
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@ -478,7 +478,6 @@ static int esp6_output_encap(struct xfrm_state *x, struct sk_buff *skb,
 int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
 {
 	u8 *tail;
-	u8 *vaddr;
 	int nfrags;
 	int esph_offset;
 	struct page *page;
@@ -519,14 +518,10 @@ int esp6_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info
 			page = pfrag->page;
 			get_page(page);
 
-			vaddr = kmap_atomic(page);
-
-			tail = vaddr + pfrag->offset;
+			tail = page_address(page) + pfrag->offset;
 
 			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
 
-			kunmap_atomic(vaddr);
-
 			nfrags = skb_shinfo(skb)->nr_frags;
 
 			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 374105e4394f..6126f8bf94b3 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -906,11 +906,6 @@ void ipv6_exthdrs_exit(void)
 /*
  * Note: we cannot rely on skb_dst(skb) before we assign it in ip6_route_input().
  */
-static inline struct inet6_dev *ipv6_skb_idev(struct sk_buff *skb)
-{
-	return skb_dst(skb) ? ip6_dst_idev(skb_dst(skb)) : __in6_dev_get(skb->dev);
-}
-
 static inline struct net *ipv6_skb_net(struct sk_buff *skb)
 {
 	return skb_dst(skb) ? dev_net(skb_dst(skb)->dev) : dev_net(skb->dev);
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index a4e4912ad607..f3d05866692e 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -158,7 +158,13 @@ static bool is_ineligible(const struct sk_buff *skb)
 		tp = skb_header_pointer(skb,
 			ptr+offsetof(struct icmp6hdr, icmp6_type),
 			sizeof(_type), &_type);
-		if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
+
+		/* Based on RFC 8200, Section 4.5 Fragment Header, return
+		 * false if this is a fragment packet with no icmp header info.
+		 */
+		if (!tp && frag_off != 0)
+			return false;
+		else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
 			return true;
 	}
 	return false;
@@ -314,10 +320,10 @@ static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, st
 {
 	struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
 	struct sk_buff *org_skb = msg->skb;
-	__wsum csum = 0;
+	__wsum csum;
 
 	csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
-				      to, len, csum);
+				      to, len);
 	skb->csum = csum_block_add(skb->csum, csum, odd);
 	if (!(msg->type & ICMPV6_INFOMSG_MASK))
 		nf_ct_attach(skb, org_skb);
@@ -501,8 +507,11 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	if (__ipv6_addr_needs_scope_id(addr_type)) {
 		iif = icmp6_iif(skb);
 	} else {
-		dst = skb_dst(skb);
-		iif = l3mdev_master_ifindex(dst ? dst->dev : skb->dev);
+		/*
+		 * The source device is used for looking up which routing table
+		 * to use for sending an ICMP error.
+		 */
+		iif = l3mdev_master_ifindex(skb->dev);
 	}
 
 	/*
@@ -564,7 +573,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	fl6.fl6_icmp_code = code;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
 	fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
-	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
 
 	np = inet6_sk(sk);
 
@@ -746,7 +755,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	fl6.fl6_icmp_type = ICMPV6_ECHO_REPLY;
 	fl6.flowi6_mark = mark;
 	fl6.flowi6_uid = sock_net_uid(net, NULL);
-	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
 
 	local_bh_disable();
 	sk = icmpv6_xmit_lock(net);
@@ -999,7 +1008,7 @@ void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
 	fl6->fl6_icmp_type	= type;
 	fl6->fl6_icmp_code	= 0;
 	fl6->flowi6_oif		= oif;
-	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
 }
 
 static void __net_exit icmpv6_sk_exit(struct net *net)
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index e315526fa244..5a9f4d722f35 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -46,7 +46,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 	fl6->fl6_dport = ireq->ir_rmt_port;
 	fl6->fl6_sport = htons(ireq->ir_num);
 	fl6->flowi6_uid = sk->sk_uid;
-	security_req_classify_flow(req, flowi6_to_flowi(fl6));
+	security_req_classify_flow(req, flowi6_to_flowi_common(fl6));
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p);
 	if (IS_ERR(dst))
@@ -95,7 +95,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk,
 	fl6->fl6_sport = inet->inet_sport;
 	fl6->fl6_dport = inet->inet_dport;
 	fl6->flowi6_uid = sk->sk_uid;
-	security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
 
 	rcu_read_lock();
 	final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 2d3add9e6116..55c290d55605 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -94,7 +94,7 @@ EXPORT_SYMBOL(__inet6_lookup_established);
 static inline int compute_score(struct sock *sk, struct net *net,
 				const unsigned short hnum,
 				const struct in6_addr *daddr,
-				const int dif, const int sdif, bool exact_dif)
+				const int dif, const int sdif)
 {
 	int score = -1;
 
@@ -138,15 +138,13 @@ static struct sock *inet6_lhash2_lookup(struct net *net,
 		const __be16 sport, const struct in6_addr *daddr,
 		const unsigned short hnum, const int dif, const int sdif)
 {
-	bool exact_dif = inet6_exact_dif_match(net, skb);
 	struct inet_connection_sock *icsk;
 	struct sock *sk, *result = NULL;
 	int score, hiscore = 0;
 
 	inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) {
 		sk = (struct sock *)icsk;
-		score = compute_score(sk, net, hnum, daddr, dif, sdif,
-				      exact_dif);
+		score = compute_score(sk, net, hnum, daddr, dif, sdif);
 		if (score > hiscore) {
 			result = lookup_reuseport(net, sk, skb, doff,
 						  saddr, sport, daddr, hnum);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 4a664ad4f4d4..f43e27555725 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1025,6 +1025,8 @@ static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
 {
 	struct fib6_table *table = rt->fib6_table;
 
+	/* Flush all cached dst in exception table */
+	rt6_flush_exceptions(rt);
 	fib6_drop_pcpu_from(rt, table);
 
 	if (rt->nh && !list_empty(&rt->nh_list))
@@ -1812,10 +1814,14 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
 
 		children = 0;
 		child = NULL;
-		if (fn_r)
-			child = fn_r, children |= 1;
-		if (fn_l)
-			child = fn_l, children |= 2;
+		if (fn_r) {
+			child = fn_r;
+			children |= 1;
+		}
+		if (fn_l) {
+			child = fn_l;
+			children |= 2;
+		}
 
 		if (children == 3 || FIB6_SUBTREE(fn)
 #ifdef CONFIG_IPV6_SUBTREES
@@ -1923,9 +1929,6 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
 	net->ipv6.rt6_stats->fib_rt_entries--;
 	net->ipv6.rt6_stats->fib_discarded_routes++;
 
-	/* Flush all cached dst in exception table */
-	rt6_flush_exceptions(rt);
-
 	/* Reset round-robin state, if necessary */
 	if (rcu_access_pointer(fn->rr_ptr) == rt)
 		fn->rr_ptr = NULL;
@@ -2618,8 +2621,10 @@ static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
 	iter->skip = *pos;
 
 	if (iter->tbl) {
+		loff_t p = 0;
+
 		ipv6_route_seq_setup_walk(iter, net);
-		return ipv6_route_seq_next(seq, NULL, pos);
+		return ipv6_route_seq_next(seq, NULL, &p);
 	} else {
 		return NULL;
 	}
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 3a57fb9ce049..c3bc89b6b1a1 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -707,6 +707,17 @@ static int prepare_ip6gre_xmit_ipv6(struct sk_buff *skb,
 	return 0;
 }
 
+static struct ip_tunnel_info *skb_tunnel_info_txcheck(struct sk_buff *skb)
+{
+	struct ip_tunnel_info *tun_info;
+
+	tun_info = skb_tunnel_info(skb);
+	if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX)))
+		return ERR_PTR(-EINVAL);
+
+	return tun_info;
+}
+
 static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 			       struct net_device *dev, __u8 dsfield,
 			       struct flowi6 *fl6, int encap_limit,
@@ -734,10 +745,9 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb,
 		const struct ip_tunnel_key *key;
 		__be16 flags;
 
-		tun_info = skb_tunnel_info(skb);
-		if (unlikely(!tun_info ||
-			     !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
-			     ip_tunnel_info_af(tun_info) != AF_INET6))
+		tun_info = skb_tunnel_info_txcheck(skb);
+		if (IS_ERR(tun_info) ||
+		    unlikely(ip_tunnel_info_af(tun_info) != AF_INET6))
 			return -EINVAL;
 
 		key = &tun_info->key;
@@ -908,7 +918,8 @@ static netdev_tx_t ip6gre_tunnel_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 
 tx_err:
-	stats->tx_errors++;
+	if (!t->parms.collect_md || !IS_ERR(skb_tunnel_info_txcheck(skb)))
+		stats->tx_errors++;
 	stats->tx_dropped++;
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
@@ -917,6 +928,7 @@ tx_err:
 static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 					 struct net_device *dev)
 {
+	struct ip_tunnel_info *tun_info = NULL;
 	struct ip6_tnl *t = netdev_priv(dev);
 	struct dst_entry *dst = skb_dst(skb);
 	struct net_device_stats *stats;
@@ -964,15 +976,13 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	 * for native mode, call prepare_ip6gre_xmit_{ipv4,ipv6}.
 	 */
 	if (t->parms.collect_md) {
-		struct ip_tunnel_info *tun_info;
 		const struct ip_tunnel_key *key;
 		struct erspan_metadata *md;
 		__be32 tun_id;
 
-		tun_info = skb_tunnel_info(skb);
-		if (unlikely(!tun_info ||
-			     !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
-			     ip_tunnel_info_af(tun_info) != AF_INET6))
+		tun_info = skb_tunnel_info_txcheck(skb);
+		if (IS_ERR(tun_info) ||
+		    unlikely(ip_tunnel_info_af(tun_info) != AF_INET6))
 			goto tx_err;
 
 		key = &tun_info->key;
@@ -1065,7 +1075,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 
 tx_err:
 	stats = &t->dev->stats;
-	stats->tx_errors++;
+	if (!IS_ERR(tun_info))
+		stats->tx_errors++;
 	stats->tx_dropped++;
 	kfree_skb(skb);
 	return NETDEV_TX_OK;
@@ -1122,8 +1133,13 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu,
 			return;
 
 		if (rt->dst.dev) {
-			dev->needed_headroom = rt->dst.dev->hard_header_len +
-					       t_hlen;
+			unsigned short dst_len = rt->dst.dev->hard_header_len +
+						 t_hlen;
+
+			if (t->dev->header_ops)
+				dev->hard_header_len = dst_len;
+			else
+				dev->needed_headroom = dst_len;
 
 			if (set_mtu) {
 				dev->mtu = rt->dst.dev->mtu - t_hlen;
@@ -1148,7 +1164,12 @@ static int ip6gre_calc_hlen(struct ip6_tnl *tunnel)
 	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
 
 	t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
-	tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen;
+
+	if (tunnel->dev->header_ops)
+		tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+	else
+		tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen;
+
 	return t_hlen;
 }
 
@@ -1380,7 +1401,7 @@ static const struct net_device_ops ip6gre_netdev_ops = {
 	.ndo_start_xmit		= ip6gre_tunnel_xmit,
 	.ndo_do_ioctl		= ip6gre_tunnel_ioctl,
 	.ndo_change_mtu		= ip6_tnl_change_mtu,
-	.ndo_get_stats64	= ip_tunnel_get_stats64,
+	.ndo_get_stats64	= dev_get_tstats64,
 	.ndo_get_iflink		= ip6_tnl_get_iflink,
 };
 
@@ -1817,7 +1838,7 @@ static const struct net_device_ops ip6gre_tap_netdev_ops = {
 	.ndo_set_mac_address = eth_mac_addr,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_change_mtu = ip6_tnl_change_mtu,
-	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_stats64 = dev_get_tstats64,
 	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
@@ -1885,7 +1906,7 @@ static const struct net_device_ops ip6erspan_netdev_ops = {
 	.ndo_set_mac_address =	eth_mac_addr,
 	.ndo_validate_addr =	eth_validate_addr,
 	.ndo_change_mtu =	ip6_tnl_change_mtu,
-	.ndo_get_stats64 =	ip_tunnel_get_stats64,
+	.ndo_get_stats64 =	dev_get_tstats64,
 	.ndo_get_iflink =	ip6_tnl_get_iflink,
 };
 
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index c78e67d7747f..077d43af8226 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -125,8 +125,43 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 	return -EINVAL;
 }
 
+static int
+ip6_finish_output_gso_slowpath_drop(struct net *net, struct sock *sk,
+				    struct sk_buff *skb, unsigned int mtu)
+{
+	struct sk_buff *segs, *nskb;
+	netdev_features_t features;
+	int ret = 0;
+
+	/* Please see corresponding comment in ip_finish_output_gso
+	 * describing the cases where GSO segment length exceeds the
+	 * egress MTU.
+	 */
+	features = netif_skb_features(skb);
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+	if (IS_ERR_OR_NULL(segs)) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	consume_skb(skb);
+
+	skb_list_walk_safe(segs, segs, nskb) {
+		int err;
+
+		skb_mark_not_on_list(segs);
+		err = ip6_fragment(net, sk, segs, ip6_finish_output2);
+		if (err && ret == 0)
+			ret = err;
+	}
+
+	return ret;
+}
+
 static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
+	unsigned int mtu;
+
 #if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
 	/* Policy lookup after SNAT yielded a new policy */
 	if (skb_dst(skb)->xfrm) {
@@ -135,7 +170,11 @@ static int __ip6_finish_output(struct net *net, struct sock *sk, struct sk_buff
 	}
 #endif
 
-	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
+	mtu = ip6_skb_dst_mtu(skb);
+	if (skb_is_gso(skb) && !skb_gso_validate_network_len(skb, mtu))
+		return ip6_finish_output_gso_slowpath_drop(net, sk, skb, mtu);
+
+	if ((skb->len > mtu && !skb_is_gso(skb)) ||
 	    dst_allfrag(skb_dst(skb)) ||
 	    (IP6CB(skb)->frag_max_size && skb->len > IP6CB(skb)->frag_max_size))
 		return ip6_fragment(net, sk, skb, ip6_finish_output2);
@@ -468,8 +507,6 @@ int ip6_forward(struct sk_buff *skb)
 	 *	check and decrement ttl
 	 */
 	if (hdr->hop_limit <= 1) {
-		/* Force OUTPUT device used as source address */
-		skb->dev = dst->dev;
 		icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0);
 		__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 
@@ -1492,7 +1529,7 @@ emsgsize:
 	 * Otherwise, we need to reserve fragment header and
 	 * fragment alignment (= 8-15 octects, in total).
 	 *
-	 * Note that we may need to "move" the data from the tail of
+	 * Note that we may need to "move" the data from the tail
 	 * of the buffer to the new fragment when we split
 	 * the message.
 	 *
@@ -1615,7 +1652,7 @@ alloc_new_skb:
 			if (fraggap) {
 				skb->csum = skb_copy_and_csum_bits(
 					skb_prev, maxfraglen,
-					data + transhdrlen, fraggap, 0);
+					data + transhdrlen, fraggap);
 				skb_prev->csum = csum_sub(skb_prev->csum,
 							  skb->csum);
 				data += fraggap;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index a0217e5bf3bc..a7950baa05e5 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -94,36 +94,6 @@ static inline int ip6_tnl_mpls_supported(void)
 	return IS_ENABLED(CONFIG_MPLS);
 }
 
-static struct net_device_stats *ip6_get_stats(struct net_device *dev)
-{
-	struct pcpu_sw_netstats tmp, sum = { 0 };
-	int i;
-
-	for_each_possible_cpu(i) {
-		unsigned int start;
-		const struct pcpu_sw_netstats *tstats =
-						   per_cpu_ptr(dev->tstats, i);
-
-		do {
-			start = u64_stats_fetch_begin_irq(&tstats->syncp);
-			tmp.rx_packets = tstats->rx_packets;
-			tmp.rx_bytes = tstats->rx_bytes;
-			tmp.tx_packets = tstats->tx_packets;
-			tmp.tx_bytes =  tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
-
-		sum.rx_packets += tmp.rx_packets;
-		sum.rx_bytes   += tmp.rx_bytes;
-		sum.tx_packets += tmp.tx_packets;
-		sum.tx_bytes   += tmp.tx_bytes;
-	}
-	dev->stats.rx_packets = sum.rx_packets;
-	dev->stats.rx_bytes   = sum.rx_bytes;
-	dev->stats.tx_packets = sum.tx_packets;
-	dev->stats.tx_bytes   = sum.tx_bytes;
-	return &dev->stats;
-}
-
 #define for_each_ip6_tunnel_rcu(start) \
 	for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
 
@@ -204,6 +174,7 @@ ip6_tnl_lookup(struct net *net, int link,
 
 /**
  * ip6_tnl_bucket - get head of list matching given tunnel parameters
+ *   @ip6n: the private data for ip6_vti in the netns
  *   @p: parameters containing tunnel end-points
  *
  * Description:
@@ -230,6 +201,7 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p)
 
 /**
  * ip6_tnl_link - add tunnel to hash table
+ *   @ip6n: the private data for ip6_vti in the netns
  *   @t: tunnel to be added
  **/
 
@@ -246,6 +218,7 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
 
 /**
  * ip6_tnl_unlink - remove tunnel from hash table
+ *   @ip6n: the private data for ip6_vti in the netns
  *   @t: tunnel to be removed
  **/
 
@@ -417,6 +390,7 @@ ip6_tnl_dev_uninit(struct net_device *dev)
 /**
  * parse_tvl_tnl_enc_lim - handle encapsulation limit option
  *   @skb: received socket buffer
+ *   @raw: the ICMPv6 error message data
  *
  * Return:
  *   0 if none was found,
@@ -485,14 +459,9 @@ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
 }
 EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim);
 
-/**
- * ip6_tnl_err - tunnel error handler
- *
- * Description:
- *   ip6_tnl_err() should handle errors in the tunnel according
- *   to the specifications in RFC 2473.
- **/
-
+/* ip6_tnl_err() should handle errors in the tunnel according to the
+ * specifications in RFC 2473.
+ */
 static int
 ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
 	    u8 *type, u8 *code, int *msg, __u32 *info, int offset)
@@ -1271,6 +1240,8 @@ route_lookup:
 	if (max_headroom > dev->needed_headroom)
 		dev->needed_headroom = max_headroom;
 
+	skb_set_inner_ipproto(skb, proto);
+
 	err = ip6_tnl_encap(skb, t, &proto, fl6);
 	if (err)
 		return err;
@@ -1280,8 +1251,6 @@ route_lookup:
 		ipv6_push_frag_opts(skb, &opt.ops, &proto);
 	}
 
-	skb_set_inner_ipproto(skb, proto);
-
 	skb_push(skb, sizeof(struct ipv6hdr));
 	skb_reset_network_header(skb);
 	ipv6h = ipv6_hdr(skb);
@@ -1835,7 +1804,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = {
 	.ndo_start_xmit = ip6_tnl_start_xmit,
 	.ndo_do_ioctl	= ip6_tnl_ioctl,
 	.ndo_change_mtu = ip6_tnl_change_mtu,
-	.ndo_get_stats	= ip6_get_stats,
+	.ndo_get_stats64 = dev_get_tstats64,
 	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index fac01b80a104..0225fd694192 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -125,6 +125,7 @@ vti6_tnl_lookup(struct net *net, const struct in6_addr *remote,
 
 /**
  * vti6_tnl_bucket - get head of list matching given tunnel parameters
+ *   @ip6n: the private data for ip6_vti in the netns
  *   @p: parameters containing tunnel end-points
  *
  * Description:
@@ -347,7 +348,6 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
 {
 	unsigned short family;
 	struct net_device *dev;
-	struct pcpu_sw_netstats *tstats;
 	struct xfrm_state *x;
 	const struct xfrm_mode *inner_mode;
 	struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6;
@@ -390,12 +390,7 @@ static int vti6_rcv_cb(struct sk_buff *skb, int err)
 
 	skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev)));
 	skb->dev = dev;
-
-	tstats = this_cpu_ptr(dev->tstats);
-	u64_stats_update_begin(&tstats->syncp);
-	tstats->rx_packets++;
-	tstats->rx_bytes += skb->len;
-	u64_stats_update_end(&tstats->syncp);
+	dev_sw_netstats_rx_add(dev, skb->len);
 
 	return 0;
 }
@@ -895,7 +890,7 @@ static const struct net_device_ops vti6_netdev_ops = {
 	.ndo_uninit	= vti6_dev_uninit,
 	.ndo_start_xmit = vti6_tnl_xmit,
 	.ndo_do_ioctl	= vti6_ioctl,
-	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_stats64 = dev_get_tstats64,
 	.ndo_get_iflink = ip6_tnl_get_iflink,
 };
 
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 43a894bf9a1b..a6804a7e34c1 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1148,7 +1148,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname,
 		if (sk->sk_type != SOCK_STREAM)
 			return -ENOPROTOOPT;
 
-		msg.msg_control = optval;
+		msg.msg_control_user = optval;
 		msg.msg_controllen = len;
 		msg.msg_flags = flags;
 		msg.msg_control_is_user = true;
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 8cd2782a31e4..6c8604390266 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -548,7 +548,7 @@ done:
 }
 
 int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf,
-	struct sockaddr_storage *p)
+		  struct sockaddr_storage __user *p)
 {
 	int err, i, count, copycount;
 	const struct in6_addr *group;
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 27f29b957ee7..76717478f173 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -81,6 +81,7 @@ static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
 static int pndisc_constructor(struct pneigh_entry *n);
 static void pndisc_destructor(struct pneigh_entry *n);
 static void pndisc_redo(struct sk_buff *skb);
+static int ndisc_is_multicast(const void *pkey);
 
 static const struct neigh_ops ndisc_generic_ops = {
 	.family =		AF_INET6,
@@ -115,6 +116,7 @@ struct neigh_table nd_tbl = {
 	.pconstructor =	pndisc_constructor,
 	.pdestructor =	pndisc_destructor,
 	.proxy_redo =	pndisc_redo,
+	.is_multicast =	ndisc_is_multicast,
 	.allow_add  =   ndisc_allow_add,
 	.id =		"ndisc_cache",
 	.parms = {
@@ -1706,6 +1708,11 @@ static void pndisc_redo(struct sk_buff *skb)
 	kfree_skb(skb);
 }
 
+static int ndisc_is_multicast(const void *pkey)
+{
+	return ipv6_addr_is_multicast((struct in6_addr *)pkey);
+}
+
 static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
 {
 	struct inet6_dev *idev = __in6_dev_get(skb->dev);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 6d0e942d082d..ab9a279dd6d4 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -20,10 +20,10 @@
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #include "../bridge/br_private.h"
 
-int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
+int ip6_route_me_harder(struct net *net, struct sock *sk_partial, struct sk_buff *skb)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
-	struct sock *sk = sk_to_full_sk(skb->sk);
+	struct sock *sk = sk_to_full_sk(sk_partial);
 	unsigned int hh_len;
 	struct dst_entry *dst;
 	int strict = (ipv6_addr_type(&iph->daddr) &
@@ -84,7 +84,7 @@ static int nf_ip6_reroute(struct sk_buff *skb,
 		if (!ipv6_addr_equal(&iph->daddr, &rt_info->daddr) ||
 		    !ipv6_addr_equal(&iph->saddr, &rt_info->saddr) ||
 		    skb->mark != rt_info->mark)
-			return ip6_route_me_harder(entry->state.net, skb);
+			return ip6_route_me_harder(entry->state.net, entry->state.sk, skb);
 	}
 	return 0;
 }
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 2e2119bfcf13..0d453fa9e327 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb,
 
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
-	private = READ_ONCE(table->private); /* Address dependency. */
+	private = rcu_access_pointer(table->private);
 	cpu        = smp_processor_id();
 	table_base = private->entries;
 	jumpstack  = (struct ip6t_entry **)private->jumpstack[cpu];
@@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table)
 {
 	unsigned int countersize;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 
 	/* We need atomic snapshot of counters: rest doesn't change
 	   (other than comefrom, which userspace doesn't care
@@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size,
 	unsigned int off, num;
 	const struct ip6t_entry *e;
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	int ret = 0;
 	const void *loc_cpu_entry;
 
@@ -980,7 +980,7 @@ static int get_info(struct net *net, void __user *user, const int *len)
 	t = xt_request_find_table_lock(net, AF_INET6, name);
 	if (!IS_ERR(t)) {
 		struct ip6t_getinfo info;
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 #ifdef CONFIG_COMPAT
 		struct xt_table_info tmp;
 
@@ -1035,7 +1035,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr,
 
 	t = xt_find_table_lock(net, AF_INET6, get.name);
 	if (!IS_ERR(t)) {
-		struct xt_table_info *private = t->private;
+		struct xt_table_info *private = xt_table_get_private_protected(t);
 		if (get.size == private->size)
 			ret = copy_entries_to_user(private->size,
 						   t, uptr->entrytable);
@@ -1189,7 +1189,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len)
 	}
 
 	local_bh_disable();
-	private = t->private;
+	private = xt_table_get_private_protected(t);
 	if (private->number != tmp.num_counters) {
 		ret = -EINVAL;
 		goto unlock_up_free;
@@ -1552,7 +1552,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table,
 			    void __user *userptr)
 {
 	struct xt_counters *counters;
-	const struct xt_table_info *private = table->private;
+	const struct xt_table_info *private = xt_table_get_private_protected(table);
 	void __user *pos;
 	unsigned int size;
 	int ret = 0;
@@ -1598,7 +1598,7 @@ compat_get_entries(struct net *net, struct compat_ip6t_get_entries __user *uptr,
 	xt_compat_lock(AF_INET6);
 	t = xt_find_table_lock(net, AF_INET6, get.name);
 	if (!IS_ERR(t)) {
-		const struct xt_table_info *private = t->private;
+		const struct xt_table_info *private = xt_table_get_private_protected(t);
 		struct xt_table_info info;
 		ret = compat_table_info(private, &info);
 		if (!ret && get.size == info.size)
diff --git a/net/ipv6/netfilter/ip6t_NPT.c b/net/ipv6/netfilter/ip6t_NPT.c
index 9ee077bf4f49..787c74aa85e3 100644
--- a/net/ipv6/netfilter/ip6t_NPT.c
+++ b/net/ipv6/netfilter/ip6t_NPT.c
@@ -77,16 +77,43 @@ static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt,
 	return true;
 }
 
+static struct ipv6hdr *icmpv6_bounced_ipv6hdr(struct sk_buff *skb,
+					      struct ipv6hdr *_bounced_hdr)
+{
+	if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6)
+		return NULL;
+
+	if (!icmpv6_is_err(icmp6_hdr(skb)->icmp6_type))
+		return NULL;
+
+	return skb_header_pointer(skb,
+				  skb_transport_offset(skb) + sizeof(struct icmp6hdr),
+				  sizeof(struct ipv6hdr),
+				  _bounced_hdr);
+}
+
 static unsigned int
 ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ip6t_npt_tginfo *npt = par->targinfo;
+	struct ipv6hdr _bounced_hdr;
+	struct ipv6hdr *bounced_hdr;
+	struct in6_addr bounced_pfx;
 
 	if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) {
 		icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD,
 			    offsetof(struct ipv6hdr, saddr));
 		return NF_DROP;
 	}
+
+	/* rewrite dst addr of bounced packet which was sent to dst range */
+	bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr);
+	if (bounced_hdr) {
+		ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->daddr, npt->src_pfx_len);
+		if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0)
+			ip6t_npt_map_pfx(npt, &bounced_hdr->daddr);
+	}
+
 	return XT_CONTINUE;
 }
 
@@ -94,12 +121,24 @@ static unsigned int
 ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par)
 {
 	const struct ip6t_npt_tginfo *npt = par->targinfo;
+	struct ipv6hdr _bounced_hdr;
+	struct ipv6hdr *bounced_hdr;
+	struct in6_addr bounced_pfx;
 
 	if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) {
 		icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD,
 			    offsetof(struct ipv6hdr, daddr));
 		return NF_DROP;
 	}
+
+	/* rewrite src addr of bounced packet which was sent from dst range */
+	bounced_hdr = icmpv6_bounced_ipv6hdr(skb, &_bounced_hdr);
+	if (bounced_hdr) {
+		ipv6_addr_prefix(&bounced_pfx, &bounced_hdr->saddr, npt->src_pfx_len);
+		if (ipv6_addr_cmp(&bounced_pfx, &npt->src_pfx.in6) == 0)
+			ip6t_npt_map_pfx(npt, &bounced_hdr->saddr);
+	}
+
 	return XT_CONTINUE;
 }
 
diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c
index 3ac5485049f0..a35019d2e480 100644
--- a/net/ipv6/netfilter/ip6t_REJECT.c
+++ b/net/ipv6/netfilter/ip6t_REJECT.c
@@ -61,7 +61,7 @@ reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 		/* Do nothing */
 		break;
 	case IP6T_TCP_RESET:
-		nf_send_reset6(net, skb, xt_hooknum(par));
+		nf_send_reset6(net, par->state->sk, skb, xt_hooknum(par));
 		break;
 	case IP6T_ICMP6_POLICY_FAIL:
 		nf_send_unreach6(net, skb, ICMPV6_POLICY_FAIL, xt_hooknum(par));
diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c
index 1a2748611e00..cee74803d7a1 100644
--- a/net/ipv6/netfilter/ip6table_mangle.c
+++ b/net/ipv6/netfilter/ip6table_mangle.c
@@ -57,7 +57,7 @@ ip6t_mangle_out(struct sk_buff *skb, const struct nf_hook_state *state)
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
 	     flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
-		err = ip6_route_me_harder(state->net, skb);
+		err = ip6_route_me_harder(state->net, state->sk, skb);
 		if (err < 0)
 			ret = NF_DROP_ERR(err);
 	}
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index fed9666a2f7d..c129ad334eb3 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -355,6 +355,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
 	ipv6_hdr(skb)->payload_len = htons(payload_len);
 	ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn);
 	IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
+	IP6CB(skb)->flags |= IP6SKB_FRAGMENTED;
 
 	/* Yes, and fold redundant checksum back. 8) */
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
@@ -439,6 +440,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
 int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 {
 	u16 savethdr = skb->transport_header;
+	u8 nexthdr = NEXTHDR_FRAGMENT;
 	int fhoff, nhoff, ret;
 	struct frag_hdr *fhdr;
 	struct frag_queue *fq;
@@ -454,6 +456,14 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
 		return 0;
 
+	/* Discard the first fragment if it does not include all headers
+	 * RFC 8200, Section 4.5
+	 */
+	if (ipv6frag_thdr_truncated(skb, fhoff, &nexthdr)) {
+		pr_debug("Drop incomplete fragment\n");
+		return 0;
+	}
+
 	if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr)))
 		return -ENOMEM;
 
diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c
index da64550a5707..8210ff34ed9b 100644
--- a/net/ipv6/netfilter/nf_log_ipv6.c
+++ b/net/ipv6/netfilter/nf_log_ipv6.c
@@ -297,9 +297,11 @@ static void dump_ipv6_mac_header(struct nf_log_buf *m,
 
 	switch (dev->type) {
 	case ARPHRD_ETHER:
-		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ",
-		       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest,
-		       ntohs(eth_hdr(skb)->h_proto));
+		nf_log_buf_add(m, "MACSRC=%pM MACDST=%pM ",
+			       eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest);
+		nf_log_dump_vlan(m, skb);
+		nf_log_buf_add(m, "MACPROTO=%04x ",
+			       ntohs(eth_hdr(skb)->h_proto));
 		return;
 	default:
 		break;
diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
index 4aef6baaa55e..dffeaaaadcde 100644
--- a/net/ipv6/netfilter/nf_reject_ipv6.c
+++ b/net/ipv6/netfilter/nf_reject_ipv6.c
@@ -12,6 +12,140 @@
 #include <linux/netfilter_ipv6.h>
 #include <linux/netfilter_bridge.h>
 
+static bool nf_reject_v6_csum_ok(struct sk_buff *skb, int hook)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	int thoff;
+	__be16 fo;
+	u8 proto = ip6h->nexthdr;
+
+	if (skb_csum_unnecessary(skb))
+		return true;
+
+	if (ip6h->payload_len &&
+	    pskb_trim_rcsum(skb, ntohs(ip6h->payload_len) + sizeof(*ip6h)))
+		return false;
+
+	ip6h = ipv6_hdr(skb);
+	thoff = ipv6_skip_exthdr(skb, ((u8*)(ip6h+1) - skb->data), &proto, &fo);
+	if (thoff < 0 || thoff >= skb->len || (fo & htons(~0x7)) != 0)
+		return false;
+
+	if (!nf_reject_verify_csum(proto))
+		return true;
+
+	return nf_ip6_checksum(skb, hook, thoff, proto) == 0;
+}
+
+static int nf_reject_ip6hdr_validate(struct sk_buff *skb)
+{
+	struct ipv6hdr *hdr;
+	u32 pkt_len;
+
+	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
+		return 0;
+
+	hdr = ipv6_hdr(skb);
+	if (hdr->version != 6)
+		return 0;
+
+	pkt_len = ntohs(hdr->payload_len);
+	if (pkt_len + sizeof(struct ipv6hdr) > skb->len)
+		return 0;
+
+	return 1;
+}
+
+struct sk_buff *nf_reject_skb_v6_tcp_reset(struct net *net,
+					   struct sk_buff *oldskb,
+					   const struct net_device *dev,
+					   int hook)
+{
+	struct sk_buff *nskb;
+	const struct tcphdr *oth;
+	struct tcphdr _oth;
+	unsigned int otcplen;
+	struct ipv6hdr *nip6h;
+
+	if (!nf_reject_ip6hdr_validate(oldskb))
+		return NULL;
+
+	oth = nf_reject_ip6_tcphdr_get(oldskb, &_oth, &otcplen, hook);
+	if (!oth)
+		return NULL;
+
+	nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct tcphdr) +
+			 LL_MAX_HEADER, GFP_ATOMIC);
+	if (!nskb)
+		return NULL;
+
+	nskb->dev = (struct net_device *)dev;
+
+	skb_reserve(nskb, LL_MAX_HEADER);
+	nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
+				     net->ipv6.devconf_all->hop_limit);
+	nf_reject_ip6_tcphdr_put(nskb, oldskb, oth, otcplen);
+	nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
+
+	return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v6_tcp_reset);
+
+struct sk_buff *nf_reject_skb_v6_unreach(struct net *net,
+					 struct sk_buff *oldskb,
+					 const struct net_device *dev,
+					 int hook, u8 code)
+{
+	struct sk_buff *nskb;
+	struct ipv6hdr *nip6h;
+	struct icmp6hdr *icmp6h;
+	unsigned int len;
+
+	if (!nf_reject_ip6hdr_validate(oldskb))
+		return NULL;
+
+	/* Include "As much of invoking packet as possible without the ICMPv6
+	 * packet exceeding the minimum IPv6 MTU" in the ICMP payload.
+	 */
+	len = min_t(unsigned int, 1220, oldskb->len);
+
+	if (!pskb_may_pull(oldskb, len))
+		return NULL;
+
+	if (!nf_reject_v6_csum_ok(oldskb, hook))
+		return NULL;
+
+	nskb = alloc_skb(sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr) +
+			 LL_MAX_HEADER + len, GFP_ATOMIC);
+	if (!nskb)
+		return NULL;
+
+	nskb->dev = (struct net_device *)dev;
+
+	skb_reserve(nskb, LL_MAX_HEADER);
+	nip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_ICMPV6,
+				     net->ipv6.devconf_all->hop_limit);
+
+	skb_reset_transport_header(nskb);
+	icmp6h = skb_put_zero(nskb, sizeof(struct icmp6hdr));
+	icmp6h->icmp6_type = ICMPV6_DEST_UNREACH;
+	icmp6h->icmp6_code = code;
+
+	skb_put_data(nskb, skb_network_header(oldskb), len);
+	nip6h->payload_len = htons(nskb->len - sizeof(struct ipv6hdr));
+
+	icmp6h->icmp6_cksum =
+		csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr,
+				nskb->len - sizeof(struct ipv6hdr),
+				IPPROTO_ICMPV6,
+				csum_partial(icmp6h,
+					     nskb->len - sizeof(struct ipv6hdr),
+					     0));
+
+	return nskb;
+}
+EXPORT_SYMBOL_GPL(nf_reject_skb_v6_unreach);
+
 const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb,
 					      struct tcphdr *otcph,
 					      unsigned int *otcplen, int hook)
@@ -141,7 +275,8 @@ static int nf_reject6_fill_skb_dst(struct sk_buff *skb_in)
 	return 0;
 }
 
-void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
+void nf_send_reset6(struct net *net, struct sock *sk, struct sk_buff *oldskb,
+		    int hook)
 {
 	struct net_device *br_indev __maybe_unused;
 	struct sk_buff *nskb;
@@ -170,7 +305,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 	fl6.fl6_sport = otcph->dest;
 	fl6.fl6_dport = otcph->source;
 
-	if (hook == NF_INET_PRE_ROUTING) {
+	if (hook == NF_INET_PRE_ROUTING || hook == NF_INET_INGRESS) {
 		nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
 		if (!dst)
 			return;
@@ -179,7 +314,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 
 	fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev);
 	fl6.flowi6_mark = IP6_REPLY_MARK(net, oldskb->mark);
-	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(oldskb, flowi6_to_flowi_common(&fl6));
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (dst->error) {
 		dst_release(dst);
@@ -233,7 +368,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
 		dev_queue_xmit(nskb);
 	} else
 #endif
-		ip6_local_out(net, nskb->sk, nskb);
+		ip6_local_out(net, sk, nskb);
 }
 EXPORT_SYMBOL_GPL(nf_send_reset6);
 
@@ -268,7 +403,8 @@ void nf_send_unreach6(struct net *net, struct sk_buff *skb_in,
 	if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
 		skb_in->dev = net->loopback_dev;
 
-	if (hooknum == NF_INET_PRE_ROUTING && nf_reject6_fill_skb_dst(skb_in))
+	if ((hooknum == NF_INET_PRE_ROUTING || hooknum == NF_INET_INGRESS) &&
+	    nf_reject6_fill_skb_dst(skb_in) < 0)
 		return;
 
 	icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
diff --git a/net/ipv6/netfilter/nft_reject_ipv6.c b/net/ipv6/netfilter/nft_reject_ipv6.c
index c1098a1968e1..7969d1f3018d 100644
--- a/net/ipv6/netfilter/nft_reject_ipv6.c
+++ b/net/ipv6/netfilter/nft_reject_ipv6.c
@@ -28,7 +28,8 @@ static void nft_reject_ipv6_eval(const struct nft_expr *expr,
 				 nft_hook(pkt));
 		break;
 	case NFT_REJECT_TCP_RST:
-		nf_send_reset6(nft_net(pkt), pkt->skb, nft_hook(pkt));
+		nf_send_reset6(nft_net(pkt), pkt->xt.state->sk, pkt->skb,
+			       nft_hook(pkt));
 		break;
 	default:
 		break;
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 6caa062f68e7..6ac88fe24a8e 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -111,7 +111,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.flowi6_uid = sk->sk_uid;
 	fl6.fl6_icmp_type = user_icmph.icmp6_type;
 	fl6.fl6_icmp_code = user_icmph.icmp6_code;
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	ipcm6_init_sk(&ipc6, np);
 	ipc6.sockc.mark = sk->sk_mark;
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index bbff3e02e302..d6306aa46bb1 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -126,6 +126,7 @@ static const struct snmp_mib snmp6_udp6_list[] = {
 	SNMP_MIB_ITEM("Udp6SndbufErrors", UDP_MIB_SNDBUFERRORS),
 	SNMP_MIB_ITEM("Udp6InCsumErrors", UDP_MIB_CSUMERRORS),
 	SNMP_MIB_ITEM("Udp6IgnoredMulti", UDP_MIB_IGNOREDMULTI),
+	SNMP_MIB_ITEM("Udp6MemErrors", UDP_MIB_MEMERRORS),
 	SNMP_MIB_SENTINEL
 };
 
@@ -137,6 +138,7 @@ static const struct snmp_mib snmp6_udplite6_list[] = {
 	SNMP_MIB_ITEM("UdpLite6RcvbufErrors", UDP_MIB_RCVBUFERRORS),
 	SNMP_MIB_ITEM("UdpLite6SndbufErrors", UDP_MIB_SNDBUFERRORS),
 	SNMP_MIB_ITEM("UdpLite6InCsumErrors", UDP_MIB_CSUMERRORS),
+	SNMP_MIB_ITEM("UdpLite6MemErrors", UDP_MIB_MEMERRORS),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 874f01cd7aec..1f56d9aae589 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -746,7 +746,7 @@ static int raw6_getfrag(void *from, char *to, int offset, int len, int odd,
 			skb->csum = csum_block_add(
 				skb->csum,
 				csum_partial_copy_nocheck(rfv->c + offset,
-							  to, copy, 0),
+							  to, copy),
 				odd);
 
 		odd = 0;
@@ -915,7 +915,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.flowi6_oif = np->mcast_oif;
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	if (hdrincl)
 		fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 1f5d4d196dcc..47a0dc46cbdb 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -42,6 +42,8 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
 
 #include <net/sock.h>
 #include <net/snmp.h>
@@ -322,6 +324,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	struct frag_queue *fq;
 	const struct ipv6hdr *hdr = ipv6_hdr(skb);
 	struct net *net = dev_net(skb_dst(skb)->dev);
+	u8 nexthdr;
 	int iif;
 
 	if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED)
@@ -351,6 +354,20 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		return 1;
 	}
 
+	/* RFC 8200, Section 4.5 Fragment Header:
+	 * If the first fragment does not include all headers through an
+	 * Upper-Layer header, then that fragment should be discarded and
+	 * an ICMP Parameter Problem, Code 3, message should be sent to
+	 * the source of the fragment, with the Pointer field set to zero.
+	 */
+	nexthdr = hdr->nexthdr;
+	if (ipv6frag_thdr_truncated(skb, skb_transport_offset(skb), &nexthdr)) {
+		__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
+				IPSTATS_MIB_INHDRERRORS);
+		icmpv6_param_prob(skb, ICMPV6_HDR_INCOMP, 0);
+		return -1;
+	}
+
 	iif = skb->dev ? skb->dev->ifindex : 0;
 	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index fb075d9545b9..188e114b29b4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2745,7 +2745,8 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
 	if (confirm_neigh)
 		dst_confirm_neigh(dst, daddr);
 
-	mtu = max_t(u32, mtu, IPV6_MIN_MTU);
+	if (mtu < IPV6_MIN_MTU)
+		return;
 	if (mtu >= dst_mtu(dst))
 		return;
 
@@ -5284,9 +5285,10 @@ static int ip6_route_multipath_del(struct fib6_config *cfg,
 {
 	struct fib6_config r_cfg;
 	struct rtnexthop *rtnh;
+	int last_err = 0;
 	int remaining;
 	int attrlen;
-	int err = 1, last_err = 0;
+	int err;
 
 	remaining = cfg->fc_mp_len;
 	rtnh = (struct rtnexthop *)cfg->fc_mp;
@@ -5556,6 +5558,10 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
 
 		if (dst->dev && nla_put_u32(skb, RTA_OIF, dst->dev->ifindex))
 			goto nla_put_failure;
+
+		if (dst->lwtstate &&
+		    lwtunnel_fill_encap(skb, dst->lwtstate, RTA_ENCAP, RTA_ENCAP_TYPE) < 0)
+			goto nla_put_failure;
 	} else if (rt->fib6_nsiblings) {
 		struct fib6_info *sibling, *next_sibling;
 		struct nlattr *mp;
@@ -6037,11 +6043,6 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt,
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 
-	/* call_fib6_entry_notifiers will be removed when in-kernel notifier
-	 * is implemented and supported for nexthop objects
-	 */
-	call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, rt, NULL);
-
 	skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
 	if (!skb)
 		goto errout;
diff --git a/net/ipv6/rpl.c b/net/ipv6/rpl.c
index 307f336b5353..488aec9e1a74 100644
--- a/net/ipv6/rpl.c
+++ b/net/ipv6/rpl.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * Authors:
  * (C) 2020 Alexander Aring <alex.aring@gmail.com>
  */
diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 5fdf3ebb953f..ff691d9f4a04 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0-only
-/**
+/*
  * Authors:
  * (C) 2020 Alexander Aring <alex.aring@gmail.com>
  */
@@ -190,18 +190,13 @@ static int rpl_do_srh(struct sk_buff *skb, const struct rpl_lwt *rlwt)
 {
 	struct dst_entry *dst = skb_dst(skb);
 	struct rpl_iptunnel_encap *tinfo;
-	int err = 0;
 
 	if (skb->protocol != htons(ETH_P_IPV6))
 		return -EINVAL;
 
 	tinfo = rpl_encap_lwtunnel(dst->lwtstate);
 
-	err = rpl_do_srh_inline(skb, rlwt, tinfo->srh);
-	if (err)
-		return err;
-
-	return 0;
+	return rpl_do_srh_inline(skb, rlwt, tinfo->srh);
 }
 
 static int rpl_output(struct net *net, struct sock *sk, struct sk_buff *skb)
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 85dddfe3a2c6..687d95dce085 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -35,7 +35,6 @@
 #include <net/xfrm.h>
 
 #include <crypto/hash.h>
-#include <crypto/sha.h>
 #include <net/seg6.h>
 #include <net/genetlink.h>
 #include <net/seg6_hmac.h>
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index eba23279912d..b07f7c1c82a4 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -33,11 +33,35 @@
 
 struct seg6_local_lwt;
 
+/* callbacks used for customizing the creation and destruction of a behavior */
+struct seg6_local_lwtunnel_ops {
+	int (*build_state)(struct seg6_local_lwt *slwt, const void *cfg,
+			   struct netlink_ext_ack *extack);
+	void (*destroy_state)(struct seg6_local_lwt *slwt);
+};
+
 struct seg6_action_desc {
 	int action;
 	unsigned long attrs;
+
+	/* The optattrs field is used for specifying all the optional
+	 * attributes supported by a specific behavior.
+	 * It means that if one of these attributes is not provided in the
+	 * netlink message during the behavior creation, no errors will be
+	 * returned to the userspace.
+	 *
+	 * Each attribute can be only of two types (mutually exclusive):
+	 * 1) required or 2) optional.
+	 * Every user MUST obey to this rule! If you set an attribute as
+	 * required the same attribute CANNOT be set as optional and vice
+	 * versa.
+	 */
+	unsigned long optattrs;
+
 	int (*input)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
 	int static_headroom;
+
+	struct seg6_local_lwtunnel_ops slwt_ops;
 };
 
 struct bpf_lwt_prog {
@@ -45,6 +69,28 @@ struct bpf_lwt_prog {
 	char *name;
 };
 
+enum seg6_end_dt_mode {
+	DT_INVALID_MODE	= -EINVAL,
+	DT_LEGACY_MODE	= 0,
+	DT_VRF_MODE	= 1,
+};
+
+struct seg6_end_dt_info {
+	enum seg6_end_dt_mode mode;
+
+	struct net *net;
+	/* VRF device associated to the routing table used by the SRv6
+	 * End.DT4/DT6 behavior for routing IPv4/IPv6 packets.
+	 */
+	int vrf_ifindex;
+	int vrf_table;
+
+	/* tunneled packet proto and family (IPv4 or IPv6) */
+	__be16 proto;
+	u16 family;
+	int hdrlen;
+};
+
 struct seg6_local_lwt {
 	int action;
 	struct ipv6_sr_hdr *srh;
@@ -54,9 +100,16 @@ struct seg6_local_lwt {
 	int iif;
 	int oif;
 	struct bpf_lwt_prog bpf;
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	struct seg6_end_dt_info dt_info;
+#endif
 
 	int headroom;
 	struct seg6_action_desc *desc;
+	/* unlike the required attrs, we have to track the optional attributes
+	 * that have been effectively parsed.
+	 */
+	unsigned long parsed_optattrs;
 };
 
 static struct seg6_local_lwt *seg6_local_lwtunnel(struct lwtunnel_state *lwt)
@@ -401,6 +454,248 @@ drop:
 	return -EINVAL;
 }
 
+#ifdef CONFIG_NET_L3_MASTER_DEV
+static struct net *fib6_config_get_net(const struct fib6_config *fib6_cfg)
+{
+	const struct nl_info *nli = &fib6_cfg->fc_nlinfo;
+
+	return nli->nl_net;
+}
+
+static int __seg6_end_dt_vrf_build(struct seg6_local_lwt *slwt, const void *cfg,
+				   u16 family, struct netlink_ext_ack *extack)
+{
+	struct seg6_end_dt_info *info = &slwt->dt_info;
+	int vrf_ifindex;
+	struct net *net;
+
+	net = fib6_config_get_net(cfg);
+
+	/* note that vrf_table was already set by parse_nla_vrftable() */
+	vrf_ifindex = l3mdev_ifindex_lookup_by_table_id(L3MDEV_TYPE_VRF, net,
+							info->vrf_table);
+	if (vrf_ifindex < 0) {
+		if (vrf_ifindex == -EPERM) {
+			NL_SET_ERR_MSG(extack,
+				       "Strict mode for VRF is disabled");
+		} else if (vrf_ifindex == -ENODEV) {
+			NL_SET_ERR_MSG(extack,
+				       "Table has no associated VRF device");
+		} else {
+			pr_debug("seg6local: SRv6 End.DT* creation error=%d\n",
+				 vrf_ifindex);
+		}
+
+		return vrf_ifindex;
+	}
+
+	info->net = net;
+	info->vrf_ifindex = vrf_ifindex;
+
+	switch (family) {
+	case AF_INET:
+		info->proto = htons(ETH_P_IP);
+		info->hdrlen = sizeof(struct iphdr);
+		break;
+	case AF_INET6:
+		info->proto = htons(ETH_P_IPV6);
+		info->hdrlen = sizeof(struct ipv6hdr);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	info->family = family;
+	info->mode = DT_VRF_MODE;
+
+	return 0;
+}
+
+/* The SRv6 End.DT4/DT6 behavior extracts the inner (IPv4/IPv6) packet and
+ * routes the IPv4/IPv6 packet by looking at the configured routing table.
+ *
+ * In the SRv6 End.DT4/DT6 use case, we can receive traffic (IPv6+Segment
+ * Routing Header packets) from several interfaces and the outer IPv6
+ * destination address (DA) is used for retrieving the specific instance of the
+ * End.DT4/DT6 behavior that should process the packets.
+ *
+ * However, the inner IPv4/IPv6 packet is not really bound to any receiving
+ * interface and thus the End.DT4/DT6 sets the VRF (associated with the
+ * corresponding routing table) as the *receiving* interface.
+ * In other words, the End.DT4/DT6 processes a packet as if it has been received
+ * directly by the VRF (and not by one of its slave devices, if any).
+ * In this way, the VRF interface is used for routing the IPv4/IPv6 packet in
+ * according to the routing table configured by the End.DT4/DT6 instance.
+ *
+ * This design allows you to get some interesting features like:
+ *  1) the statistics on rx packets;
+ *  2) the possibility to install a packet sniffer on the receiving interface
+ *     (the VRF one) for looking at the incoming packets;
+ *  3) the possibility to leverage the netfilter prerouting hook for the inner
+ *     IPv4 packet.
+ *
+ * This function returns:
+ *  - the sk_buff* when the VRF rcv handler has processed the packet correctly;
+ *  - NULL when the skb is consumed by the VRF rcv handler;
+ *  - a pointer which encodes a negative error number in case of error.
+ *    Note that in this case, the function takes care of freeing the skb.
+ */
+static struct sk_buff *end_dt_vrf_rcv(struct sk_buff *skb, u16 family,
+				      struct net_device *dev)
+{
+	/* based on l3mdev_ip_rcv; we are only interested in the master */
+	if (unlikely(!netif_is_l3_master(dev) && !netif_has_l3_rx_handler(dev)))
+		goto drop;
+
+	if (unlikely(!dev->l3mdev_ops->l3mdev_l3_rcv))
+		goto drop;
+
+	/* the decap packet IPv4/IPv6 does not come with any mac header info.
+	 * We must unset the mac header to allow the VRF device to rebuild it,
+	 * just in case there is a sniffer attached on the device.
+	 */
+	skb_unset_mac_header(skb);
+
+	skb = dev->l3mdev_ops->l3mdev_l3_rcv(dev, skb, family);
+	if (!skb)
+		/* the skb buffer was consumed by the handler */
+		return NULL;
+
+	/* when a packet is received by a VRF or by one of its slaves, the
+	 * master device reference is set into the skb.
+	 */
+	if (unlikely(skb->dev != dev || skb->skb_iif != dev->ifindex))
+		goto drop;
+
+	return skb;
+
+drop:
+	kfree_skb(skb);
+	return ERR_PTR(-EINVAL);
+}
+
+static struct net_device *end_dt_get_vrf_rcu(struct sk_buff *skb,
+					     struct seg6_end_dt_info *info)
+{
+	int vrf_ifindex = info->vrf_ifindex;
+	struct net *net = info->net;
+
+	if (unlikely(vrf_ifindex < 0))
+		goto error;
+
+	if (unlikely(!net_eq(dev_net(skb->dev), net)))
+		goto error;
+
+	return dev_get_by_index_rcu(net, vrf_ifindex);
+
+error:
+	return NULL;
+}
+
+static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb,
+				       struct seg6_local_lwt *slwt)
+{
+	struct seg6_end_dt_info *info = &slwt->dt_info;
+	struct net_device *vrf;
+
+	vrf = end_dt_get_vrf_rcu(skb, info);
+	if (unlikely(!vrf))
+		goto drop;
+
+	skb->protocol = info->proto;
+
+	skb_dst_drop(skb);
+
+	skb_set_transport_header(skb, info->hdrlen);
+
+	return end_dt_vrf_rcv(skb, info->family, vrf);
+
+drop:
+	kfree_skb(skb);
+	return ERR_PTR(-EINVAL);
+}
+
+static int input_action_end_dt4(struct sk_buff *skb,
+				struct seg6_local_lwt *slwt)
+{
+	struct iphdr *iph;
+	int err;
+
+	if (!decap_and_validate(skb, IPPROTO_IPIP))
+		goto drop;
+
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		goto drop;
+
+	skb = end_dt_vrf_core(skb, slwt);
+	if (!skb)
+		/* packet has been processed and consumed by the VRF */
+		return 0;
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	iph = ip_hdr(skb);
+
+	err = ip_route_input(skb, iph->daddr, iph->saddr, 0, skb->dev);
+	if (unlikely(err))
+		goto drop;
+
+	return dst_input(skb);
+
+drop:
+	kfree_skb(skb);
+	return -EINVAL;
+}
+
+static int seg6_end_dt4_build(struct seg6_local_lwt *slwt, const void *cfg,
+			      struct netlink_ext_ack *extack)
+{
+	return __seg6_end_dt_vrf_build(slwt, cfg, AF_INET, extack);
+}
+
+static enum
+seg6_end_dt_mode seg6_end_dt6_parse_mode(struct seg6_local_lwt *slwt)
+{
+	unsigned long parsed_optattrs = slwt->parsed_optattrs;
+	bool legacy, vrfmode;
+
+	legacy	= !!(parsed_optattrs & (1 << SEG6_LOCAL_TABLE));
+	vrfmode	= !!(parsed_optattrs & (1 << SEG6_LOCAL_VRFTABLE));
+
+	if (!(legacy ^ vrfmode))
+		/* both are absent or present: invalid DT6 mode */
+		return DT_INVALID_MODE;
+
+	return legacy ? DT_LEGACY_MODE : DT_VRF_MODE;
+}
+
+static enum seg6_end_dt_mode seg6_end_dt6_get_mode(struct seg6_local_lwt *slwt)
+{
+	struct seg6_end_dt_info *info = &slwt->dt_info;
+
+	return info->mode;
+}
+
+static int seg6_end_dt6_build(struct seg6_local_lwt *slwt, const void *cfg,
+			      struct netlink_ext_ack *extack)
+{
+	enum seg6_end_dt_mode mode = seg6_end_dt6_parse_mode(slwt);
+	struct seg6_end_dt_info *info = &slwt->dt_info;
+
+	switch (mode) {
+	case DT_LEGACY_MODE:
+		info->mode = DT_LEGACY_MODE;
+		return 0;
+	case DT_VRF_MODE:
+		return __seg6_end_dt_vrf_build(slwt, cfg, AF_INET6, extack);
+	default:
+		NL_SET_ERR_MSG(extack, "table or vrftable must be specified");
+		return -EINVAL;
+	}
+}
+#endif
+
 static int input_action_end_dt6(struct sk_buff *skb,
 				struct seg6_local_lwt *slwt)
 {
@@ -410,6 +705,28 @@ static int input_action_end_dt6(struct sk_buff *skb,
 	if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
 		goto drop;
 
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	if (seg6_end_dt6_get_mode(slwt) == DT_LEGACY_MODE)
+		goto legacy_mode;
+
+	/* DT6_VRF_MODE */
+	skb = end_dt_vrf_core(skb, slwt);
+	if (!skb)
+		/* packet has been processed and consumed by the VRF */
+		return 0;
+
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	/* note: this time we do not need to specify the table because the VRF
+	 * takes care of selecting the correct table.
+	 */
+	seg6_lookup_any_nexthop(skb, NULL, 0, true);
+
+	return dst_input(skb);
+
+legacy_mode:
+#endif
 	skb_set_transport_header(skb, sizeof(struct ipv6hdr));
 
 	seg6_lookup_any_nexthop(skb, NULL, slwt->table, true);
@@ -590,8 +907,27 @@ static struct seg6_action_desc seg6_action_table[] = {
 		.input		= input_action_end_dx4,
 	},
 	{
+		.action		= SEG6_LOCAL_ACTION_END_DT4,
+		.attrs		= (1 << SEG6_LOCAL_VRFTABLE),
+#ifdef CONFIG_NET_L3_MASTER_DEV
+		.input		= input_action_end_dt4,
+		.slwt_ops	= {
+					.build_state = seg6_end_dt4_build,
+				  },
+#endif
+	},
+	{
 		.action		= SEG6_LOCAL_ACTION_END_DT6,
+#ifdef CONFIG_NET_L3_MASTER_DEV
+		.attrs		= 0,
+		.optattrs	= (1 << SEG6_LOCAL_TABLE) |
+				  (1 << SEG6_LOCAL_VRFTABLE),
+		.slwt_ops	= {
+					.build_state = seg6_end_dt6_build,
+				  },
+#else
 		.attrs		= (1 << SEG6_LOCAL_TABLE),
+#endif
 		.input		= input_action_end_dt6,
 	},
 	{
@@ -649,6 +985,7 @@ static const struct nla_policy seg6_local_policy[SEG6_LOCAL_MAX + 1] = {
 	[SEG6_LOCAL_ACTION]	= { .type = NLA_U32 },
 	[SEG6_LOCAL_SRH]	= { .type = NLA_BINARY },
 	[SEG6_LOCAL_TABLE]	= { .type = NLA_U32 },
+	[SEG6_LOCAL_VRFTABLE]	= { .type = NLA_U32 },
 	[SEG6_LOCAL_NH4]	= { .type = NLA_BINARY,
 				    .len = sizeof(struct in_addr) },
 	[SEG6_LOCAL_NH6]	= { .type = NLA_BINARY,
@@ -710,6 +1047,11 @@ static int cmp_nla_srh(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
 	return memcmp(a->srh, b->srh, len);
 }
 
+static void destroy_attr_srh(struct seg6_local_lwt *slwt)
+{
+	kfree(slwt->srh);
+}
+
 static int parse_nla_table(struct nlattr **attrs, struct seg6_local_lwt *slwt)
 {
 	slwt->table = nla_get_u32(attrs[SEG6_LOCAL_TABLE]);
@@ -733,6 +1075,53 @@ static int cmp_nla_table(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
 	return 0;
 }
 
+static struct
+seg6_end_dt_info *seg6_possible_end_dt_info(struct seg6_local_lwt *slwt)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	return &slwt->dt_info;
+#else
+	return ERR_PTR(-EOPNOTSUPP);
+#endif
+}
+
+static int parse_nla_vrftable(struct nlattr **attrs,
+			      struct seg6_local_lwt *slwt)
+{
+	struct seg6_end_dt_info *info = seg6_possible_end_dt_info(slwt);
+
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+
+	info->vrf_table = nla_get_u32(attrs[SEG6_LOCAL_VRFTABLE]);
+
+	return 0;
+}
+
+static int put_nla_vrftable(struct sk_buff *skb, struct seg6_local_lwt *slwt)
+{
+	struct seg6_end_dt_info *info = seg6_possible_end_dt_info(slwt);
+
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+
+	if (nla_put_u32(skb, SEG6_LOCAL_VRFTABLE, info->vrf_table))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+static int cmp_nla_vrftable(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
+{
+	struct seg6_end_dt_info *info_a = seg6_possible_end_dt_info(a);
+	struct seg6_end_dt_info *info_b = seg6_possible_end_dt_info(b);
+
+	if (info_a->vrf_table != info_b->vrf_table)
+		return 1;
+
+	return 0;
+}
+
 static int parse_nla_nh4(struct nlattr **attrs, struct seg6_local_lwt *slwt)
 {
 	memcpy(&slwt->nh4, nla_data(attrs[SEG6_LOCAL_NH4]),
@@ -901,16 +1290,30 @@ static int cmp_nla_bpf(struct seg6_local_lwt *a, struct seg6_local_lwt *b)
 	return strcmp(a->bpf.name, b->bpf.name);
 }
 
+static void destroy_attr_bpf(struct seg6_local_lwt *slwt)
+{
+	kfree(slwt->bpf.name);
+	if (slwt->bpf.prog)
+		bpf_prog_put(slwt->bpf.prog);
+}
+
 struct seg6_action_param {
 	int (*parse)(struct nlattr **attrs, struct seg6_local_lwt *slwt);
 	int (*put)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
 	int (*cmp)(struct seg6_local_lwt *a, struct seg6_local_lwt *b);
+
+	/* optional destroy() callback useful for releasing resources which
+	 * have been previously acquired in the corresponding parse()
+	 * function.
+	 */
+	void (*destroy)(struct seg6_local_lwt *slwt);
 };
 
 static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = {
 	[SEG6_LOCAL_SRH]	= { .parse = parse_nla_srh,
 				    .put = put_nla_srh,
-				    .cmp = cmp_nla_srh },
+				    .cmp = cmp_nla_srh,
+				    .destroy = destroy_attr_srh },
 
 	[SEG6_LOCAL_TABLE]	= { .parse = parse_nla_table,
 				    .put = put_nla_table,
@@ -934,14 +1337,130 @@ static struct seg6_action_param seg6_action_params[SEG6_LOCAL_MAX + 1] = {
 
 	[SEG6_LOCAL_BPF]	= { .parse = parse_nla_bpf,
 				    .put = put_nla_bpf,
-				    .cmp = cmp_nla_bpf },
+				    .cmp = cmp_nla_bpf,
+				    .destroy = destroy_attr_bpf },
+
+	[SEG6_LOCAL_VRFTABLE]	= { .parse = parse_nla_vrftable,
+				    .put = put_nla_vrftable,
+				    .cmp = cmp_nla_vrftable },
 
 };
 
+/* call the destroy() callback (if available) for each set attribute in
+ * @parsed_attrs, starting from the first attribute up to the @max_parsed
+ * (excluded) attribute.
+ */
+static void __destroy_attrs(unsigned long parsed_attrs, int max_parsed,
+			    struct seg6_local_lwt *slwt)
+{
+	struct seg6_action_param *param;
+	int i;
+
+	/* Every required seg6local attribute is identified by an ID which is
+	 * encoded as a flag (i.e: 1 << ID) in the 'attrs' bitmask;
+	 *
+	 * We scan the 'parsed_attrs' bitmask, starting from the first attribute
+	 * up to the @max_parsed (excluded) attribute.
+	 * For each set attribute, we retrieve the corresponding destroy()
+	 * callback. If the callback is not available, then we skip to the next
+	 * attribute; otherwise, we call the destroy() callback.
+	 */
+	for (i = 0; i < max_parsed; ++i) {
+		if (!(parsed_attrs & (1 << i)))
+			continue;
+
+		param = &seg6_action_params[i];
+
+		if (param->destroy)
+			param->destroy(slwt);
+	}
+}
+
+/* release all the resources that may have been acquired during parsing
+ * operations.
+ */
+static void destroy_attrs(struct seg6_local_lwt *slwt)
+{
+	unsigned long attrs = slwt->desc->attrs | slwt->parsed_optattrs;
+
+	__destroy_attrs(attrs, SEG6_LOCAL_MAX + 1, slwt);
+}
+
+static int parse_nla_optional_attrs(struct nlattr **attrs,
+				    struct seg6_local_lwt *slwt)
+{
+	struct seg6_action_desc *desc = slwt->desc;
+	unsigned long parsed_optattrs = 0;
+	struct seg6_action_param *param;
+	int err, i;
+
+	for (i = 0; i < SEG6_LOCAL_MAX + 1; ++i) {
+		if (!(desc->optattrs & (1 << i)) || !attrs[i])
+			continue;
+
+		/* once here, the i-th attribute is provided by the
+		 * userspace AND it is identified optional as well.
+		 */
+		param = &seg6_action_params[i];
+
+		err = param->parse(attrs, slwt);
+		if (err < 0)
+			goto parse_optattrs_err;
+
+		/* current attribute has been correctly parsed */
+		parsed_optattrs |= (1 << i);
+	}
+
+	/* store in the tunnel state all the optional attributed successfully
+	 * parsed.
+	 */
+	slwt->parsed_optattrs = parsed_optattrs;
+
+	return 0;
+
+parse_optattrs_err:
+	__destroy_attrs(parsed_optattrs, i, slwt);
+
+	return err;
+}
+
+/* call the custom constructor of the behavior during its initialization phase
+ * and after that all its attributes have been parsed successfully.
+ */
+static int
+seg6_local_lwtunnel_build_state(struct seg6_local_lwt *slwt, const void *cfg,
+				struct netlink_ext_ack *extack)
+{
+	struct seg6_action_desc *desc = slwt->desc;
+	struct seg6_local_lwtunnel_ops *ops;
+
+	ops = &desc->slwt_ops;
+	if (!ops->build_state)
+		return 0;
+
+	return ops->build_state(slwt, cfg, extack);
+}
+
+/* call the custom destructor of the behavior which is invoked before the
+ * tunnel is going to be destroyed.
+ */
+static void seg6_local_lwtunnel_destroy_state(struct seg6_local_lwt *slwt)
+{
+	struct seg6_action_desc *desc = slwt->desc;
+	struct seg6_local_lwtunnel_ops *ops;
+
+	ops = &desc->slwt_ops;
+	if (!ops->destroy_state)
+		return;
+
+	ops->destroy_state(slwt);
+}
+
 static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)
 {
 	struct seg6_action_param *param;
 	struct seg6_action_desc *desc;
+	unsigned long invalid_attrs;
 	int i, err;
 
 	desc = __get_action_desc(slwt->action);
@@ -954,6 +1473,26 @@ static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)
 	slwt->desc = desc;
 	slwt->headroom += desc->static_headroom;
 
+	/* Forcing the desc->optattrs *set* and the desc->attrs *set* to be
+	 * disjoined, this allow us to release acquired resources by optional
+	 * attributes and by required attributes independently from each other
+	 * without any interfarence.
+	 * In other terms, we are sure that we do not release some the acquired
+	 * resources twice.
+	 *
+	 * Note that if an attribute is configured both as required and as
+	 * optional, it means that the user has messed something up in the
+	 * seg6_action_table. Therefore, this check is required for SRv6
+	 * behaviors to work properly.
+	 */
+	invalid_attrs = desc->attrs & desc->optattrs;
+	if (invalid_attrs) {
+		WARN_ONCE(1,
+			  "An attribute cannot be both required AND optional");
+		return -EINVAL;
+	}
+
+	/* parse the required attributes */
 	for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
 		if (desc->attrs & (1 << i)) {
 			if (!attrs[i])
@@ -963,11 +1502,24 @@ static int parse_nla_action(struct nlattr **attrs, struct seg6_local_lwt *slwt)
 
 			err = param->parse(attrs, slwt);
 			if (err < 0)
-				return err;
+				goto parse_attrs_err;
 		}
 	}
 
+	/* parse the optional attributes, if any */
+	err = parse_nla_optional_attrs(attrs, slwt);
+	if (err < 0)
+		goto parse_attrs_err;
+
 	return 0;
+
+parse_attrs_err:
+	/* release any resource that may have been acquired during the i-1
+	 * parse() operations.
+	 */
+	__destroy_attrs(desc->attrs, i, slwt);
+
+	return err;
 }
 
 static int seg6_local_build_state(struct net *net, struct nlattr *nla,
@@ -1003,6 +1555,10 @@ static int seg6_local_build_state(struct net *net, struct nlattr *nla,
 	if (err < 0)
 		goto out_free;
 
+	err = seg6_local_lwtunnel_build_state(slwt, cfg, extack);
+	if (err < 0)
+		goto out_destroy_attrs;
+
 	newts->type = LWTUNNEL_ENCAP_SEG6_LOCAL;
 	newts->flags = LWTUNNEL_STATE_INPUT_REDIRECT;
 	newts->headroom = slwt->headroom;
@@ -1011,8 +1567,9 @@ static int seg6_local_build_state(struct net *net, struct nlattr *nla,
 
 	return 0;
 
+out_destroy_attrs:
+	destroy_attrs(slwt);
 out_free:
-	kfree(slwt->srh);
 	kfree(newts);
 	return err;
 }
@@ -1021,12 +1578,9 @@ static void seg6_local_destroy_state(struct lwtunnel_state *lwt)
 {
 	struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);
 
-	kfree(slwt->srh);
+	seg6_local_lwtunnel_destroy_state(slwt);
 
-	if (slwt->desc->attrs & (1 << SEG6_LOCAL_BPF)) {
-		kfree(slwt->bpf.name);
-		bpf_prog_put(slwt->bpf.prog);
-	}
+	destroy_attrs(slwt);
 
 	return;
 }
@@ -1036,13 +1590,16 @@ static int seg6_local_fill_encap(struct sk_buff *skb,
 {
 	struct seg6_local_lwt *slwt = seg6_local_lwtunnel(lwt);
 	struct seg6_action_param *param;
+	unsigned long attrs;
 	int i, err;
 
 	if (nla_put_u32(skb, SEG6_LOCAL_ACTION, slwt->action))
 		return -EMSGSIZE;
 
+	attrs = slwt->desc->attrs | slwt->parsed_optattrs;
+
 	for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
-		if (slwt->desc->attrs & (1 << i)) {
+		if (attrs & (1 << i)) {
 			param = &seg6_action_params[i];
 			err = param->put(skb, slwt);
 			if (err < 0)
@@ -1061,7 +1618,7 @@ static int seg6_local_get_encap_size(struct lwtunnel_state *lwt)
 
 	nlsize = nla_total_size(4); /* action */
 
-	attrs = slwt->desc->attrs;
+	attrs = slwt->desc->attrs | slwt->parsed_optattrs;
 
 	if (attrs & (1 << SEG6_LOCAL_SRH))
 		nlsize += nla_total_size((slwt->srh->hdrlen + 1) << 3);
@@ -1086,6 +1643,9 @@ static int seg6_local_get_encap_size(struct lwtunnel_state *lwt)
 		       nla_total_size(MAX_PROG_NAME) +
 		       nla_total_size(4);
 
+	if (attrs & (1 << SEG6_LOCAL_VRFTABLE))
+		nlsize += nla_total_size(4);
+
 	return nlsize;
 }
 
@@ -1094,6 +1654,7 @@ static int seg6_local_cmp_encap(struct lwtunnel_state *a,
 {
 	struct seg6_local_lwt *slwt_a, *slwt_b;
 	struct seg6_action_param *param;
+	unsigned long attrs_a, attrs_b;
 	int i;
 
 	slwt_a = seg6_local_lwtunnel(a);
@@ -1102,11 +1663,14 @@ static int seg6_local_cmp_encap(struct lwtunnel_state *a,
 	if (slwt_a->action != slwt_b->action)
 		return 1;
 
-	if (slwt_a->desc->attrs != slwt_b->desc->attrs)
+	attrs_a = slwt_a->desc->attrs | slwt_a->parsed_optattrs;
+	attrs_b = slwt_b->desc->attrs | slwt_b->parsed_optattrs;
+
+	if (attrs_a != attrs_b)
 		return 1;
 
 	for (i = 0; i < SEG6_LOCAL_MAX + 1; i++) {
-		if (slwt_a->desc->attrs & (1 << i)) {
+		if (attrs_a & (1 << i)) {
 			param = &seg6_action_params[i];
 			if (param->cmp(slwt_a, slwt_b))
 				return 1;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 5e2c34c0ac97..93636867aee2 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1128,7 +1128,6 @@ static void ipip6_tunnel_bind_dev(struct net_device *dev)
 	if (tdev && !netif_is_l3_master(tdev)) {
 		int t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
-		dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
 		dev->mtu = tdev->mtu - t_hlen;
 		if (dev->mtu < IPV6_MIN_MTU)
 			dev->mtu = IPV6_MIN_MTU;
@@ -1396,7 +1395,7 @@ static const struct net_device_ops ipip6_netdev_ops = {
 	.ndo_uninit	= ipip6_tunnel_uninit,
 	.ndo_start_xmit	= sit_tunnel_xmit,
 	.ndo_do_ioctl	= ipip6_tunnel_ioctl,
-	.ndo_get_stats64 = ip_tunnel_get_stats64,
+	.ndo_get_stats64 = dev_get_tstats64,
 	.ndo_get_iflink = ip_tunnel_get_iflink,
 	.ndo_tunnel_ctl = ipip6_tunnel_ctl,
 };
@@ -1426,7 +1425,6 @@ static void ipip6_tunnel_setup(struct net_device *dev)
 	dev->priv_destructor	= ipip6_dev_free;
 
 	dev->type		= ARPHRD_SIT;
-	dev->hard_header_len	= LL_MAX_HEADER + t_hlen;
 	dev->mtu		= ETH_DATA_LEN - t_hlen;
 	dev->min_mtu		= IPV6_MIN_MTU;
 	dev->max_mtu		= IP6_MAX_MTU - t_hlen;
@@ -1647,8 +1645,11 @@ static int ipip6_newlink(struct net *src_net, struct net_device *dev,
 	}
 
 #ifdef CONFIG_IPV6_SIT_6RD
-	if (ipip6_netlink_6rd_parms(data, &ip6rd))
+	if (ipip6_netlink_6rd_parms(data, &ip6rd)) {
 		err = ipip6_tunnel_update_6rd(nt, &ip6rd);
+		if (err < 0)
+			unregister_netdevice_queue(dev, NULL);
+	}
 #endif
 
 	return err;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index e796a64be308..e8cfb9e997bf 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -136,7 +136,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	__u32 cookie = ntohl(th->ack_seq) - 1;
 	struct sock *ret = sk;
 	struct request_sock *req;
-	int mss;
+	int full_space, mss;
 	struct dst_entry *dst;
 	__u8 rcv_wscale;
 	u32 tsoff = 0;
@@ -233,7 +233,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 		fl6.fl6_dport = ireq->ir_rmt_port;
 		fl6.fl6_sport = inet_sk(sk)->inet_sport;
 		fl6.flowi6_uid = sk->sk_uid;
-		security_req_classify_flow(req, flowi6_to_flowi(&fl6));
+		security_req_classify_flow(req, flowi6_to_flowi_common(&fl6));
 
 		dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 		if (IS_ERR(dst))
@@ -241,7 +241,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	}
 
 	req->rsk_window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
-	tcp_select_initial_window(sk, tcp_full_space(sk), req->mss,
+	/* limit the window selection if the user enforce a smaller rx buffer */
+	full_space = tcp_full_space(sk);
+	if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+	    (req->rsk_window_clamp > full_space || req->rsk_window_clamp == 0))
+		req->rsk_window_clamp = full_space;
+
+	tcp_select_initial_window(sk, full_space, req->mss,
 				  &req->rsk_rcv_wnd, &req->rsk_window_clamp,
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(dst, RTAX_INITRWND));
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 305870a72352..0e1509b02cb3 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -278,7 +278,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
 	opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk));
 	final_p = fl6_update_dst(&fl6, opt, &final);
 
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
 	if (IS_ERR(dst)) {
@@ -458,7 +458,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	case TCP_SYN_SENT:
 	case TCP_SYN_RECV:
 		/* Only in fast or simultaneous open. If a fast open socket is
-		 * is already accepted it is treated as a connected one below.
+		 * already accepted it is treated as a connected one below.
 		 */
 		if (fastopen && !fastopen->sk)
 			break;
@@ -501,7 +501,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 			      struct flowi *fl,
 			      struct request_sock *req,
 			      struct tcp_fastopen_cookie *foc,
-			      enum tcp_synack_type synack_type)
+			      enum tcp_synack_type synack_type,
+			      struct sk_buff *syn_skb)
 {
 	struct inet_request_sock *ireq = inet_rsk(req);
 	struct ipv6_pinfo *np = tcp_inet6_sk(sk);
@@ -509,13 +510,14 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 	struct flowi6 *fl6 = &fl->u.ip6;
 	struct sk_buff *skb;
 	int err = -ENOMEM;
+	u8 tclass;
 
 	/* First, grab a route. */
 	if (!dst && (dst = inet6_csk_route_req(sk, fl6, req,
 					       IPPROTO_TCP)) == NULL)
 		goto done;
 
-	skb = tcp_make_synack(sk, dst, req, foc, synack_type);
+	skb = tcp_make_synack(sk, dst, req, foc, synack_type, syn_skb);
 
 	if (skb) {
 		__tcp_v6_send_check(skb, &ireq->ir_v6_loc_addr,
@@ -525,12 +527,21 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 		if (np->repflow && ireq->pktopts)
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
+		tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
+				(np->tclass & INET_ECN_MASK) :
+				np->tclass;
+
+		if (!INET_ECN_is_capable(tclass) &&
+		    tcp_bpf_ca_needs_ecn((struct sock *)req))
+			tclass |= INET_ECN_ECT_0;
+
 		rcu_read_lock();
 		opt = ireq->ipv6_opt;
 		if (!opt)
 			opt = rcu_dereference(np->opt);
-		err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt, np->tclass,
-			       sk->sk_priority);
+		err = ip6_xmit(sk, skb, fl6, sk->sk_mark, opt,
+			       tclass, sk->sk_priority);
 		rcu_read_unlock();
 		err = net_xmit_eval(err);
 	}
@@ -818,9 +829,15 @@ static void tcp_v6_init_req(struct request_sock *req,
 }
 
 static struct dst_entry *tcp_v6_route_req(const struct sock *sk,
+					  struct sk_buff *skb,
 					  struct flowi *fl,
-					  const struct request_sock *req)
+					  struct request_sock *req)
 {
+	tcp_v6_init_req(req, sk, skb);
+
+	if (security_inet_conn_request(sk, skb, req))
+		return NULL;
+
 	return inet6_csk_route_req(sk, &fl->u.ip6, req, IPPROTO_TCP);
 }
 
@@ -841,7 +858,6 @@ const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.req_md5_lookup	=	tcp_v6_md5_lookup,
 	.calc_md5_hash	=	tcp_v6_md5_hash_skb,
 #endif
-	.init_req	=	tcp_v6_init_req,
 #ifdef CONFIG_SYN_COOKIES
 	.cookie_init_seq =	cookie_v6_init_sequence,
 #endif
@@ -949,7 +965,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	fl6.fl6_dport = t1->dest;
 	fl6.fl6_sport = t1->source;
 	fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
-	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
+	security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
 
 	/* Pass a socket to ip6_dst_lookup either it is for RST
 	 * Underlying function will use this to retrieve the network
@@ -958,8 +974,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL);
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
-		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass,
-			 priority);
+		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL,
+			 tclass & ~INET_ECN_MASK, priority);
 		TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 		if (rst)
 			TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -1067,8 +1083,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb)
 			label = ip6_flowlabel(ipv6h);
 	}
 
-	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1, 0,
-			     label, priority);
+	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, key, 1,
+			     ipv6_get_dsfield(ipv6h), label, priority);
 
 #ifdef CONFIG_TCP_MD5SIG
 out:
@@ -1121,7 +1137,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_time_stamp_raw() + tcp_rsk(req)->ts_off,
 			req->ts_recent, sk->sk_bound_dev_if,
 			tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index),
-			0, 0, sk->sk_priority);
+			ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority);
 }
 
 
@@ -1188,6 +1204,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	const struct ipv6_pinfo *np = tcp_inet6_sk(sk);
 	struct ipv6_txoptions *opt;
 	struct inet_sock *newinet;
+	bool found_dup_sk = false;
 	struct tcp_sock *newtp;
 	struct sock *newsk;
 #ifdef CONFIG_TCP_MD5SIG
@@ -1309,6 +1326,12 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	if (np->repflow)
 		newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
 
+	/* Set ToS of the new socket based upon the value of incoming SYN.
+	 * ECT bits are set later in tcp_init_transfer().
+	 */
+	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+		newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
+
 	/* Clone native IPv6 options from listening socket (if any)
 
 	   Yes, keeping reference count would be much more clever,
@@ -1359,7 +1382,8 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 		tcp_done(newsk);
 		goto out;
 	}
-	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash));
+	*own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash),
+				       &found_dup_sk);
 	if (*own_req) {
 		tcp_move_syn(newtp, req);
 
@@ -1374,6 +1398,15 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 				skb_set_owner_r(newnp->pktoptions, newsk);
 			}
 		}
+	} else {
+		if (!req_unhash && found_dup_sk) {
+			/* This code path should only be executed in the
+			 * syncookie case only
+			 */
+			bh_unlock_sock(newsk);
+			sock_put(newsk);
+			newsk = NULL;
+		}
 	}
 
 	return newsk;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 29d9691359b9..b9f3dfdd2383 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -276,7 +276,7 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 				 inet6_sdif(skb), udptable, skb);
 }
 
-struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
+struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
 				 __be16 sport, __be16 dport)
 {
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
@@ -285,7 +285,6 @@ struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
 				 &iph->daddr, dport, inet6_iif(skb),
 				 inet6_sdif(skb), &udp_table, NULL);
 }
-EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb);
 
 /* Must be called under rcu_read_lock().
  * Does increment socket refcount.
@@ -560,7 +559,7 @@ int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 
 	sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
 			       inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
-	if (!sk) {
+	if (!sk || udp_sk(sk)->encap_type) {
 		/* No socket for error: try tunnels before discarding */
 		sk = ERR_PTR(-ENOENT);
 		if (static_branch_unlikely(&udpv6_encap_needed_key)) {
@@ -637,6 +636,9 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		if (rc == -ENOMEM)
 			UDP6_INC_STATS(sock_net(sk),
 					 UDP_MIB_RCVBUFERRORS, is_udplite);
+		else
+			UDP6_INC_STATS(sock_net(sk),
+				       UDP_MIB_MEMERRORS, is_udplite);
 		UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 		kfree_skb(skb);
 		return -1;
@@ -1496,7 +1498,7 @@ do_udp_sendmsg:
 	} else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	if (ipc6.tclass < 0)
 		ipc6.tclass = np->tclass;
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 584157a07759..faa823c24292 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -28,10 +28,6 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 	int tnl_hlen;
 	int err;
 
-	mss = skb_shinfo(skb)->gso_size;
-	if (unlikely(skb->len <= mss))
-		goto out;
-
 	if (skb->encapsulation && skb_shinfo(skb)->gso_type &
 	    (SKB_GSO_UDP_TUNNEL|SKB_GSO_UDP_TUNNEL_CSUM))
 		segs = skb_udp_tunnel_segment(skb, features, true);
@@ -46,7 +42,11 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb,
 			goto out;
 
 		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
-			return __udp_gso_segment(skb, features);
+			return __udp_gso_segment(skb, features, true);
+
+		mss = skb_shinfo(skb)->gso_size;
+		if (unlikely(skb->len <= mss))
+			goto out;
 
 		/* Do software UFO. Complete and fill in the UDP checksum as HW cannot
 		 * do checksum of UDP packets sent as multiple IP fragments.
@@ -111,12 +111,22 @@ out:
 	return segs;
 }
 
+static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
+					__be16 dport)
+{
+	const struct ipv6hdr *iph = skb_gro_network_header(skb);
+
+	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
+				 &iph->daddr, dport, inet6_iif(skb),
+				 inet6_sdif(skb), &udp_table, NULL);
+}
+
 INDIRECT_CALLABLE_SCOPE
 struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
+	struct sock *sk = NULL;
 	struct sk_buff *pp;
-	struct sock *sk;
 
 	if (unlikely(!uh))
 		goto flush;
@@ -135,7 +145,10 @@ struct sk_buff *udp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 skip:
 	NAPI_GRO_CB(skb)->is_ipv6 = 1;
 	rcu_read_lock();
-	sk = static_branch_unlikely(&udpv6_encap_needed_key) ? udp6_lib_lookup_skb(skb, uh->source, uh->dest) : NULL;
+
+	if (static_branch_unlikely(&udpv6_encap_needed_key))
+		sk = udp6_gro_lookup_skb(skb, uh->source, uh->dest);
+
 	pp = udp_gro_receive(head, skb, uh, sk);
 	rcu_read_unlock();
 	return pp;
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 25b7ebda2fab..f696d46e6910 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -303,13 +303,13 @@ static const struct xfrm_type xfrm6_tunnel_type = {
 static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = {
 	.handler	= xfrm6_tunnel_rcv,
 	.err_handler	= xfrm6_tunnel_err,
-	.priority	= 2,
+	.priority	= 3,
 };
 
 static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = {
 	.handler	= xfrm6_tunnel_rcv,
 	.err_handler	= xfrm6_tunnel_err,
-	.priority	= 2,
+	.priority	= 3,
 };
 
 static int __net_init xfrm6_tunnel_net_init(struct net *net)
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index a95af62acb52..882f028992c3 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -587,12 +587,12 @@ static void __iucv_auto_name(struct iucv_sock *iucv)
 static int iucv_sock_bind(struct socket *sock, struct sockaddr *addr,
 			  int addr_len)
 {
-	struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr;
+	DECLARE_SOCKADDR(struct sockaddr_iucv *, sa, addr);
+	char uid[sizeof(sa->siucv_user_id)];
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv;
 	int err = 0;
 	struct net_device *dev;
-	char uid[9];
 
 	/* Verify the input sockaddr */
 	if (addr_len < sizeof(struct sockaddr_iucv) ||
@@ -691,7 +691,7 @@ static int iucv_sock_autobind(struct sock *sk)
 
 static int afiucv_path_connect(struct socket *sock, struct sockaddr *addr)
 {
-	struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr;
+	DECLARE_SOCKADDR(struct sockaddr_iucv *, sa, addr);
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv = iucv_sk(sk);
 	unsigned char user_data[16];
@@ -738,7 +738,7 @@ done:
 static int iucv_sock_connect(struct socket *sock, struct sockaddr *addr,
 			     int alen, int flags)
 {
-	struct sockaddr_iucv *sa = (struct sockaddr_iucv *) addr;
+	DECLARE_SOCKADDR(struct sockaddr_iucv *, sa, addr);
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv = iucv_sk(sk);
 	int err;
@@ -874,7 +874,7 @@ done:
 static int iucv_sock_getname(struct socket *sock, struct sockaddr *addr,
 			     int peer)
 {
-	struct sockaddr_iucv *siucv = (struct sockaddr_iucv *) addr;
+	DECLARE_SOCKADDR(struct sockaddr_iucv *, siucv, addr);
 	struct sock *sk = sock->sk;
 	struct iucv_sock *iucv = iucv_sk(sk);
 
@@ -1434,7 +1434,8 @@ static int iucv_sock_shutdown(struct socket *sock, int how)
 		break;
 	}
 
-	if (how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) {
+	if ((how == SEND_SHUTDOWN || how == SHUTDOWN_MASK) &&
+	    sk->sk_state == IUCV_CONNECTED) {
 		if (iucv->transport == AF_IUCV_TRANS_IUCV) {
 			txmsg.class = 0;
 			txmsg.tag = 0;
@@ -1644,7 +1645,7 @@ static int iucv_callback_connreq(struct iucv_path *path,
 	}
 
 	/* Create the new socket */
-	nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0);
+	nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0);
 	if (!nsk) {
 		err = pr_iucv->path_sever(path, user_data);
 		iucv_path_free(path);
@@ -1850,7 +1851,7 @@ static int afiucv_hs_callback_syn(struct sock *sk, struct sk_buff *skb)
 		goto out;
 	}
 
-	nsk = iucv_sock_alloc(NULL, sk->sk_type, GFP_ATOMIC, 0);
+	nsk = iucv_sock_alloc(NULL, sk->sk_protocol, GFP_ATOMIC, 0);
 	bh_lock_sock(sk);
 	if ((sk->sk_state != IUCV_LISTEN) ||
 	    sk_acceptq_is_full(sk) ||
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index cd2e468852e7..349c6ac3313f 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -1116,10 +1116,9 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
 	if (msg->flags & IUCV_IPRMDATA)
 		return iucv_message_receive_iprmdata(path, msg, flags,
 						     buffer, size, residual);
-	 if (cpumask_empty(&iucv_buffer_cpumask)) {
-		rc = -EIO;
-		goto out;
-	}
+	if (cpumask_empty(&iucv_buffer_cpumask))
+		return -EIO;
+
 	parm = iucv_param[smp_processor_id()];
 	memset(parm, 0, sizeof(union iucv_param));
 	parm->db.ipbfadr1 = (u32)(addr_t) buffer;
@@ -1135,7 +1134,6 @@ int __iucv_message_receive(struct iucv_path *path, struct iucv_message *msg,
 		if (residual)
 			*residual = parm->db.ipbfln1f;
 	}
-out:
 	return rc;
 }
 EXPORT_SYMBOL(__iucv_message_receive);
diff --git a/net/key/af_key.c b/net/key/af_key.c
index c12dbc51ef5f..ef9b4ac03e7b 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -2902,7 +2902,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t)
 			break;
 		if (!aalg->pfkey_supported)
 			continue;
-		if (aalg_tmpl_set(t, aalg) && aalg->available)
+		if (aalg_tmpl_set(t, aalg))
 			sz += sizeof(struct sadb_comb);
 	}
 	return sz + sizeof(struct sadb_prop);
@@ -2920,7 +2920,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 		if (!ealg->pfkey_supported)
 			continue;
 
-		if (!(ealg_tmpl_set(t, ealg) && ealg->available))
+		if (!(ealg_tmpl_set(t, ealg)))
 			continue;
 
 		for (k = 1; ; k++) {
@@ -2931,7 +2931,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t)
 			if (!aalg->pfkey_supported)
 				continue;
 
-			if (aalg_tmpl_set(t, aalg) && aalg->available)
+			if (aalg_tmpl_set(t, aalg))
 				sz += sizeof(struct sadb_comb);
 		}
 	}
diff --git a/net/l2tp/Makefile b/net/l2tp/Makefile
index 399a7e5db2f4..cf8f27071d3f 100644
--- a/net/l2tp/Makefile
+++ b/net/l2tp/Makefile
@@ -5,6 +5,8 @@
 
 obj-$(CONFIG_L2TP) += l2tp_core.o
 
+CFLAGS_l2tp_core.o += -I$(src)
+
 # Build l2tp as modules if L2TP is M
 obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_PPPOL2TP)) += l2tp_ppp.o
 obj-$(subst y,$(CONFIG_L2TP),$(CONFIG_L2TP_IP)) += l2tp_ip.o
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 701fc72ad9f4..7be5103ff2a8 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -61,6 +61,10 @@
 #include <linux/atomic.h>
 
 #include "l2tp_core.h"
+#include "trace.h"
+
+#define CREATE_TRACE_POINTS
+#include "trace.h"
 
 #define L2TP_DRV_VERSION	"V2.0"
 
@@ -116,11 +120,6 @@ static bool l2tp_sk_is_v6(struct sock *sk)
 }
 #endif
 
-static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
-{
-	return sk->sk_user_data;
-}
-
 static inline struct l2tp_net *l2tp_pernet(const struct net *net)
 {
 	return net_generic(net, l2tp_net_id);
@@ -151,23 +150,30 @@ l2tp_session_id_hash(struct l2tp_tunnel *tunnel, u32 session_id)
 
 static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel)
 {
+	trace_free_tunnel(tunnel);
 	sock_put(tunnel->sock);
 	/* the tunnel is freed in the socket destructor */
 }
 
 static void l2tp_session_free(struct l2tp_session *session)
 {
-	struct l2tp_tunnel *tunnel = session->tunnel;
+	trace_free_session(session);
+	if (session->tunnel)
+		l2tp_tunnel_dec_refcount(session->tunnel);
+	kfree(session);
+}
 
-	if (tunnel) {
+struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk)
+{
+	struct l2tp_tunnel *tunnel = sk->sk_user_data;
+
+	if (tunnel)
 		if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC))
-			goto out;
-		l2tp_tunnel_dec_refcount(tunnel);
-	}
+			return NULL;
 
-out:
-	kfree(session);
+	return tunnel;
 }
+EXPORT_SYMBOL_GPL(l2tp_sk_to_tunnel);
 
 void l2tp_tunnel_inc_refcount(struct l2tp_tunnel *tunnel)
 {
@@ -381,6 +387,8 @@ int l2tp_session_register(struct l2tp_session *session,
 	hlist_add_head(&session->hlist, head);
 	write_unlock_bh(&tunnel->hlist_lock);
 
+	trace_register_session(session);
+
 	return 0;
 
 err_tlock_pnlock:
@@ -409,10 +417,6 @@ static void l2tp_recv_queue_skb(struct l2tp_session *session, struct sk_buff *sk
 	skb_queue_walk_safe(&session->reorder_q, skbp, tmp) {
 		if (L2TP_SKB_CB(skbp)->ns > ns) {
 			__skb_queue_before(&session->reorder_q, skbp, skb);
-			l2tp_dbg(session, L2TP_MSG_SEQ,
-				 "%s: pkt %hu, inserted before %hu, reorder_q len=%d\n",
-				 session->name, ns, L2TP_SKB_CB(skbp)->ns,
-				 skb_queue_len(&session->reorder_q));
 			atomic_long_inc(&session->stats.rx_oos_packets);
 			goto out;
 		}
@@ -445,9 +449,7 @@ static void l2tp_recv_dequeue_skb(struct l2tp_session *session, struct sk_buff *
 		/* Bump our Nr */
 		session->nr++;
 		session->nr &= session->nr_max;
-
-		l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated nr to %hu\n",
-			 session->name, session->nr);
+		trace_session_seqnum_update(session);
 	}
 
 	/* call private receive handler */
@@ -472,37 +474,27 @@ static void l2tp_recv_dequeue(struct l2tp_session *session)
 start:
 	spin_lock_bh(&session->reorder_q.lock);
 	skb_queue_walk_safe(&session->reorder_q, skb, tmp) {
-		if (time_after(jiffies, L2TP_SKB_CB(skb)->expires)) {
+		struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb);
+
+		/* If the packet has been pending on the queue for too long, discard it */
+		if (time_after(jiffies, cb->expires)) {
 			atomic_long_inc(&session->stats.rx_seq_discards);
 			atomic_long_inc(&session->stats.rx_errors);
-			l2tp_dbg(session, L2TP_MSG_SEQ,
-				 "%s: oos pkt %u len %d discarded (too old), waiting for %u, reorder_q_len=%d\n",
-				 session->name, L2TP_SKB_CB(skb)->ns,
-				 L2TP_SKB_CB(skb)->length, session->nr,
-				 skb_queue_len(&session->reorder_q));
+			trace_session_pkt_expired(session, cb->ns);
 			session->reorder_skip = 1;
 			__skb_unlink(skb, &session->reorder_q);
 			kfree_skb(skb);
 			continue;
 		}
 
-		if (L2TP_SKB_CB(skb)->has_seq) {
+		if (cb->has_seq) {
 			if (session->reorder_skip) {
-				l2tp_dbg(session, L2TP_MSG_SEQ,
-					 "%s: advancing nr to next pkt: %u -> %u",
-					 session->name, session->nr,
-					 L2TP_SKB_CB(skb)->ns);
 				session->reorder_skip = 0;
-				session->nr = L2TP_SKB_CB(skb)->ns;
+				session->nr = cb->ns;
+				trace_session_seqnum_reset(session);
 			}
-			if (L2TP_SKB_CB(skb)->ns != session->nr) {
-				l2tp_dbg(session, L2TP_MSG_SEQ,
-					 "%s: holding oos pkt %u len %d, waiting for %u, reorder_q_len=%d\n",
-					 session->name, L2TP_SKB_CB(skb)->ns,
-					 L2TP_SKB_CB(skb)->length, session->nr,
-					 skb_queue_len(&session->reorder_q));
+			if (cb->ns != session->nr)
 				goto out;
-			}
 		}
 		__skb_unlink(skb, &session->reorder_q);
 
@@ -535,14 +527,13 @@ static int l2tp_seq_check_rx_window(struct l2tp_session *session, u32 nr)
  */
 static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb)
 {
-	if (!l2tp_seq_check_rx_window(session, L2TP_SKB_CB(skb)->ns)) {
+	struct l2tp_skb_cb *cb = L2TP_SKB_CB(skb);
+
+	if (!l2tp_seq_check_rx_window(session, cb->ns)) {
 		/* Packet sequence number is outside allowed window.
 		 * Discard it.
 		 */
-		l2tp_dbg(session, L2TP_MSG_SEQ,
-			 "%s: pkt %u len %d discarded, outside window, nr=%u\n",
-			 session->name, L2TP_SKB_CB(skb)->ns,
-			 L2TP_SKB_CB(skb)->length, session->nr);
+		trace_session_pkt_outside_rx_window(session, cb->ns);
 		goto discard;
 	}
 
@@ -559,10 +550,10 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb)
 	 * is seen. After nr_oos_count_max in-sequence packets, reset the
 	 * sequence number to re-enable packet reception.
 	 */
-	if (L2TP_SKB_CB(skb)->ns == session->nr) {
+	if (cb->ns == session->nr) {
 		skb_queue_tail(&session->reorder_q, skb);
 	} else {
-		u32 nr_oos = L2TP_SKB_CB(skb)->ns;
+		u32 nr_oos = cb->ns;
 		u32 nr_next = (session->nr_oos + 1) & session->nr_max;
 
 		if (nr_oos == nr_next)
@@ -573,17 +564,10 @@ static int l2tp_recv_data_seq(struct l2tp_session *session, struct sk_buff *skb)
 		session->nr_oos = nr_oos;
 		if (session->nr_oos_count > session->nr_oos_count_max) {
 			session->reorder_skip = 1;
-			l2tp_dbg(session, L2TP_MSG_SEQ,
-				 "%s: %d oos packets received. Resetting sequence numbers\n",
-				 session->name, session->nr_oos_count);
 		}
 		if (!session->reorder_skip) {
 			atomic_long_inc(&session->stats.rx_seq_discards);
-			l2tp_dbg(session, L2TP_MSG_SEQ,
-				 "%s: oos pkt %u len %d discarded, waiting for %u, reorder_q_len=%d\n",
-				 session->name, L2TP_SKB_CB(skb)->ns,
-				 L2TP_SKB_CB(skb)->length, session->nr,
-				 skb_queue_len(&session->reorder_q));
+			trace_session_pkt_oos(session, cb->ns);
 			goto discard;
 		}
 		skb_queue_tail(&session->reorder_q, skb);
@@ -660,16 +644,14 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		      int length)
 {
 	struct l2tp_tunnel *tunnel = session->tunnel;
-	u32 ns = 0, nr = 0;
 	int offset;
 
 	/* Parse and check optional cookie */
 	if (session->peer_cookie_len > 0) {
 		if (memcmp(ptr, &session->peer_cookie[0], session->peer_cookie_len)) {
-			l2tp_info(tunnel, L2TP_MSG_DATA,
-				  "%s: cookie mismatch (%u/%u). Discarding.\n",
-				  tunnel->name, tunnel->tunnel_id,
-				  session->session_id);
+			pr_warn_ratelimited("%s: cookie mismatch (%u/%u). Discarding.\n",
+					    tunnel->name, tunnel->tunnel_id,
+					    session->session_id);
 			atomic_long_inc(&session->stats.rx_cookie_discards);
 			goto discard;
 		}
@@ -686,32 +668,21 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 	L2TP_SKB_CB(skb)->has_seq = 0;
 	if (tunnel->version == L2TP_HDR_VER_2) {
 		if (hdrflags & L2TP_HDRFLAG_S) {
-			ns = ntohs(*(__be16 *)ptr);
-			ptr += 2;
-			nr = ntohs(*(__be16 *)ptr);
-			ptr += 2;
-
 			/* Store L2TP info in the skb */
-			L2TP_SKB_CB(skb)->ns = ns;
+			L2TP_SKB_CB(skb)->ns = ntohs(*(__be16 *)ptr);
 			L2TP_SKB_CB(skb)->has_seq = 1;
+			ptr += 2;
+			/* Skip past nr in the header */
+			ptr += 2;
 
-			l2tp_dbg(session, L2TP_MSG_SEQ,
-				 "%s: recv data ns=%u, nr=%u, session nr=%u\n",
-				 session->name, ns, nr, session->nr);
 		}
 	} else if (session->l2specific_type == L2TP_L2SPECTYPE_DEFAULT) {
 		u32 l2h = ntohl(*(__be32 *)ptr);
 
 		if (l2h & 0x40000000) {
-			ns = l2h & 0x00ffffff;
-
 			/* Store L2TP info in the skb */
-			L2TP_SKB_CB(skb)->ns = ns;
+			L2TP_SKB_CB(skb)->ns = l2h & 0x00ffffff;
 			L2TP_SKB_CB(skb)->has_seq = 1;
-
-			l2tp_dbg(session, L2TP_MSG_SEQ,
-				 "%s: recv data ns=%u, session nr=%u\n",
-				 session->name, ns, session->nr);
 		}
 		ptr += 4;
 	}
@@ -722,9 +693,7 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		 * configure it so.
 		 */
 		if (!session->lns_mode && !session->send_seq) {
-			l2tp_info(session, L2TP_MSG_SEQ,
-				  "%s: requested to enable seq numbers by LNS\n",
-				  session->name);
+			trace_session_seqnum_lns_enable(session);
 			session->send_seq = 1;
 			l2tp_session_set_header_len(session, tunnel->version);
 		}
@@ -733,9 +702,8 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		 * If user has configured mandatory sequence numbers, discard.
 		 */
 		if (session->recv_seq) {
-			l2tp_warn(session, L2TP_MSG_SEQ,
-				  "%s: recv data has no seq numbers when required. Discarding.\n",
-				  session->name);
+			pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
+					    session->name);
 			atomic_long_inc(&session->stats.rx_seq_discards);
 			goto discard;
 		}
@@ -746,15 +714,12 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		 * LAC is broken. Discard the frame.
 		 */
 		if (!session->lns_mode && session->send_seq) {
-			l2tp_info(session, L2TP_MSG_SEQ,
-				  "%s: requested to disable seq numbers by LNS\n",
-				  session->name);
+			trace_session_seqnum_lns_disable(session);
 			session->send_seq = 0;
 			l2tp_session_set_header_len(session, tunnel->version);
 		} else if (session->send_seq) {
-			l2tp_warn(session, L2TP_MSG_SEQ,
-				  "%s: recv data has no seq numbers when required. Discarding.\n",
-				  session->name);
+			pr_warn_ratelimited("%s: recv data has no seq numbers when required. Discarding.\n",
+					    session->name);
 			atomic_long_inc(&session->stats.rx_seq_discards);
 			goto discard;
 		}
@@ -816,9 +781,6 @@ static void l2tp_session_queue_purge(struct l2tp_session *session)
 {
 	struct sk_buff *skb = NULL;
 
-	if (WARN_ON(session->magic != L2TP_SESSION_MAGIC))
-		return;
-
 	while ((skb = skb_dequeue(&session->reorder_q))) {
 		atomic_long_inc(&session->stats.rx_errors);
 		kfree_skb(skb);
@@ -847,22 +809,11 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 
 	/* Short packet? */
 	if (!pskb_may_pull(skb, L2TP_HDR_SIZE_MAX)) {
-		l2tp_info(tunnel, L2TP_MSG_DATA,
-			  "%s: recv short packet (len=%d)\n",
-			  tunnel->name, skb->len);
+		pr_warn_ratelimited("%s: recv short packet (len=%d)\n",
+				    tunnel->name, skb->len);
 		goto error;
 	}
 
-	/* Trace packet contents, if enabled */
-	if (tunnel->debug & L2TP_MSG_DATA) {
-		length = min(32u, skb->len);
-		if (!pskb_may_pull(skb, length))
-			goto error;
-
-		pr_debug("%s: recv\n", tunnel->name);
-		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length);
-	}
-
 	/* Point to L2TP header */
 	optr = skb->data;
 	ptr = skb->data;
@@ -873,9 +824,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 	/* Check protocol version */
 	version = hdrflags & L2TP_HDR_VER_MASK;
 	if (version != tunnel->version) {
-		l2tp_info(tunnel, L2TP_MSG_DATA,
-			  "%s: recv protocol version mismatch: got %d expected %d\n",
-			  tunnel->name, version, tunnel->version);
+		pr_warn_ratelimited("%s: recv protocol version mismatch: got %d expected %d\n",
+				    tunnel->name, version, tunnel->version);
 		goto error;
 	}
 
@@ -883,12 +833,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 	length = skb->len;
 
 	/* If type is control packet, it is handled by userspace. */
-	if (hdrflags & L2TP_HDRFLAG_T) {
-		l2tp_dbg(tunnel, L2TP_MSG_DATA,
-			 "%s: recv control packet, len=%d\n",
-			 tunnel->name, length);
+	if (hdrflags & L2TP_HDRFLAG_T)
 		goto error;
-	}
 
 	/* Skip flags */
 	ptr += 2;
@@ -917,9 +863,8 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 			l2tp_session_dec_refcount(session);
 
 		/* Not found? Pass to userspace to deal with */
-		l2tp_info(tunnel, L2TP_MSG_DATA,
-			  "%s: no session found (%u/%u). Passing up.\n",
-			  tunnel->name, tunnel_id, session_id);
+		pr_warn_ratelimited("%s: no session found (%u/%u). Passing up.\n",
+				    tunnel->name, tunnel_id, session_id);
 		goto error;
 	}
 
@@ -949,12 +894,17 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct l2tp_tunnel *tunnel;
 
+	/* Note that this is called from the encap_rcv hook inside an
+	 * RCU-protected region, but without the socket being locked.
+	 * Hence we use rcu_dereference_sk_user_data to access the
+	 * tunnel data structure rather the usual l2tp_sk_to_tunnel
+	 * accessor function.
+	 */
 	tunnel = rcu_dereference_sk_user_data(sk);
 	if (!tunnel)
 		goto pass_up;
-
-	l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n",
-		 tunnel->name, skb->len);
+	if (WARN_ON(tunnel->magic != L2TP_TUNNEL_MAGIC))
+		goto pass_up;
 
 	if (l2tp_udp_recv_core(tunnel, skb))
 		goto pass_up;
@@ -993,8 +943,7 @@ static int l2tp_build_l2tpv2_header(struct l2tp_session *session, void *buf)
 		*bufp++ = 0;
 		session->ns++;
 		session->ns &= 0xffff;
-		l2tp_dbg(session, L2TP_MSG_SEQ, "%s: updated ns to %u\n",
-			 session->name, session->ns);
+		trace_session_seqnum_update(session);
 	}
 
 	return bufp - optr;
@@ -1030,9 +979,7 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf)
 			l2h = 0x40000000 | session->ns;
 			session->ns++;
 			session->ns &= 0xffffff;
-			l2tp_dbg(session, L2TP_MSG_SEQ,
-				 "%s: updated ns to %u\n",
-				 session->name, session->ns);
+			trace_session_seqnum_update(session);
 		}
 
 		*((__be32 *)bufp) = htonl(l2h);
@@ -1042,74 +989,39 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf)
 	return bufp - optr;
 }
 
-static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
-			   struct flowi *fl, size_t data_len)
+/* Queue the packet to IP for output: tunnel socket lock must be held */
+static int l2tp_xmit_queue(struct l2tp_tunnel *tunnel, struct sk_buff *skb, struct flowi *fl)
 {
-	struct l2tp_tunnel *tunnel = session->tunnel;
-	unsigned int len = skb->len;
-	int error;
-
-	/* Debug */
-	if (session->send_seq)
-		l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes, ns=%u\n",
-			 session->name, data_len, session->ns - 1);
-	else
-		l2tp_dbg(session, L2TP_MSG_DATA, "%s: send %zd bytes\n",
-			 session->name, data_len);
-
-	if (session->debug & L2TP_MSG_DATA) {
-		int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
-		unsigned char *datap = skb->data + uhlen;
-
-		pr_debug("%s: xmit\n", session->name);
-		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET,
-				     datap, min_t(size_t, 32, len - uhlen));
-	}
+	int err;
 
-	/* Queue the packet to IP for output */
 	skb->ignore_df = 1;
 	skb_dst_drop(skb);
 #if IS_ENABLED(CONFIG_IPV6)
 	if (l2tp_sk_is_v6(tunnel->sock))
-		error = inet6_csk_xmit(tunnel->sock, skb, NULL);
+		err = inet6_csk_xmit(tunnel->sock, skb, NULL);
 	else
 #endif
-		error = ip_queue_xmit(tunnel->sock, skb, fl);
+		err = ip_queue_xmit(tunnel->sock, skb, fl);
 
-	/* Update stats */
-	if (error >= 0) {
-		atomic_long_inc(&tunnel->stats.tx_packets);
-		atomic_long_add(len, &tunnel->stats.tx_bytes);
-		atomic_long_inc(&session->stats.tx_packets);
-		atomic_long_add(len, &session->stats.tx_bytes);
-	} else {
-		atomic_long_inc(&tunnel->stats.tx_errors);
-		atomic_long_inc(&session->stats.tx_errors);
-	}
+	return err >= 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
 }
 
-/* If caller requires the skb to have a ppp header, the header must be
- * inserted in the skb data before calling this function.
- */
-int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len)
+static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, unsigned int *len)
 {
-	int data_len = skb->len;
 	struct l2tp_tunnel *tunnel = session->tunnel;
+	unsigned int data_len = skb->len;
 	struct sock *sk = tunnel->sock;
-	struct flowi *fl;
-	struct udphdr *uh;
-	struct inet_sock *inet;
-	int headroom;
-	int uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(struct udphdr) : 0;
-	int udp_len;
+	int headroom, uhlen, udp_len;
 	int ret = NET_XMIT_SUCCESS;
+	struct inet_sock *inet;
+	struct udphdr *uh;
 
 	/* Check that there's enough headroom in the skb to insert IP,
 	 * UDP and L2TP headers. If not enough, expand it to
 	 * make room. Adjust truesize.
 	 */
-	headroom = NET_SKB_PAD + sizeof(struct iphdr) +
-		uhlen + hdr_len;
+	uhlen = (tunnel->encap == L2TP_ENCAPTYPE_UDP) ? sizeof(*uh) : 0;
+	headroom = NET_SKB_PAD + sizeof(struct iphdr) + uhlen + session->hdr_len;
 	if (skb_cow_head(skb, headroom)) {
 		kfree_skb(skb);
 		return NET_XMIT_DROP;
@@ -1117,14 +1029,13 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 
 	/* Setup L2TP header */
 	if (tunnel->version == L2TP_HDR_VER_2)
-		l2tp_build_l2tpv2_header(session, __skb_push(skb, hdr_len));
+		l2tp_build_l2tpv2_header(session, __skb_push(skb, session->hdr_len));
 	else
-		l2tp_build_l2tpv3_header(session, __skb_push(skb, hdr_len));
+		l2tp_build_l2tpv3_header(session, __skb_push(skb, session->hdr_len));
 
 	/* Reset skb netfilter state */
 	memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
-	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
-			      IPSKB_REROUTED);
+	IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED);
 	nf_reset_ct(skb);
 
 	bh_lock_sock(sk);
@@ -1143,8 +1054,12 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		goto out_unlock;
 	}
 
+	/* Report transmitted length before we add encap header, which keeps
+	 * statistics consistent for both UDP and IP encap tx/rx paths.
+	 */
+	*len = skb->len;
+
 	inet = inet_sk(sk);
-	fl = &inet->cork.fl;
 	switch (tunnel->encap) {
 	case L2TP_ENCAPTYPE_UDP:
 		/* Setup UDP header */
@@ -1153,7 +1068,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		uh = udp_hdr(skb);
 		uh->source = inet->inet_sport;
 		uh->dest = inet->inet_dport;
-		udp_len = uhlen + hdr_len + data_len;
+		udp_len = uhlen + session->hdr_len + data_len;
 		uh->len = htons(udp_len);
 
 		/* Calculate UDP checksum if configured to do so */
@@ -1172,12 +1087,34 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 		break;
 	}
 
-	l2tp_xmit_core(session, skb, fl, data_len);
+	ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl);
+
 out_unlock:
 	bh_unlock_sock(sk);
 
 	return ret;
 }
+
+/* If caller requires the skb to have a ppp header, the header must be
+ * inserted in the skb data before calling this function.
+ */
+int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb)
+{
+	unsigned int len = 0;
+	int ret;
+
+	ret = l2tp_xmit_core(session, skb, &len);
+	if (ret == NET_XMIT_SUCCESS) {
+		atomic_long_inc(&session->tunnel->stats.tx_packets);
+		atomic_long_add(len, &session->tunnel->stats.tx_bytes);
+		atomic_long_inc(&session->stats.tx_packets);
+		atomic_long_add(len, &session->stats.tx_bytes);
+	} else {
+		atomic_long_inc(&session->tunnel->stats.tx_errors);
+		atomic_long_inc(&session->stats.tx_errors);
+	}
+	return ret;
+}
 EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
 
 /*****************************************************************************
@@ -1190,13 +1127,11 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
  */
 static void l2tp_tunnel_destruct(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
+	struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk);
 
 	if (!tunnel)
 		goto end;
 
-	l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing...\n", tunnel->name);
-
 	/* Disable udp encapsulation */
 	switch (tunnel->encap) {
 	case L2TP_ENCAPTYPE_UDP:
@@ -1255,34 +1190,16 @@ static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
 	struct hlist_node *tmp;
 	struct l2tp_session *session;
 
-	l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: closing all sessions...\n",
-		  tunnel->name);
-
 	write_lock_bh(&tunnel->hlist_lock);
 	tunnel->acpt_newsess = false;
 	for (hash = 0; hash < L2TP_HASH_SIZE; hash++) {
 again:
 		hlist_for_each_safe(walk, tmp, &tunnel->session_hlist[hash]) {
 			session = hlist_entry(walk, struct l2tp_session, hlist);
-
-			l2tp_info(session, L2TP_MSG_CONTROL,
-				  "%s: closing session\n", session->name);
-
 			hlist_del_init(&session->hlist);
 
-			if (test_and_set_bit(0, &session->dead))
-				goto again;
-
 			write_unlock_bh(&tunnel->hlist_lock);
-
-			l2tp_session_unhash(session);
-			l2tp_session_queue_purge(session);
-
-			if (session->session_close)
-				(*session->session_close)(session);
-
-			l2tp_session_dec_refcount(session);
-
+			l2tp_session_delete(session);
 			write_lock_bh(&tunnel->hlist_lock);
 
 			/* Now restart from the beginning of this hash
@@ -1299,7 +1216,7 @@ again:
 /* Tunnel socket destroy hook for UDP encapsulation */
 static void l2tp_udp_encap_destroy(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
+	struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk);
 
 	if (tunnel)
 		l2tp_tunnel_delete(tunnel);
@@ -1464,7 +1381,7 @@ out:
 
 static struct lock_class_key l2tp_socket_class;
 
-int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32 peer_tunnel_id,
+int l2tp_tunnel_create(int fd, int version, u32 tunnel_id, u32 peer_tunnel_id,
 		       struct l2tp_tunnel_cfg *cfg, struct l2tp_tunnel **tunnelp)
 {
 	struct l2tp_tunnel *tunnel = NULL;
@@ -1483,16 +1400,12 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
 	tunnel->version = version;
 	tunnel->tunnel_id = tunnel_id;
 	tunnel->peer_tunnel_id = peer_tunnel_id;
-	tunnel->debug = L2TP_DEFAULT_DEBUG_FLAGS;
 
 	tunnel->magic = L2TP_TUNNEL_MAGIC;
 	sprintf(&tunnel->name[0], "tunl %u", tunnel_id);
 	rwlock_init(&tunnel->hlist_lock);
 	tunnel->acpt_newsess = true;
 
-	if (cfg)
-		tunnel->debug = cfg->debug;
-
 	tunnel->encap = encap;
 
 	refcount_set(&tunnel->ref_count, 1);
@@ -1597,6 +1510,8 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 				   "l2tp_sock");
 	sk->sk_allocation = GFP_ATOMIC;
 
+	trace_register_tunnel(tunnel);
+
 	if (tunnel->fd >= 0)
 		sockfd_put(sock);
 
@@ -1617,6 +1532,7 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_register);
 void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
 	if (!test_and_set_bit(0, &tunnel->dead)) {
+		trace_delete_tunnel(tunnel);
 		l2tp_tunnel_inc_refcount(tunnel);
 		queue_work(l2tp_wq, &tunnel->del_work);
 	}
@@ -1628,6 +1544,7 @@ void l2tp_session_delete(struct l2tp_session *session)
 	if (test_and_set_bit(0, &session->dead))
 		return;
 
+	trace_delete_session(session);
 	l2tp_session_unhash(session);
 	l2tp_session_queue_purge(session);
 	if (session->session_close)
@@ -1686,12 +1603,8 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 		INIT_HLIST_NODE(&session->hlist);
 		INIT_HLIST_NODE(&session->global_hlist);
 
-		/* Inherit debug options from tunnel */
-		session->debug = tunnel->debug;
-
 		if (cfg) {
 			session->pwtype = cfg->pw_type;
-			session->debug = cfg->debug;
 			session->send_seq = cfg->send_seq;
 			session->recv_seq = cfg->recv_seq;
 			session->lns_mode = cfg->lns_mode;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 3468d6b177a0..cb21d906343e 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -51,7 +51,6 @@ struct l2tp_session_cfg {
 	unsigned int		lns_mode:1;	/* behave as LNS?
 						 * LAC enables sequence numbers under LNS control.
 						 */
-	int			debug;		/* bitmask of debug message categories */
 	u16			l2specific_type; /* Layer 2 specific type */
 	u8			cookie[8];	/* optional cookie */
 	int			cookie_len;	/* 0, 4 or 8 bytes */
@@ -66,6 +65,7 @@ struct l2tp_session_cfg {
  * Is linked into a per-tunnel session hashlist; and in the case of an L2TPv3 session into
  * an additional per-net ("global") hashlist.
  */
+#define L2TP_SESSION_NAME_MAX 32
 struct l2tp_session {
 	int			magic;		/* should be L2TP_SESSION_MAGIC */
 	long			dead;
@@ -90,14 +90,13 @@ struct l2tp_session {
 	struct hlist_node	hlist;		/* hash list node */
 	refcount_t		ref_count;
 
-	char			name[32];	/* for logging */
+	char			name[L2TP_SESSION_NAME_MAX]; /* for logging */
 	char			ifname[IFNAMSIZ];
 	unsigned int		recv_seq:1;	/* expect receive packets with sequence numbers? */
 	unsigned int		send_seq:1;	/* send packets with sequence numbers? */
 	unsigned int		lns_mode:1;	/* behave as LNS?
 						 * LAC enables sequence numbers under LNS control.
 						 */
-	int			debug;		/* bitmask of debug message categories */
 	int			reorder_timeout; /* configured reorder timeout (in jiffies) */
 	int			reorder_skip;	/* set if skip to next nr */
 	enum l2tp_pwtype	pwtype;
@@ -131,7 +130,6 @@ struct l2tp_session {
 
 /* L2TP tunnel configuration */
 struct l2tp_tunnel_cfg {
-	int			debug;		/* bitmask of debug message categories */
 	enum l2tp_encap_type	encap;
 
 	/* Used only for kernel-created sockets */
@@ -154,6 +152,7 @@ struct l2tp_tunnel_cfg {
  * Maintains a hashlist of sessions belonging to the tunnel instance.
  * Is linked into a per-net list of tunnels.
  */
+#define L2TP_TUNNEL_NAME_MAX 20
 struct l2tp_tunnel {
 	int			magic;		/* Should be L2TP_TUNNEL_MAGIC */
 
@@ -170,8 +169,7 @@ struct l2tp_tunnel {
 	u32			peer_tunnel_id;
 	int			version;	/* 2=>L2TPv2, 3=>L2TPv3 */
 
-	char			name[20];	/* for logging */
-	int			debug;		/* bitmask of debug message categories */
+	char			name[L2TP_TUNNEL_NAME_MAX]; /* for logging */
 	enum l2tp_encap_type	encap;
 	struct l2tp_stats	stats;
 
@@ -237,7 +235,7 @@ struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
  * Creation of a new instance is a two-step process: create, then register.
  * Destruction is triggered using the *_delete functions, and completes asynchronously.
  */
-int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
+int l2tp_tunnel_create(int fd, int version, u32 tunnel_id,
 		       u32 peer_tunnel_id, struct l2tp_tunnel_cfg *cfg,
 		       struct l2tp_tunnel **tunnelp);
 int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
@@ -263,8 +261,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
 
 /* Transmit path helpers for sending packets over the tunnel socket. */
 void l2tp_session_set_header_len(struct l2tp_session *session, int version);
-int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb,
-		  int hdr_len);
+int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb);
 
 /* Pseudowire management.
  * Pseudowires should register with l2tp core on module init, and unregister
@@ -276,6 +273,11 @@ void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type);
 /* IOCTL helper for IP encap modules. */
 int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg);
 
+/* Extract the tunnel structure from a socket's sk_user_data pointer,
+ * validating the tunnel magic feather.
+ */
+struct l2tp_tunnel *l2tp_sk_to_tunnel(struct sock *sk);
+
 static inline int l2tp_get_l2specific_len(struct l2tp_session *session)
 {
 	switch (session->l2specific_type) {
@@ -337,19 +339,6 @@ static inline int l2tp_v3_ensure_opt_in_linear(struct l2tp_session *session, str
 	return 0;
 }
 
-#define l2tp_printk(ptr, type, func, fmt, ...)				\
-do {									\
-	if (((ptr)->debug) & (type))					\
-		func(fmt, ##__VA_ARGS__);				\
-} while (0)
-
-#define l2tp_warn(ptr, type, fmt, ...)					\
-	l2tp_printk(ptr, type, pr_warn, fmt, ##__VA_ARGS__)
-#define l2tp_info(ptr, type, fmt, ...)					\
-	l2tp_printk(ptr, type, pr_info, fmt, ##__VA_ARGS__)
-#define l2tp_dbg(ptr, type, fmt, ...)					\
-	l2tp_printk(ptr, type, pr_debug, fmt, ##__VA_ARGS__)
-
 #define MODULE_ALIAS_L2TP_PWTYPE(type) \
 	MODULE_ALIAS("net-l2tp-type-" __stringify(type))
 
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 96cb9601c21b..bca75bef8282 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -167,7 +167,7 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
 		   tunnel->sock ? refcount_read(&tunnel->sock->sk_refcnt) : 0,
 		   refcount_read(&tunnel->ref_count));
 	seq_printf(m, " %08x rx %ld/%ld/%ld rx %ld/%ld/%ld\n",
-		   tunnel->debug,
+		   0,
 		   atomic_long_read(&tunnel->stats.tx_packets),
 		   atomic_long_read(&tunnel->stats.tx_bytes),
 		   atomic_long_read(&tunnel->stats.tx_errors),
@@ -192,7 +192,7 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v)
 		   session->recv_seq ? 'R' : '-',
 		   session->send_seq ? 'S' : '-',
 		   session->lns_mode ? "LNS" : "LAC",
-		   session->debug,
+		   0,
 		   jiffies_to_msecs(session->reorder_timeout));
 	seq_printf(m, "   offset 0 l2specific %hu/%hu\n",
 		   session->l2specific_type, l2tp_get_l2specific_len(session));
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 7ed2b4eced94..6cd97c75445c 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -76,7 +76,7 @@ static netdev_tx_t l2tp_eth_dev_xmit(struct sk_buff *skb, struct net_device *dev
 	struct l2tp_eth *priv = netdev_priv(dev);
 	struct l2tp_session *session = priv->session;
 	unsigned int len = skb->len;
-	int ret = l2tp_xmit_skb(session, skb, session->hdr_len);
+	int ret = l2tp_xmit_skb(session, skb);
 
 	if (likely(ret == NET_XMIT_SUCCESS)) {
 		atomic_long_add(len, &priv->tx_bytes);
@@ -128,17 +128,6 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb,
 	struct net_device *dev;
 	struct l2tp_eth *priv;
 
-	if (session->debug & L2TP_MSG_DATA) {
-		unsigned int length;
-
-		length = min(32u, skb->len);
-		if (!pskb_may_pull(skb, length))
-			goto error;
-
-		pr_debug("%s: eth recv\n", session->name);
-		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, skb->data, length);
-	}
-
 	if (!pskb_may_pull(skb, ETH_HLEN))
 		goto error;
 
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index df2a35b5714a..97ae1255fcb6 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -118,7 +118,6 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	struct l2tp_session *session;
 	struct l2tp_tunnel *tunnel = NULL;
 	struct iphdr *iph;
-	int length;
 
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
@@ -147,20 +146,6 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	if (!tunnel)
 		goto discard_sess;
 
-	/* Trace packet contents, if enabled */
-	if (tunnel->debug & L2TP_MSG_DATA) {
-		length = min(32u, skb->len);
-		if (!pskb_may_pull(skb, length))
-			goto discard_sess;
-
-		/* Point to L2TP header */
-		optr = skb->data;
-		ptr = skb->data;
-		ptr += 4;
-		pr_debug("%s: ip recv\n", tunnel->name);
-		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
-	}
-
 	if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
 		goto discard_sess;
 
@@ -248,8 +233,8 @@ static void l2tp_ip_close(struct sock *sk, long timeout)
 
 static void l2tp_ip_destroy_sock(struct sock *sk)
 {
+	struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk);
 	struct sk_buff *skb;
-	struct l2tp_tunnel *tunnel = sk->sk_user_data;
 
 	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
 		kfree_skb(skb);
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index bc757bc7e264..96f975777438 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -131,7 +131,6 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	struct l2tp_session *session;
 	struct l2tp_tunnel *tunnel = NULL;
 	struct ipv6hdr *iph;
-	int length;
 
 	if (!pskb_may_pull(skb, 4))
 		goto discard;
@@ -160,20 +159,6 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	if (!tunnel)
 		goto discard_sess;
 
-	/* Trace packet contents, if enabled */
-	if (tunnel->debug & L2TP_MSG_DATA) {
-		length = min(32u, skb->len);
-		if (!pskb_may_pull(skb, length))
-			goto discard_sess;
-
-		/* Point to L2TP header */
-		optr = skb->data;
-		ptr = skb->data;
-		ptr += 4;
-		pr_debug("%s: ip recv\n", tunnel->name);
-		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
-	}
-
 	if (l2tp_v3_ensure_opt_in_linear(session, skb, &ptr, &optr))
 		goto discard_sess;
 
@@ -262,7 +247,7 @@ static void l2tp_ip6_close(struct sock *sk, long timeout)
 
 static void l2tp_ip6_destroy_sock(struct sock *sk)
 {
-	struct l2tp_tunnel *tunnel = sk->sk_user_data;
+	struct l2tp_tunnel *tunnel = l2tp_sk_to_tunnel(sk);
 
 	lock_sock(sk);
 	ip6_flush_pending_frames(sk);
@@ -621,7 +606,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
-	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
+	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
 	if (ipc6.tclass < 0)
 		ipc6.tclass = np->tclass;
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index def78eebca4c..83956c9ee1fc 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -229,14 +229,11 @@ static int l2tp_nl_cmd_tunnel_create(struct sk_buff *skb, struct genl_info *info
 			goto out;
 	}
 
-	if (attrs[L2TP_ATTR_DEBUG])
-		cfg.debug = nla_get_u32(attrs[L2TP_ATTR_DEBUG]);
-
 	ret = -EINVAL;
 	switch (cfg.encap) {
 	case L2TP_ENCAPTYPE_UDP:
 	case L2TP_ENCAPTYPE_IP:
-		ret = l2tp_tunnel_create(net, fd, proto_version, tunnel_id,
+		ret = l2tp_tunnel_create(fd, proto_version, tunnel_id,
 					 peer_tunnel_id, &cfg, &tunnel);
 		break;
 	}
@@ -307,9 +304,6 @@ static int l2tp_nl_cmd_tunnel_modify(struct sk_buff *skb, struct genl_info *info
 		goto out;
 	}
 
-	if (info->attrs[L2TP_ATTR_DEBUG])
-		tunnel->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
-
 	ret = l2tp_tunnel_notify(&l2tp_nl_family, info,
 				 tunnel, L2TP_CMD_TUNNEL_MODIFY);
 
@@ -400,7 +394,7 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	if (nla_put_u8(skb, L2TP_ATTR_PROTO_VERSION, tunnel->version) ||
 	    nla_put_u32(skb, L2TP_ATTR_CONN_ID, tunnel->tunnel_id) ||
 	    nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) ||
-	    nla_put_u32(skb, L2TP_ATTR_DEBUG, tunnel->debug) ||
+	    nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) ||
 	    nla_put_u16(skb, L2TP_ATTR_ENCAP_TYPE, tunnel->encap))
 		goto nla_put_failure;
 
@@ -426,6 +420,9 @@ static int l2tp_nl_tunnel_send(struct sk_buff *skb, u32 portid, u32 seq, int fla
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_SEQ_DISCARDS,
 			      atomic_long_read(&tunnel->stats.rx_seq_discards),
 			      L2TP_ATTR_STATS_PAD) ||
+	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_COOKIE_DISCARDS,
+			      atomic_long_read(&tunnel->stats.rx_cookie_discards),
+			      L2TP_ATTR_STATS_PAD) ||
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_OOS_PACKETS,
 			      atomic_long_read(&tunnel->stats.rx_oos_packets),
 			      L2TP_ATTR_STATS_PAD) ||
@@ -605,9 +602,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 			cfg.ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
 	}
 
-	if (info->attrs[L2TP_ATTR_DEBUG])
-		cfg.debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
-
 	if (info->attrs[L2TP_ATTR_RECV_SEQ])
 		cfg.recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
 
@@ -689,9 +683,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 		goto out;
 	}
 
-	if (info->attrs[L2TP_ATTR_DEBUG])
-		session->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
-
 	if (info->attrs[L2TP_ATTR_RECV_SEQ])
 		session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
 
@@ -730,7 +721,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 	    nla_put_u32(skb, L2TP_ATTR_SESSION_ID, session->session_id) ||
 	    nla_put_u32(skb, L2TP_ATTR_PEER_CONN_ID, tunnel->peer_tunnel_id) ||
 	    nla_put_u32(skb, L2TP_ATTR_PEER_SESSION_ID, session->peer_session_id) ||
-	    nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) ||
+	    nla_put_u32(skb, L2TP_ATTR_DEBUG, 0) ||
 	    nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype))
 		goto nla_put_failure;
 
@@ -772,6 +763,9 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_SEQ_DISCARDS,
 			      atomic_long_read(&session->stats.rx_seq_discards),
 			      L2TP_ATTR_STATS_PAD) ||
+	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_COOKIE_DISCARDS,
+			      atomic_long_read(&session->stats.rx_cookie_discards),
+			      L2TP_ATTR_STATS_PAD) ||
 	    nla_put_u64_64bit(skb, L2TP_ATTR_RX_OOS_PACKETS,
 			      atomic_long_read(&session->stats.rx_oos_packets),
 			      L2TP_ATTR_STATS_PAD) ||
@@ -920,7 +914,7 @@ static const struct nla_policy l2tp_nl_policy[L2TP_ATTR_MAX + 1] = {
 	},
 };
 
-static const struct genl_ops l2tp_nl_ops[] = {
+static const struct genl_small_ops l2tp_nl_ops[] = {
 	{
 		.cmd = L2TP_CMD_NOOP,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -987,8 +981,8 @@ static struct genl_family l2tp_nl_family __ro_after_init = {
 	.policy = l2tp_nl_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= l2tp_nl_ops,
-	.n_ops		= ARRAY_SIZE(l2tp_nl_ops),
+	.small_ops	= l2tp_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(l2tp_nl_ops),
 	.mcgrps		= l2tp_multicast_group,
 	.n_mcgrps	= ARRAY_SIZE(l2tp_multicast_group),
 };
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 13c3153b40d6..aea85f91f059 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -237,17 +237,9 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
 	if (sk->sk_state & PPPOX_BOUND) {
 		struct pppox_sock *po;
 
-		l2tp_dbg(session, L2TP_MSG_DATA,
-			 "%s: recv %d byte data frame, passing to ppp\n",
-			 session->name, data_len);
-
 		po = pppox_sk(sk);
 		ppp_input(&po->chan, skb);
 	} else {
-		l2tp_dbg(session, L2TP_MSG_DATA,
-			 "%s: recv %d byte data frame, passing to L2TP socket\n",
-			 session->name, data_len);
-
 		if (sock_queue_rcv_skb(sk, skb) < 0) {
 			atomic_long_inc(&session->stats.rx_errors);
 			kfree_skb(skb);
@@ -259,7 +251,7 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
 
 no_sock:
 	rcu_read_unlock();
-	l2tp_info(session, L2TP_MSG_DATA, "%s: no socket\n", session->name);
+	pr_warn_ratelimited("%s: no socket in recv\n", session->name);
 	kfree_skb(skb);
 }
 
@@ -324,7 +316,7 @@ static int pppol2tp_sendmsg(struct socket *sock, struct msghdr *m,
 	}
 
 	local_bh_disable();
-	l2tp_xmit_skb(session, skb, session->hdr_len);
+	l2tp_xmit_skb(session, skb);
 	local_bh_enable();
 
 	sock_put(sk);
@@ -383,7 +375,7 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
 	skb->data[1] = PPP_UI;
 
 	local_bh_disable();
-	l2tp_xmit_skb(session, skb, session->hdr_len);
+	l2tp_xmit_skb(session, skb);
 	local_bh_enable();
 
 	sock_put(sk);
@@ -710,7 +702,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 		if (!tunnel) {
 			struct l2tp_tunnel_cfg tcfg = {
 				.encap = L2TP_ENCAPTYPE_UDP,
-				.debug = 0,
 			};
 
 			/* Prevent l2tp_tunnel_register() from trying to set up
@@ -721,7 +712,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 				goto end;
 			}
 
-			error = l2tp_tunnel_create(sock_net(sk), info.fd,
+			error = l2tp_tunnel_create(info.fd,
 						   info.version,
 						   info.tunnel_id,
 						   info.peer_tunnel_id, &tcfg,
@@ -840,8 +831,6 @@ out_no_ppp:
 	drop_refcnt = false;
 
 	sk->sk_state = PPPOX_CONNECTED;
-	l2tp_info(session, L2TP_MSG_CONTROL, "%s: created\n",
-		  session->name);
 
 end:
 	if (error) {
@@ -1076,6 +1065,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 		if (!session)
 			return -ENOTCONN;
 
+		if (WARN_ON(session->magic != L2TP_SESSION_MAGIC))
+			return -EBADF;
+
 		/* Not defined for tunnels */
 		if (!session->session_id && !session->peer_session_id)
 			return -ENOSYS;
@@ -1090,6 +1082,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 		if (!session)
 			return -ENOTCONN;
 
+		if (WARN_ON(session->magic != L2TP_SESSION_MAGIC))
+			return -EBADF;
+
 		/* Not defined for tunnels */
 		if (!session->session_id && !session->peer_session_id)
 			return -ENOSYS;
@@ -1103,6 +1098,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 		if (!session)
 			return -ENOTCONN;
 
+		if (WARN_ON(session->magic != L2TP_SESSION_MAGIC))
+			return -EBADF;
+
 		/* Session 0 represents the parent tunnel */
 		if (!session->session_id && !session->peer_session_id) {
 			u32 session_id;
@@ -1157,9 +1155,7 @@ static int pppol2tp_tunnel_setsockopt(struct sock *sk,
 
 	switch (optname) {
 	case PPPOL2TP_SO_DEBUG:
-		tunnel->debug = val;
-		l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: set debug=%x\n",
-			  tunnel->name, tunnel->debug);
+		/* Tunnel debug flags option is deprecated */
 		break;
 
 	default:
@@ -1185,9 +1181,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
 			break;
 		}
 		session->recv_seq = !!val;
-		l2tp_info(session, L2TP_MSG_CONTROL,
-			  "%s: set recv_seq=%d\n",
-			  session->name, session->recv_seq);
 		break;
 
 	case PPPOL2TP_SO_SENDSEQ:
@@ -1203,9 +1196,6 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
 				PPPOL2TP_L2TP_HDR_SIZE_NOSEQ;
 		}
 		l2tp_session_set_header_len(session, session->tunnel->version);
-		l2tp_info(session, L2TP_MSG_CONTROL,
-			  "%s: set send_seq=%d\n",
-			  session->name, session->send_seq);
 		break;
 
 	case PPPOL2TP_SO_LNSMODE:
@@ -1214,22 +1204,14 @@ static int pppol2tp_session_setsockopt(struct sock *sk,
 			break;
 		}
 		session->lns_mode = !!val;
-		l2tp_info(session, L2TP_MSG_CONTROL,
-			  "%s: set lns_mode=%d\n",
-			  session->name, session->lns_mode);
 		break;
 
 	case PPPOL2TP_SO_DEBUG:
-		session->debug = val;
-		l2tp_info(session, L2TP_MSG_CONTROL, "%s: set debug=%x\n",
-			  session->name, session->debug);
+		/* Session debug flags option is deprecated */
 		break;
 
 	case PPPOL2TP_SO_REORDERTO:
 		session->reorder_timeout = msecs_to_jiffies(val);
-		l2tp_info(session, L2TP_MSG_CONTROL,
-			  "%s: set reorder_timeout=%d\n",
-			  session->name, session->reorder_timeout);
 		break;
 
 	default:
@@ -1297,9 +1279,8 @@ static int pppol2tp_tunnel_getsockopt(struct sock *sk,
 
 	switch (optname) {
 	case PPPOL2TP_SO_DEBUG:
-		*val = tunnel->debug;
-		l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: get debug=%x\n",
-			  tunnel->name, tunnel->debug);
+		/* Tunnel debug flags option is deprecated */
+		*val = 0;
 		break;
 
 	default:
@@ -1321,32 +1302,23 @@ static int pppol2tp_session_getsockopt(struct sock *sk,
 	switch (optname) {
 	case PPPOL2TP_SO_RECVSEQ:
 		*val = session->recv_seq;
-		l2tp_info(session, L2TP_MSG_CONTROL,
-			  "%s: get recv_seq=%d\n", session->name, *val);
 		break;
 
 	case PPPOL2TP_SO_SENDSEQ:
 		*val = session->send_seq;
-		l2tp_info(session, L2TP_MSG_CONTROL,
-			  "%s: get send_seq=%d\n", session->name, *val);
 		break;
 
 	case PPPOL2TP_SO_LNSMODE:
 		*val = session->lns_mode;
-		l2tp_info(session, L2TP_MSG_CONTROL,
-			  "%s: get lns_mode=%d\n", session->name, *val);
 		break;
 
 	case PPPOL2TP_SO_DEBUG:
-		*val = session->debug;
-		l2tp_info(session, L2TP_MSG_CONTROL, "%s: get debug=%d\n",
-			  session->name, *val);
+		/* Session debug flags option is deprecated */
+		*val = 0;
 		break;
 
 	case PPPOL2TP_SO_REORDERTO:
 		*val = (int)jiffies_to_msecs(session->reorder_timeout);
-		l2tp_info(session, L2TP_MSG_CONTROL,
-			  "%s: get reorder_timeout=%d\n", session->name, *val);
 		break;
 
 	default:
@@ -1534,7 +1506,7 @@ static void pppol2tp_seq_tunnel_show(struct seq_file *m, void *v)
 		   (tunnel == tunnel->sock->sk_user_data) ? 'Y' : 'N',
 		   refcount_read(&tunnel->ref_count) - 1);
 	seq_printf(m, " %08x %ld/%ld/%ld %ld/%ld/%ld\n",
-		   tunnel->debug,
+		   0,
 		   atomic_long_read(&tunnel->stats.tx_packets),
 		   atomic_long_read(&tunnel->stats.tx_bytes),
 		   atomic_long_read(&tunnel->stats.tx_errors),
@@ -1580,7 +1552,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		   session->recv_seq ? 'R' : '-',
 		   session->send_seq ? 'S' : '-',
 		   session->lns_mode ? "LNS" : "LAC",
-		   session->debug,
+		   0,
 		   jiffies_to_msecs(session->reorder_timeout));
 	seq_printf(m, "   %hu/%hu %ld/%ld/%ld %ld/%ld/%ld\n",
 		   session->nr, session->ns,
diff --git a/net/l2tp/trace.h b/net/l2tp/trace.h
new file mode 100644
index 000000000000..8596eaa12a2e
--- /dev/null
+++ b/net/l2tp/trace.h
@@ -0,0 +1,211 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM l2tp
+
+#if !defined(_TRACE_L2TP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_L2TP_H
+
+#include <linux/tracepoint.h>
+#include <linux/l2tp.h>
+#include "l2tp_core.h"
+
+#define encap_type_name(e) { L2TP_ENCAPTYPE_##e, #e }
+#define show_encap_type_name(val) \
+	__print_symbolic(val, \
+			encap_type_name(UDP), \
+			encap_type_name(IP))
+
+#define pw_type_name(p) { L2TP_PWTYPE_##p, #p }
+#define show_pw_type_name(val) \
+	__print_symbolic(val, \
+	pw_type_name(ETH_VLAN), \
+	pw_type_name(ETH), \
+	pw_type_name(PPP), \
+	pw_type_name(PPP_AC), \
+	pw_type_name(IP))
+
+DECLARE_EVENT_CLASS(tunnel_only_evt,
+	TP_PROTO(struct l2tp_tunnel *tunnel),
+	TP_ARGS(tunnel),
+	TP_STRUCT__entry(
+		__array(char, name, L2TP_TUNNEL_NAME_MAX)
+	),
+	TP_fast_assign(
+		memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX);
+	),
+	TP_printk("%s", __entry->name)
+);
+
+DECLARE_EVENT_CLASS(session_only_evt,
+	TP_PROTO(struct l2tp_session *session),
+	TP_ARGS(session),
+	TP_STRUCT__entry(
+		__array(char, name, L2TP_SESSION_NAME_MAX)
+	),
+	TP_fast_assign(
+		memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX);
+	),
+	TP_printk("%s", __entry->name)
+);
+
+TRACE_EVENT(register_tunnel,
+	TP_PROTO(struct l2tp_tunnel *tunnel),
+	TP_ARGS(tunnel),
+	TP_STRUCT__entry(
+		__array(char, name, L2TP_TUNNEL_NAME_MAX)
+		__field(int, fd)
+		__field(u32, tid)
+		__field(u32, ptid)
+		__field(int, version)
+		__field(enum l2tp_encap_type, encap)
+	),
+	TP_fast_assign(
+		memcpy(__entry->name, tunnel->name, L2TP_TUNNEL_NAME_MAX);
+		__entry->fd = tunnel->fd;
+		__entry->tid = tunnel->tunnel_id;
+		__entry->ptid = tunnel->peer_tunnel_id;
+		__entry->version = tunnel->version;
+		__entry->encap = tunnel->encap;
+	),
+	TP_printk("%s: type=%s encap=%s version=L2TPv%d tid=%u ptid=%u fd=%d",
+		__entry->name,
+		__entry->fd > 0 ? "managed" : "unmanaged",
+		show_encap_type_name(__entry->encap),
+		__entry->version,
+		__entry->tid,
+		__entry->ptid,
+		__entry->fd)
+);
+
+DEFINE_EVENT(tunnel_only_evt, delete_tunnel,
+	TP_PROTO(struct l2tp_tunnel *tunnel),
+	TP_ARGS(tunnel)
+);
+
+DEFINE_EVENT(tunnel_only_evt, free_tunnel,
+	TP_PROTO(struct l2tp_tunnel *tunnel),
+	TP_ARGS(tunnel)
+);
+
+TRACE_EVENT(register_session,
+	TP_PROTO(struct l2tp_session *session),
+	TP_ARGS(session),
+	TP_STRUCT__entry(
+		__array(char, name, L2TP_SESSION_NAME_MAX)
+		__field(u32, tid)
+		__field(u32, ptid)
+		__field(u32, sid)
+		__field(u32, psid)
+		__field(enum l2tp_pwtype, pwtype)
+	),
+	TP_fast_assign(
+		memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX);
+		__entry->tid = session->tunnel ? session->tunnel->tunnel_id : 0;
+		__entry->ptid = session->tunnel ? session->tunnel->peer_tunnel_id : 0;
+		__entry->sid = session->session_id;
+		__entry->psid = session->peer_session_id;
+		__entry->pwtype = session->pwtype;
+	),
+	TP_printk("%s: pseudowire=%s sid=%u psid=%u tid=%u ptid=%u",
+		__entry->name,
+		show_pw_type_name(__entry->pwtype),
+		__entry->sid,
+		__entry->psid,
+		__entry->sid,
+		__entry->psid)
+);
+
+DEFINE_EVENT(session_only_evt, delete_session,
+	TP_PROTO(struct l2tp_session *session),
+	TP_ARGS(session)
+);
+
+DEFINE_EVENT(session_only_evt, free_session,
+	TP_PROTO(struct l2tp_session *session),
+	TP_ARGS(session)
+);
+
+DEFINE_EVENT(session_only_evt, session_seqnum_lns_enable,
+	TP_PROTO(struct l2tp_session *session),
+	TP_ARGS(session)
+);
+
+DEFINE_EVENT(session_only_evt, session_seqnum_lns_disable,
+	TP_PROTO(struct l2tp_session *session),
+	TP_ARGS(session)
+);
+
+DECLARE_EVENT_CLASS(session_seqnum_evt,
+	TP_PROTO(struct l2tp_session *session),
+	TP_ARGS(session),
+	TP_STRUCT__entry(
+		__array(char, name, L2TP_SESSION_NAME_MAX)
+		__field(u32, ns)
+		__field(u32, nr)
+	),
+	TP_fast_assign(
+		memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX);
+		__entry->ns = session->ns;
+		__entry->nr = session->nr;
+	),
+	TP_printk("%s: ns=%u nr=%u",
+		__entry->name,
+		__entry->ns,
+		__entry->nr)
+);
+
+DEFINE_EVENT(session_seqnum_evt, session_seqnum_update,
+	TP_PROTO(struct l2tp_session *session),
+	TP_ARGS(session)
+);
+
+DEFINE_EVENT(session_seqnum_evt, session_seqnum_reset,
+	TP_PROTO(struct l2tp_session *session),
+	TP_ARGS(session)
+);
+
+DECLARE_EVENT_CLASS(session_pkt_discard_evt,
+	TP_PROTO(struct l2tp_session *session, u32 pkt_ns),
+	TP_ARGS(session, pkt_ns),
+	TP_STRUCT__entry(
+		__array(char, name, L2TP_SESSION_NAME_MAX)
+		__field(u32, pkt_ns)
+		__field(u32, my_nr)
+		__field(u32, reorder_q_len)
+	),
+	TP_fast_assign(
+		memcpy(__entry->name, session->name, L2TP_SESSION_NAME_MAX);
+		__entry->pkt_ns = pkt_ns,
+		__entry->my_nr = session->nr;
+		__entry->reorder_q_len = skb_queue_len(&session->reorder_q);
+	),
+	TP_printk("%s: pkt_ns=%u my_nr=%u reorder_q_len=%u",
+		__entry->name,
+		__entry->pkt_ns,
+		__entry->my_nr,
+		__entry->reorder_q_len)
+);
+
+DEFINE_EVENT(session_pkt_discard_evt, session_pkt_expired,
+	TP_PROTO(struct l2tp_session *session, u32 pkt_ns),
+	TP_ARGS(session, pkt_ns)
+);
+
+DEFINE_EVENT(session_pkt_discard_evt, session_pkt_outside_rx_window,
+	TP_PROTO(struct l2tp_session *session, u32 pkt_ns),
+	TP_ARGS(session, pkt_ns)
+);
+
+DEFINE_EVENT(session_pkt_discard_evt, session_pkt_oos,
+	TP_PROTO(struct l2tp_session *session, u32 pkt_ns),
+	TP_ARGS(session, pkt_ns)
+);
+
+#endif /* _TRACE_L2TP_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+#include <trace/define_trace.h>
diff --git a/net/l3mdev/l3mdev.c b/net/l3mdev/l3mdev.c
index 864326f150e2..ad7730b68772 100644
--- a/net/l3mdev/l3mdev.c
+++ b/net/l3mdev/l3mdev.c
@@ -241,6 +241,7 @@ EXPORT_SYMBOL_GPL(l3mdev_link_scope_lookup);
  *				L3 master device
  *	@net: network namespace for device index lookup
  *	@fl:  flow struct
+ *	@arg: store the table the rule matched with here
  */
 
 int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c
index 3c03f6512c5f..0511bbe4af7b 100644
--- a/net/lapb/lapb_iface.c
+++ b/net/lapb/lapb_iface.c
@@ -122,6 +122,8 @@ static struct lapb_cb *lapb_create_cb(void)
 
 	timer_setup(&lapb->t1timer, NULL, 0);
 	timer_setup(&lapb->t2timer, NULL, 0);
+	lapb->t1timer_stop = true;
+	lapb->t2timer_stop = true;
 
 	lapb->t1      = LAPB_DEFAULT_T1;
 	lapb->t2      = LAPB_DEFAULT_T2;
@@ -129,6 +131,8 @@ static struct lapb_cb *lapb_create_cb(void)
 	lapb->mode    = LAPB_DEFAULT_MODE;
 	lapb->window  = LAPB_DEFAULT_WINDOW;
 	lapb->state   = LAPB_STATE_0;
+
+	spin_lock_init(&lapb->lock);
 	refcount_set(&lapb->refcnt, 1);
 out:
 	return lapb;
@@ -178,11 +182,23 @@ int lapb_unregister(struct net_device *dev)
 		goto out;
 	lapb_put(lapb);
 
+	/* Wait for other refs to "lapb" to drop */
+	while (refcount_read(&lapb->refcnt) > 2)
+		usleep_range(1, 10);
+
+	spin_lock_bh(&lapb->lock);
+
 	lapb_stop_t1timer(lapb);
 	lapb_stop_t2timer(lapb);
 
 	lapb_clear_queues(lapb);
 
+	spin_unlock_bh(&lapb->lock);
+
+	/* Wait for running timers to stop */
+	del_timer_sync(&lapb->t1timer);
+	del_timer_sync(&lapb->t2timer);
+
 	__lapb_remove_cb(lapb);
 
 	lapb_put(lapb);
@@ -201,6 +217,8 @@ int lapb_getparms(struct net_device *dev, struct lapb_parms_struct *parms)
 	if (!lapb)
 		goto out;
 
+	spin_lock_bh(&lapb->lock);
+
 	parms->t1      = lapb->t1 / HZ;
 	parms->t2      = lapb->t2 / HZ;
 	parms->n2      = lapb->n2;
@@ -219,6 +237,7 @@ int lapb_getparms(struct net_device *dev, struct lapb_parms_struct *parms)
 	else
 		parms->t2timer = (lapb->t2timer.expires - jiffies) / HZ;
 
+	spin_unlock_bh(&lapb->lock);
 	lapb_put(lapb);
 	rc = LAPB_OK;
 out:
@@ -234,6 +253,8 @@ int lapb_setparms(struct net_device *dev, struct lapb_parms_struct *parms)
 	if (!lapb)
 		goto out;
 
+	spin_lock_bh(&lapb->lock);
+
 	rc = LAPB_INVALUE;
 	if (parms->t1 < 1 || parms->t2 < 1 || parms->n2 < 1)
 		goto out_put;
@@ -256,6 +277,7 @@ int lapb_setparms(struct net_device *dev, struct lapb_parms_struct *parms)
 
 	rc = LAPB_OK;
 out_put:
+	spin_unlock_bh(&lapb->lock);
 	lapb_put(lapb);
 out:
 	return rc;
@@ -270,6 +292,8 @@ int lapb_connect_request(struct net_device *dev)
 	if (!lapb)
 		goto out;
 
+	spin_lock_bh(&lapb->lock);
+
 	rc = LAPB_OK;
 	if (lapb->state == LAPB_STATE_1)
 		goto out_put;
@@ -285,24 +309,18 @@ int lapb_connect_request(struct net_device *dev)
 
 	rc = LAPB_OK;
 out_put:
+	spin_unlock_bh(&lapb->lock);
 	lapb_put(lapb);
 out:
 	return rc;
 }
 EXPORT_SYMBOL(lapb_connect_request);
 
-int lapb_disconnect_request(struct net_device *dev)
+static int __lapb_disconnect_request(struct lapb_cb *lapb)
 {
-	struct lapb_cb *lapb = lapb_devtostruct(dev);
-	int rc = LAPB_BADTOKEN;
-
-	if (!lapb)
-		goto out;
-
 	switch (lapb->state) {
 	case LAPB_STATE_0:
-		rc = LAPB_NOTCONNECTED;
-		goto out_put;
+		return LAPB_NOTCONNECTED;
 
 	case LAPB_STATE_1:
 		lapb_dbg(1, "(%p) S1 TX DISC(1)\n", lapb->dev);
@@ -310,12 +328,10 @@ int lapb_disconnect_request(struct net_device *dev)
 		lapb_send_control(lapb, LAPB_DISC, LAPB_POLLON, LAPB_COMMAND);
 		lapb->state = LAPB_STATE_0;
 		lapb_start_t1timer(lapb);
-		rc = LAPB_NOTCONNECTED;
-		goto out_put;
+		return LAPB_NOTCONNECTED;
 
 	case LAPB_STATE_2:
-		rc = LAPB_OK;
-		goto out_put;
+		return LAPB_OK;
 	}
 
 	lapb_clear_queues(lapb);
@@ -328,8 +344,22 @@ int lapb_disconnect_request(struct net_device *dev)
 	lapb_dbg(1, "(%p) S3 DISC(1)\n", lapb->dev);
 	lapb_dbg(0, "(%p) S3 -> S2\n", lapb->dev);
 
-	rc = LAPB_OK;
-out_put:
+	return LAPB_OK;
+}
+
+int lapb_disconnect_request(struct net_device *dev)
+{
+	struct lapb_cb *lapb = lapb_devtostruct(dev);
+	int rc = LAPB_BADTOKEN;
+
+	if (!lapb)
+		goto out;
+
+	spin_lock_bh(&lapb->lock);
+
+	rc = __lapb_disconnect_request(lapb);
+
+	spin_unlock_bh(&lapb->lock);
 	lapb_put(lapb);
 out:
 	return rc;
@@ -344,6 +374,8 @@ int lapb_data_request(struct net_device *dev, struct sk_buff *skb)
 	if (!lapb)
 		goto out;
 
+	spin_lock_bh(&lapb->lock);
+
 	rc = LAPB_NOTCONNECTED;
 	if (lapb->state != LAPB_STATE_3 && lapb->state != LAPB_STATE_4)
 		goto out_put;
@@ -352,6 +384,7 @@ int lapb_data_request(struct net_device *dev, struct sk_buff *skb)
 	lapb_kick(lapb);
 	rc = LAPB_OK;
 out_put:
+	spin_unlock_bh(&lapb->lock);
 	lapb_put(lapb);
 out:
 	return rc;
@@ -364,7 +397,9 @@ int lapb_data_received(struct net_device *dev, struct sk_buff *skb)
 	int rc = LAPB_BADTOKEN;
 
 	if (lapb) {
+		spin_lock_bh(&lapb->lock);
 		lapb_data_input(lapb, skb);
+		spin_unlock_bh(&lapb->lock);
 		lapb_put(lapb);
 		rc = LAPB_OK;
 	}
@@ -418,14 +453,98 @@ int lapb_data_transmit(struct lapb_cb *lapb, struct sk_buff *skb)
 	return used;
 }
 
+/* Handle device status changes. */
+static int lapb_device_event(struct notifier_block *this, unsigned long event,
+			     void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct lapb_cb *lapb;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		return NOTIFY_DONE;
+
+	if (dev->type != ARPHRD_X25)
+		return NOTIFY_DONE;
+
+	lapb = lapb_devtostruct(dev);
+	if (!lapb)
+		return NOTIFY_DONE;
+
+	spin_lock_bh(&lapb->lock);
+
+	switch (event) {
+	case NETDEV_UP:
+		lapb_dbg(0, "(%p) Interface up: %s\n", dev, dev->name);
+
+		if (netif_carrier_ok(dev)) {
+			lapb_dbg(0, "(%p): Carrier is already up: %s\n", dev,
+				 dev->name);
+			if (lapb->mode & LAPB_DCE) {
+				lapb_start_t1timer(lapb);
+			} else {
+				if (lapb->state == LAPB_STATE_0) {
+					lapb->state = LAPB_STATE_1;
+					lapb_establish_data_link(lapb);
+				}
+			}
+		}
+		break;
+	case NETDEV_GOING_DOWN:
+		if (netif_carrier_ok(dev))
+			__lapb_disconnect_request(lapb);
+		break;
+	case NETDEV_DOWN:
+		lapb_dbg(0, "(%p) Interface down: %s\n", dev, dev->name);
+		lapb_dbg(0, "(%p) S%d -> S0\n", dev, lapb->state);
+		lapb_clear_queues(lapb);
+		lapb->state = LAPB_STATE_0;
+		lapb->n2count   = 0;
+		lapb_stop_t1timer(lapb);
+		lapb_stop_t2timer(lapb);
+		break;
+	case NETDEV_CHANGE:
+		if (netif_carrier_ok(dev)) {
+			lapb_dbg(0, "(%p): Carrier detected: %s\n", dev,
+				 dev->name);
+			if (lapb->mode & LAPB_DCE) {
+				lapb_start_t1timer(lapb);
+			} else {
+				if (lapb->state == LAPB_STATE_0) {
+					lapb->state = LAPB_STATE_1;
+					lapb_establish_data_link(lapb);
+				}
+			}
+		} else {
+			lapb_dbg(0, "(%p) Carrier lost: %s\n", dev, dev->name);
+			lapb_dbg(0, "(%p) S%d -> S0\n", dev, lapb->state);
+			lapb_clear_queues(lapb);
+			lapb->state = LAPB_STATE_0;
+			lapb->n2count   = 0;
+			lapb_stop_t1timer(lapb);
+			lapb_stop_t2timer(lapb);
+		}
+		break;
+	}
+
+	spin_unlock_bh(&lapb->lock);
+	lapb_put(lapb);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block lapb_dev_notifier = {
+	.notifier_call = lapb_device_event,
+};
+
 static int __init lapb_init(void)
 {
-	return 0;
+	return register_netdevice_notifier(&lapb_dev_notifier);
 }
 
 static void __exit lapb_exit(void)
 {
 	WARN_ON(!list_empty(&lapb_list));
+
+	unregister_netdevice_notifier(&lapb_dev_notifier);
 }
 
 MODULE_AUTHOR("Jonathan Naylor <g4klx@g4klx.demon.co.uk>");
diff --git a/net/lapb/lapb_out.c b/net/lapb/lapb_out.c
index 7a4d0715d1c3..a966d29c772d 100644
--- a/net/lapb/lapb_out.c
+++ b/net/lapb/lapb_out.c
@@ -82,7 +82,8 @@ void lapb_kick(struct lapb_cb *lapb)
 		skb = skb_dequeue(&lapb->write_queue);
 
 		do {
-			if ((skbn = skb_clone(skb, GFP_ATOMIC)) == NULL) {
+			skbn = skb_copy(skb, GFP_ATOMIC);
+			if (!skbn) {
 				skb_queue_head(&lapb->write_queue, skb);
 				break;
 			}
diff --git a/net/lapb/lapb_timer.c b/net/lapb/lapb_timer.c
index 8f5b17001a07..0230b272b7d1 100644
--- a/net/lapb/lapb_timer.c
+++ b/net/lapb/lapb_timer.c
@@ -40,6 +40,7 @@ void lapb_start_t1timer(struct lapb_cb *lapb)
 	lapb->t1timer.function = lapb_t1timer_expiry;
 	lapb->t1timer.expires  = jiffies + lapb->t1;
 
+	lapb->t1timer_stop = false;
 	add_timer(&lapb->t1timer);
 }
 
@@ -50,16 +51,19 @@ void lapb_start_t2timer(struct lapb_cb *lapb)
 	lapb->t2timer.function = lapb_t2timer_expiry;
 	lapb->t2timer.expires  = jiffies + lapb->t2;
 
+	lapb->t2timer_stop = false;
 	add_timer(&lapb->t2timer);
 }
 
 void lapb_stop_t1timer(struct lapb_cb *lapb)
 {
+	lapb->t1timer_stop = true;
 	del_timer(&lapb->t1timer);
 }
 
 void lapb_stop_t2timer(struct lapb_cb *lapb)
 {
+	lapb->t2timer_stop = true;
 	del_timer(&lapb->t2timer);
 }
 
@@ -72,24 +76,46 @@ static void lapb_t2timer_expiry(struct timer_list *t)
 {
 	struct lapb_cb *lapb = from_timer(lapb, t, t2timer);
 
+	spin_lock_bh(&lapb->lock);
+	if (timer_pending(&lapb->t2timer)) /* A new timer has been set up */
+		goto out;
+	if (lapb->t2timer_stop) /* The timer has been stopped */
+		goto out;
+
 	if (lapb->condition & LAPB_ACK_PENDING_CONDITION) {
 		lapb->condition &= ~LAPB_ACK_PENDING_CONDITION;
 		lapb_timeout_response(lapb);
 	}
+
+out:
+	spin_unlock_bh(&lapb->lock);
 }
 
 static void lapb_t1timer_expiry(struct timer_list *t)
 {
 	struct lapb_cb *lapb = from_timer(lapb, t, t1timer);
 
+	spin_lock_bh(&lapb->lock);
+	if (timer_pending(&lapb->t1timer)) /* A new timer has been set up */
+		goto out;
+	if (lapb->t1timer_stop) /* The timer has been stopped */
+		goto out;
+
 	switch (lapb->state) {
 
 		/*
-		 *	If we are a DCE, keep going DM .. DM .. DM
+		 *	If we are a DCE, send DM up to N2 times, then switch to
+		 *	STATE_1 and send SABM(E).
 		 */
 		case LAPB_STATE_0:
-			if (lapb->mode & LAPB_DCE)
+			if (lapb->mode & LAPB_DCE &&
+			    lapb->n2count != lapb->n2) {
+				lapb->n2count++;
 				lapb_send_control(lapb, LAPB_DM, LAPB_POLLOFF, LAPB_RESPONSE);
+			} else {
+				lapb->state = LAPB_STATE_1;
+				lapb_establish_data_link(lapb);
+			}
 			break;
 
 		/*
@@ -101,7 +127,7 @@ static void lapb_t1timer_expiry(struct timer_list *t)
 				lapb->state = LAPB_STATE_0;
 				lapb_disconnect_indication(lapb, LAPB_TIMEDOUT);
 				lapb_dbg(0, "(%p) S1 -> S0\n", lapb->dev);
-				return;
+				goto out;
 			} else {
 				lapb->n2count++;
 				if (lapb->mode & LAPB_EXTENDED) {
@@ -125,7 +151,7 @@ static void lapb_t1timer_expiry(struct timer_list *t)
 				lapb->state = LAPB_STATE_0;
 				lapb_disconnect_confirmation(lapb, LAPB_TIMEDOUT);
 				lapb_dbg(0, "(%p) S2 -> S0\n", lapb->dev);
-				return;
+				goto out;
 			} else {
 				lapb->n2count++;
 				lapb_dbg(1, "(%p) S2 TX DISC(1)\n", lapb->dev);
@@ -143,7 +169,7 @@ static void lapb_t1timer_expiry(struct timer_list *t)
 				lapb_stop_t2timer(lapb);
 				lapb_disconnect_indication(lapb, LAPB_TIMEDOUT);
 				lapb_dbg(0, "(%p) S3 -> S0\n", lapb->dev);
-				return;
+				goto out;
 			} else {
 				lapb->n2count++;
 				lapb_requeue_frames(lapb);
@@ -160,7 +186,7 @@ static void lapb_t1timer_expiry(struct timer_list *t)
 				lapb->state = LAPB_STATE_0;
 				lapb_disconnect_indication(lapb, LAPB_TIMEDOUT);
 				lapb_dbg(0, "(%p) S4 -> S0\n", lapb->dev);
-				return;
+				goto out;
 			} else {
 				lapb->n2count++;
 				lapb_transmit_frmr(lapb);
@@ -169,4 +195,7 @@ static void lapb_t1timer_expiry(struct timer_list *t)
 	}
 
 	lapb_start_t1timer(lapb);
+
+out:
+	spin_unlock_bh(&lapb->lock);
 }
diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c
index 1144cda2a0fc..912aa9bd5e29 100644
--- a/net/llc/llc_conn.c
+++ b/net/llc/llc_conn.c
@@ -909,6 +909,8 @@ static void llc_sk_init(struct sock *sk)
  *	@net: network namespace
  *	@family: upper layer protocol family
  *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
+ *	@prot: struct proto associated with this new sock instance
+ *	@kern: is this to be a kernel socket?
  *
  *	Allocates a LLC sock and initializes it. Returns the new LLC sock
  *	or %NULL if there's no memory available for one
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index cd9a9bd242ba..51ec8256b7fa 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -69,7 +69,7 @@ config MAC80211_MESH
 config MAC80211_LEDS
 	bool "Enable LED triggers"
 	depends on MAC80211
-	depends on LEDS_CLASS
+	depends on LEDS_CLASS=y || LEDS_CLASS=MAC80211
 	select LEDS_TRIGGERS
 	help
 	  This option enables a few LED triggers for different
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index 6cbb1286d6c0..ad04c361cba5 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -13,6 +13,7 @@ mac80211-y := \
 	ht.o agg-tx.o agg-rx.o \
 	vht.o \
 	he.o \
+	s1g.o \
 	ibss.o \
 	iface.o \
 	rate.o \
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 313ba97acae3..cce28e3b2232 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -250,10 +250,10 @@ static void ieee80211_send_addba_resp(struct sta_info *sta, u8 *da, u16 tid,
 	mgmt->u.action.u.addba_resp.action_code = WLAN_ACTION_ADDBA_RESP;
 	mgmt->u.action.u.addba_resp.dialog_token = dialog_token;
 
-	capab = (u16)(amsdu << 0);	/* bit 0 A-MSDU support */
-	capab |= (u16)(policy << 1);	/* bit 1 aggregation policy */
-	capab |= (u16)(tid << 2); 	/* bit 5:2 TID number */
-	capab |= (u16)(buf_size << 6);	/* bit 15:6 max size of aggregation */
+	capab = u16_encode_bits(amsdu, IEEE80211_ADDBA_PARAM_AMSDU_MASK);
+	capab |= u16_encode_bits(policy, IEEE80211_ADDBA_PARAM_POLICY_MASK);
+	capab |= u16_encode_bits(tid, IEEE80211_ADDBA_PARAM_TID_MASK);
+	capab |= u16_encode_bits(buf_size, IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK);
 
 	mgmt->u.action.u.addba_resp.capab = cpu_to_le16(capab);
 	mgmt->u.action.u.addba_resp.timeout = cpu_to_le16(timeout);
@@ -350,7 +350,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta,
 					   sta->sta.addr, tid);
 			/* We have no API to update the timeout value in the
 			 * driver so reject the timeout update if the timeout
-			 * changed. If if did not change, i.e., no real update,
+			 * changed. If it did not change, i.e., no real update,
 			 * just reply with success.
 			 */
 			rcu_read_lock();
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index b37c8a983d88..430a58587538 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -95,10 +95,10 @@ static void ieee80211_send_addba_request(struct ieee80211_sub_if_data *sdata,
 	mgmt->u.action.u.addba_req.action_code = WLAN_ACTION_ADDBA_REQ;
 
 	mgmt->u.action.u.addba_req.dialog_token = dialog_token;
-	capab = (u16)(1 << 0);		/* bit 0 A-MSDU support */
-	capab |= (u16)(1 << 1);		/* bit 1 aggregation policy */
-	capab |= (u16)(tid << 2); 	/* bit 5:2 TID number */
-	capab |= (u16)(agg_size << 6);	/* bit 15:6 max size of aggergation */
+	capab = IEEE80211_ADDBA_PARAM_AMSDU_MASK;
+	capab |= IEEE80211_ADDBA_PARAM_POLICY_MASK;
+	capab |= u16_encode_bits(tid, IEEE80211_ADDBA_PARAM_TID_MASK);
+	capab |= u16_encode_bits(agg_size, IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK);
 
 	mgmt->u.action.u.addba_req.capab = cpu_to_le16(capab);
 
@@ -950,8 +950,8 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
 
 	capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab);
 	amsdu = capab & IEEE80211_ADDBA_PARAM_AMSDU_MASK;
-	tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2;
-	buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6;
+	tid = u16_get_bits(capab, IEEE80211_ADDBA_PARAM_TID_MASK);
+	buf_size = u16_get_bits(capab, IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK);
 	buf_size = min(buf_size, local->hw.max_tx_aggregation_subframes);
 
 	txq = sta->sta.txq[tid];
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 87fddd84c621..c4c70e30ad7f 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -405,6 +405,7 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev,
 	case WLAN_CIPHER_SUITE_WEP104:
 		if (WARN_ON_ONCE(fips_enabled))
 			return -EINVAL;
+		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_AES_CMAC:
@@ -709,7 +710,8 @@ void sta_set_rate_info_tx(struct sta_info *sta,
 		u16 brate;
 
 		sband = ieee80211_get_sband(sta->sdata);
-		if (sband) {
+		WARN_ON_ONCE(sband && !sband->bitrates);
+		if (sband && sband->bitrates) {
 			brate = sband->bitrates[rate->idx].bitrate;
 			rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
 		}
@@ -826,9 +828,9 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata,
 	memcpy(new->data, resp, resp_len);
 
 	if (csa)
-		memcpy(new->csa_counter_offsets, csa->counter_offsets_presp,
+		memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_presp,
 		       csa->n_counter_offsets_presp *
-		       sizeof(new->csa_counter_offsets[0]));
+		       sizeof(new->cntdwn_counter_offsets[0]));
 
 	rcu_assign_pointer(sdata->u.ap.probe_resp, new);
 	if (old)
@@ -837,6 +839,59 @@ static int ieee80211_set_probe_resp(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
+static int ieee80211_set_fils_discovery(struct ieee80211_sub_if_data *sdata,
+					struct cfg80211_fils_discovery *params)
+{
+	struct fils_discovery_data *new, *old = NULL;
+	struct ieee80211_fils_discovery *fd;
+
+	if (!params->tmpl || !params->tmpl_len)
+		return -EINVAL;
+
+	fd = &sdata->vif.bss_conf.fils_discovery;
+	fd->min_interval = params->min_interval;
+	fd->max_interval = params->max_interval;
+
+	old = sdata_dereference(sdata->u.ap.fils_discovery, sdata);
+	new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+	new->len = params->tmpl_len;
+	memcpy(new->data, params->tmpl, params->tmpl_len);
+	rcu_assign_pointer(sdata->u.ap.fils_discovery, new);
+
+	if (old)
+		kfree_rcu(old, rcu_head);
+
+	return 0;
+}
+
+static int
+ieee80211_set_unsol_bcast_probe_resp(struct ieee80211_sub_if_data *sdata,
+				     struct cfg80211_unsol_bcast_probe_resp *params)
+{
+	struct unsol_bcast_probe_resp_data *new, *old = NULL;
+
+	if (!params->tmpl || !params->tmpl_len)
+		return -EINVAL;
+
+	old = sdata_dereference(sdata->u.ap.unsol_bcast_probe_resp, sdata);
+	new = kzalloc(sizeof(*new) + params->tmpl_len, GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+	new->len = params->tmpl_len;
+	memcpy(new->data, params->tmpl, params->tmpl_len);
+	rcu_assign_pointer(sdata->u.ap.unsol_bcast_probe_resp, new);
+
+	if (old)
+		kfree_rcu(old, rcu_head);
+
+	sdata->vif.bss_conf.unsol_bcast_probe_resp_interval =
+							params->interval;
+
+	return 0;
+}
+
 static int ieee80211_set_ftm_responder_params(
 				struct ieee80211_sub_if_data *sdata,
 				const u8 *lci, size_t lci_len,
@@ -926,10 +981,10 @@ static int ieee80211_assign_beacon(struct ieee80211_sub_if_data *sdata,
 	new->tail_len = new_tail_len;
 
 	if (csa) {
-		new->csa_current_counter = csa->count;
-		memcpy(new->csa_counter_offsets, csa->counter_offsets_beacon,
+		new->cntdwn_current_counter = csa->count;
+		memcpy(new->cntdwn_counter_offsets, csa->counter_offsets_beacon,
 		       csa->n_counter_offsets_beacon *
-		       sizeof(new->csa_counter_offsets[0]));
+		       sizeof(new->cntdwn_counter_offsets[0]));
 	}
 
 	/* copy in head */
@@ -1067,10 +1122,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 	sdata->vif.bss_conf.enable_beacon = true;
 	sdata->vif.bss_conf.allow_p2p_go_ps = sdata->vif.p2p;
 	sdata->vif.bss_conf.twt_responder = params->twt_responder;
-	memcpy(&sdata->vif.bss_conf.he_obss_pd, &params->he_obss_pd,
-	       sizeof(struct ieee80211_he_obss_pd));
-	memcpy(&sdata->vif.bss_conf.he_bss_color, &params->he_bss_color,
-	       sizeof(struct ieee80211_he_bss_color));
+	sdata->vif.bss_conf.he_obss_pd = params->he_obss_pd;
+	sdata->vif.bss_conf.he_bss_color = params->he_bss_color;
+	sdata->vif.bss_conf.s1g = params->chandef.chan->band ==
+				  NL80211_BAND_S1GHZ;
 
 	sdata->vif.bss_conf.ssid_len = params->ssid_len;
 	if (params->ssid_len)
@@ -1098,13 +1153,30 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		}
 	}
 
+	if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL))
+		sdata->vif.bss_conf.beacon_tx_rate = params->beacon_rate;
+
 	err = ieee80211_assign_beacon(sdata, &params->beacon, NULL);
-	if (err < 0) {
-		ieee80211_vif_release_channel(sdata);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 	changed |= err;
 
+	if (params->fils_discovery.max_interval) {
+		err = ieee80211_set_fils_discovery(sdata,
+						   &params->fils_discovery);
+		if (err < 0)
+			goto error;
+		changed |= BSS_CHANGED_FILS_DISCOVERY;
+	}
+
+	if (params->unsol_bcast_probe_resp.interval) {
+		err = ieee80211_set_unsol_bcast_probe_resp(sdata,
+							   &params->unsol_bcast_probe_resp);
+		if (err < 0)
+			goto error;
+		changed |= BSS_CHANGED_UNSOL_BCAST_PROBE_RESP;
+	}
+
 	err = drv_start_ap(sdata->local, sdata);
 	if (err) {
 		old = sdata_dereference(sdata->u.ap.beacon, sdata);
@@ -1112,8 +1184,7 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		if (old)
 			kfree_rcu(old, rcu_head);
 		RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
-		ieee80211_vif_release_channel(sdata);
-		return err;
+		goto error;
 	}
 
 	ieee80211_recalc_dtim(local, sdata);
@@ -1124,6 +1195,10 @@ static int ieee80211_start_ap(struct wiphy *wiphy, struct net_device *dev,
 		netif_carrier_on(vlan->dev);
 
 	return 0;
+
+error:
+	ieee80211_vif_release_channel(sdata);
+	return err;
 }
 
 static int ieee80211_change_beacon(struct wiphy *wiphy, struct net_device *dev,
@@ -1160,6 +1235,8 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	struct ieee80211_local *local = sdata->local;
 	struct beacon_data *old_beacon;
 	struct probe_resp *old_probe_resp;
+	struct fils_discovery_data *old_fils_discovery;
+	struct unsol_bcast_probe_resp_data *old_unsol_bcast_probe_resp;
 	struct cfg80211_chan_def chandef;
 
 	sdata_assert_lock(sdata);
@@ -1168,6 +1245,11 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	if (!old_beacon)
 		return -ENOENT;
 	old_probe_resp = sdata_dereference(sdata->u.ap.probe_resp, sdata);
+	old_fils_discovery = sdata_dereference(sdata->u.ap.fils_discovery,
+					       sdata);
+	old_unsol_bcast_probe_resp =
+		sdata_dereference(sdata->u.ap.unsol_bcast_probe_resp,
+				  sdata);
 
 	/* abort any running channel switch */
 	mutex_lock(&local->mtx);
@@ -1191,9 +1273,15 @@ static int ieee80211_stop_ap(struct wiphy *wiphy, struct net_device *dev)
 	/* remove beacon and probe response */
 	RCU_INIT_POINTER(sdata->u.ap.beacon, NULL);
 	RCU_INIT_POINTER(sdata->u.ap.probe_resp, NULL);
+	RCU_INIT_POINTER(sdata->u.ap.fils_discovery, NULL);
+	RCU_INIT_POINTER(sdata->u.ap.unsol_bcast_probe_resp, NULL);
 	kfree_rcu(old_beacon, rcu_head);
 	if (old_probe_resp)
 		kfree_rcu(old_probe_resp, rcu_head);
+	if (old_fils_discovery)
+		kfree_rcu(old_fils_discovery, rcu_head);
+	if (old_unsol_bcast_probe_resp)
+		kfree_rcu(old_unsol_bcast_probe_resp, rcu_head);
 
 	kfree(sdata->vif.bss_conf.ftmr_params);
 	sdata->vif.bss_conf.ftmr_params = NULL;
@@ -1696,6 +1784,7 @@ static int ieee80211_change_station(struct wiphy *wiphy,
 
 			rcu_assign_pointer(vlansdata->u.vlan.sta, sta);
 			__ieee80211_check_fast_rx_iface(vlansdata);
+			drv_sta_set_4addr(local, sta->sdata, &sta->sta, true);
 		}
 
 		if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN &&
@@ -2618,16 +2707,6 @@ static int ieee80211_get_tx_power(struct wiphy *wiphy,
 	return 0;
 }
 
-static int ieee80211_set_wds_peer(struct wiphy *wiphy, struct net_device *dev,
-				  const u8 *addr)
-{
-	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-
-	memcpy(&sdata->u.wds.remote_addr, addr, ETH_ALEN);
-
-	return 0;
-}
-
 static void ieee80211_rfkill_poll(struct wiphy *wiphy)
 {
 	struct ieee80211_local *local = wiphy_priv(wiphy);
@@ -3186,9 +3265,9 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
 			break;
 
 		if ((params->n_counter_offsets_beacon >
-		     IEEE80211_MAX_CSA_COUNTERS_NUM) ||
+		     IEEE80211_MAX_CNTDWN_COUNTERS_NUM) ||
 		    (params->n_counter_offsets_presp >
-		     IEEE80211_MAX_CSA_COUNTERS_NUM))
+		     IEEE80211_MAX_CNTDWN_COUNTERS_NUM))
 			return -EINVAL;
 
 		csa.counter_offsets_beacon = params->counter_offsets_beacon;
@@ -3217,6 +3296,7 @@ static int ieee80211_set_csa_beacon(struct ieee80211_sub_if_data *sdata,
 			if (cfg80211_get_chandef_type(&params->chandef) !=
 			    cfg80211_get_chandef_type(&sdata->u.ibss.chandef))
 				return -EINVAL;
+			break;
 		case NL80211_CHAN_WIDTH_5:
 		case NL80211_CHAN_WIDTH_10:
 		case NL80211_CHAN_WIDTH_20_NOHT:
@@ -3368,7 +3448,7 @@ __ieee80211_channel_switch(struct wiphy *wiphy, struct net_device *dev,
 					  IEEE80211_QUEUE_STOP_REASON_CSA);
 
 	cfg80211_ch_switch_started_notify(sdata->dev, &sdata->csa_chandef,
-					  params->count);
+					  params->count, params->block_tx);
 
 	if (changed) {
 		ieee80211_bss_info_change_notify(sdata, changed);
@@ -3993,6 +4073,17 @@ static int ieee80211_reset_tid_config(struct wiphy *wiphy,
 	return ret;
 }
 
+static int ieee80211_set_sar_specs(struct wiphy *wiphy,
+				   struct cfg80211_sar_specs *sar)
+{
+	struct ieee80211_local *local = wiphy_priv(wiphy);
+
+	if (!local->ops->set_sar_specs)
+		return -EOPNOTSUPP;
+
+	return local->ops->set_sar_specs(&local->hw, sar);
+}
+
 const struct cfg80211_ops mac80211_config_ops = {
 	.add_virtual_intf = ieee80211_add_iface,
 	.del_virtual_intf = ieee80211_del_iface,
@@ -4048,7 +4139,6 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.set_wiphy_params = ieee80211_set_wiphy_params,
 	.set_tx_power = ieee80211_set_tx_power,
 	.get_tx_power = ieee80211_get_tx_power,
-	.set_wds_peer = ieee80211_set_wds_peer,
 	.rfkill_poll = ieee80211_rfkill_poll,
 	CFG80211_TESTMODE_CMD(ieee80211_testmode_cmd)
 	CFG80211_TESTMODE_DUMP(ieee80211_testmode_dump)
@@ -4096,4 +4186,5 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.probe_mesh_link = ieee80211_probe_mesh_link,
 	.set_tid_config = ieee80211_set_tid_config,
 	.reset_tid_config = ieee80211_reset_tid_config,
+	.set_sar_specs = ieee80211_set_sar_specs,
 };
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index bdc0f29dc6cd..907bb1f748a1 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -9,6 +9,7 @@
 #include <net/cfg80211.h>
 #include "ieee80211_i.h"
 #include "driver-ops.h"
+#include "rate.h"
 
 static int ieee80211_chanctx_num_assigned(struct ieee80211_local *local,
 					  struct ieee80211_chanctx *ctx)
@@ -191,11 +192,13 @@ ieee80211_find_reservation_chanctx(struct ieee80211_local *local,
 	return NULL;
 }
 
-enum nl80211_chan_width ieee80211_get_sta_bw(struct ieee80211_sta *sta)
+static enum nl80211_chan_width ieee80211_get_sta_bw(struct sta_info *sta)
 {
-	switch (sta->bandwidth) {
+	enum ieee80211_sta_rx_bandwidth width = ieee80211_sta_cap_rx_bw(sta);
+
+	switch (width) {
 	case IEEE80211_STA_RX_BW_20:
-		if (sta->ht_cap.ht_supported)
+		if (sta->sta.ht_cap.ht_supported)
 			return NL80211_CHAN_WIDTH_20;
 		else
 			return NL80211_CHAN_WIDTH_20_NOHT;
@@ -232,7 +235,7 @@ ieee80211_get_max_required_bw(struct ieee80211_sub_if_data *sdata)
 		    !(sta->sdata->bss && sta->sdata->bss == sdata->bss))
 			continue;
 
-		max_bw = max(max_bw, ieee80211_get_sta_bw(&sta->sta));
+		max_bw = max(max_bw, ieee80211_get_sta_bw(sta));
 	}
 	rcu_read_unlock();
 
@@ -275,11 +278,11 @@ ieee80211_get_chanctx_max_required_bw(struct ieee80211_local *local,
 		case NL80211_IFTYPE_NAN:
 			continue;
 		case NL80211_IFTYPE_ADHOC:
-		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_MESH_POINT:
 		case NL80211_IFTYPE_OCB:
 			width = vif->bss_conf.chandef.width;
 			break;
+		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_UNSPECIFIED:
 		case NUM_NL80211_IFTYPES:
 		case NL80211_IFTYPE_MONITOR:
@@ -343,10 +346,42 @@ void ieee80211_recalc_chanctx_min_def(struct ieee80211_local *local,
 	drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_MIN_WIDTH);
 }
 
+static void ieee80211_chan_bw_change(struct ieee80211_local *local,
+				     struct ieee80211_chanctx *ctx)
+{
+	struct sta_info *sta;
+	struct ieee80211_supported_band *sband =
+		local->hw.wiphy->bands[ctx->conf.def.chan->band];
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(sta, &local->sta_list,
+				list) {
+		enum ieee80211_sta_rx_bandwidth new_sta_bw;
+
+		if (!ieee80211_sdata_running(sta->sdata))
+			continue;
+
+		if (rcu_access_pointer(sta->sdata->vif.chanctx_conf) !=
+		    &ctx->conf)
+			continue;
+
+		new_sta_bw = ieee80211_sta_cur_vht_bw(sta);
+		if (new_sta_bw == sta->sta.bandwidth)
+			continue;
+
+		sta->sta.bandwidth = new_sta_bw;
+		rate_control_rate_update(local, sband, sta,
+					 IEEE80211_RC_BW_CHANGED);
+	}
+	rcu_read_unlock();
+}
+
 static void ieee80211_change_chanctx(struct ieee80211_local *local,
 				     struct ieee80211_chanctx *ctx,
 				     const struct cfg80211_chan_def *chandef)
 {
+	enum nl80211_chan_width width;
+
 	if (cfg80211_chandef_identical(&ctx->conf.def, chandef)) {
 		ieee80211_recalc_chanctx_min_def(local, ctx);
 		return;
@@ -354,7 +389,25 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local,
 
 	WARN_ON(!cfg80211_chandef_compatible(&ctx->conf.def, chandef));
 
+	width = ctx->conf.def.width;
 	ctx->conf.def = *chandef;
+
+	/* expected to handle only 20/40/80/160 channel widths */
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_20_NOHT:
+	case NL80211_CHAN_WIDTH_20:
+	case NL80211_CHAN_WIDTH_40:
+	case NL80211_CHAN_WIDTH_80:
+	case NL80211_CHAN_WIDTH_80P80:
+	case NL80211_CHAN_WIDTH_160:
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	if (chandef->width < width)
+		ieee80211_chan_bw_change(local, ctx);
+
 	drv_change_chanctx(local, ctx, IEEE80211_CHANCTX_CHANGE_WIDTH);
 	ieee80211_recalc_chanctx_min_def(local, ctx);
 
@@ -362,6 +415,9 @@ static void ieee80211_change_chanctx(struct ieee80211_local *local,
 		local->_oper_chandef = *chandef;
 		ieee80211_hw_config(local, 0);
 	}
+
+	if (chandef->width > width)
+		ieee80211_chan_bw_change(local, ctx);
 }
 
 static struct ieee80211_chanctx *
@@ -536,7 +592,14 @@ static void ieee80211_del_chanctx(struct ieee80211_local *local,
 
 	if (!local->use_chanctx) {
 		struct cfg80211_chan_def *chandef = &local->_oper_chandef;
-		chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
+		/* S1G doesn't have 20MHz, so get the correct width for the
+		 * current channel.
+		 */
+		if (chandef->chan->band == NL80211_BAND_S1GHZ)
+			chandef->width =
+				ieee80211_s1g_channel_width(chandef->chan);
+		else
+			chandef->width = NL80211_CHAN_WIDTH_20_NOHT;
 		chandef->center_freq1 = chandef->chan->center_freq;
 		chandef->freq1_offset = chandef->chan->freq_offset;
 		chandef->center_freq2 = 0;
@@ -736,7 +799,6 @@ void ieee80211_recalc_smps_chanctx(struct ieee80211_local *local,
 			continue;
 		case NL80211_IFTYPE_AP:
 		case NL80211_IFTYPE_ADHOC:
-		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_MESH_POINT:
 		case NL80211_IFTYPE_OCB:
 			break;
@@ -1045,8 +1107,14 @@ ieee80211_vif_use_reserved_reassign(struct ieee80211_sub_if_data *sdata)
 	if (WARN_ON(!chandef))
 		return -EINVAL;
 
+	if (old_ctx->conf.def.width > new_ctx->conf.def.width)
+		ieee80211_chan_bw_change(local, new_ctx);
+
 	ieee80211_change_chanctx(local, new_ctx, chandef);
 
+	if (old_ctx->conf.def.width < new_ctx->conf.def.width)
+		ieee80211_chan_bw_change(local, new_ctx);
+
 	vif_chsw[0].vif = &sdata->vif;
 	vif_chsw[0].old_ctx = &old_ctx->conf;
 	vif_chsw[0].new_ctx = &new_ctx->conf;
@@ -1437,6 +1505,7 @@ static int ieee80211_vif_use_reserved_switch(struct ieee80211_local *local)
 		ieee80211_recalc_smps_chanctx(local, ctx);
 		ieee80211_recalc_radar_chanctx(local, ctx);
 		ieee80211_recalc_chanctx_min_def(local, ctx);
+		ieee80211_chan_bw_change(local, ctx);
 
 		list_for_each_entry_safe(sdata, sdata_tmp, &ctx->reserved_vifs,
 					 reserved_chanctx_list) {
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index 54080290d6e2..9e723d943421 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -53,7 +53,7 @@ static const struct file_operations name## _ops = {			\
 	DEBUGFS_READONLY_FILE_OPS(name)
 
 #define DEBUGFS_ADD(name)						\
-	debugfs_create_file(#name, 0400, phyd, local, &name## _ops);
+	debugfs_create_file(#name, 0400, phyd, local, &name## _ops)
 
 #define DEBUGFS_ADD_MODE(name, mode)					\
 	debugfs_create_file(#name, mode, phyd, local, &name## _ops);
@@ -120,18 +120,17 @@ static ssize_t aqm_write(struct file *file,
 {
 	struct ieee80211_local *local = file->private_data;
 	char buf[100];
-	size_t len;
 
-	if (count > sizeof(buf))
+	if (count >= sizeof(buf))
 		return -EINVAL;
 
 	if (copy_from_user(buf, user_buf, count))
 		return -EFAULT;
 
-	buf[sizeof(buf) - 1] = '\0';
-	len = strlen(buf);
-	if (len > 0 && buf[len-1] == '\n')
-		buf[len-1] = 0;
+	if (count && buf[count - 1] == '\n')
+		buf[count - 1] = '\0';
+	else
+		buf[count] = '\0';
 
 	if (sscanf(buf, "fq_limit %u", &local->fq.limit) == 1)
 		return count;
@@ -177,18 +176,17 @@ static ssize_t airtime_flags_write(struct file *file,
 {
 	struct ieee80211_local *local = file->private_data;
 	char buf[16];
-	size_t len;
 
-	if (count > sizeof(buf))
+	if (count >= sizeof(buf))
 		return -EINVAL;
 
 	if (copy_from_user(buf, user_buf, count))
 		return -EFAULT;
 
-	buf[sizeof(buf) - 1] = 0;
-	len = strlen(buf);
-	if (len > 0 && buf[len - 1] == '\n')
-		buf[len - 1] = 0;
+	if (count && buf[count - 1] == '\n')
+		buf[count - 1] = '\0';
+	else
+		buf[count] = '\0';
 
 	if (kstrtou16(buf, 0, &local->airtime_flags))
 		return -EINVAL;
@@ -237,20 +235,19 @@ static ssize_t aql_txq_limit_write(struct file *file,
 {
 	struct ieee80211_local *local = file->private_data;
 	char buf[100];
-	size_t len;
 	u32 ac, q_limit_low, q_limit_high, q_limit_low_old, q_limit_high_old;
 	struct sta_info *sta;
 
-	if (count > sizeof(buf))
+	if (count >= sizeof(buf))
 		return -EINVAL;
 
 	if (copy_from_user(buf, user_buf, count))
 		return -EFAULT;
 
-	buf[sizeof(buf) - 1] = 0;
-	len = strlen(buf);
-	if (len > 0 && buf[len - 1] == '\n')
-		buf[len - 1] = 0;
+	if (count && buf[count - 1] == '\n')
+		buf[count - 1] = '\0';
+	else
+		buf[count] = '\0';
 
 	if (sscanf(buf, "%u %u %u", &ac, &q_limit_low, &q_limit_high) != 3)
 		return -EINVAL;
@@ -306,18 +303,17 @@ static ssize_t force_tx_status_write(struct file *file,
 {
 	struct ieee80211_local *local = file->private_data;
 	char buf[3];
-	size_t len;
 
-	if (count > sizeof(buf))
+	if (count >= sizeof(buf))
 		return -EINVAL;
 
 	if (copy_from_user(buf, user_buf, count))
 		return -EFAULT;
 
-	buf[sizeof(buf) - 1] = '\0';
-	len = strlen(buf);
-	if (len > 0 && buf[len - 1] == '\n')
-		buf[len - 1] = 0;
+	if (count && buf[count - 1] == '\n')
+		buf[count - 1] = '\0';
+	else
+		buf[count] = '\0';
 
 	if (buf[0] == '0' && buf[1] == '\0')
 		local->force_tx_status = 0;
@@ -408,6 +404,7 @@ static const char *hw_flag_names[] = {
 	FLAG(SUPPORTS_MULTI_BSSID),
 	FLAG(SUPPORTS_ONLY_HE_MULTI_BSSID),
 	FLAG(AMPDU_KEYBORDER_SUPPORT),
+	FLAG(SUPPORTS_TX_ENCAP_OFFLOAD),
 #undef FLAG
 };
 
diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c
index 98a713475e0f..f53dec8a3d5c 100644
--- a/net/mac80211/debugfs_key.c
+++ b/net/mac80211/debugfs_key.c
@@ -319,7 +319,7 @@ KEY_OPS(key);
 
 #define DEBUGFS_ADD(name) \
 	debugfs_create_file(#name, 0400, key->debugfs.dir, \
-			    key, &key_##name##_ops);
+			    key, &key_##name##_ops)
 #define DEBUGFS_ADD_W(name) \
 	debugfs_create_file(#name, 0600, key->debugfs.dir, \
 			    key, &key_##name##_ops);
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index fe8a7a87e513..0ad3860852ff 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -574,9 +574,6 @@ static ssize_t ieee80211_if_parse_tsf(
 IEEE80211_IF_FILE_RW(tsf);
 
 
-/* WDS attributes */
-IEEE80211_IF_FILE(peer, u.wds.remote_addr, MAC);
-
 #ifdef CONFIG_MAC80211_MESH
 IEEE80211_IF_FILE(estab_plinks, u.mesh.estab_plinks, ATOMIC);
 
@@ -645,7 +642,7 @@ IEEE80211_IF_FILE(dot11MeshConnectedToAuthServer,
 
 #define DEBUGFS_ADD_MODE(name, mode) \
 	debugfs_create_file(#name, mode, sdata->vif.debugfs_dir, \
-			    sdata, &name##_ops);
+			    sdata, &name##_ops)
 
 #define DEBUGFS_ADD(name) DEBUGFS_ADD_MODE(name, 0400)
 
@@ -701,11 +698,6 @@ static void add_ibss_files(struct ieee80211_sub_if_data *sdata)
 	DEBUGFS_ADD_MODE(tsf, 0600);
 }
 
-static void add_wds_files(struct ieee80211_sub_if_data *sdata)
-{
-	DEBUGFS_ADD(peer);
-}
-
 #ifdef CONFIG_MAC80211_MESH
 
 static void add_mesh_files(struct ieee80211_sub_if_data *sdata)
@@ -719,7 +711,7 @@ static void add_mesh_stats(struct ieee80211_sub_if_data *sdata)
 	struct dentry *dir = debugfs_create_dir("mesh_stats",
 						sdata->vif.debugfs_dir);
 #define MESHSTATS_ADD(name)\
-	debugfs_create_file(#name, 0400, dir, sdata, &name##_ops);
+	debugfs_create_file(#name, 0400, dir, sdata, &name##_ops)
 
 	MESHSTATS_ADD(fwded_mcast);
 	MESHSTATS_ADD(fwded_unicast);
@@ -736,7 +728,7 @@ static void add_mesh_config(struct ieee80211_sub_if_data *sdata)
 						sdata->vif.debugfs_dir);
 
 #define MESHPARAMS_ADD(name) \
-	debugfs_create_file(#name, 0600, dir, sdata, &name##_ops);
+	debugfs_create_file(#name, 0600, dir, sdata, &name##_ops)
 
 	MESHPARAMS_ADD(dot11MeshMaxRetries);
 	MESHPARAMS_ADD(dot11MeshRetryTimeout);
@@ -805,9 +797,6 @@ static void add_files(struct ieee80211_sub_if_data *sdata)
 	case NL80211_IFTYPE_AP_VLAN:
 		add_vlan_files(sdata);
 		break;
-	case NL80211_IFTYPE_WDS:
-		add_wds_files(sdata);
-		break;
 	default:
 		break;
 	}
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index 829dcad69c2c..eb4bb79d936a 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -274,7 +274,7 @@ static ssize_t sta_aql_read(struct file *file, char __user *userbuf,
 		"Q limit[low/high]: VO: %u/%u VI: %u/%u BE: %u/%u BK: %u/%u\n",
 		q_depth[0], q_depth[1], q_depth[2], q_depth[3],
 		q_limit_l[0], q_limit_h[0], q_limit_l[1], q_limit_h[1],
-		q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]),
+		q_limit_l[2], q_limit_h[2], q_limit_l[3], q_limit_h[3]);
 
 	rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf);
 	kfree(buf);
@@ -985,7 +985,7 @@ STA_OPS(he_capa);
 
 #define DEBUGFS_ADD(name) \
 	debugfs_create_file(#name, 0400, \
-		sta->debugfs_dir, sta, &sta_ ##name## _ops);
+		sta->debugfs_dir, sta, &sta_ ##name## _ops)
 
 #define DEBUGFS_ADD_COUNTER(name, field)				\
 	debugfs_create_ulong(#name, 0400, sta->debugfs_dir, &sta->field);
diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index c9a8a2433e8a..48322e45e7dd 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -125,8 +125,11 @@ int drv_sta_state(struct ieee80211_local *local,
 	} else if (old_state == IEEE80211_STA_AUTH &&
 		   new_state == IEEE80211_STA_ASSOC) {
 		ret = drv_sta_add(local, sdata, &sta->sta);
-		if (ret == 0)
+		if (ret == 0) {
 			sta->uploaded = true;
+			if (rcu_access_pointer(sta->sta.rates))
+				drv_sta_rate_tbl_update(local, sdata, &sta->sta);
+		}
 	} else if (old_state == IEEE80211_STA_ASSOC &&
 		   new_state == IEEE80211_STA_AUTH) {
 		drv_sta_remove(local, sdata, &sta->sta);
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 41d495d73d3a..bcdfd19a596b 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -1384,4 +1384,33 @@ static inline int drv_reset_tid_config(struct ieee80211_local *local,
 
 	return ret;
 }
+
+static inline void drv_update_vif_offload(struct ieee80211_local *local,
+					  struct ieee80211_sub_if_data *sdata)
+{
+	might_sleep();
+	check_sdata_in_driver(sdata);
+
+	if (!local->ops->update_vif_offload)
+		return;
+
+	trace_drv_update_vif_offload(local, sdata);
+	local->ops->update_vif_offload(&local->hw, &sdata->vif);
+	trace_drv_return_void(local);
+}
+
+static inline void drv_sta_set_4addr(struct ieee80211_local *local,
+				     struct ieee80211_sub_if_data *sdata,
+				     struct ieee80211_sta *sta, bool enabled)
+{
+	sdata = get_bss_sdata(sdata);
+	if (!check_sdata_in_driver(sdata))
+		return;
+
+	trace_drv_sta_set_4addr(local, sdata, sta, enabled);
+	if (local->ops->sta_set_4addr)
+		local->ops->sta_set_4addr(&local->hw, &sdata->vif, sta, enabled);
+	trace_drv_return_void(local);
+}
+
 #endif /* __MAC80211_DRIVER_OPS */
diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c
index 53632c2f5217..1f552f374e97 100644
--- a/net/mac80211/ibss.c
+++ b/net/mac80211/ibss.c
@@ -145,9 +145,9 @@ ieee80211_ibss_build_presp(struct ieee80211_sub_if_data *sdata,
 		*pos++ = csa_settings->block_tx ? 1 : 0;
 		*pos++ = ieee80211_frequency_to_channel(
 				csa_settings->chandef.chan->center_freq);
-		presp->csa_counter_offsets[0] = (pos - presp->head);
+		presp->cntdwn_counter_offsets[0] = (pos - presp->head);
 		*pos++ = csa_settings->count;
-		presp->csa_current_counter = csa_settings->count;
+		presp->cntdwn_current_counter = csa_settings->count;
 	}
 
 	/* put the remaining rates in WLAN_EID_EXT_SUPP_RATES */
@@ -1037,7 +1037,8 @@ static void ieee80211_update_sta_info(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (sta && !sta->sta.wme &&
-	    elems->wmm_info && local->hw.queues >= IEEE80211_NUM_ACS) {
+	    (elems->wmm_info || elems->s1g_capab) &&
+	    local->hw.queues >= IEEE80211_NUM_ACS) {
 		sta->sta.wme = true;
 		ieee80211_check_fast_xmit(sta);
 	}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 0b1eaec6649f..8e281c2e644d 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -259,15 +259,27 @@ struct beacon_data {
 	u8 *head, *tail;
 	int head_len, tail_len;
 	struct ieee80211_meshconf_ie *meshconf;
-	u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM];
-	u8 csa_current_counter;
+	u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM];
+	u8 cntdwn_current_counter;
 	struct rcu_head rcu_head;
 };
 
 struct probe_resp {
 	struct rcu_head rcu_head;
 	int len;
-	u16 csa_counter_offsets[IEEE80211_MAX_CSA_COUNTERS_NUM];
+	u16 cntdwn_counter_offsets[IEEE80211_MAX_CNTDWN_COUNTERS_NUM];
+	u8 data[];
+};
+
+struct fils_discovery_data {
+	struct rcu_head rcu_head;
+	int len;
+	u8 data[];
+};
+
+struct unsol_bcast_probe_resp_data {
+	struct rcu_head rcu_head;
+	int len;
 	u8 data[];
 };
 
@@ -286,6 +298,8 @@ struct ps_data {
 struct ieee80211_if_ap {
 	struct beacon_data __rcu *beacon;
 	struct probe_resp __rcu *probe_resp;
+	struct fils_discovery_data __rcu *fils_discovery;
+	struct unsol_bcast_probe_resp_data __rcu *unsol_bcast_probe_resp;
 
 	/* to be used after channel switch. */
 	struct cfg80211_beacon_data *next_beacon;
@@ -297,11 +311,6 @@ struct ieee80211_if_ap {
 	bool multicast_to_unicast;
 };
 
-struct ieee80211_if_wds {
-	struct sta_info *sta;
-	u8 remote_addr[ETH_ALEN];
-};
-
 struct ieee80211_if_vlan {
 	struct list_head list; /* write-protected with RTNL and local->mtx */
 
@@ -443,7 +452,9 @@ struct ieee80211_if_managed {
 	unsigned long probe_timeout;
 	int probe_send_count;
 	bool nullfunc_failed;
-	bool connection_loss;
+	u8 connection_loss:1,
+	   driver_disconnect:1,
+	   reconnect:1;
 
 	struct cfg80211_bss *associated;
 	struct ieee80211_mgd_auth_data *auth_data;
@@ -530,6 +541,8 @@ struct ieee80211_if_managed {
 	struct ieee80211_ht_cap ht_capa_mask; /* Valid parts of ht_capa */
 	struct ieee80211_vht_cap vht_capa; /* configured VHT overrides */
 	struct ieee80211_vht_cap vht_capa_mask; /* Valid parts of vht_capa */
+	struct ieee80211_s1g_cap s1g_capa; /* configured S1G overrides */
+	struct ieee80211_s1g_cap s1g_capa_mask; /* valid s1g_capa bits */
 
 	/* TDLS support */
 	u8 tdls_peer[ETH_ALEN] __aligned(2);
@@ -969,7 +982,6 @@ struct ieee80211_sub_if_data {
 
 	union {
 		struct ieee80211_if_ap ap;
-		struct ieee80211_if_wds wds;
 		struct ieee80211_if_vlan vlan;
 		struct ieee80211_if_managed mgd;
 		struct ieee80211_if_ibss ibss;
@@ -989,8 +1001,6 @@ struct ieee80211_sub_if_data {
 	} debugfs;
 #endif
 
-	bool hw_80211_encap;
-
 	/* must be last, dynamically sized area in this! */
 	struct ieee80211_vif vif;
 };
@@ -1068,6 +1078,7 @@ enum queue_stop_reason {
 	IEEE80211_QUEUE_STOP_REASON_FLUSH,
 	IEEE80211_QUEUE_STOP_REASON_TDLS_TEARDOWN,
 	IEEE80211_QUEUE_STOP_REASON_RESERVE_TID,
+	IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE,
 
 	IEEE80211_QUEUE_STOP_REASONS,
 };
@@ -1364,7 +1375,6 @@ struct ieee80211_local {
 				*/
 
 	bool pspolling;
-	bool offchannel_ps_enabled;
 	/*
 	 * PS can only be enabled when we have exactly one managed
 	 * interface (and monitors) in PS, this then points there.
@@ -1522,6 +1532,10 @@ struct ieee802_11_elems {
 	u8 dtim_count;
 	u8 dtim_period;
 	const struct ieee80211_addba_ext_ie *addba_ext_ie;
+	const struct ieee80211_s1g_cap *s1g_capab;
+	const struct ieee80211_s1g_oper_ie *s1g_oper;
+	const struct ieee80211_s1g_bcn_compat_ie *s1g_bcn_compat;
+	const struct ieee80211_aid_response_ie *aid_resp;
 
 	/* length of them, respectively */
 	u8 ext_capab_len;
@@ -1576,13 +1590,8 @@ ieee80211_have_rx_timestamp(struct ieee80211_rx_status *status)
 {
 	WARN_ON_ONCE(status->flag & RX_FLAG_MACTIME_START &&
 		     status->flag & RX_FLAG_MACTIME_END);
-	if (status->flag & (RX_FLAG_MACTIME_START | RX_FLAG_MACTIME_END))
-		return true;
-	/* can't handle non-legacy preamble yet */
-	if (status->flag & RX_FLAG_MACTIME_PLCP_START &&
-	    status->encoding == RX_ENC_LEGACY)
-		return true;
-	return false;
+	return !!(status->flag & (RX_FLAG_MACTIME_START | RX_FLAG_MACTIME_END |
+				  RX_FLAG_MACTIME_PLCP_START));
 }
 
 void ieee80211_vif_inc_num_mcast(struct ieee80211_sub_if_data *sdata);
@@ -1640,6 +1649,8 @@ int ieee80211_set_arp_filter(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				  struct sk_buff *skb);
+void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata,
+				 struct sk_buff *skb);
 void ieee80211_sta_reset_beacon_monitor(struct ieee80211_sub_if_data *sdata);
 void ieee80211_sta_reset_conn_monitor(struct ieee80211_sub_if_data *sdata);
 void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata);
@@ -1767,6 +1778,7 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local);
 bool __ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata);
 void ieee80211_recalc_txpower(struct ieee80211_sub_if_data *sdata,
 			      bool update_bss);
+void ieee80211_recalc_offload(struct ieee80211_local *local);
 
 static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata)
 {
@@ -1775,7 +1787,7 @@ static inline bool ieee80211_sdata_running(struct ieee80211_sub_if_data *sdata)
 
 /* tx handling */
 void ieee80211_clear_tx_pending(struct ieee80211_local *local);
-void ieee80211_tx_pending(unsigned long data);
+void ieee80211_tx_pending(struct tasklet_struct *t);
 netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 					 struct net_device *dev);
 netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
@@ -1908,6 +1920,9 @@ void
 ieee80211_he_op_ie_to_bss_conf(struct ieee80211_vif *vif,
 			const struct ieee80211_he_operation *he_op_ie_elem);
 
+/* S1G */
+void ieee80211_s1g_sta_rate_init(struct sta_info *sta);
+
 /* Spectrum management */
 void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata,
 				       struct ieee80211_mgmt *mgmt,
@@ -2040,8 +2055,6 @@ void ieee80211_dynamic_ps_timer(struct timer_list *t);
 void ieee80211_send_nullfunc(struct ieee80211_local *local,
 			     struct ieee80211_sub_if_data *sdata,
 			     bool powersave);
-void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata,
-			     struct ieee80211_hdr *hdr);
 void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
 			     struct ieee80211_hdr *hdr, bool ack, u16 tx_time);
 
@@ -2125,7 +2138,7 @@ void ieee80211_txq_remove_vlan(struct ieee80211_local *local,
 			       struct ieee80211_sub_if_data *sdata);
 void ieee80211_fill_txq_stats(struct cfg80211_txq_stats *txqstats,
 			      struct txq_info *txqi);
-void ieee80211_wake_txqs(unsigned long data);
+void ieee80211_wake_txqs(struct tasklet_struct *t);
 void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 			 u16 transaction, u16 auth_alg, u16 status,
 			 const u8 *extra, size_t extra_len, const u8 *bssid,
@@ -2193,6 +2206,11 @@ int ieee80211_add_ext_srates_ie(struct ieee80211_sub_if_data *sdata,
 				struct sk_buff *skb, bool need_basic,
 				enum nl80211_band band);
 u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo);
+void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata,
+				struct ieee80211_sta_s1g_cap *caps,
+				struct sk_buff *skb);
+void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata,
+				  struct sk_buff *skb);
 
 /* channel management */
 bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper,
@@ -2204,6 +2222,8 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, u32 vht_cap_info,
 bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
 				    const struct ieee80211_he_operation *he_oper,
 				    struct cfg80211_chan_def *chandef);
+bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper,
+				struct cfg80211_chan_def *chandef);
 u32 ieee80211_chandef_downgrade(struct cfg80211_chan_def *c);
 
 int __must_check
@@ -2258,7 +2278,6 @@ int ieee80211_check_combinations(struct ieee80211_sub_if_data *sdata,
 				 enum ieee80211_chanctx_mode chanmode,
 				 u8 radar_detect);
 int ieee80211_max_num_channels(struct ieee80211_local *local);
-enum nl80211_chan_width ieee80211_get_sta_bw(struct ieee80211_sta *sta);
 void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local,
 				       struct ieee80211_chanctx *ctx);
 
@@ -2282,6 +2301,9 @@ void ieee80211_tdls_chsw_work(struct work_struct *wk);
 void ieee80211_tdls_handle_disconnect(struct ieee80211_sub_if_data *sdata,
 				      const u8 *peer, u16 reason);
 const char *ieee80211_get_reason_code_string(u16 reason_code);
+u16 ieee80211_encode_usf(int val);
+u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
+			enum nl80211_iftype type);
 
 extern const struct ethtool_ops ieee80211_ethtool_ops;
 
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 9740ae8fa697..b31417f40bd5 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -230,10 +230,6 @@ static inline int identical_mac_addr_allowed(int type1, int type2)
 		type2 == NL80211_IFTYPE_MONITOR ||
 		type1 == NL80211_IFTYPE_P2P_DEVICE ||
 		type2 == NL80211_IFTYPE_P2P_DEVICE ||
-		(type1 == NL80211_IFTYPE_AP && type2 == NL80211_IFTYPE_WDS) ||
-		(type1 == NL80211_IFTYPE_WDS &&
-			(type2 == NL80211_IFTYPE_WDS ||
-			 type2 == NL80211_IFTYPE_AP)) ||
 		(type1 == NL80211_IFTYPE_AP && type2 == NL80211_IFTYPE_AP_VLAN) ||
 		(type1 == NL80211_IFTYPE_AP_VLAN &&
 			(type2 == NL80211_IFTYPE_AP ||
@@ -348,439 +344,6 @@ static int ieee80211_check_queues(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
-void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata,
-				    const int offset)
-{
-	struct ieee80211_local *local = sdata->local;
-	u32 flags = sdata->u.mntr.flags;
-
-#define ADJUST(_f, _s)	do {					\
-	if (flags & MONITOR_FLAG_##_f)				\
-		local->fif_##_s += offset;			\
-	} while (0)
-
-	ADJUST(FCSFAIL, fcsfail);
-	ADJUST(PLCPFAIL, plcpfail);
-	ADJUST(CONTROL, control);
-	ADJUST(CONTROL, pspoll);
-	ADJUST(OTHER_BSS, other_bss);
-
-#undef ADJUST
-}
-
-static void ieee80211_set_default_queues(struct ieee80211_sub_if_data *sdata)
-{
-	struct ieee80211_local *local = sdata->local;
-	int i;
-
-	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
-		if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL))
-			sdata->vif.hw_queue[i] = IEEE80211_INVAL_HW_QUEUE;
-		else if (local->hw.queues >= IEEE80211_NUM_ACS)
-			sdata->vif.hw_queue[i] = i;
-		else
-			sdata->vif.hw_queue[i] = 0;
-	}
-	sdata->vif.cab_queue = IEEE80211_INVAL_HW_QUEUE;
-}
-
-int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
-{
-	struct ieee80211_sub_if_data *sdata;
-	int ret;
-
-	if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
-		return 0;
-
-	ASSERT_RTNL();
-
-	if (local->monitor_sdata)
-		return 0;
-
-	sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL);
-	if (!sdata)
-		return -ENOMEM;
-
-	/* set up data */
-	sdata->local = local;
-	sdata->vif.type = NL80211_IFTYPE_MONITOR;
-	snprintf(sdata->name, IFNAMSIZ, "%s-monitor",
-		 wiphy_name(local->hw.wiphy));
-	sdata->wdev.iftype = NL80211_IFTYPE_MONITOR;
-
-	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
-
-	ieee80211_set_default_queues(sdata);
-
-	ret = drv_add_interface(local, sdata);
-	if (WARN_ON(ret)) {
-		/* ok .. stupid driver, it asked for this! */
-		kfree(sdata);
-		return ret;
-	}
-
-	ret = ieee80211_check_queues(sdata, NL80211_IFTYPE_MONITOR);
-	if (ret) {
-		kfree(sdata);
-		return ret;
-	}
-
-	mutex_lock(&local->iflist_mtx);
-	rcu_assign_pointer(local->monitor_sdata, sdata);
-	mutex_unlock(&local->iflist_mtx);
-
-	mutex_lock(&local->mtx);
-	ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef,
-					IEEE80211_CHANCTX_EXCLUSIVE);
-	mutex_unlock(&local->mtx);
-	if (ret) {
-		mutex_lock(&local->iflist_mtx);
-		RCU_INIT_POINTER(local->monitor_sdata, NULL);
-		mutex_unlock(&local->iflist_mtx);
-		synchronize_net();
-		drv_remove_interface(local, sdata);
-		kfree(sdata);
-		return ret;
-	}
-
-	skb_queue_head_init(&sdata->skb_queue);
-	INIT_WORK(&sdata->work, ieee80211_iface_work);
-
-	return 0;
-}
-
-void ieee80211_del_virtual_monitor(struct ieee80211_local *local)
-{
-	struct ieee80211_sub_if_data *sdata;
-
-	if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
-		return;
-
-	ASSERT_RTNL();
-
-	mutex_lock(&local->iflist_mtx);
-
-	sdata = rcu_dereference_protected(local->monitor_sdata,
-					  lockdep_is_held(&local->iflist_mtx));
-	if (!sdata) {
-		mutex_unlock(&local->iflist_mtx);
-		return;
-	}
-
-	RCU_INIT_POINTER(local->monitor_sdata, NULL);
-	mutex_unlock(&local->iflist_mtx);
-
-	synchronize_net();
-
-	mutex_lock(&local->mtx);
-	ieee80211_vif_release_channel(sdata);
-	mutex_unlock(&local->mtx);
-
-	drv_remove_interface(local, sdata);
-
-	kfree(sdata);
-}
-
-/*
- * NOTE: Be very careful when changing this function, it must NOT return
- * an error on interface type changes that have been pre-checked, so most
- * checks should be in ieee80211_check_concurrent_iface.
- */
-int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
-{
-	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
-	struct net_device *dev = wdev->netdev;
-	struct ieee80211_local *local = sdata->local;
-	struct sta_info *sta;
-	u32 changed = 0;
-	int res;
-	u32 hw_reconf_flags = 0;
-
-	switch (sdata->vif.type) {
-	case NL80211_IFTYPE_WDS:
-		if (!is_valid_ether_addr(sdata->u.wds.remote_addr))
-			return -ENOLINK;
-		break;
-	case NL80211_IFTYPE_AP_VLAN: {
-		struct ieee80211_sub_if_data *master;
-
-		if (!sdata->bss)
-			return -ENOLINK;
-
-		mutex_lock(&local->mtx);
-		list_add(&sdata->u.vlan.list, &sdata->bss->vlans);
-		mutex_unlock(&local->mtx);
-
-		master = container_of(sdata->bss,
-				      struct ieee80211_sub_if_data, u.ap);
-		sdata->control_port_protocol =
-			master->control_port_protocol;
-		sdata->control_port_no_encrypt =
-			master->control_port_no_encrypt;
-		sdata->control_port_over_nl80211 =
-			master->control_port_over_nl80211;
-		sdata->control_port_no_preauth =
-			master->control_port_no_preauth;
-		sdata->vif.cab_queue = master->vif.cab_queue;
-		memcpy(sdata->vif.hw_queue, master->vif.hw_queue,
-		       sizeof(sdata->vif.hw_queue));
-		sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef;
-
-		mutex_lock(&local->key_mtx);
-		sdata->crypto_tx_tailroom_needed_cnt +=
-			master->crypto_tx_tailroom_needed_cnt;
-		mutex_unlock(&local->key_mtx);
-
-		break;
-		}
-	case NL80211_IFTYPE_AP:
-		sdata->bss = &sdata->u.ap;
-		break;
-	case NL80211_IFTYPE_MESH_POINT:
-	case NL80211_IFTYPE_STATION:
-	case NL80211_IFTYPE_MONITOR:
-	case NL80211_IFTYPE_ADHOC:
-	case NL80211_IFTYPE_P2P_DEVICE:
-	case NL80211_IFTYPE_OCB:
-	case NL80211_IFTYPE_NAN:
-		/* no special treatment */
-		break;
-	case NL80211_IFTYPE_UNSPECIFIED:
-	case NUM_NL80211_IFTYPES:
-	case NL80211_IFTYPE_P2P_CLIENT:
-	case NL80211_IFTYPE_P2P_GO:
-		/* cannot happen */
-		WARN_ON(1);
-		break;
-	}
-
-	if (local->open_count == 0) {
-		res = drv_start(local);
-		if (res)
-			goto err_del_bss;
-		/* we're brought up, everything changes */
-		hw_reconf_flags = ~0;
-		ieee80211_led_radio(local, true);
-		ieee80211_mod_tpt_led_trig(local,
-					   IEEE80211_TPT_LEDTRIG_FL_RADIO, 0);
-	}
-
-	/*
-	 * Copy the hopefully now-present MAC address to
-	 * this interface, if it has the special null one.
-	 */
-	if (dev && is_zero_ether_addr(dev->dev_addr)) {
-		memcpy(dev->dev_addr,
-		       local->hw.wiphy->perm_addr,
-		       ETH_ALEN);
-		memcpy(dev->perm_addr, dev->dev_addr, ETH_ALEN);
-
-		if (!is_valid_ether_addr(dev->dev_addr)) {
-			res = -EADDRNOTAVAIL;
-			goto err_stop;
-		}
-	}
-
-	switch (sdata->vif.type) {
-	case NL80211_IFTYPE_AP_VLAN:
-		/* no need to tell driver, but set carrier and chanctx */
-		if (rtnl_dereference(sdata->bss->beacon)) {
-			ieee80211_vif_vlan_copy_chanctx(sdata);
-			netif_carrier_on(dev);
-		} else {
-			netif_carrier_off(dev);
-		}
-		break;
-	case NL80211_IFTYPE_MONITOR:
-		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) {
-			local->cooked_mntrs++;
-			break;
-		}
-
-		if (sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) {
-			res = drv_add_interface(local, sdata);
-			if (res)
-				goto err_stop;
-		} else if (local->monitors == 0 && local->open_count == 0) {
-			res = ieee80211_add_virtual_monitor(local);
-			if (res)
-				goto err_stop;
-		}
-
-		/* must be before the call to ieee80211_configure_filter */
-		local->monitors++;
-		if (local->monitors == 1) {
-			local->hw.conf.flags |= IEEE80211_CONF_MONITOR;
-			hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR;
-		}
-
-		ieee80211_adjust_monitor_flags(sdata, 1);
-		ieee80211_configure_filter(local);
-		mutex_lock(&local->mtx);
-		ieee80211_recalc_idle(local);
-		mutex_unlock(&local->mtx);
-
-		netif_carrier_on(dev);
-		break;
-	default:
-		if (coming_up) {
-			ieee80211_del_virtual_monitor(local);
-
-			res = drv_add_interface(local, sdata);
-			if (res)
-				goto err_stop;
-			res = ieee80211_check_queues(sdata,
-				ieee80211_vif_type_p2p(&sdata->vif));
-			if (res)
-				goto err_del_interface;
-		}
-
-		if (sdata->vif.type == NL80211_IFTYPE_AP) {
-			local->fif_pspoll++;
-			local->fif_probe_req++;
-
-			ieee80211_configure_filter(local);
-		} else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) {
-			local->fif_probe_req++;
-		}
-
-		if (sdata->vif.probe_req_reg)
-			drv_config_iface_filter(local, sdata,
-						FIF_PROBE_REQ,
-						FIF_PROBE_REQ);
-
-		if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
-		    sdata->vif.type != NL80211_IFTYPE_NAN)
-			changed |= ieee80211_reset_erp_info(sdata);
-		ieee80211_bss_info_change_notify(sdata, changed);
-
-		switch (sdata->vif.type) {
-		case NL80211_IFTYPE_STATION:
-		case NL80211_IFTYPE_ADHOC:
-		case NL80211_IFTYPE_AP:
-		case NL80211_IFTYPE_MESH_POINT:
-		case NL80211_IFTYPE_OCB:
-			netif_carrier_off(dev);
-			break;
-		case NL80211_IFTYPE_WDS:
-		case NL80211_IFTYPE_P2P_DEVICE:
-		case NL80211_IFTYPE_NAN:
-			break;
-		default:
-			/* not reached */
-			WARN_ON(1);
-		}
-
-		/*
-		 * Set default queue parameters so drivers don't
-		 * need to initialise the hardware if the hardware
-		 * doesn't start up with sane defaults.
-		 * Enable QoS for anything but station interfaces.
-		 */
-		ieee80211_set_wmm_default(sdata, true,
-			sdata->vif.type != NL80211_IFTYPE_STATION);
-	}
-
-	set_bit(SDATA_STATE_RUNNING, &sdata->state);
-
-	switch (sdata->vif.type) {
-	case NL80211_IFTYPE_WDS:
-		/* Create STA entry for the WDS peer */
-		sta = sta_info_alloc(sdata, sdata->u.wds.remote_addr,
-				     GFP_KERNEL);
-		if (!sta) {
-			res = -ENOMEM;
-			goto err_del_interface;
-		}
-
-		sta_info_pre_move_state(sta, IEEE80211_STA_AUTH);
-		sta_info_pre_move_state(sta, IEEE80211_STA_ASSOC);
-		sta_info_pre_move_state(sta, IEEE80211_STA_AUTHORIZED);
-
-		res = sta_info_insert(sta);
-		if (res) {
-			/* STA has been freed */
-			goto err_del_interface;
-		}
-
-		rate_control_rate_init(sta);
-		netif_carrier_on(dev);
-		break;
-	case NL80211_IFTYPE_P2P_DEVICE:
-		rcu_assign_pointer(local->p2p_sdata, sdata);
-		break;
-	case NL80211_IFTYPE_MONITOR:
-		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES)
-			break;
-		list_add_tail_rcu(&sdata->u.mntr.list, &local->mon_list);
-		break;
-	default:
-		break;
-	}
-
-	/*
-	 * set_multicast_list will be invoked by the networking core
-	 * which will check whether any increments here were done in
-	 * error and sync them down to the hardware as filter flags.
-	 */
-	if (sdata->flags & IEEE80211_SDATA_ALLMULTI)
-		atomic_inc(&local->iff_allmultis);
-
-	if (coming_up)
-		local->open_count++;
-
-	if (hw_reconf_flags)
-		ieee80211_hw_config(local, hw_reconf_flags);
-
-	ieee80211_recalc_ps(local);
-
-	if (sdata->vif.type == NL80211_IFTYPE_MONITOR ||
-	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
-	    local->ops->wake_tx_queue) {
-		/* XXX: for AP_VLAN, actually track AP queues */
-		if (dev)
-			netif_tx_start_all_queues(dev);
-	} else if (dev) {
-		unsigned long flags;
-		int n_acs = IEEE80211_NUM_ACS;
-		int ac;
-
-		if (local->hw.queues < IEEE80211_NUM_ACS)
-			n_acs = 1;
-
-		spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
-		if (sdata->vif.cab_queue == IEEE80211_INVAL_HW_QUEUE ||
-		    (local->queue_stop_reasons[sdata->vif.cab_queue] == 0 &&
-		     skb_queue_empty(&local->pending[sdata->vif.cab_queue]))) {
-			for (ac = 0; ac < n_acs; ac++) {
-				int ac_queue = sdata->vif.hw_queue[ac];
-
-				if (local->queue_stop_reasons[ac_queue] == 0 &&
-				    skb_queue_empty(&local->pending[ac_queue]))
-					netif_start_subqueue(dev, ac);
-			}
-		}
-		spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
-	}
-
-	return 0;
- err_del_interface:
-	drv_remove_interface(local, sdata);
- err_stop:
-	if (!local->open_count)
-		drv_stop(local);
- err_del_bss:
-	sdata->bss = NULL;
-	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
-		mutex_lock(&local->mtx);
-		list_del(&sdata->u.vlan.list);
-		mutex_unlock(&local->mtx);
-	}
-	/* might already be clear but that doesn't matter */
-	clear_bit(SDATA_STATE_RUNNING, &sdata->state);
-	return res;
-}
-
 static int ieee80211_open(struct net_device *dev)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
@@ -850,15 +413,12 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 	 * (because if we remove a STA after ops->remove_interface()
 	 * the driver will have removed the vif info already!)
 	 *
-	 * In WDS mode a station must exist here and be flushed, for
-	 * AP_VLANs stations may exist since there's nothing else that
+	 * For AP_VLANs stations may exist since there's nothing else that
 	 * would have removed them, but in other modes there shouldn't
 	 * be any stations.
 	 */
 	flushed = sta_info_flush(sdata);
-	WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN &&
-		     ((sdata->vif.type != NL80211_IFTYPE_WDS && flushed > 0) ||
-		      (sdata->vif.type == NL80211_IFTYPE_WDS && flushed != 1)));
+	WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_AP_VLAN && flushed > 0);
 
 	/* don't count this interface for allmulti while it is down */
 	if (sdata->flags & IEEE80211_SDATA_ALLMULTI)
@@ -985,8 +545,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata,
 		 * When we get here, the interface is marked down.
 		 * Free the remaining keys, if there are any
 		 * (which can happen in AP mode if userspace sets
-		 * keys before the interface is operating, and maybe
-		 * also in WDS mode)
+		 * keys before the interface is operating)
 		 *
 		 * Force the key freeing to always synchronize_net()
 		 * to wait for the RX path in case it is using this
@@ -1142,28 +701,7 @@ static u16 ieee80211_netdev_select_queue(struct net_device *dev,
 static void
 ieee80211_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
-	int i;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_sw_netstats *tstats;
-		u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
-		unsigned int start;
-
-		tstats = per_cpu_ptr(dev->tstats, i);
-
-		do {
-			start = u64_stats_fetch_begin_irq(&tstats->syncp);
-			rx_packets = tstats->rx_packets;
-			tx_packets = tstats->tx_packets;
-			rx_bytes = tstats->rx_bytes;
-			tx_bytes = tstats->tx_bytes;
-		} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
-
-		stats->rx_packets += rx_packets;
-		stats->tx_packets += tx_packets;
-		stats->rx_bytes   += rx_bytes;
-		stats->tx_bytes   += tx_bytes;
-	}
+	dev_fetch_sw_netstats(stats, dev->tstats);
 }
 
 static const struct net_device_ops ieee80211_dataif_ops = {
@@ -1227,60 +765,522 @@ static const struct net_device_ops ieee80211_dataif_8023_ops = {
 	.ndo_get_stats64	= ieee80211_get_stats64,
 };
 
-static void __ieee80211_set_hw_80211_encap(struct ieee80211_sub_if_data *sdata,
-					   bool enable)
+static bool ieee80211_iftype_supports_encap_offload(enum nl80211_iftype iftype)
 {
-	sdata->dev->netdev_ops = enable ? &ieee80211_dataif_8023_ops :
-					  &ieee80211_dataif_ops;
-	sdata->hw_80211_encap = enable;
+	switch (iftype) {
+	/* P2P GO and client are mapped to AP/STATION types */
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_STATION:
+		return true;
+	default:
+		return false;
+	}
 }
 
-bool ieee80211_set_hw_80211_encap(struct ieee80211_vif *vif, bool enable)
+static bool ieee80211_set_sdata_offload_flags(struct ieee80211_sub_if_data *sdata)
 {
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_sub_if_data *iter;
-	struct ieee80211_key *key;
+	u32 flags;
+
+	flags = sdata->vif.offload_flags;
+
+	if (ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) &&
+	    ieee80211_iftype_supports_encap_offload(sdata->vif.type)) {
+		flags |= IEEE80211_OFFLOAD_ENCAP_ENABLED;
+
+		if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) &&
+		    local->hw.wiphy->frag_threshold != (u32)-1)
+			flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
+
+		if (local->monitors)
+			flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
+	} else {
+		flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
+	}
+
+	if (sdata->vif.offload_flags == flags)
+		return false;
+
+	sdata->vif.offload_flags = flags;
+	return true;
+}
+
+static void ieee80211_set_vif_encap_ops(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_sub_if_data *bss = sdata;
+	bool enabled;
+
+	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+		if (!sdata->bss)
+			return;
+
+		bss = container_of(sdata->bss, struct ieee80211_sub_if_data, u.ap);
+	}
+
+	if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD) ||
+	    !ieee80211_iftype_supports_encap_offload(bss->vif.type))
+		return;
+
+	enabled = bss->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_ENABLED;
+	if (sdata->wdev.use_4addr &&
+	    !(bss->vif.offload_flags & IEEE80211_OFFLOAD_ENCAP_4ADDR))
+		enabled = false;
+
+	sdata->dev->netdev_ops = enabled ? &ieee80211_dataif_8023_ops :
+					   &ieee80211_dataif_ops;
+}
+
+static void ieee80211_recalc_sdata_offload(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_sub_if_data *vsdata;
+
+	if (ieee80211_set_sdata_offload_flags(sdata)) {
+		drv_update_vif_offload(local, sdata);
+		ieee80211_set_vif_encap_ops(sdata);
+	}
+
+	list_for_each_entry(vsdata, &local->interfaces, list) {
+		if (vsdata->vif.type != NL80211_IFTYPE_AP_VLAN ||
+		    vsdata->bss != &sdata->u.ap)
+			continue;
+
+		ieee80211_set_vif_encap_ops(vsdata);
+	}
+}
+
+void ieee80211_recalc_offload(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_ENCAP_OFFLOAD))
+		return;
 
 	mutex_lock(&local->iflist_mtx);
-	list_for_each_entry(iter, &local->interfaces, list) {
-		struct ieee80211_sub_if_data *disable = NULL;
-
-		if (vif->type == NL80211_IFTYPE_MONITOR) {
-			disable = iter;
-			__ieee80211_set_hw_80211_encap(iter, false);
-		} else if (iter->vif.type == NL80211_IFTYPE_MONITOR) {
-			disable = sdata;
-			enable = false;
-		}
-		if (disable)
-			sdata_dbg(disable,
-				  "disable hw 80211 encap due to mon co-exist\n");
+
+	list_for_each_entry(sdata, &local->interfaces, list) {
+		if (!ieee80211_sdata_running(sdata))
+			continue;
+
+		ieee80211_recalc_sdata_offload(sdata);
 	}
+
 	mutex_unlock(&local->iflist_mtx);
+}
 
-	if (enable == sdata->hw_80211_encap)
-		return enable;
+void ieee80211_adjust_monitor_flags(struct ieee80211_sub_if_data *sdata,
+				    const int offset)
+{
+	struct ieee80211_local *local = sdata->local;
+	u32 flags = sdata->u.mntr.flags;
 
-	if (!sdata->dev)
-		return false;
+#define ADJUST(_f, _s)	do {					\
+	if (flags & MONITOR_FLAG_##_f)				\
+		local->fif_##_s += offset;			\
+	} while (0)
+
+	ADJUST(FCSFAIL, fcsfail);
+	ADJUST(PLCPFAIL, plcpfail);
+	ADJUST(CONTROL, control);
+	ADJUST(CONTROL, pspoll);
+	ADJUST(OTHER_BSS, other_bss);
+
+#undef ADJUST
+}
+
+static void ieee80211_set_default_queues(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	int i;
+
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		if (ieee80211_hw_check(&local->hw, QUEUE_CONTROL))
+			sdata->vif.hw_queue[i] = IEEE80211_INVAL_HW_QUEUE;
+		else if (local->hw.queues >= IEEE80211_NUM_ACS)
+			sdata->vif.hw_queue[i] = i;
+		else
+			sdata->vif.hw_queue[i] = 0;
+	}
+	sdata->vif.cab_queue = IEEE80211_INVAL_HW_QUEUE;
+}
+
+int ieee80211_add_virtual_monitor(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+	int ret;
+
+	if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
+		return 0;
+
+	ASSERT_RTNL();
+
+	if (local->monitor_sdata)
+		return 0;
+
+	sdata = kzalloc(sizeof(*sdata) + local->hw.vif_data_size, GFP_KERNEL);
+	if (!sdata)
+		return -ENOMEM;
+
+	/* set up data */
+	sdata->local = local;
+	sdata->vif.type = NL80211_IFTYPE_MONITOR;
+	snprintf(sdata->name, IFNAMSIZ, "%s-monitor",
+		 wiphy_name(local->hw.wiphy));
+	sdata->wdev.iftype = NL80211_IFTYPE_MONITOR;
+
+	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
+
+	ieee80211_set_default_queues(sdata);
+
+	ret = drv_add_interface(local, sdata);
+	if (WARN_ON(ret)) {
+		/* ok .. stupid driver, it asked for this! */
+		kfree(sdata);
+		return ret;
+	}
+
+	set_bit(SDATA_STATE_RUNNING, &sdata->state);
+
+	ret = ieee80211_check_queues(sdata, NL80211_IFTYPE_MONITOR);
+	if (ret) {
+		kfree(sdata);
+		return ret;
+	}
+
+	mutex_lock(&local->iflist_mtx);
+	rcu_assign_pointer(local->monitor_sdata, sdata);
+	mutex_unlock(&local->iflist_mtx);
+
+	mutex_lock(&local->mtx);
+	ret = ieee80211_vif_use_channel(sdata, &local->monitor_chandef,
+					IEEE80211_CHANCTX_EXCLUSIVE);
+	mutex_unlock(&local->mtx);
+	if (ret) {
+		mutex_lock(&local->iflist_mtx);
+		RCU_INIT_POINTER(local->monitor_sdata, NULL);
+		mutex_unlock(&local->iflist_mtx);
+		synchronize_net();
+		drv_remove_interface(local, sdata);
+		kfree(sdata);
+		return ret;
+	}
+
+	skb_queue_head_init(&sdata->skb_queue);
+	INIT_WORK(&sdata->work, ieee80211_iface_work);
+
+	return 0;
+}
+
+void ieee80211_del_virtual_monitor(struct ieee80211_local *local)
+{
+	struct ieee80211_sub_if_data *sdata;
+
+	if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
+		return;
+
+	ASSERT_RTNL();
+
+	mutex_lock(&local->iflist_mtx);
+
+	sdata = rcu_dereference_protected(local->monitor_sdata,
+					  lockdep_is_held(&local->iflist_mtx));
+	if (!sdata) {
+		mutex_unlock(&local->iflist_mtx);
+		return;
+	}
+
+	RCU_INIT_POINTER(local->monitor_sdata, NULL);
+	mutex_unlock(&local->iflist_mtx);
+
+	synchronize_net();
+
+	mutex_lock(&local->mtx);
+	ieee80211_vif_release_channel(sdata);
+	mutex_unlock(&local->mtx);
+
+	drv_remove_interface(local, sdata);
+
+	kfree(sdata);
+}
+
+/*
+ * NOTE: Be very careful when changing this function, it must NOT return
+ * an error on interface type changes that have been pre-checked, so most
+ * checks should be in ieee80211_check_concurrent_iface.
+ */
+int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
+	struct net_device *dev = wdev->netdev;
+	struct ieee80211_local *local = sdata->local;
+	u32 changed = 0;
+	int res;
+	u32 hw_reconf_flags = 0;
+
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_AP_VLAN: {
+		struct ieee80211_sub_if_data *master;
+
+		if (!sdata->bss)
+			return -ENOLINK;
+
+		mutex_lock(&local->mtx);
+		list_add(&sdata->u.vlan.list, &sdata->bss->vlans);
+		mutex_unlock(&local->mtx);
+
+		master = container_of(sdata->bss,
+				      struct ieee80211_sub_if_data, u.ap);
+		sdata->control_port_protocol =
+			master->control_port_protocol;
+		sdata->control_port_no_encrypt =
+			master->control_port_no_encrypt;
+		sdata->control_port_over_nl80211 =
+			master->control_port_over_nl80211;
+		sdata->control_port_no_preauth =
+			master->control_port_no_preauth;
+		sdata->vif.cab_queue = master->vif.cab_queue;
+		memcpy(sdata->vif.hw_queue, master->vif.hw_queue,
+		       sizeof(sdata->vif.hw_queue));
+		sdata->vif.bss_conf.chandef = master->vif.bss_conf.chandef;
+
+		mutex_lock(&local->key_mtx);
+		sdata->crypto_tx_tailroom_needed_cnt +=
+			master->crypto_tx_tailroom_needed_cnt;
+		mutex_unlock(&local->key_mtx);
+
+		break;
+		}
+	case NL80211_IFTYPE_AP:
+		sdata->bss = &sdata->u.ap;
+		break;
+	case NL80211_IFTYPE_MESH_POINT:
+	case NL80211_IFTYPE_STATION:
+	case NL80211_IFTYPE_MONITOR:
+	case NL80211_IFTYPE_ADHOC:
+	case NL80211_IFTYPE_P2P_DEVICE:
+	case NL80211_IFTYPE_OCB:
+	case NL80211_IFTYPE_NAN:
+		/* no special treatment */
+		break;
+	case NL80211_IFTYPE_UNSPECIFIED:
+	case NUM_NL80211_IFTYPES:
+	case NL80211_IFTYPE_P2P_CLIENT:
+	case NL80211_IFTYPE_P2P_GO:
+	case NL80211_IFTYPE_WDS:
+		/* cannot happen */
+		WARN_ON(1);
+		break;
+	}
+
+	if (local->open_count == 0) {
+		res = drv_start(local);
+		if (res)
+			goto err_del_bss;
+		/* we're brought up, everything changes */
+		hw_reconf_flags = ~0;
+		ieee80211_led_radio(local, true);
+		ieee80211_mod_tpt_led_trig(local,
+					   IEEE80211_TPT_LEDTRIG_FL_RADIO, 0);
+	}
 
-	if (!ieee80211_hw_check(&local->hw, SUPPORTS_TX_FRAG) &&
-	    (local->hw.wiphy->frag_threshold != (u32)-1))
-		enable = false;
+	/*
+	 * Copy the hopefully now-present MAC address to
+	 * this interface, if it has the special null one.
+	 */
+	if (dev && is_zero_ether_addr(dev->dev_addr)) {
+		memcpy(dev->dev_addr,
+		       local->hw.wiphy->perm_addr,
+		       ETH_ALEN);
+		memcpy(dev->perm_addr, dev->dev_addr, ETH_ALEN);
 
-	mutex_lock(&sdata->local->key_mtx);
-	list_for_each_entry(key, &sdata->key_list, list) {
-		if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP)
-			enable = false;
+		if (!is_valid_ether_addr(dev->dev_addr)) {
+			res = -EADDRNOTAVAIL;
+			goto err_stop;
+		}
 	}
-	mutex_unlock(&sdata->local->key_mtx);
 
-	__ieee80211_set_hw_80211_encap(sdata, enable);
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_AP_VLAN:
+		/* no need to tell driver, but set carrier and chanctx */
+		if (rtnl_dereference(sdata->bss->beacon)) {
+			ieee80211_vif_vlan_copy_chanctx(sdata);
+			netif_carrier_on(dev);
+			ieee80211_set_vif_encap_ops(sdata);
+		} else {
+			netif_carrier_off(dev);
+		}
+		break;
+	case NL80211_IFTYPE_MONITOR:
+		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) {
+			local->cooked_mntrs++;
+			break;
+		}
 
-	return enable;
+		if (sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) {
+			res = drv_add_interface(local, sdata);
+			if (res)
+				goto err_stop;
+		} else if (local->monitors == 0 && local->open_count == 0) {
+			res = ieee80211_add_virtual_monitor(local);
+			if (res)
+				goto err_stop;
+		}
+
+		/* must be before the call to ieee80211_configure_filter */
+		local->monitors++;
+		if (local->monitors == 1) {
+			local->hw.conf.flags |= IEEE80211_CONF_MONITOR;
+			hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR;
+		}
+
+		ieee80211_adjust_monitor_flags(sdata, 1);
+		ieee80211_configure_filter(local);
+		ieee80211_recalc_offload(local);
+		mutex_lock(&local->mtx);
+		ieee80211_recalc_idle(local);
+		mutex_unlock(&local->mtx);
+
+		netif_carrier_on(dev);
+		break;
+	default:
+		if (coming_up) {
+			ieee80211_del_virtual_monitor(local);
+			ieee80211_set_sdata_offload_flags(sdata);
+
+			res = drv_add_interface(local, sdata);
+			if (res)
+				goto err_stop;
+
+			ieee80211_set_vif_encap_ops(sdata);
+			res = ieee80211_check_queues(sdata,
+				ieee80211_vif_type_p2p(&sdata->vif));
+			if (res)
+				goto err_del_interface;
+		}
+
+		if (sdata->vif.type == NL80211_IFTYPE_AP) {
+			local->fif_pspoll++;
+			local->fif_probe_req++;
+
+			ieee80211_configure_filter(local);
+		} else if (sdata->vif.type == NL80211_IFTYPE_ADHOC) {
+			local->fif_probe_req++;
+		}
+
+		if (sdata->vif.probe_req_reg)
+			drv_config_iface_filter(local, sdata,
+						FIF_PROBE_REQ,
+						FIF_PROBE_REQ);
+
+		if (sdata->vif.type != NL80211_IFTYPE_P2P_DEVICE &&
+		    sdata->vif.type != NL80211_IFTYPE_NAN)
+			changed |= ieee80211_reset_erp_info(sdata);
+		ieee80211_bss_info_change_notify(sdata, changed);
+
+		switch (sdata->vif.type) {
+		case NL80211_IFTYPE_STATION:
+		case NL80211_IFTYPE_ADHOC:
+		case NL80211_IFTYPE_AP:
+		case NL80211_IFTYPE_MESH_POINT:
+		case NL80211_IFTYPE_OCB:
+			netif_carrier_off(dev);
+			break;
+		case NL80211_IFTYPE_P2P_DEVICE:
+		case NL80211_IFTYPE_NAN:
+			break;
+		default:
+			/* not reached */
+			WARN_ON(1);
+		}
+
+		/*
+		 * Set default queue parameters so drivers don't
+		 * need to initialise the hardware if the hardware
+		 * doesn't start up with sane defaults.
+		 * Enable QoS for anything but station interfaces.
+		 */
+		ieee80211_set_wmm_default(sdata, true,
+			sdata->vif.type != NL80211_IFTYPE_STATION);
+	}
+
+	set_bit(SDATA_STATE_RUNNING, &sdata->state);
+
+	switch (sdata->vif.type) {
+	case NL80211_IFTYPE_P2P_DEVICE:
+		rcu_assign_pointer(local->p2p_sdata, sdata);
+		break;
+	case NL80211_IFTYPE_MONITOR:
+		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES)
+			break;
+		list_add_tail_rcu(&sdata->u.mntr.list, &local->mon_list);
+		break;
+	default:
+		break;
+	}
+
+	/*
+	 * set_multicast_list will be invoked by the networking core
+	 * which will check whether any increments here were done in
+	 * error and sync them down to the hardware as filter flags.
+	 */
+	if (sdata->flags & IEEE80211_SDATA_ALLMULTI)
+		atomic_inc(&local->iff_allmultis);
+
+	if (coming_up)
+		local->open_count++;
+
+	if (hw_reconf_flags)
+		ieee80211_hw_config(local, hw_reconf_flags);
+
+	ieee80211_recalc_ps(local);
+
+	if (sdata->vif.type == NL80211_IFTYPE_MONITOR ||
+	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
+	    local->ops->wake_tx_queue) {
+		/* XXX: for AP_VLAN, actually track AP queues */
+		if (dev)
+			netif_tx_start_all_queues(dev);
+	} else if (dev) {
+		unsigned long flags;
+		int n_acs = IEEE80211_NUM_ACS;
+		int ac;
+
+		if (local->hw.queues < IEEE80211_NUM_ACS)
+			n_acs = 1;
+
+		spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
+		if (sdata->vif.cab_queue == IEEE80211_INVAL_HW_QUEUE ||
+		    (local->queue_stop_reasons[sdata->vif.cab_queue] == 0 &&
+		     skb_queue_empty(&local->pending[sdata->vif.cab_queue]))) {
+			for (ac = 0; ac < n_acs; ac++) {
+				int ac_queue = sdata->vif.hw_queue[ac];
+
+				if (local->queue_stop_reasons[ac_queue] == 0 &&
+				    skb_queue_empty(&local->pending[ac_queue]))
+					netif_start_subqueue(dev, ac);
+			}
+		}
+		spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
+	}
+
+	return 0;
+ err_del_interface:
+	drv_remove_interface(local, sdata);
+ err_stop:
+	if (!local->open_count)
+		drv_stop(local);
+ err_del_bss:
+	sdata->bss = NULL;
+	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
+		mutex_lock(&local->mtx);
+		list_del(&sdata->u.vlan.list);
+		mutex_unlock(&local->mtx);
+	}
+	/* might already be clear but that doesn't matter */
+	clear_bit(SDATA_STATE_RUNNING, &sdata->state);
+	return res;
 }
-EXPORT_SYMBOL(ieee80211_set_hw_80211_encap);
 
 static void ieee80211_if_free(struct net_device *dev)
 {
@@ -1323,6 +1323,7 @@ static void ieee80211_iface_work(struct work_struct *work)
 	while ((skb = skb_dequeue(&sdata->skb_queue))) {
 		struct ieee80211_mgmt *mgmt = (void *)skb->data;
 
+		kcov_remote_start_common(skb_get_kcov_handle(skb));
 		if (ieee80211_is_action(mgmt->frame_control) &&
 		    mgmt->u.action.category == WLAN_CATEGORY_BACK) {
 			int len = skb->len;
@@ -1379,6 +1380,11 @@ static void ieee80211_iface_work(struct work_struct *work)
 				WARN_ON(1);
 				break;
 			}
+		} else if (ieee80211_is_ext(mgmt->frame_control)) {
+			if (sdata->vif.type == NL80211_IFTYPE_STATION)
+				ieee80211_sta_rx_queued_ext(sdata, skb);
+			else
+				WARN_ON(1);
 		} else if (ieee80211_is_data_qos(mgmt->frame_control)) {
 			struct ieee80211_hdr *hdr = (void *)mgmt;
 			/*
@@ -1427,6 +1433,7 @@ static void ieee80211_iface_work(struct work_struct *work)
 		}
 
 		kfree_skb(skb);
+		kcov_remote_stop();
 	}
 
 	/* then other type-dependent work */
@@ -1484,7 +1491,6 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 	sdata->vif.bss_conf.txpower = INT_MIN; /* unset */
 
 	sdata->noack_map = 0;
-	sdata->hw_80211_encap = false;
 
 	/* only monitor/p2p-device differ */
 	if (sdata->dev) {
@@ -1537,9 +1543,6 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 		sdata->u.mntr.flags = MONITOR_FLAG_CONTROL |
 				      MONITOR_FLAG_OTHER_BSS;
 		break;
-	case NL80211_IFTYPE_WDS:
-		sdata->vif.bss_conf.bssid = NULL;
-		break;
 	case NL80211_IFTYPE_NAN:
 		idr_init(&sdata->u.nan.function_inst_ids);
 		spin_lock_init(&sdata->u.nan.func_lock);
@@ -1550,6 +1553,7 @@ static void ieee80211_setup_sdata(struct ieee80211_sub_if_data *sdata,
 		sdata->vif.bss_conf.bssid = sdata->vif.addr;
 		break;
 	case NL80211_IFTYPE_UNSPECIFIED:
+	case NL80211_IFTYPE_WDS:
 	case NUM_NL80211_IFTYPES:
 		WARN_ON(1);
 		break;
@@ -1594,9 +1598,7 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
 	case NL80211_IFTYPE_OCB:
 		/*
 		 * Could probably support everything
-		 * but WDS here (WDS do_open can fail
-		 * under memory pressure, which this
-		 * code isn't prepared to handle).
+		 * but here.
 		 */
 		break;
 	case NL80211_IFTYPE_P2P_CLIENT:
@@ -1615,10 +1617,15 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
 	if (ret)
 		return ret;
 
+	ieee80211_stop_vif_queues(local, sdata,
+				  IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE);
+	synchronize_net();
+
 	ieee80211_do_stop(sdata, false);
 
 	ieee80211_teardown_sdata(sdata);
 
+	ieee80211_set_sdata_offload_flags(sdata);
 	ret = drv_change_interface(local, sdata, internal_type, p2p);
 	if (ret)
 		type = ieee80211_vif_type_p2p(&sdata->vif);
@@ -1631,10 +1638,13 @@ static int ieee80211_runtime_change_iftype(struct ieee80211_sub_if_data *sdata,
 	ieee80211_check_queues(sdata, type);
 
 	ieee80211_setup_sdata(sdata, type);
+	ieee80211_set_vif_encap_ops(sdata);
 
 	err = ieee80211_do_open(&sdata->wdev, false);
 	WARN(err, "type change: do_open returned %d", err);
 
+	ieee80211_wake_vif_queues(local, sdata,
+				  IEEE80211_QUEUE_STOP_REASON_IFTYPE_CHANGE);
 	return ret;
 }
 
@@ -1687,7 +1697,6 @@ static void ieee80211_assign_perm_addr(struct ieee80211_local *local,
 	case NL80211_IFTYPE_MONITOR:
 		/* doesn't matter */
 		break;
-	case NL80211_IFTYPE_WDS:
 	case NL80211_IFTYPE_AP_VLAN:
 		/* match up with an AP interface */
 		list_for_each_entry(sdata, &local->interfaces, list) {
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index 2df636c32432..a4817aa4b171 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -177,13 +177,6 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 		}
 	}
 
-	/* TKIP countermeasures don't work in encap offload mode */
-	if (key->conf.cipher == WLAN_CIPHER_SUITE_TKIP &&
-	    sdata->hw_80211_encap) {
-		sdata_dbg(sdata, "TKIP is not allowed in hw 80211 encap mode\n");
-		return -EINVAL;
-	}
-
 	ret = drv_set_key(key->local, SET_KEY, sdata,
 			  sta ? &sta->sta : NULL, &key->conf);
 
@@ -219,14 +212,6 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key)
 	case WLAN_CIPHER_SUITE_CCMP_256:
 	case WLAN_CIPHER_SUITE_GCMP:
 	case WLAN_CIPHER_SUITE_GCMP_256:
-		/* We cannot do software crypto of data frames with
-		 * encapsulation offload enabled. However for 802.11w to
-		 * function properly we need cmac/gmac keys.
-		 */
-		if (sdata->hw_80211_encap)
-			return -EINVAL;
-		fallthrough;
-
 	case WLAN_CIPHER_SUITE_AES_CMAC:
 	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
 	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
@@ -1315,3 +1300,52 @@ ieee80211_gtk_rekey_add(struct ieee80211_vif *vif,
 	return &key->conf;
 }
 EXPORT_SYMBOL_GPL(ieee80211_gtk_rekey_add);
+
+void ieee80211_key_mic_failure(struct ieee80211_key_conf *keyconf)
+{
+	struct ieee80211_key *key;
+
+	key = container_of(keyconf, struct ieee80211_key, conf);
+
+	switch (key->conf.cipher) {
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		key->u.aes_cmac.icverrors++;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		key->u.aes_gmac.icverrors++;
+		break;
+	default:
+		/* ignore the others for now, we don't keep counters now */
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(ieee80211_key_mic_failure);
+
+void ieee80211_key_replay(struct ieee80211_key_conf *keyconf)
+{
+	struct ieee80211_key *key;
+
+	key = container_of(keyconf, struct ieee80211_key, conf);
+
+	switch (key->conf.cipher) {
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_CCMP_256:
+		key->u.ccmp.replays++;
+		break;
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		key->u.aes_cmac.replays++;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		key->u.aes_gmac.replays++;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		key->u.gcmp.replays++;
+		break;
+	}
+}
+EXPORT_SYMBOL_GPL(ieee80211_key_replay);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index b4a2efe8e83a..dee88ec566ad 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -220,9 +220,9 @@ u32 ieee80211_reset_erp_info(struct ieee80211_sub_if_data *sdata)
 	       BSS_CHANGED_ERP_SLOT;
 }
 
-static void ieee80211_tasklet_handler(unsigned long data)
+static void ieee80211_tasklet_handler(struct tasklet_struct *t)
 {
-	struct ieee80211_local *local = (struct ieee80211_local *) data;
+	struct ieee80211_local *local = from_tasklet(local, t, tasklet);
 	struct sk_buff *skb;
 
 	while ((skb = skb_dequeue(&local->skb_queue)) ||
@@ -733,16 +733,12 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
 		skb_queue_head_init(&local->pending[i]);
 		atomic_set(&local->agg_queue_stop[i], 0);
 	}
-	tasklet_init(&local->tx_pending_tasklet, ieee80211_tx_pending,
-		     (unsigned long)local);
+	tasklet_setup(&local->tx_pending_tasklet, ieee80211_tx_pending);
 
 	if (ops->wake_tx_queue)
-		tasklet_init(&local->wake_txqs_tasklet, ieee80211_wake_txqs,
-			     (unsigned long)local);
+		tasklet_setup(&local->wake_txqs_tasklet, ieee80211_wake_txqs);
 
-	tasklet_init(&local->tasklet,
-		     ieee80211_tasklet_handler,
-		     (unsigned long) local);
+	tasklet_setup(&local->tasklet, ieee80211_tasklet_handler);
 
 	skb_queue_head_init(&local->skb_queue);
 	skb_queue_head_init(&local->skb_queue_unreliable);
@@ -935,14 +931,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 				return -EINVAL;
 		}
 	} else {
-		/*
-		 * WDS is currently prohibited when channel contexts are used
-		 * because there's no clear definition of which channel WDS
-		 * type interfaces use
-		 */
-		if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS))
-			return -EINVAL;
-
 		/* DFS is not supported with multi-channel combinations yet */
 		for (i = 0; i < local->hw.wiphy->n_iface_combinations; i++) {
 			const struct ieee80211_iface_combination *comb;
@@ -1168,7 +1156,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 				WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT;
 	}
 
-	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM;
+	local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CNTDWN_COUNTERS_NUM;
 
 	/*
 	 * We use the number of queues for feature tests (QoS, HT) internally
diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c
index 7ecd801a943b..97095b7c9c64 100644
--- a/net/mac80211/mesh.c
+++ b/net/mac80211/mesh.c
@@ -667,12 +667,41 @@ void ieee80211_mesh_root_setup(struct ieee80211_if_mesh *ifmsh)
 	}
 }
 
+static void
+ieee80211_mesh_update_bss_params(struct ieee80211_sub_if_data *sdata,
+				 u8 *ie, u8 ie_len)
+{
+	struct ieee80211_supported_band *sband;
+	const u8 *cap;
+	const struct ieee80211_he_operation *he_oper = NULL;
+
+	sband = ieee80211_get_sband(sdata);
+	if (!sband)
+		return;
+
+	if (!ieee80211_get_he_iftype_cap(sband, NL80211_IFTYPE_MESH_POINT) ||
+	    sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_20_NOHT ||
+	    sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_5 ||
+	    sdata->vif.bss_conf.chandef.width == NL80211_CHAN_WIDTH_10)
+		return;
+
+	sdata->vif.bss_conf.he_support = true;
+
+	cap = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION, ie, ie_len);
+	if (cap && cap[1] >= ieee80211_he_oper_size(&cap[3]))
+		he_oper = (void *)(cap + 3);
+
+	if (he_oper)
+		sdata->vif.bss_conf.he_oper.params =
+			__le32_to_cpu(he_oper->he_oper_params);
+}
+
 /**
  * ieee80211_fill_mesh_addresses - fill addresses of a locally originated mesh frame
  * @hdr:	802.11 frame header
  * @fc:		frame control field
  * @meshda:	destination address in the mesh
- * @meshsa:	source address address in the mesh.  Same as TA, as frame is
+ * @meshsa:	source address in the mesh.  Same as TA, as frame is
  *              locally originated.
  *
  * Return the length of the 802.11 (does not include a mesh control header)
@@ -864,8 +893,8 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 		*pos++ = 0x0;
 		*pos++ = ieee80211_frequency_to_channel(
 				csa->settings.chandef.chan->center_freq);
-		bcn->csa_current_counter = csa->settings.count;
-		bcn->csa_counter_offsets[0] = hdr_len + 6;
+		bcn->cntdwn_current_counter = csa->settings.count;
+		bcn->cntdwn_counter_offsets[0] = hdr_len + 6;
 		*pos++ = csa->settings.count;
 		*pos++ = WLAN_EID_CHAN_SWITCH_PARAM;
 		*pos++ = 6;
@@ -943,6 +972,7 @@ ieee80211_mesh_build_beacon(struct ieee80211_if_mesh *ifmsh)
 
 	bcn->tail_len = skb->len;
 	memcpy(bcn->tail, skb->data, bcn->tail_len);
+	ieee80211_mesh_update_bss_params(sdata, bcn->tail, bcn->tail_len);
 	bcn->meshconf = (struct ieee80211_meshconf_ie *)
 					(bcn->tail + ifmsh->meshconf_offset);
 
diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index bec23d2eee7a..313eee12410e 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -212,7 +212,7 @@ static void prepare_frame_for_deferred_tx(struct ieee80211_sub_if_data *sdata,
 	skb->priority = 7;
 
 	info->control.vif = &sdata->vif;
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 	ieee80211_set_qos_hdr(sdata, skb);
 	ieee80211_mps_set_frame_flags(sdata, NULL, hdr);
 }
@@ -1163,7 +1163,7 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata,
 	if (skb_queue_len(&mpath->frame_queue) >= MESH_FRAME_QUEUE_LEN)
 		skb_to_free = skb_dequeue(&mpath->frame_queue);
 
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 	ieee80211_set_qos_hdr(sdata, skb);
 	skb_queue_tail(&mpath->frame_queue, skb);
 	if (skb_to_free)
diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c
index 48f31ac9233c..620ecf922408 100644
--- a/net/mac80211/mesh_pathtbl.c
+++ b/net/mac80211/mesh_pathtbl.c
@@ -60,6 +60,7 @@ static struct mesh_table *mesh_table_alloc(void)
 	atomic_set(&newtbl->entries,  0);
 	spin_lock_init(&newtbl->gates_lock);
 	spin_lock_init(&newtbl->walk_lock);
+	rhashtable_init(&newtbl->rhead, &mesh_rht_params);
 
 	return newtbl;
 }
@@ -773,9 +774,6 @@ int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata)
 		goto free_path;
 	}
 
-	rhashtable_init(&tbl_path->rhead, &mesh_rht_params);
-	rhashtable_init(&tbl_mpp->rhead, &mesh_rht_params);
-
 	sdata->u.mesh.mesh_paths = tbl_path;
 	sdata->u.mesh.mpp_paths = tbl_mpp;
 
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 15f2fc658f70..aca26df7587d 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -144,6 +144,7 @@ out:
 
 /**
  * mesh_set_ht_prot_mode - set correct HT protection mode
+ * @sdata: the (mesh) interface to handle
  *
  * Section 9.23.3.5 of IEEE 80211-2012 describes the protection rules for HT
  * mesh STA in a MBSS. Three HT protection modes are supported for now, non-HT
diff --git a/net/mac80211/mesh_ps.c b/net/mac80211/mesh_ps.c
index 031e905f684a..204830a55240 100644
--- a/net/mac80211/mesh_ps.c
+++ b/net/mac80211/mesh_ps.c
@@ -12,6 +12,7 @@
 
 /**
  * mps_qos_null_get - create pre-addressed QoS Null frame for mesh powersave
+ * @sta: the station to get the frame for
  */
 static struct sk_buff *mps_qos_null_get(struct sta_info *sta)
 {
@@ -44,6 +45,7 @@ static struct sk_buff *mps_qos_null_get(struct sta_info *sta)
 
 /**
  * mps_qos_null_tx - send a QoS Null to indicate link-specific power mode
+ * @sta: the station to send to
  */
 static void mps_qos_null_tx(struct sta_info *sta)
 {
@@ -400,6 +402,8 @@ static void mpsp_trigger_send(struct sta_info *sta, bool rspi, bool eosp)
 
 /**
  * mpsp_qos_null_append - append QoS Null frame to MPSP skb queue if needed
+ * @sta: the station to handle
+ * @frames: the frame list to append to
  *
  * To properly end a mesh MPSP the last transmitted frame has to set the EOSP
  * flag in the QoS Control field. In case the current tailing frame is not a
@@ -432,7 +436,7 @@ static void mpsp_qos_null_append(struct sta_info *sta,
 
 	info = IEEE80211_SKB_CB(new_skb);
 	info->control.vif = &sdata->vif;
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 
 	__skb_queue_tail(frames, new_skb);
 }
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 2e400b0ff696..0e4d950cf907 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -149,6 +149,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 			     const struct ieee80211_ht_operation *ht_oper,
 			     const struct ieee80211_vht_operation *vht_oper,
 			     const struct ieee80211_he_operation *he_oper,
+			     const struct ieee80211_s1g_oper_ie *s1g_oper,
 			     struct cfg80211_chan_def *chandef, bool tracking)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -171,6 +172,18 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 			ret = 0;
 		vht_chandef = *chandef;
 		goto out;
+	} else if (sband->band == NL80211_BAND_S1GHZ) {
+		if (!ieee80211_chandef_s1g_oper(s1g_oper, chandef)) {
+			sdata_info(sdata,
+				   "Missing S1G Operation Element? Trying operating == primary\n");
+			chandef->width = ieee80211_s1g_channel_width(channel);
+		}
+
+		ret = IEEE80211_STA_DISABLE_HT | IEEE80211_STA_DISABLE_40MHZ |
+		      IEEE80211_STA_DISABLE_VHT |
+		      IEEE80211_STA_DISABLE_80P80MHZ |
+		      IEEE80211_STA_DISABLE_160MHZ;
+		goto out;
 	}
 
 	memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap));
@@ -347,6 +360,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 			       const struct ieee80211_ht_operation *ht_oper,
 			       const struct ieee80211_vht_operation *vht_oper,
 			       const struct ieee80211_he_operation *he_oper,
+			       const struct ieee80211_s1g_oper_ie *s1g_oper,
 			       const u8 *bssid, u32 *changed)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -393,7 +407,7 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 	/* calculate new channel (type) based on HT/VHT/HE operation IEs */
 	flags = ieee80211_determine_chantype(sdata, sband, chan, vht_cap_info,
 					     ht_oper, vht_oper, he_oper,
-					     &chandef, true);
+					     s1g_oper, &chandef, true);
 
 	/*
 	 * Downgrade the new channel if we associated with restricted
@@ -696,6 +710,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	struct ieee80211_chanctx_conf *chanctx_conf;
 	struct ieee80211_channel *chan;
 	u32 rates = 0;
+	__le16 listen_int;
 	struct element *ext_capa = NULL;
 
 	/* we know it's writable, cast away the const */
@@ -784,13 +799,15 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
 	memcpy(mgmt->bssid, assoc_data->bss->bssid, ETH_ALEN);
 
+	listen_int = cpu_to_le16(sband->band == NL80211_BAND_S1GHZ ?
+			ieee80211_encode_usf(local->hw.conf.listen_interval) :
+			local->hw.conf.listen_interval);
 	if (!is_zero_ether_addr(assoc_data->prev_bssid)) {
 		skb_put(skb, 10);
 		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 						  IEEE80211_STYPE_REASSOC_REQ);
 		mgmt->u.reassoc_req.capab_info = cpu_to_le16(capab);
-		mgmt->u.reassoc_req.listen_interval =
-				cpu_to_le16(local->hw.conf.listen_interval);
+		mgmt->u.reassoc_req.listen_interval = listen_int;
 		memcpy(mgmt->u.reassoc_req.current_ap, assoc_data->prev_bssid,
 		       ETH_ALEN);
 	} else {
@@ -798,8 +815,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 						  IEEE80211_STYPE_ASSOC_REQ);
 		mgmt->u.assoc_req.capab_info = cpu_to_le16(capab);
-		mgmt->u.assoc_req.listen_interval =
-				cpu_to_le16(local->hw.conf.listen_interval);
+		mgmt->u.assoc_req.listen_interval = listen_int;
 	}
 
 	/* SSID */
@@ -809,6 +825,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	*pos++ = assoc_data->ssid_len;
 	memcpy(pos, assoc_data->ssid, assoc_data->ssid_len);
 
+	if (sband->band == NL80211_BAND_S1GHZ)
+		goto skip_rates;
+
 	/* add all rates which were marked to be used above */
 	supp_rates_len = rates_len;
 	if (supp_rates_len > 8)
@@ -844,6 +863,7 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		}
 	}
 
+skip_rates:
 	if (capab & WLAN_CAPABILITY_SPECTRUM_MGMT ||
 	    capab & WLAN_CAPABILITY_RADIO_MEASURE) {
 		pos = skb_put(skb, 4);
@@ -1018,6 +1038,11 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		pos = ieee80211_add_wmm_info_ie(skb_put(skb, 9), qos_info);
 	}
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		ieee80211_add_aid_request_ie(sdata, skb);
+		ieee80211_add_s1g_capab_ie(sdata, &sband->s1g_cap, skb);
+	}
+
 	/* add any remaining custom (i.e. vendor specific here) IEs */
 	if (assoc_data->ie_len) {
 		noffset = assoc_data->ie_len;
@@ -1392,6 +1417,17 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
+	if (sdata->vif.bss_conf.chandef.chan->band !=
+	    csa_ie.chandef.chan->band) {
+		sdata_info(sdata,
+			   "AP %pM switches to different band (%d MHz, width:%d, CF1/2: %d/%d MHz), disconnecting\n",
+			   ifmgd->associated->bssid,
+			   csa_ie.chandef.chan->center_freq,
+			   csa_ie.chandef.width, csa_ie.chandef.center_freq1,
+			   csa_ie.chandef.center_freq2);
+		goto lock_and_drop_connection;
+	}
+
 	if (!cfg80211_chandef_usable(local->hw.wiphy, &csa_ie.chandef,
 				     IEEE80211_CHAN_DISABLED)) {
 		sdata_info(sdata,
@@ -1404,9 +1440,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 			   csa_ie.chandef.width, csa_ie.chandef.center_freq1,
 			   csa_ie.chandef.freq1_offset,
 			   csa_ie.chandef.center_freq2);
-		ieee80211_queue_work(&local->hw,
-				     &ifmgd->csa_connection_drop_work);
-		return;
+		goto lock_and_drop_connection;
 	}
 
 	if (cfg80211_chandef_identical(&csa_ie.chandef,
@@ -1468,6 +1502,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	sdata->csa_chandef = csa_ie.chandef;
 	sdata->csa_block_tx = csa_ie.mode;
 	ifmgd->csa_ignored_same_chan = false;
+	ifmgd->beacon_crc_valid = false;
 
 	if (sdata->csa_block_tx)
 		ieee80211_stop_vif_queues(local, sdata,
@@ -1475,7 +1510,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 	mutex_unlock(&local->mtx);
 
 	cfg80211_ch_switch_started_notify(sdata->dev, &csa_ie.chandef,
-					  csa_ie.count);
+					  csa_ie.count, csa_ie.mode);
 
 	if (local->ops->channel_switch) {
 		/* use driver's channel switch callback */
@@ -1491,6 +1526,9 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata,
 			  TU_TO_EXP_TIME((csa_ie.count - 1) *
 					 cbss->beacon_interval));
 	return;
+ lock_and_drop_connection:
+	mutex_lock(&local->mtx);
+	mutex_lock(&local->chanctx_mtx);
  drop_connection:
 	/*
 	 * This is just so that the disconnect flow will know that
@@ -1535,9 +1573,17 @@ ieee80211_find_80211h_pwr_constr(struct ieee80211_sub_if_data *sdata,
 		chan_increment = 1;
 		break;
 	case NL80211_BAND_5GHZ:
-	case NL80211_BAND_6GHZ:
 		chan_increment = 4;
 		break;
+	case NL80211_BAND_6GHZ:
+		/*
+		 * In the 6 GHz band, the "maximum transmit power level"
+		 * field in the triplets is reserved, and thus will be
+		 * zero and we shouldn't use it to control TX power.
+		 * The actual TX power will be given in the transmit
+		 * power envelope element instead.
+		 */
+		return false;
 	}
 
 	/* find channel */
@@ -1597,6 +1643,9 @@ static u32 ieee80211_handle_pwr_constr(struct ieee80211_sub_if_data *sdata,
 	int new_ap_level;
 	__le16 capab = mgmt->u.probe_resp.capab_info;
 
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control))
+		return 0;	/* TODO */
+
 	if (country_ie &&
 	    (capab & cpu_to_le16(WLAN_CAPABILITY_SPECTRUM_MGMT) ||
 	     capab & cpu_to_le16(WLAN_CAPABILITY_RADIO_MEASURE))) {
@@ -2354,6 +2403,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	/* clear bssid only after building the needed mgmt frames */
 	eth_zero_addr(ifmgd->bssid);
 
+	sdata->vif.bss_conf.ssid_len = 0;
+
 	/* remove AP and TDLS peers */
 	sta_info_flush(sdata);
 
@@ -2432,23 +2483,6 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	sdata->encrypt_headroom = IEEE80211_ENCRYPT_HEADROOM;
 }
 
-void ieee80211_sta_rx_notify(struct ieee80211_sub_if_data *sdata,
-			     struct ieee80211_hdr *hdr)
-{
-	/*
-	 * We can postpone the mgd.timer whenever receiving unicast frames
-	 * from AP because we know that the connection is working both ways
-	 * at that time. But multicast frames (and hence also beacons) must
-	 * be ignored here, because we need to trigger the timer during
-	 * data idle periods for sending the periodic probe request to the
-	 * AP we're connected to.
-	 */
-	if (is_multicast_ether_addr(hdr->addr1))
-		return;
-
-	ieee80211_sta_reset_conn_monitor(sdata);
-}
-
 static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -2521,21 +2555,15 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
 {
 	ieee80211_sta_tx_wmm_ac_notify(sdata, hdr, tx_time);
 
-	if (!ieee80211_is_data(hdr->frame_control))
-	    return;
-
-	if (ieee80211_is_any_nullfunc(hdr->frame_control) &&
-	    sdata->u.mgd.probe_send_count > 0) {
-		if (ack)
-			ieee80211_sta_reset_conn_monitor(sdata);
-		else
-			sdata->u.mgd.nullfunc_failed = true;
-		ieee80211_queue_work(&sdata->local->hw, &sdata->work);
+	if (!ieee80211_is_any_nullfunc(hdr->frame_control) ||
+	    !sdata->u.mgd.probe_send_count)
 		return;
-	}
 
 	if (ack)
-		ieee80211_sta_reset_conn_monitor(sdata);
+		sdata->u.mgd.probe_send_count = 0;
+	else
+		sdata->u.mgd.nullfunc_failed = true;
+	ieee80211_queue_work(&sdata->local->hw, &sdata->work);
 }
 
 static void ieee80211_mlme_send_probe_req(struct ieee80211_sub_if_data *sdata,
@@ -2715,7 +2743,7 @@ EXPORT_SYMBOL(ieee80211_ap_probereq_get);
 
 static void ieee80211_report_disconnect(struct ieee80211_sub_if_data *sdata,
 					const u8 *buf, size_t len, bool tx,
-					u16 reason)
+					u16 reason, bool reconnect)
 {
 	struct ieee80211_event event = {
 		.type = MLME_EVENT,
@@ -2724,7 +2752,7 @@ static void ieee80211_report_disconnect(struct ieee80211_sub_if_data *sdata,
 	};
 
 	if (tx)
-		cfg80211_tx_mlme_mgmt(sdata->dev, buf, len);
+		cfg80211_tx_mlme_mgmt(sdata->dev, buf, len, reconnect);
 	else
 		cfg80211_rx_mlme_mgmt(sdata->dev, buf, len);
 
@@ -2746,13 +2774,18 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 
 	tx = !sdata->csa_block_tx;
 
-	/* AP is probably out of range (or not reachable for another reason) so
-	 * remove the bss struct for that AP.
-	 */
-	cfg80211_unlink_bss(local->hw.wiphy, ifmgd->associated);
+	if (!ifmgd->driver_disconnect) {
+		/*
+		 * AP is probably out of range (or not reachable for another
+		 * reason) so remove the bss struct for that AP.
+		 */
+		cfg80211_unlink_bss(local->hw.wiphy, ifmgd->associated);
+	}
 
 	ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH,
-			       WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
+			       ifmgd->driver_disconnect ?
+					WLAN_REASON_DEAUTH_LEAVING :
+					WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
 			       tx, frame_buf);
 	mutex_lock(&local->mtx);
 	sdata->vif.csa_active = false;
@@ -2765,7 +2798,9 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 	mutex_unlock(&local->mtx);
 
 	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), tx,
-				    WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY);
+				    WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
+				    ifmgd->reconnect);
+	ifmgd->reconnect = false;
 
 	sdata_unlock(sdata);
 }
@@ -2784,6 +2819,13 @@ static void ieee80211_beacon_connection_loss_work(struct work_struct *work)
 		sdata_info(sdata, "Connection to AP %pM lost\n",
 			   ifmgd->bssid);
 		__ieee80211_disconnect(sdata);
+		ifmgd->connection_loss = false;
+	} else if (ifmgd->driver_disconnect) {
+		sdata_info(sdata,
+			   "Driver requested disconnection from AP %pM\n",
+			   ifmgd->bssid);
+		__ieee80211_disconnect(sdata);
+		ifmgd->driver_disconnect = false;
 	} else {
 		ieee80211_mgd_probe_ap(sdata, true);
 	}
@@ -2822,6 +2864,21 @@ void ieee80211_connection_loss(struct ieee80211_vif *vif)
 }
 EXPORT_SYMBOL(ieee80211_connection_loss);
 
+void ieee80211_disconnect(struct ieee80211_vif *vif, bool reconnect)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+	struct ieee80211_hw *hw = &sdata->local->hw;
+
+	trace_api_disconnect(sdata, reconnect);
+
+	if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION))
+		return;
+
+	sdata->u.mgd.driver_disconnect = true;
+	sdata->u.mgd.reconnect = reconnect;
+	ieee80211_queue_work(hw, &sdata->u.mgd.beacon_connection_loss_work);
+}
+EXPORT_SYMBOL(ieee80211_disconnect);
 
 static void ieee80211_destroy_auth_data(struct ieee80211_sub_if_data *sdata,
 					bool assoc)
@@ -3125,7 +3182,7 @@ static void ieee80211_rx_mgmt_deauth(struct ieee80211_sub_if_data *sdata,
 		ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
 
 		ieee80211_report_disconnect(sdata, (u8 *)mgmt, len, false,
-					    reason_code);
+					    reason_code, false);
 		return;
 	}
 
@@ -3174,7 +3231,8 @@ static void ieee80211_rx_mgmt_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	ieee80211_set_disassoc(sdata, 0, 0, false, NULL);
 
-	ieee80211_report_disconnect(sdata, (u8 *)mgmt, len, false, reason_code);
+	ieee80211_report_disconnect(sdata, (u8 *)mgmt, len, false, reason_code,
+				    false);
 }
 
 static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
@@ -3194,8 +3252,8 @@ static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
 			*have_higher_than_11mbit = true;
 
 		/*
-		 * Skip HT, VHT and HE BSS membership selectors since they're
-		 * not rates.
+		 * Skip HT, VHT, HE and SAE H2E only BSS membership selectors
+		 * since they're not rates.
 		 *
 		 * Note: Even though the membership selector and the basic
 		 *	 rate flag share the same bit, they are not exactly
@@ -3203,7 +3261,8 @@ static void ieee80211_get_rates(struct ieee80211_supported_band *sband,
 		 */
 		if (supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_HT_PHY) ||
 		    supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_VHT_PHY) ||
-		    supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_HE_PHY))
+		    supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_HE_PHY) ||
+		    supp_rates[i] == (0x80 | BSS_MEMBERSHIP_SELECTOR_SAE_H2E))
 			continue;
 
 		for (j = 0; j < sband->n_bitrates; j++) {
@@ -3267,14 +3326,26 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	const struct cfg80211_bss_ies *bss_ies = NULL;
 	struct ieee80211_mgd_assoc_data *assoc_data = ifmgd->assoc_data;
 	bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ;
+	bool is_s1g = cbss->channel->band == NL80211_BAND_S1GHZ;
 	u32 changed = 0;
+	u8 *pos;
 	int err;
 	bool ret;
 
 	/* AssocResp and ReassocResp have identical structure */
 
+	pos = mgmt->u.assoc_resp.variable;
 	aid = le16_to_cpu(mgmt->u.assoc_resp.aid);
+	if (is_s1g) {
+		pos = (u8 *) mgmt->u.s1g_assoc_resp.variable;
+		aid = 0; /* TODO */
+	}
 	capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
+	ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, elems,
+			       mgmt->bssid, assoc_data->bss->bssid);
+
+	if (elems->aid_resp)
+		aid = le16_to_cpu(elems->aid_resp->aid);
 
 	/*
 	 * The 5 MSB of the AID field are reserved
@@ -3291,7 +3362,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		ifmgd->broken_ap = true;
 	}
 
-	if (!elems->supp_rates) {
+	if (!is_s1g && !elems->supp_rates) {
 		sdata_info(sdata, "no SuppRates element in AssocResp\n");
 		return false;
 	}
@@ -3477,14 +3548,6 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 			le32_get_bits(elems->he_operation->he_oper_params,
 			      IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK);
 
-		bss_conf->multi_sta_back_32bit =
-			sta->sta.he_cap.he_cap_elem.mac_cap_info[2] &
-			IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP;
-
-		bss_conf->ack_enabled =
-			sta->sta.he_cap.he_cap_elem.mac_cap_info[2] &
-			IEEE80211_HE_MAC_CAP2_ACK_EN;
-
 		bss_conf->uora_exists = !!elems->uora_element;
 		if (elems->uora_element)
 			bss_conf->uora_ocw_range = elems->uora_element[0];
@@ -3533,7 +3596,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		sta->sta.mfp = false;
 	}
 
-	sta->sta.wme = elems->wmm_param && local->hw.queues >= IEEE80211_NUM_ACS;
+	sta->sta.wme = (elems->wmm_param || elems->s1g_capab) &&
+		       local->hw.queues >= IEEE80211_NUM_ACS;
 
 	err = sta_info_move_state(sta, IEEE80211_STA_ASSOC);
 	if (!err && !(ifmgd->flags & IEEE80211_STA_CONTROL_PORT))
@@ -3548,6 +3612,9 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
+	if (sdata->wdev.use_4addr)
+		drv_sta_set_4addr(local, sdata, &sta->sta, true);
+
 	mutex_unlock(&sdata->local->sta_mtx);
 
 	/*
@@ -3605,8 +3672,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	 * Start timer to probe the connection to the AP now.
 	 * Also start the timer that will detect beacon loss.
 	 */
-	ieee80211_sta_rx_notify(sdata, (struct ieee80211_hdr *)mgmt);
 	ieee80211_sta_reset_beacon_monitor(sdata);
+	ieee80211_sta_reset_conn_monitor(sdata);
 
 	ret = true;
  out:
@@ -3625,7 +3692,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	int ac, uapsd_queues = -1;
 	u8 *pos;
 	bool reassoc;
-	struct cfg80211_bss *bss;
+	struct cfg80211_bss *cbss;
 	struct ieee80211_event event = {
 		.type = MLME_EVENT,
 		.u.mlme.data = ASSOC_EVENT,
@@ -3635,9 +3702,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 
 	if (!assoc_data)
 		return;
+
 	if (!ether_addr_equal(assoc_data->bss->bssid, mgmt->bssid))
 		return;
 
+	cbss = assoc_data->bss;
+
 	/*
 	 * AssocResp and ReassocResp have identical structure, so process both
 	 * of them in this function.
@@ -3649,7 +3719,12 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	reassoc = ieee80211_is_reassoc_resp(mgmt->frame_control);
 	capab_info = le16_to_cpu(mgmt->u.assoc_resp.capab_info);
 	status_code = le16_to_cpu(mgmt->u.assoc_resp.status_code);
+	pos = mgmt->u.assoc_resp.variable;
 	aid = le16_to_cpu(mgmt->u.assoc_resp.aid);
+	if (cbss->channel->band == NL80211_BAND_S1GHZ) {
+		pos = (u8 *) mgmt->u.s1g_assoc_resp.variable;
+		aid = 0; /* TODO */
+	}
 
 	sdata_info(sdata,
 		   "RX %sssocResp from %pM (capab=0x%x status=%d aid=%d)\n",
@@ -3660,7 +3735,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 	    fils_decrypt_assoc_resp(sdata, (u8 *)mgmt, &len, assoc_data) < 0)
 		return;
 
-	pos = mgmt->u.assoc_resp.variable;
 	ieee802_11_parse_elems(pos, len - (pos - (u8 *)mgmt), false, &elems,
 			       mgmt->bssid, assoc_data->bss->bssid);
 
@@ -3680,8 +3754,6 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
-	bss = assoc_data->bss;
-
 	if (status_code != WLAN_STATUS_SUCCESS) {
 		sdata_info(sdata, "%pM denied association (code=%d)\n",
 			   mgmt->sa, status_code);
@@ -3690,10 +3762,10 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 		event.u.mlme.reason = status_code;
 		drv_event_callback(sdata->local, sdata, &event);
 	} else {
-		if (!ieee80211_assoc_success(sdata, bss, mgmt, len, &elems)) {
+		if (!ieee80211_assoc_success(sdata, cbss, mgmt, len, &elems)) {
 			/* oops -- internal error -- send timeout for now */
 			ieee80211_destroy_assoc_data(sdata, false, false);
-			cfg80211_assoc_timeout(sdata->dev, bss);
+			cfg80211_assoc_timeout(sdata->dev, cbss);
 			return;
 		}
 		event.u.mlme.status = MLME_SUCCESS;
@@ -3714,7 +3786,7 @@ static void ieee80211_rx_mgmt_assoc_resp(struct ieee80211_sub_if_data *sdata,
 				uapsd_queues |= ieee80211_ac_to_qos_mask[ac];
 	}
 
-	cfg80211_rx_assoc_resp(sdata->dev, bss, (u8 *)mgmt, len, uapsd_queues,
+	cfg80211_rx_assoc_resp(sdata->dev, cbss, (u8 *)mgmt, len, uapsd_queues,
 			       ifmgd->assoc_req_ies, ifmgd->assoc_req_ies_len);
 }
 
@@ -3913,11 +3985,12 @@ static bool ieee80211_rx_our_beacon(const u8 *tx_bssid,
 }
 
 static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
-				     struct ieee80211_mgmt *mgmt, size_t len,
+				     struct ieee80211_hdr *hdr, size_t len,
 				     struct ieee80211_rx_status *rx_status)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf;
+	struct ieee80211_mgmt *mgmt = (void *) hdr;
 	size_t baselen;
 	struct ieee802_11_elems elems;
 	struct ieee80211_local *local = sdata->local;
@@ -3927,14 +4000,24 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	u32 changed = 0;
 	bool erp_valid;
 	u8 erp_value = 0;
-	u32 ncrc;
-	u8 *bssid;
+	u32 ncrc = 0;
+	u8 *bssid, *variable = mgmt->u.beacon.variable;
 	u8 deauth_buf[IEEE80211_DEAUTH_FRAME_LEN];
 
 	sdata_assert_lock(sdata);
 
 	/* Process beacon from the current BSS */
-	baselen = (u8 *) mgmt->u.beacon.variable - (u8 *) mgmt;
+	bssid = ieee80211_get_bssid(hdr, len, sdata->vif.type);
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		struct ieee80211_ext *ext = (void *) mgmt;
+
+		if (ieee80211_is_s1g_short_beacon(ext->frame_control))
+			variable = ext->u.s1g_short_beacon.variable;
+		else
+			variable = ext->u.s1g_beacon.variable;
+	}
+
+	baselen = (u8 *) variable - (u8 *) mgmt;
 	if (baselen > len)
 		return;
 
@@ -3954,10 +4037,10 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	rcu_read_unlock();
 
 	if (ifmgd->assoc_data && ifmgd->assoc_data->need_beacon &&
-	    ieee80211_rx_our_beacon(mgmt->bssid, ifmgd->assoc_data->bss)) {
-		ieee802_11_parse_elems(mgmt->u.beacon.variable,
+	    ieee80211_rx_our_beacon(bssid, ifmgd->assoc_data->bss)) {
+		ieee802_11_parse_elems(variable,
 				       len - baselen, false, &elems,
-				       mgmt->bssid,
+				       bssid,
 				       ifmgd->assoc_data->bss->bssid);
 
 		ieee80211_rx_bss_info(sdata, mgmt, len, rx_status);
@@ -3990,7 +4073,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (!ifmgd->associated ||
-	    !ieee80211_rx_our_beacon(mgmt->bssid,  ifmgd->associated))
+	    !ieee80211_rx_our_beacon(bssid,  ifmgd->associated))
 		return;
 	bssid = ifmgd->associated->bssid;
 
@@ -4010,8 +4093,14 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	 */
 	ieee80211_sta_reset_beacon_monitor(sdata);
 
-	ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4);
-	ncrc = ieee802_11_parse_elems_crc(mgmt->u.beacon.variable,
+	/* TODO: CRC urrently not calculated on S1G Beacon Compatibility
+	 * element (which carries the beacon interval). Don't forget to add a
+	 * bit to care_about_ies[] above if mac80211 is interested in a
+	 * changing S1G element.
+	 */
+	if (!ieee80211_is_s1g_beacon(hdr->frame_control))
+		ncrc = crc32_be(0, (void *)&mgmt->u.beacon.beacon_int, 4);
+	ncrc = ieee802_11_parse_elems_crc(variable,
 					  len - baselen, false, &elems,
 					  care_about_ies, ncrc,
 					  mgmt->bssid, bssid);
@@ -4045,7 +4134,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		struct ieee80211_p2p_noa_attr noa = {};
 		int ret;
 
-		ret = cfg80211_get_p2p_attr(mgmt->u.beacon.variable,
+		ret = cfg80211_get_p2p_attr(variable,
 					    len - baselen,
 					    IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
 					    (u8 *) &noa, sizeof(noa));
@@ -4081,7 +4170,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	 * the driver will use them. The synchronized view is currently
 	 * guaranteed only in certain callbacks.
 	 */
-	if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY)) {
+	if (ieee80211_hw_check(&local->hw, TIMING_BEACON_ONLY) &&
+	    !ieee80211_is_s1g_beacon(hdr->frame_control)) {
 		sdata->vif.bss_conf.sync_tsf =
 			le64_to_cpu(mgmt->u.beacon.timestamp);
 		sdata->vif.bss_conf.sync_device_ts =
@@ -4089,7 +4179,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 		sdata->vif.bss_conf.sync_dtim_count = elems.dtim_count;
 	}
 
-	if (ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid)
+	if ((ncrc == ifmgd->beacon_crc && ifmgd->beacon_crc_valid) ||
+	    ieee80211_is_s1g_short_beacon(mgmt->frame_control))
 		return;
 	ifmgd->beacon_crc = ncrc;
 	ifmgd->beacon_crc_valid = true;
@@ -4130,9 +4221,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	} else {
 		erp_valid = false;
 	}
-	changed |= ieee80211_handle_bss_capability(sdata,
-			le16_to_cpu(mgmt->u.beacon.capab_info),
-			erp_valid, erp_value);
+
+	if (!ieee80211_is_s1g_beacon(hdr->frame_control))
+		changed |= ieee80211_handle_bss_capability(sdata,
+				le16_to_cpu(mgmt->u.beacon.capab_info),
+				erp_valid, erp_value);
 
 	mutex_lock(&local->sta_mtx);
 	sta = sta_info_get(sdata, bssid);
@@ -4142,7 +4235,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	if (ieee80211_config_bw(sdata, sta, elems.ht_cap_elem,
 				elems.vht_cap_elem, elems.ht_operation,
 				elems.vht_operation, elems.he_operation,
-				bssid, &changed)) {
+				elems.s1g_oper, bssid, &changed)) {
 		mutex_unlock(&local->sta_mtx);
 		sdata_info(sdata,
 			   "failed to follow AP %pM bandwidth change, disconnect\n",
@@ -4152,7 +4245,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 				       true, deauth_buf);
 		ieee80211_report_disconnect(sdata, deauth_buf,
 					    sizeof(deauth_buf), true,
-					    WLAN_REASON_DEAUTH_LEAVING);
+					    WLAN_REASON_DEAUTH_LEAVING,
+					    false);
 		return;
 	}
 
@@ -4170,6 +4264,26 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 	ieee80211_bss_info_change_notify(sdata, changed);
 }
 
+void ieee80211_sta_rx_queued_ext(struct ieee80211_sub_if_data *sdata,
+				 struct sk_buff *skb)
+{
+	struct ieee80211_rx_status *rx_status;
+	struct ieee80211_hdr *hdr;
+	u16 fc;
+
+	rx_status = (struct ieee80211_rx_status *) skb->cb;
+	hdr = (struct ieee80211_hdr *) skb->data;
+	fc = le16_to_cpu(hdr->frame_control);
+
+	sdata_lock(sdata);
+	switch (fc & IEEE80211_FCTL_STYPE) {
+	case IEEE80211_STYPE_S1G_BEACON:
+		ieee80211_rx_mgmt_beacon(sdata, hdr, skb->len, rx_status);
+		break;
+	}
+	sdata_unlock(sdata);
+}
+
 void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 				  struct sk_buff *skb)
 {
@@ -4187,7 +4301,8 @@ void ieee80211_sta_rx_queued_mgmt(struct ieee80211_sub_if_data *sdata,
 
 	switch (fc & IEEE80211_FCTL_STYPE) {
 	case IEEE80211_STYPE_BEACON:
-		ieee80211_rx_mgmt_beacon(sdata, mgmt, skb->len, rx_status);
+		ieee80211_rx_mgmt_beacon(sdata, (void *)mgmt,
+					 skb->len, rx_status);
 		break;
 	case IEEE80211_STYPE_PROBE_RESP:
 		ieee80211_rx_mgmt_probe_resp(sdata, skb);
@@ -4276,7 +4391,7 @@ static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata,
 			       tx, frame_buf);
 
 	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true,
-				    reason);
+				    reason, false);
 }
 
 static int ieee80211_auth(struct ieee80211_sub_if_data *sdata)
@@ -4577,10 +4692,26 @@ static void ieee80211_sta_conn_mon_timer(struct timer_list *t)
 		from_timer(sdata, t, u.mgd.conn_mon_timer);
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_local *local = sdata->local;
+	struct sta_info *sta;
+	unsigned long timeout;
 
 	if (sdata->vif.csa_active && !ifmgd->csa_waiting_bcn)
 		return;
 
+	sta = sta_info_get(sdata, ifmgd->bssid);
+	if (!sta)
+		return;
+
+	timeout = sta->status_stats.last_ack;
+	if (time_before(sta->status_stats.last_ack, sta->rx_stats.last_rx))
+		timeout = sta->rx_stats.last_rx;
+	timeout += IEEE80211_CONNECTION_IDLE_TIME;
+
+	if (time_is_before_jiffies(timeout)) {
+		mod_timer(&ifmgd->conn_mon_timer, round_jiffies_up(timeout));
+		return;
+	}
+
 	ieee80211_queue_work(&local->hw, &ifmgd->monitor_work);
 }
 
@@ -4632,7 +4763,8 @@ void ieee80211_mgd_quiesce(struct ieee80211_sub_if_data *sdata)
 		if (ifmgd->auth_data)
 			ieee80211_destroy_auth_data(sdata, false);
 		cfg80211_tx_mlme_mgmt(sdata->dev, frame_buf,
-				      IEEE80211_DEAUTH_FRAME_LEN);
+				      IEEE80211_DEAUTH_FRAME_LEN,
+				      false);
 	}
 
 	/* This is a bit of a hack - we should find a better and more generic
@@ -4858,6 +4990,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	const struct ieee80211_ht_operation *ht_oper = NULL;
 	const struct ieee80211_vht_operation *vht_oper = NULL;
 	const struct ieee80211_he_operation *he_oper = NULL;
+	const struct ieee80211_s1g_oper_ie *s1g_oper = NULL;
 	struct ieee80211_supported_band *sband;
 	struct cfg80211_chan_def chandef;
 	bool is_6ghz = cbss->channel->band == NL80211_BAND_6GHZ;
@@ -4961,10 +5094,23 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	if (!have_80mhz)
 		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		const u8 *s1g_oper_ie;
+
+		s1g_oper_ie = ieee80211_bss_get_ie(cbss,
+						   WLAN_EID_S1G_OPERATION);
+		if (s1g_oper_ie && s1g_oper_ie[1] >= sizeof(*s1g_oper))
+			s1g_oper = (void *)(s1g_oper_ie + 2);
+		else
+			sdata_info(sdata,
+				   "AP missing S1G operation element?\n");
+	}
+
 	ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
 						     cbss->channel,
 						     bss->vht_cap_info,
 						     ht_oper, vht_oper, he_oper,
+						     s1g_oper,
 						     &chandef, false);
 
 	sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
@@ -5091,6 +5237,12 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		const struct cfg80211_bss_ies *ies;
 		int shift = ieee80211_vif_get_shift(&sdata->vif);
 
+		/* TODO: S1G Basic Rate Set is expressed elsewhere */
+		if (cbss->channel->band == NL80211_BAND_S1GHZ) {
+			ieee80211_s1g_sta_rate_init(new_sta);
+			goto skip_rates;
+		}
+
 		ieee80211_get_rates(sband, bss->supp_rates,
 				    bss->supp_rates_len,
 				    &rates, &basic_rates,
@@ -5135,6 +5287,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata,
 		else
 			sdata->flags &= ~IEEE80211_SDATA_OPERATING_GMODE;
 
+skip_rates:
 		memcpy(ifmgd->bssid, cbss->bssid, ETH_ALEN);
 
 		/* set timing information */
@@ -5325,7 +5478,8 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata,
 
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
-					    WLAN_REASON_UNSPECIFIED);
+					    WLAN_REASON_UNSPECIFIED,
+					    false);
 	}
 
 	sdata_info(sdata, "authenticate with %pM\n", req->bss->bssid);
@@ -5359,12 +5513,14 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 			struct cfg80211_assoc_request *req)
 {
 	bool is_6ghz = req->bss->channel->band == NL80211_BAND_6GHZ;
+	bool is_5ghz = req->bss->channel->band == NL80211_BAND_5GHZ;
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	struct ieee80211_bss *bss = (void *)req->bss->priv;
 	struct ieee80211_mgd_assoc_data *assoc_data;
 	const struct cfg80211_bss_ies *beacon_ies;
 	struct ieee80211_supported_band *sband;
+	struct ieee80211_bss_conf *bss_conf = &sdata->vif.bss_conf;
 	const u8 *ssidie, *ht_ie, *vht_ie;
 	int i, err;
 	bool override = false;
@@ -5382,6 +5538,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	}
 	memcpy(assoc_data->ssid, ssidie + 2, ssidie[1]);
 	assoc_data->ssid_len = ssidie[1];
+	memcpy(bss_conf->ssid, assoc_data->ssid, assoc_data->ssid_len);
+	bss_conf->ssid_len = assoc_data->ssid_len;
 	rcu_read_unlock();
 
 	if (ifmgd->associated) {
@@ -5396,7 +5554,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
-					    WLAN_REASON_UNSPECIFIED);
+					    WLAN_REASON_UNSPECIFIED,
+					    false);
 	}
 
 	if (ifmgd->auth_data && !ifmgd->auth_data->done) {
@@ -5462,6 +5621,10 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	memcpy(&ifmgd->vht_capa_mask, &req->vht_capa_mask,
 	       sizeof(ifmgd->vht_capa_mask));
 
+	memcpy(&ifmgd->s1g_capa, &req->s1g_capa, sizeof(ifmgd->s1g_capa));
+	memcpy(&ifmgd->s1g_capa_mask, &req->s1g_capa_mask,
+	       sizeof(ifmgd->s1g_capa_mask));
+
 	if (req->ie && req->ie_len) {
 		memcpy(assoc_data->ie, req->ie, req->ie_len);
 		assoc_data->ie_len = req->ie_len;
@@ -5507,7 +5670,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	if (vht_ie && vht_ie[1] >= sizeof(struct ieee80211_vht_cap))
 		memcpy(&assoc_data->ap_vht_cap, vht_ie + 2,
 		       sizeof(struct ieee80211_vht_cap));
-	else if (!is_6ghz)
+	else if (is_5ghz)
 		ifmgd->flags |= IEEE80211_STA_DISABLE_VHT |
 				IEEE80211_STA_DISABLE_HE;
 	rcu_read_unlock();
@@ -5691,7 +5854,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 		ieee80211_destroy_auth_data(sdata, false);
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
-					    req->reason_code);
+					    req->reason_code, false);
 
 		return 0;
 	}
@@ -5711,7 +5874,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 		ieee80211_destroy_assoc_data(sdata, false, true);
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
-					    req->reason_code);
+					    req->reason_code, false);
 		return 0;
 	}
 
@@ -5726,7 +5889,7 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 				       req->reason_code, tx, frame_buf);
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
-					    req->reason_code);
+					    req->reason_code, false);
 		return 0;
 	}
 
@@ -5759,7 +5922,7 @@ int ieee80211_mgd_disassoc(struct ieee80211_sub_if_data *sdata,
 			       frame_buf);
 
 	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true,
-				    req->reason_code);
+				    req->reason_code, false);
 
 	return 0;
 }
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index f470d1a7ce9b..853c9a369d72 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -26,8 +26,7 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
-
-	local->offchannel_ps_enabled = false;
+	bool offchannel_ps_enabled = false;
 
 	/* FIXME: what to do when local->pspolling is true? */
 
@@ -38,12 +37,12 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata)
 	cancel_work_sync(&local->dynamic_ps_enable_work);
 
 	if (local->hw.conf.flags & IEEE80211_CONF_PS) {
-		local->offchannel_ps_enabled = true;
+		offchannel_ps_enabled = true;
 		local->hw.conf.flags &= ~IEEE80211_CONF_PS;
 		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS);
 	}
 
-	if (!local->offchannel_ps_enabled ||
+	if (!offchannel_ps_enabled ||
 	    !ieee80211_hw_check(&local->hw, PS_NULLFUNC_STACK))
 		/*
 		 * If power save was enabled, no need to send a nullfunc
@@ -58,38 +57,19 @@ static void ieee80211_offchannel_ps_enable(struct ieee80211_sub_if_data *sdata)
 		ieee80211_send_nullfunc(local, sdata, true);
 }
 
-/* inform AP that we are awake again, unless power save is enabled */
+/* inform AP that we are awake again */
 static void ieee80211_offchannel_ps_disable(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
 
 	if (!local->ps_sdata)
 		ieee80211_send_nullfunc(local, sdata, false);
-	else if (local->offchannel_ps_enabled) {
-		/*
-		 * In !IEEE80211_HW_PS_NULLFUNC_STACK case the hardware
-		 * will send a nullfunc frame with the powersave bit set
-		 * even though the AP already knows that we are sleeping.
-		 * This could be avoided by sending a null frame with power
-		 * save bit disabled before enabling the power save, but
-		 * this doesn't gain anything.
-		 *
-		 * When IEEE80211_HW_PS_NULLFUNC_STACK is enabled, no need
-		 * to send a nullfunc frame because AP already knows that
-		 * we are sleeping, let's just enable power save mode in
-		 * hardware.
-		 */
-		/* TODO:  Only set hardware if CONF_PS changed?
-		 * TODO:  Should we set offchannel_ps_enabled to false?
-		 */
-		local->hw.conf.flags |= IEEE80211_CONF_PS;
-		ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS);
-	} else if (local->hw.conf.dynamic_ps_timeout > 0) {
+	else if (local->hw.conf.dynamic_ps_timeout > 0) {
 		/*
-		 * If IEEE80211_CONF_PS was not set and the dynamic_ps_timer
-		 * had been running before leaving the operating channel,
-		 * restart the timer now and send a nullfunc frame to inform
-		 * the AP that we are awake.
+		 * the dynamic_ps_timer had been running before leaving the
+		 * operating channel, restart the timer now and send a nullfunc
+		 * frame to inform the AP that we are awake so that AP sends
+		 * the buffered packets (if any).
 		 */
 		ieee80211_send_nullfunc(local, sdata, false);
 		mod_timer(&local->dynamic_ps_timer, jiffies +
@@ -916,7 +896,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 		if (beacon)
 			for (i = 0; i < params->n_csa_offsets; i++)
 				data[params->csa_offsets[i]] =
-					beacon->csa_current_counter;
+					beacon->cntdwn_current_counter;
 
 		rcu_read_unlock();
 	}
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 38c45e1dafd8..ae378a41c927 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -150,21 +150,6 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
 		case NL80211_IFTYPE_STATION:
 			ieee80211_mgd_quiesce(sdata);
 			break;
-		case NL80211_IFTYPE_WDS:
-			/* tear down aggregation sessions and remove STAs */
-			mutex_lock(&local->sta_mtx);
-			sta = sdata->u.wds.sta;
-			if (sta && sta->uploaded) {
-				enum ieee80211_sta_state state;
-
-				state = sta->sta_state;
-				for (; state > IEEE80211_STA_NOTEXIST; state--)
-					WARN_ON(drv_sta_state(local, sta->sdata,
-							      sta, state,
-							      state - 1));
-			}
-			mutex_unlock(&local->sta_mtx);
-			break;
 		default:
 			break;
 		}
diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
index b051f125d3af..63652c39c8e0 100644
--- a/net/mac80211/rate.c
+++ b/net/mac80211/rate.c
@@ -51,6 +51,13 @@ void rate_control_rate_init(struct sta_info *sta)
 
 	sband = local->hw.wiphy->bands[chanctx_conf->def.chan->band];
 
+	/* TODO: check for minstrel_s1g ? */
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		ieee80211_s1g_sta_rate_init(sta);
+		rcu_read_unlock();
+		return;
+	}
+
 	spin_lock_bh(&sta->rate_ctrl_lock);
 	ref->ops->rate_init(ref->priv, sband, &chanctx_conf->def, ista,
 			    priv_sta);
@@ -266,10 +273,15 @@ void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata)
 	if (WARN_ON(!sdata->vif.bss_conf.chandef.chan))
 		return;
 
+	band = sdata->vif.bss_conf.chandef.chan->band;
+	if (band == NL80211_BAND_S1GHZ) {
+		/* TODO */
+		return;
+	}
+
 	if (WARN_ON_ONCE(!basic_rates))
 		return;
 
-	band = sdata->vif.bss_conf.chandef.chan->band;
 	user_mask = sdata->rc_rateidx_mask[band];
 	sband = local->hw.wiphy->bands[band];
 
@@ -296,21 +308,29 @@ static bool rc_no_data_or_no_ack_use_min(struct ieee80211_tx_rate_control *txrc)
 		!ieee80211_is_data(fc);
 }
 
-static void rc_send_low_basicrate(s8 *idx, u32 basic_rates,
+static void rc_send_low_basicrate(struct ieee80211_tx_rate *rate,
+				  u32 basic_rates,
 				  struct ieee80211_supported_band *sband)
 {
 	u8 i;
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		/* TODO */
+		rate->flags |= IEEE80211_TX_RC_S1G_MCS;
+		rate->idx = 0;
+		return;
+	}
+
 	if (basic_rates == 0)
 		return; /* assume basic rates unknown and accept rate */
-	if (*idx < 0)
+	if (rate->idx < 0)
 		return;
-	if (basic_rates & (1 << *idx))
+	if (basic_rates & (1 << rate->idx))
 		return; /* selected rate is a basic rate */
 
-	for (i = *idx + 1; i <= sband->n_bitrates; i++) {
+	for (i = rate->idx + 1; i <= sband->n_bitrates; i++) {
 		if (basic_rates & (1 << i)) {
-			*idx = i;
+			rate->idx = i;
 			return;
 		}
 	}
@@ -328,6 +348,12 @@ static void __rate_control_send_low(struct ieee80211_hw *hw,
 	u32 rate_flags =
 		ieee80211_chandef_rate_flags(&hw->conf.chandef);
 
+	if (sband->band == NL80211_BAND_S1GHZ) {
+		info->control.rates[0].flags |= IEEE80211_TX_RC_S1G_MCS;
+		info->control.rates[0].idx = 0;
+		return;
+	}
+
 	if ((sband->band == NL80211_BAND_2GHZ) &&
 	    (info->flags & IEEE80211_TX_CTL_NO_CCK_RATE))
 		rate_flags |= IEEE80211_RATE_ERP_G;
@@ -388,7 +414,7 @@ static bool rate_control_send_low(struct ieee80211_sta *pubsta,
 		}
 
 		if (use_basicrate)
-			rc_send_low_basicrate(&info->control.rates[0].idx,
+			rc_send_low_basicrate(&info->control.rates[0],
 					      txrc->bss_conf->basic_rates,
 					      sband);
 
@@ -934,7 +960,8 @@ int rate_control_set_rates(struct ieee80211_hw *hw,
 	if (old)
 		kfree_rcu(old, rcu_head);
 
-	drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta);
+	if (sta->uploaded)
+		drv_sta_rate_tbl_update(hw_to_local(hw), sta->sdata, pubsta);
 
 	ieee80211_sta_set_expected_throughput(pubsta, sta_get_expected_throughput(sta));
 
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 86bc469a28bc..b13b1da19386 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -274,7 +274,7 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband,
 	success = !!(info->flags & IEEE80211_TX_STAT_ACK);
 
 	for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) {
-		if (ar[i].idx < 0)
+		if (ar[i].idx < 0 || !ar[i].count)
 			break;
 
 		ndx = rix_to_ndx(mi, ar[i].idx);
@@ -287,12 +287,6 @@ minstrel_tx_status(void *priv, struct ieee80211_supported_band *sband,
 			mi->r[ndx].stats.success += success;
 	}
 
-	if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) && (i >= 0))
-		mi->sample_packets++;
-
-	if (mi->sample_deferred > 0)
-		mi->sample_deferred--;
-
 	if (time_after(jiffies, mi->last_stats_update +
 				mp->update_interval / (mp->new_avg ? 2 : 1)))
 		minstrel_update_stats(mp, mi);
@@ -367,7 +361,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
 		return;
 
 	delta = (mi->total_packets * sampling_ratio / 100) -
-			(mi->sample_packets + mi->sample_deferred / 2);
+			mi->sample_packets;
 
 	/* delta < 0: no sampling required */
 	prev_sample = mi->prev_sample;
@@ -376,7 +370,6 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
 		return;
 
 	if (mi->total_packets >= 10000) {
-		mi->sample_deferred = 0;
 		mi->sample_packets = 0;
 		mi->total_packets = 0;
 	} else if (delta > mi->n_rates * 2) {
@@ -401,19 +394,8 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
 	 * rate sampling method should be used.
 	 * Respect such rates that are not sampled for 20 interations.
 	 */
-	if (mrr_capable &&
-	    msr->perfect_tx_time > mr->perfect_tx_time &&
-	    msr->stats.sample_skipped < 20) {
-		/* Only use IEEE80211_TX_CTL_RATE_CTRL_PROBE to mark
-		 * packets that have the sampling rate deferred to the
-		 * second MRR stage. Increase the sample counter only
-		 * if the deferred sample rate was actually used.
-		 * Use the sample_deferred counter to make sure that
-		 * the sampling is not done in large bursts */
-		info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
-		rate++;
-		mi->sample_deferred++;
-	} else {
+	if (msr->perfect_tx_time < mr->perfect_tx_time ||
+	    msr->stats.sample_skipped >= 20) {
 		if (!msr->sample_limit)
 			return;
 
@@ -433,6 +415,7 @@ minstrel_get_rate(void *priv, struct ieee80211_sta *sta,
 
 	rate->idx = mi->r[ndx].rix;
 	rate->count = minstrel_get_retry_count(&mi->r[ndx], info);
+	info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
 }
 
 
diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h
index dbb43bcd3c45..86cd80b3ffde 100644
--- a/net/mac80211/rc80211_minstrel.h
+++ b/net/mac80211/rc80211_minstrel.h
@@ -126,7 +126,6 @@ struct minstrel_sta_info {
 	u8 max_prob_rate;
 	unsigned int total_packets;
 	unsigned int sample_packets;
-	int sample_deferred;
 
 	unsigned int sample_row;
 	unsigned int sample_column;
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index a959ebf56852..972895e9f22d 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -32,61 +32,6 @@
 #include "wme.h"
 #include "rate.h"
 
-static inline void ieee80211_rx_stats(struct net_device *dev, u32 len)
-{
-	struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
-
-	u64_stats_update_begin(&tstats->syncp);
-	tstats->rx_packets++;
-	tstats->rx_bytes += len;
-	u64_stats_update_end(&tstats->syncp);
-}
-
-static u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
-			       enum nl80211_iftype type)
-{
-	__le16 fc = hdr->frame_control;
-
-	if (ieee80211_is_data(fc)) {
-		if (len < 24) /* drop incorrect hdr len (data) */
-			return NULL;
-
-		if (ieee80211_has_a4(fc))
-			return NULL;
-		if (ieee80211_has_tods(fc))
-			return hdr->addr1;
-		if (ieee80211_has_fromds(fc))
-			return hdr->addr2;
-
-		return hdr->addr3;
-	}
-
-	if (ieee80211_is_mgmt(fc)) {
-		if (len < 24) /* drop incorrect hdr len (mgmt) */
-			return NULL;
-		return hdr->addr3;
-	}
-
-	if (ieee80211_is_ctl(fc)) {
-		if (ieee80211_is_pspoll(fc))
-			return hdr->addr1;
-
-		if (ieee80211_is_back_req(fc)) {
-			switch (type) {
-			case NL80211_IFTYPE_STATION:
-				return hdr->addr2;
-			case NL80211_IFTYPE_AP:
-			case NL80211_IFTYPE_AP_VLAN:
-				return hdr->addr1;
-			default:
-				break; /* fall through to the return */
-			}
-		}
-	}
-
-	return NULL;
-}
-
 /*
  * monitor mode reception
  *
@@ -887,7 +832,7 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 
 			if (skb) {
 				skb->dev = sdata->dev;
-				ieee80211_rx_stats(skb->dev, skb->len);
+				dev_sw_netstats_rx_add(skb->dev, skb->len);
 				netif_receive_skb(skb);
 			}
 		}
@@ -1522,7 +1467,6 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
 	if (unlikely((ieee80211_is_data(hdr->frame_control) ||
 		      ieee80211_is_pspoll(hdr->frame_control)) &&
 		     rx->sdata->vif.type != NL80211_IFTYPE_ADHOC &&
-		     rx->sdata->vif.type != NL80211_IFTYPE_WDS &&
 		     rx->sdata->vif.type != NL80211_IFTYPE_OCB &&
 		     (!rx->sta || !test_sta_flag(rx->sta, WLAN_STA_ASSOC)))) {
 		/*
@@ -1802,7 +1746,8 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 		}
 	} else if (rx->sdata->vif.type == NL80211_IFTYPE_OCB) {
 		sta->rx_stats.last_rx = jiffies;
-	} else if (!is_multicast_ether_addr(hdr->addr1)) {
+	} else if (!ieee80211_is_s1g_beacon(hdr->frame_control) &&
+		   !is_multicast_ether_addr(hdr->addr1)) {
 		/*
 		 * Mesh beacons will update last_rx when if they are found to
 		 * match the current local configuration when processed.
@@ -1812,9 +1757,6 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 			sta->rx_stats.last_rate = sta_stats_encode_rate(status);
 	}
 
-	if (rx->sdata->vif.type == NL80211_IFTYPE_STATION)
-		ieee80211_sta_rx_notify(rx->sdata, hdr);
-
 	sta->rx_stats.fragments++;
 
 	u64_stats_update_begin(&rx->sta->rx_stats.syncp);
@@ -1840,6 +1782,9 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 		}
 	}
 
+	if (ieee80211_is_s1g_beacon(hdr->frame_control))
+		return RX_CONTINUE;
+
 	/*
 	 * Change STA power saving mode only at the end of a frame
 	 * exchange sequence, and only for a data or management
@@ -1950,6 +1895,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 	__le16 fc;
 	const struct ieee80211_cipher_scheme *cs = NULL;
 
+	if (ieee80211_is_ext(hdr->frame_control))
+		return RX_CONTINUE;
+
 	/*
 	 * Key selection 101
 	 *
@@ -2258,7 +2206,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 	hdr = (struct ieee80211_hdr *)rx->skb->data;
 	fc = hdr->frame_control;
 
-	if (ieee80211_is_ctl(fc))
+	if (ieee80211_is_ctl(fc) || ieee80211_is_ext(fc))
 		return RX_CONTINUE;
 
 	sc = le16_to_cpu(hdr->seq_ctrl);
@@ -2601,7 +2549,7 @@ ieee80211_deliver_skb(struct ieee80211_rx_data *rx)
 	skb = rx->skb;
 	xmit_skb = NULL;
 
-	ieee80211_rx_stats(dev, skb->len);
+	dev_sw_netstats_rx_add(dev, skb->len);
 
 	if (rx->sta) {
 		/* The seqno index has the same property as needed
@@ -2900,7 +2848,7 @@ ieee80211_rx_h_mesh_fwding(struct ieee80211_rx_data *rx)
 	fwd_hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_RETRY);
 	info = IEEE80211_SKB_CB(fwd_skb);
 	memset(info, 0, sizeof(*info));
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 	info->control.vif = &rx->sdata->vif;
 	info->control.jiffies = jiffies;
 	if (is_multicast_ether_addr(fwd_hdr->addr1)) {
@@ -3132,6 +3080,9 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx)
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *) rx->skb->data;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
 
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control))
+		return RX_CONTINUE;
+
 	/*
 	 * From here on, look only at management frames.
 	 * Data and control frames are already handled,
@@ -3599,6 +3550,27 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx)
 }
 
 static ieee80211_rx_result debug_noinline
+ieee80211_rx_h_ext(struct ieee80211_rx_data *rx)
+{
+	struct ieee80211_sub_if_data *sdata = rx->sdata;
+	struct ieee80211_hdr *hdr = (void *)rx->skb->data;
+
+	if (!ieee80211_is_ext(hdr->frame_control))
+		return RX_CONTINUE;
+
+	if (sdata->vif.type != NL80211_IFTYPE_STATION)
+		return RX_DROP_MONITOR;
+
+	/* for now only beacons are ext, so queue them */
+	skb_queue_tail(&sdata->skb_queue, rx->skb);
+	ieee80211_queue_work(&rx->local->hw, &sdata->work);
+	if (rx->sta)
+		rx->sta->rx_stats.packets++;
+
+	return RX_QUEUED;
+}
+
+static ieee80211_rx_result debug_noinline
 ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx)
 {
 	struct ieee80211_sub_if_data *sdata = rx->sdata;
@@ -3716,7 +3688,7 @@ static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx,
 		}
 
 		prev_dev = sdata->dev;
-		ieee80211_rx_stats(sdata->dev, skb->len);
+		dev_sw_netstats_rx_add(sdata->dev, skb->len);
 	}
 
 	if (prev_dev) {
@@ -3817,6 +3789,7 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx,
 		CALL_RXH(ieee80211_rx_h_userspace_mgmt);
 		CALL_RXH(ieee80211_rx_h_action_post_userspace);
 		CALL_RXH(ieee80211_rx_h_action_return);
+		CALL_RXH(ieee80211_rx_h_ext);
 		CALL_RXH(ieee80211_rx_h_mgmt);
 
  rxh_next:
@@ -3983,7 +3956,8 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 	struct ieee80211_hdr *hdr = (void *)skb->data;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 	u8 *bssid = ieee80211_get_bssid(hdr, skb->len, sdata->vif.type);
-	bool multicast = is_multicast_ether_addr(hdr->addr1);
+	bool multicast = is_multicast_ether_addr(hdr->addr1) ||
+			 ieee80211_is_s1g_beacon(hdr->frame_control);
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_STATION:
@@ -4095,10 +4069,6 @@ static bool ieee80211_accept_frame(struct ieee80211_rx_data *rx)
 			return false;
 
 		return true;
-	case NL80211_IFTYPE_WDS:
-		if (bssid || !ieee80211_is_data(hdr->frame_control))
-			return false;
-		return ether_addr_equal(sdata->u.wds.remote_addr, hdr->addr2);
 	case NL80211_IFTYPE_P2P_DEVICE:
 		return ieee80211_is_public_action(hdr, skb->len) ||
 		       ieee80211_is_probe_req(hdr->frame_control) ||
@@ -4149,7 +4119,6 @@ void ieee80211_check_fast_rx(struct sta_info *sta)
 			fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr2);
 			fastrx.expected_ds_bits = 0;
 		} else {
-			fastrx.sta_notify = sdata->u.mgd.probe_send_count > 0;
 			fastrx.da_offs = offsetof(struct ieee80211_hdr, addr1);
 			fastrx.sa_offs = offsetof(struct ieee80211_hdr, addr3);
 			fastrx.expected_ds_bits =
@@ -4207,6 +4176,8 @@ void ieee80211_check_fast_rx(struct sta_info *sta)
 
 	rcu_read_lock();
 	key = rcu_dereference(sta->ptk[sta->ptk_idx]);
+	if (!key)
+		key = rcu_dereference(sdata->default_unicast_key);
 	if (key) {
 		switch (key->conf.cipher) {
 		case WLAN_CIPHER_SUITE_TKIP:
@@ -4379,11 +4350,6 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
 	    pskb_trim(skb, skb->len - fast_rx->icv_len))
 		goto drop;
 
-	if (unlikely(fast_rx->sta_notify)) {
-		ieee80211_sta_rx_notify(rx->sdata, hdr);
-		fast_rx->sta_notify = false;
-	}
-
 	/* statistics part of ieee80211_rx_h_sta_process() */
 	if (!(status->flag & RX_FLAG_NO_SIGNAL_VAL)) {
 		stats->last_signal = status->signal;
@@ -4437,7 +4403,7 @@ static bool ieee80211_invoke_fast_rx(struct ieee80211_rx_data *rx,
 
 	skb->dev = fast_rx->dev;
 
-	ieee80211_rx_stats(fast_rx->dev, skb->len);
+	dev_sw_netstats_rx_add(fast_rx->dev, skb->len);
 
 	/* The seqno index has the same property as needed
 	 * for the rx_msdu field, i.e. it is IEEE80211_NUM_TIDS
@@ -4587,7 +4553,8 @@ static void __ieee80211_rx_handle_packet(struct ieee80211_hw *hw,
 	ieee80211_verify_alignment(&rx);
 
 	if (unlikely(ieee80211_is_probe_resp(hdr->frame_control) ||
-		     ieee80211_is_beacon(hdr->frame_control)))
+		     ieee80211_is_beacon(hdr->frame_control) ||
+		     ieee80211_is_s1g_beacon(hdr->frame_control)))
 		ieee80211_scan_rx(local, skb);
 
 	if (ieee80211_is_data(fc)) {
@@ -4762,6 +4729,8 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 
 	status->rx_flags = 0;
 
+	kcov_remote_start_common(skb_get_kcov_handle(skb));
+
 	/*
 	 * Frames with failed FCS/PLCP checksum are not returned,
 	 * all other frames are returned without radiotap header
@@ -4769,15 +4738,15 @@ void ieee80211_rx_list(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 	 * Also, frames with less than 16 bytes are dropped.
 	 */
 	skb = ieee80211_rx_monitor(local, skb, rate);
-	if (!skb)
-		return;
-
-	ieee80211_tpt_led_trig_rx(local,
-			((struct ieee80211_hdr *)skb->data)->frame_control,
-			skb->len);
+	if (skb) {
+		ieee80211_tpt_led_trig_rx(local,
+					  ((struct ieee80211_hdr *)skb->data)->frame_control,
+					  skb->len);
 
-	__ieee80211_rx_handle_packet(hw, pubsta, skb, list);
+		__ieee80211_rx_handle_packet(hw, pubsta, skb, list);
+	}
 
+	kcov_remote_stop();
 	return;
  drop:
 	kfree_skb(skb);
diff --git a/net/mac80211/s1g.c b/net/mac80211/s1g.c
new file mode 100644
index 000000000000..c33f332b049a
--- /dev/null
+++ b/net/mac80211/s1g.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * S1G handling
+ * Copyright(c) 2020 Adapt-IP
+ */
+#include <linux/ieee80211.h>
+#include <net/mac80211.h>
+#include "ieee80211_i.h"
+
+void ieee80211_s1g_sta_rate_init(struct sta_info *sta)
+{
+	/* avoid indicating legacy bitrates for S1G STAs */
+	sta->tx_stats.last_rate.flags |= IEEE80211_TX_RC_S1G_MCS;
+	sta->rx_stats.last_rate =
+			STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_S1G);
+}
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 5ac2785cdc7b..d4cc9ac2d703 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright 2016-2017  Intel Deutschland GmbH
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 
 #include <linux/if_arp.h>
@@ -146,7 +146,8 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 			  struct ieee80211_mgmt *mgmt, size_t len,
 			  struct ieee80211_channel *channel)
 {
-	bool beacon = ieee80211_is_beacon(mgmt->frame_control);
+	bool beacon = ieee80211_is_beacon(mgmt->frame_control) ||
+		      ieee80211_is_s1g_beacon(mgmt->frame_control);
 	struct cfg80211_bss *cbss, *non_tx_cbss;
 	struct ieee80211_bss *bss, *non_tx_bss;
 	struct cfg80211_inform_bss bss_meta = {
@@ -195,6 +196,11 @@ ieee80211_bss_info_update(struct ieee80211_local *local,
 		elements = mgmt->u.probe_resp.variable;
 		baselen = offsetof(struct ieee80211_mgmt,
 				   u.probe_resp.variable);
+	} else if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		struct ieee80211_ext *ext = (void *) mgmt;
+
+		baselen = offsetof(struct ieee80211_ext, u.s1g_beacon.variable);
+		elements = ext->u.s1g_beacon.variable;
 	} else {
 		baselen = offsetof(struct ieee80211_mgmt, u.beacon.variable);
 		elements = mgmt->u.beacon.variable;
@@ -246,9 +252,12 @@ void ieee80211_scan_rx(struct ieee80211_local *local, struct sk_buff *skb)
 	struct ieee80211_bss *bss;
 	struct ieee80211_channel *channel;
 
-	if (skb->len < 24 ||
-	    (!ieee80211_is_probe_resp(mgmt->frame_control) &&
-	     !ieee80211_is_beacon(mgmt->frame_control)))
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		if (skb->len < 15)
+			return;
+	} else if (skb->len < 24 ||
+		 (!ieee80211_is_probe_resp(mgmt->frame_control) &&
+		  !ieee80211_is_beacon(mgmt->frame_control)))
 		return;
 
 	sdata1 = rcu_dereference(local->scan_sdata);
@@ -712,6 +721,10 @@ static int __ieee80211_start_scan(struct ieee80211_sub_if_data *sdata,
 			req->duration_mandatory;
 
 		local->hw_scan_band = 0;
+		local->hw_scan_req->req.n_6ghz_params = req->n_6ghz_params;
+		local->hw_scan_req->req.scan_6ghz_params =
+			req->scan_6ghz_params;
+		local->hw_scan_req->req.scan_6ghz = req->scan_6ghz;
 
 		/*
 		 * After allocating local->hw_scan_req, we must
@@ -905,6 +918,17 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
 	local->scan_chandef.center_freq1 = chan->center_freq;
 	local->scan_chandef.freq1_offset = chan->freq_offset;
 	local->scan_chandef.center_freq2 = 0;
+
+	/* For scanning on the S1G band, ignore scan_width (which is constant
+	 * across all channels) for now since channel width is specific to each
+	 * channel. Detect the required channel width here and likely revisit
+	 * later. Maybe scan_width could be used to build the channel scan list?
+	 */
+	if (chan->band == NL80211_BAND_S1GHZ) {
+		local->scan_chandef.width = ieee80211_s1g_channel_width(chan);
+		goto set_channel;
+	}
+
 	switch (scan_req->scan_width) {
 	case NL80211_BSS_CHAN_WIDTH_5:
 		local->scan_chandef.width = NL80211_CHAN_WIDTH_5;
@@ -925,8 +949,14 @@ static void ieee80211_scan_state_set_channel(struct ieee80211_local *local,
 		else
 			local->scan_chandef.width = NL80211_CHAN_WIDTH_20_NOHT;
 		break;
+	case NL80211_BSS_CHAN_WIDTH_1:
+	case NL80211_BSS_CHAN_WIDTH_2:
+		/* shouldn't get here, S1G handled above */
+		WARN_ON(1);
+		break;
 	}
 
+set_channel:
 	if (ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL))
 		skip = 1;
 
@@ -1124,7 +1154,8 @@ int ieee80211_request_ibss_scan(struct ieee80211_sub_if_data *sdata,
 		int max_n;
 
 		for (band = 0; band < NUM_NL80211_BANDS; band++) {
-			if (!local->hw.wiphy->bands[band])
+			if (!local->hw.wiphy->bands[band] ||
+			    band == NL80211_BAND_6GHZ)
 				continue;
 
 			max_n = local->hw.wiphy->bands[band]->n_channels;
diff --git a/net/mac80211/spectmgmt.c b/net/mac80211/spectmgmt.c
index ae1cb2c68722..76747bfdaddd 100644
--- a/net/mac80211/spectmgmt.c
+++ b/net/mac80211/spectmgmt.c
@@ -133,16 +133,20 @@ int ieee80211_parse_ch_switch_ie(struct ieee80211_sub_if_data *sdata,
 	}
 
 	if (wide_bw_chansw_ie) {
+		u8 new_seg1 = wide_bw_chansw_ie->new_center_freq_seg1;
 		struct ieee80211_vht_operation vht_oper = {
 			.chan_width =
 				wide_bw_chansw_ie->new_channel_width,
 			.center_freq_seg0_idx =
 				wide_bw_chansw_ie->new_center_freq_seg0,
-			.center_freq_seg1_idx =
-				wide_bw_chansw_ie->new_center_freq_seg1,
+			.center_freq_seg1_idx = new_seg1,
 			/* .basic_mcs_set doesn't matter */
 		};
-		struct ieee80211_ht_operation ht_oper = {};
+		struct ieee80211_ht_operation ht_oper = {
+			.operation_mode =
+				cpu_to_le16(new_seg1 <<
+					    IEEE80211_HT_OP_MODE_CCFS2_SHIFT),
+		};
 
 		/* default, for the case of IEEE80211_VHT_CHANWIDTH_USE_HT,
 		 * to the previously parsed chandef
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index f2840d1d95cf..ec6973ee88ef 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -258,6 +258,24 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
  */
 void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 {
+	/*
+	 * If we had used sta_info_pre_move_state() then we might not
+	 * have gone through the state transitions down again, so do
+	 * it here now (and warn if it's inserted).
+	 *
+	 * This will clear state such as fast TX/RX that may have been
+	 * allocated during state transitions.
+	 */
+	while (sta->sta_state > IEEE80211_STA_NONE) {
+		int ret;
+
+		WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED));
+
+		ret = sta_info_move_state(sta, sta->sta_state - 1);
+		if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret))
+			break;
+	}
+
 	if (sta->rate_ctrl)
 		rate_control_free_sta(sta);
 
@@ -687,7 +705,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU)
  out_drop_sta:
 	local->num_sta--;
 	synchronize_net();
-	__cleanup_single_sta(sta);
+	cleanup_single_sta(sta);
  out_err:
 	mutex_unlock(&local->sta_mtx);
 	kfree(sinfo);
@@ -706,19 +724,13 @@ int sta_info_insert_rcu(struct sta_info *sta) __acquires(RCU)
 
 	err = sta_info_insert_check(sta);
 	if (err) {
+		sta_info_free(local, sta);
 		mutex_unlock(&local->sta_mtx);
 		rcu_read_lock();
-		goto out_free;
+		return err;
 	}
 
-	err = sta_info_insert_finish(sta);
-	if (err)
-		goto out_free;
-
-	return 0;
- out_free:
-	sta_info_free(local, sta);
-	return err;
+	return sta_info_insert_finish(sta);
 }
 
 int sta_info_insert(struct sta_info *sta)
@@ -2122,6 +2134,10 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate,
 		int rate_idx = STA_STATS_GET(LEGACY_IDX, rate);
 
 		sband = local->hw.wiphy->bands[band];
+
+		if (WARN_ON_ONCE(!sband->bitrates))
+			break;
+
 		brate = sband->bitrates[rate_idx].bitrate;
 		if (rinfo->bw == RATE_INFO_BW_5)
 			shift = 2;
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index d5010116cf4d..7afd07636b81 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -336,7 +336,6 @@ struct ieee80211_fast_tx {
  * @expected_ds_bits: from/to DS bits expected
  * @icv_len: length of the MIC if present
  * @key: bool indicating encryption is expected (key is set)
- * @sta_notify: notify the MLME code (once)
  * @internal_forward: forward froms internally on AP/VLAN type interfaces
  * @uses_rss: copy of USES_RSS hw flag
  * @da_offs: offset of the DA in the header (for header conversion)
@@ -352,7 +351,6 @@ struct ieee80211_fast_rx {
 	__le16 expected_ds_bits;
 	u8 icv_len;
 	u8 key:1,
-	   sta_notify:1,
 	   internal_forward:1,
 	   uses_rss:1;
 	u8 da_offs, sa_offs;
@@ -787,7 +785,7 @@ int sta_info_init(struct ieee80211_local *local);
 void sta_info_stop(struct ieee80211_local *local);
 
 /**
- * sta_info_flush - flush matching STA entries from the STA table
+ * __sta_info_flush - flush matching STA entries from the STA table
  *
  * Returns the number of removed STA entries.
  *
@@ -796,6 +794,13 @@ void sta_info_stop(struct ieee80211_local *local);
  */
 int __sta_info_flush(struct ieee80211_sub_if_data *sdata, bool vlans);
 
+/**
+ * sta_info_flush - flush matching STA entries from the STA table
+ *
+ * Returns the number of removed STA entries.
+ *
+ * @sdata: sdata to remove all stations from
+ */
 static inline int sta_info_flush(struct ieee80211_sub_if_data *sdata)
 {
 	return __sta_info_flush(sdata, false);
@@ -825,6 +830,7 @@ enum sta_stats_type {
 	STA_STATS_RATE_TYPE_HT,
 	STA_STATS_RATE_TYPE_VHT,
 	STA_STATS_RATE_TYPE_HE,
+	STA_STATS_RATE_TYPE_S1G,
 };
 
 #define STA_STATS_FIELD_HT_MCS		GENMASK( 7,  0)
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 0794396a7988..3485610755ef 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -49,7 +49,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local,
 	int ac;
 
 	if (info->flags & (IEEE80211_TX_CTL_NO_PS_BUFFER |
-			   IEEE80211_TX_CTL_AMPDU)) {
+			   IEEE80211_TX_CTL_AMPDU |
+			   IEEE80211_TX_CTL_HW_80211_ENCAP)) {
 		ieee80211_free_txskb(&local->hw, skb);
 		return;
 	}
@@ -66,8 +67,8 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local,
 
 	info->control.jiffies = jiffies;
 	info->control.vif = &sta->sdata->vif;
-	info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING |
-		       IEEE80211_TX_INTFL_RETRANSMISSION;
+	info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
+	info->flags |= IEEE80211_TX_INTFL_RETRANSMISSION;
 	info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 
 	sta->status_stats.filtered++;
@@ -184,18 +185,6 @@ static void ieee80211_frame_acked(struct sta_info *sta, struct sk_buff *skb)
 	struct ieee80211_mgmt *mgmt = (void *) skb->data;
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
-	struct ieee80211_tx_info *txinfo = IEEE80211_SKB_CB(skb);
-
-	if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) {
-		sta->status_stats.last_ack = jiffies;
-		if (txinfo->status.is_valid_ack_signal) {
-			sta->status_stats.last_ack_signal =
-					 (s8)txinfo->status.ack_signal;
-			sta->status_stats.ack_signal_filled = true;
-			ewma_avg_signal_add(&sta->status_stats.avg_ack_signal,
-					    -txinfo->status.ack_signal);
-		}
-	}
 
 	if (ieee80211_is_data_qos(mgmt->frame_control)) {
 		struct ieee80211_hdr *hdr = (void *) skb->data;
@@ -890,7 +879,8 @@ void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
 }
 
 static void __ieee80211_tx_status(struct ieee80211_hw *hw,
-				  struct ieee80211_tx_status *status)
+				  struct ieee80211_tx_status *status,
+				  int rates_idx, int retry_count)
 {
 	struct sk_buff *skb = status->skb;
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
@@ -899,17 +889,12 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 	struct sta_info *sta;
 	__le16 fc;
 	struct ieee80211_supported_band *sband;
-	int retry_count;
-	int rates_idx;
 	bool send_to_cooked;
 	bool acked;
 	bool noack_success;
 	struct ieee80211_bar *bar;
 	int shift = 0;
 	int tid = IEEE80211_NUM_TIDS;
-	u16 tx_time_est;
-
-	rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
 
 	sband = local->hw.wiphy->bands[info->band];
 	fc = hdr->frame_control;
@@ -931,15 +916,6 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 			ieee80211_mpsp_trigger_process(
 				ieee80211_get_qos_ctl(hdr), sta, true, acked);
 
-		if (!acked && test_sta_flag(sta, WLAN_STA_PS_STA)) {
-			/*
-			 * The STA is in power save mode, so assume
-			 * that this TX packet failed because of that.
-			 */
-			ieee80211_handle_filtered_frame(local, sta, skb);
-			return;
-		}
-
 		if (ieee80211_hw_check(&local->hw, HAS_RATE_CONTROL) &&
 		    (ieee80211_is_data(hdr->frame_control)) &&
 		    (rates_idx != -1))
@@ -987,62 +963,17 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 		if (info->flags & IEEE80211_TX_STAT_TX_FILTERED) {
 			ieee80211_handle_filtered_frame(local, sta, skb);
 			return;
-		} else {
+		} else if (ieee80211_is_data_present(fc)) {
 			if (!acked && !noack_success)
-				sta->status_stats.retry_failed++;
-			sta->status_stats.retry_count += retry_count;
+				sta->status_stats.msdu_failed[tid]++;
 
-			if (ieee80211_is_data_present(fc)) {
-				if (!acked && !noack_success)
-					sta->status_stats.msdu_failed[tid]++;
-
-				sta->status_stats.msdu_retries[tid] +=
-					retry_count;
-			}
+			sta->status_stats.msdu_retries[tid] +=
+				retry_count;
 		}
 
-		rate_control_tx_status(local, sband, status);
-		if (ieee80211_vif_is_mesh(&sta->sdata->vif))
-			ieee80211s_update_metric(local, sta, status);
-
 		if (!(info->flags & IEEE80211_TX_CTL_INJECTED) && acked)
 			ieee80211_frame_acked(sta, skb);
 
-		if ((sta->sdata->vif.type == NL80211_IFTYPE_STATION) &&
-		    ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS))
-			ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data,
-						acked, info->status.tx_time);
-
-		if (info->status.tx_time &&
-		    wiphy_ext_feature_isset(local->hw.wiphy,
-					    NL80211_EXT_FEATURE_AIRTIME_FAIRNESS))
-			ieee80211_sta_register_airtime(&sta->sta, tid,
-						       info->status.tx_time, 0);
-
-		if ((tx_time_est = ieee80211_info_get_tx_time_est(info)) > 0) {
-			/* Do this here to avoid the expensive lookup of the sta
-			 * in ieee80211_report_used_skb().
-			 */
-			ieee80211_sta_update_pending_airtime(local, sta,
-							     skb_get_queue_mapping(skb),
-							     tx_time_est,
-							     true);
-			ieee80211_info_set_tx_time_est(info, 0);
-		}
-
-		if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) {
-			if (acked) {
-				if (sta->status_stats.lost_packets)
-					sta->status_stats.lost_packets = 0;
-
-				/* Track when last TDLS packet was ACKed */
-				sta->status_stats.last_pkt_time = jiffies;
-			} else if (noack_success) {
-				/* nothing to do here, do not account as lost */
-			} else {
-				ieee80211_lost_packet(sta, info);
-			}
-		}
 	}
 
 	/* SNMP counters
@@ -1101,7 +1032,10 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 	 * with this test...
 	 */
 	if (!local->monitors && (!send_to_cooked || !local->cooked_mntrs)) {
-		dev_kfree_skb(skb);
+		if (status->free_list)
+			list_add_tail(&skb->list, status->free_list);
+		else
+			dev_kfree_skb(skb);
 		return;
 	}
 
@@ -1126,7 +1060,7 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 	if (sta)
 		status.sta = &sta->sta;
 
-	__ieee80211_tx_status(hw, &status);
+	ieee80211_tx_status_ext(hw, &status);
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL(ieee80211_tx_status);
@@ -1137,10 +1071,12 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 	struct ieee80211_local *local = hw_to_local(hw);
 	struct ieee80211_tx_info *info = status->info;
 	struct ieee80211_sta *pubsta = status->sta;
+	struct sk_buff *skb = status->skb;
 	struct ieee80211_supported_band *sband;
-	struct sta_info *sta;
-	int retry_count;
+	struct sta_info *sta = NULL;
+	int rates_idx, retry_count;
 	bool acked, noack_success;
+	u16 tx_time_est;
 
 	if (pubsta) {
 		sta = container_of(pubsta, struct sta_info, sta);
@@ -1149,13 +1085,22 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 			sta->tx_stats.last_rate_info = *status->rate;
 	}
 
-	if (status->skb)
-		return __ieee80211_tx_status(hw, status);
+	if (skb && (tx_time_est =
+		    ieee80211_info_get_tx_time_est(IEEE80211_SKB_CB(skb))) > 0) {
+		/* Do this here to avoid the expensive lookup of the sta
+		 * in ieee80211_report_used_skb().
+		 */
+		ieee80211_sta_update_pending_airtime(local, sta,
+						     skb_get_queue_mapping(skb),
+						     tx_time_est,
+						     true);
+		ieee80211_info_set_tx_time_est(IEEE80211_SKB_CB(skb), 0);
+	}
 
-	if (!status->sta)
-		return;
+	if (!status->info)
+		goto free;
 
-	ieee80211_tx_get_rates(hw, info, &retry_count);
+	rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
 
 	sband = hw->wiphy->bands[info->band];
 
@@ -1163,24 +1108,52 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 	noack_success = !!(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED);
 
 	if (pubsta) {
+		struct ieee80211_sub_if_data *sdata = sta->sdata;
+
 		if (!acked && !noack_success)
 			sta->status_stats.retry_failed++;
 		sta->status_stats.retry_count += retry_count;
 
-		if (acked) {
-			sta->status_stats.last_ack = jiffies;
+		if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) {
+			if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+			    skb && !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP))
+				ieee80211_sta_tx_notify(sdata, (void *) skb->data,
+							acked, info->status.tx_time);
 
-			if (sta->status_stats.lost_packets)
-				sta->status_stats.lost_packets = 0;
+			if (acked) {
+				sta->status_stats.last_ack = jiffies;
 
-			/* Track when last packet was ACKed */
-			sta->status_stats.last_pkt_time = jiffies;
-		} else if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
-			return;
-		} else if (noack_success) {
-			/* nothing to do here, do not account as lost */
-		} else {
-			ieee80211_lost_packet(sta, info);
+				if (sta->status_stats.lost_packets)
+					sta->status_stats.lost_packets = 0;
+
+				/* Track when last packet was ACKed */
+				sta->status_stats.last_pkt_time = jiffies;
+
+				/* Reset connection monitor */
+				if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+				    unlikely(sdata->u.mgd.probe_send_count > 0))
+					sdata->u.mgd.probe_send_count = 0;
+
+				if (info->status.is_valid_ack_signal) {
+					sta->status_stats.last_ack_signal =
+							 (s8)info->status.ack_signal;
+					sta->status_stats.ack_signal_filled = true;
+					ewma_avg_signal_add(&sta->status_stats.avg_ack_signal,
+							    -info->status.ack_signal);
+				}
+			} else if (test_sta_flag(sta, WLAN_STA_PS_STA)) {
+				/*
+				 * The STA is in power save mode, so assume
+				 * that this TX packet failed because of that.
+				 */
+				if (skb)
+					ieee80211_handle_filtered_frame(local, sta, skb);
+				return;
+			} else if (noack_success) {
+				/* nothing to do here, do not account as lost */
+			} else {
+				ieee80211_lost_packet(sta, info);
+			}
 		}
 
 		rate_control_tx_status(local, sband, status);
@@ -1188,6 +1161,10 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 			ieee80211s_update_metric(local, sta, status);
 	}
 
+	if (skb && !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP))
+		return __ieee80211_tx_status(hw, status, rates_idx,
+					     retry_count);
+
 	if (acked || noack_success) {
 		I802_DEBUG_INC(local->dot11TransmittedFrameCount);
 		if (!pubsta)
@@ -1199,6 +1176,16 @@ void ieee80211_tx_status_ext(struct ieee80211_hw *hw,
 	} else {
 		I802_DEBUG_INC(local->dot11FailedCount);
 	}
+
+free:
+	if (!skb)
+		return;
+
+	ieee80211_report_used_skb(local, skb, false);
+	if (status->free_list)
+		list_add_tail(&skb->list, status->free_list);
+	else
+		dev_kfree_skb(skb);
 }
 EXPORT_SYMBOL(ieee80211_tx_status_ext);
 
@@ -1225,69 +1212,23 @@ void ieee80211_tx_status_8023(struct ieee80211_hw *hw,
 			      struct ieee80211_vif *vif,
 			      struct sk_buff *skb)
 {
-	struct ieee80211_local *local = hw_to_local(hw);
 	struct ieee80211_sub_if_data *sdata;
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_status status = {
+		.skb = skb,
+		.info = IEEE80211_SKB_CB(skb),
+	};
 	struct sta_info *sta;
-	int retry_count;
-	int rates_idx;
-	bool acked;
 
 	sdata = vif_to_sdata(vif);
 
-	acked = info->flags & IEEE80211_TX_STAT_ACK;
-	rates_idx = ieee80211_tx_get_rates(hw, info, &retry_count);
-
 	rcu_read_lock();
 
-	if (ieee80211_lookup_ra_sta(sdata, skb, &sta))
-		goto counters_update;
-
-	if (IS_ERR(sta))
-		goto counters_update;
-
-	if (!acked)
-		sta->status_stats.retry_failed++;
-
-	if (rates_idx != -1)
-		sta->tx_stats.last_rate = info->status.rates[rates_idx];
-
-	sta->status_stats.retry_count += retry_count;
-
-	if (ieee80211_hw_check(hw, REPORTS_TX_ACK_STATUS)) {
-		if (acked && vif->type == NL80211_IFTYPE_STATION)
-			ieee80211_sta_reset_conn_monitor(sdata);
-
-		sta->status_stats.last_ack = jiffies;
-		if (info->flags & IEEE80211_TX_STAT_ACK) {
-			if (sta->status_stats.lost_packets)
-				sta->status_stats.lost_packets = 0;
+	if (!ieee80211_lookup_ra_sta(sdata, skb, &sta) && !IS_ERR(sta))
+		status.sta = &sta->sta;
 
-			sta->status_stats.last_pkt_time = jiffies;
-		} else {
-			ieee80211_lost_packet(sta, info);
-		}
-	}
+	ieee80211_tx_status_ext(hw, &status);
 
-counters_update:
 	rcu_read_unlock();
-	ieee80211_led_tx(local);
-
-	if (!(info->flags & IEEE80211_TX_STAT_ACK) &&
-	    !(info->flags & IEEE80211_TX_STAT_NOACK_TRANSMITTED))
-		goto skip_stats_update;
-
-	I802_DEBUG_INC(local->dot11TransmittedFrameCount);
-	if (is_multicast_ether_addr(skb->data))
-		I802_DEBUG_INC(local->dot11MulticastTransmittedFrameCount);
-	if (retry_count > 0)
-		I802_DEBUG_INC(local->dot11RetryCount);
-	if (retry_count > 1)
-		I802_DEBUG_INC(local->dot11MultipleRetryCount);
-
-skip_stats_update:
-	ieee80211_report_used_skb(local, skb, false);
-	dev_kfree_skb(skb);
 }
 EXPORT_SYMBOL(ieee80211_tx_status_8023);
 
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 50ab5b9d8eab..601322e16957 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -2,7 +2,7 @@
 /*
 * Portions of this file
 * Copyright(c) 2016-2017 Intel Deutschland GmbH
-* Copyright (C) 2018 - 2019 Intel Corporation
+* Copyright (C) 2018 - 2020 Intel Corporation
 */
 
 #if !defined(__MAC80211_DRIVER_TRACE) || defined(TRACE_HEADER_MULTI_READ)
@@ -2086,6 +2086,27 @@ TRACE_EVENT(api_connection_loss,
 	)
 );
 
+TRACE_EVENT(api_disconnect,
+	TP_PROTO(struct ieee80211_sub_if_data *sdata, bool reconnect),
+
+	TP_ARGS(sdata, reconnect),
+
+	TP_STRUCT__entry(
+		VIF_ENTRY
+		__field(int, reconnect)
+	),
+
+	TP_fast_assign(
+		VIF_ASSIGN;
+		__entry->reconnect = reconnect;
+	),
+
+	TP_printk(
+		VIF_PR_FMT " reconnect:%d",
+		VIF_PR_ARG, __entry->reconnect
+	)
+);
+
 TRACE_EVENT(api_cqm_rssi_notify,
 	TP_PROTO(struct ieee80211_sub_if_data *sdata,
 		 enum nl80211_cqm_rssi_threshold_event rssi_event,
@@ -2734,6 +2755,39 @@ TRACE_EVENT(drv_get_ftm_responder_stats,
 	)
 );
 
+DEFINE_EVENT(local_sdata_addr_evt, drv_update_vif_offload,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata),
+	TP_ARGS(local, sdata)
+);
+
+TRACE_EVENT(drv_sta_set_4addr,
+	TP_PROTO(struct ieee80211_local *local,
+		 struct ieee80211_sub_if_data *sdata,
+		 struct ieee80211_sta *sta, bool enabled),
+
+	TP_ARGS(local, sdata, sta, enabled),
+
+	TP_STRUCT__entry(
+		LOCAL_ENTRY
+		VIF_ENTRY
+		STA_ENTRY
+		__field(bool, enabled)
+	),
+
+	TP_fast_assign(
+		LOCAL_ASSIGN;
+		VIF_ASSIGN;
+		STA_ASSIGN;
+		__entry->enabled = enabled;
+	),
+
+	TP_printk(
+		LOCAL_PR_FMT  VIF_PR_FMT  STA_PR_FMT " enabled:%d",
+		LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->enabled
+	)
+);
+
 #endif /* !__MAC80211_DRIVER_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index dca01d7e6e3e..ebb3228ce971 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -38,16 +38,6 @@
 
 /* misc utils */
 
-static inline void ieee80211_tx_stats(struct net_device *dev, u32 len)
-{
-	struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
-
-	u64_stats_update_begin(&tstats->syncp);
-	tstats->tx_packets++;
-	tstats->tx_bytes += len;
-	u64_stats_update_end(&tstats->syncp);
-}
-
 static __le16 ieee80211_duration(struct ieee80211_tx_data *tx,
 				 struct sk_buff *skb, int group_addr,
 				 int next_frag_len)
@@ -82,6 +72,10 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx,
 
 	erp = txrate->flags & IEEE80211_RATE_ERP_G;
 
+	/* device is expected to do this */
+	if (sband->band == NL80211_BAND_S1GHZ)
+		return 0;
+
 	/*
 	 * data and mgmt (except PS Poll):
 	 * - during CFP: 32768
@@ -315,9 +309,6 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx)
 	if (tx->sdata->vif.type == NL80211_IFTYPE_OCB)
 		return TX_CONTINUE;
 
-	if (tx->sdata->vif.type == NL80211_IFTYPE_WDS)
-		return TX_CONTINUE;
-
 	if (tx->flags & IEEE80211_TX_PS_BUFFERED)
 		return TX_CONTINUE;
 
@@ -531,7 +522,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 
 		info->control.jiffies = jiffies;
 		info->control.vif = &tx->sdata->vif;
-		info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+		info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 		info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 		skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
 		spin_unlock(&sta->ps_lock);
@@ -658,7 +649,7 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 		if (!skip_hw && tx->key &&
 		    tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE)
 			info->control.hw_key = &tx->key->conf;
-	} else if (!ieee80211_is_mgmt(hdr->frame_control) && tx->sta &&
+	} else if (ieee80211_is_data_present(hdr->frame_control) && tx->sta &&
 		   test_sta_flag(tx->sta, WLAN_STA_USES_ENCRYPTION)) {
 		return TX_DROP;
 	}
@@ -1134,7 +1125,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
 				       tx->sta->sta.addr, tx->sta->sta.aid);
 			}
 			info->control.vif = &tx->sdata->vif;
-			info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+			info->control.flags |= IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 			info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 			__skb_queue_tail(&tid_tx->pending, skb);
 			if (skb_queue_len(&tid_tx->pending) > STA_MAX_TX_BUFFER)
@@ -1179,7 +1170,7 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 	 * we are doing the needed processing, so remove the flag
 	 * now.
 	 */
-	info->flags &= ~IEEE80211_TX_INTFL_NEED_TXPROCESSING;
+	info->control.flags &= ~IEEE80211_TX_INTCFL_NEED_TXPROCESSING;
 
 	hdr = (struct ieee80211_hdr *) skb->data;
 
@@ -1258,7 +1249,7 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
 	    (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
 		return NULL;
 
-	if (!(info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) &&
+	if (!(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) &&
 	    unlikely(!ieee80211_is_data_present(hdr->frame_control))) {
 		if ((!ieee80211_is_mgmt(hdr->frame_control) ||
 		     ieee80211_is_bufferable_mmpdu(hdr->frame_control) ||
@@ -1938,19 +1929,24 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 
 /* device xmit handlers */
 
+enum ieee80211_encrypt {
+	ENCRYPT_NO,
+	ENCRYPT_MGMT,
+	ENCRYPT_DATA,
+};
+
 static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
 				struct sk_buff *skb,
-				int head_need, bool may_encrypt)
+				int head_need,
+				enum ieee80211_encrypt encrypt)
 {
 	struct ieee80211_local *local = sdata->local;
-	struct ieee80211_hdr *hdr;
 	bool enc_tailroom;
 	int tail_need = 0;
 
-	hdr = (struct ieee80211_hdr *) skb->data;
-	enc_tailroom = may_encrypt &&
-		       (sdata->crypto_tx_tailroom_needed_cnt ||
-			ieee80211_is_mgmt(hdr->frame_control));
+	enc_tailroom = encrypt == ENCRYPT_MGMT ||
+		       (encrypt == ENCRYPT_DATA &&
+			sdata->crypto_tx_tailroom_needed_cnt);
 
 	if (enc_tailroom) {
 		tail_need = IEEE80211_ENCRYPT_TAILROOM;
@@ -1981,23 +1977,29 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_hdr *hdr;
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
 	int headroom;
-	bool may_encrypt;
+	enum ieee80211_encrypt encrypt;
 
-	may_encrypt = !(info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT);
+	if (info->flags & IEEE80211_TX_INTFL_DONT_ENCRYPT)
+		encrypt = ENCRYPT_NO;
+	else if (ieee80211_is_mgmt(hdr->frame_control))
+		encrypt = ENCRYPT_MGMT;
+	else
+		encrypt = ENCRYPT_DATA;
 
 	headroom = local->tx_headroom;
-	if (may_encrypt)
+	if (encrypt != ENCRYPT_NO)
 		headroom += sdata->encrypt_headroom;
 	headroom -= skb_headroom(skb);
 	headroom = max_t(int, 0, headroom);
 
-	if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) {
+	if (ieee80211_skb_resize(sdata, skb, headroom, encrypt)) {
 		ieee80211_free_txskb(&local->hw, skb);
 		return;
 	}
 
+	/* reload after potential resize */
 	hdr = (struct ieee80211_hdr *) skb->data;
 	info->control.vif = &sdata->vif;
 
@@ -2098,6 +2100,9 @@ bool ieee80211_parse_tx_radiotap(struct sk_buff *skb,
 				info->flags |= IEEE80211_TX_CTL_NO_ACK;
 			if (txflags & IEEE80211_RADIOTAP_F_TX_NOSEQNO)
 				info->control.flags |= IEEE80211_TX_CTRL_NO_SEQNO;
+			if (txflags & IEEE80211_RADIOTAP_F_TX_ORDER)
+				info->control.flags |=
+					IEEE80211_TX_CTRL_DONT_REORDER;
 			break;
 
 		case IEEE80211_RADIOTAP_RATE:
@@ -2264,11 +2269,13 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 						    payload[7]);
 	}
 
-	/*
-	 * Initialize skb->priority for QoS frames. This is put in the TID field
-	 * of the frame before passing it to the driver.
+	/* Initialize skb->priority for QoS frames. If the DONT_REORDER flag
+	 * is set, stick to the default value for skb->priority to assure
+	 * frames injected with this flag are not reordered relative to each
+	 * other.
 	 */
-	if (ieee80211_is_data_qos(hdr->frame_control)) {
+	if (ieee80211_is_data_qos(hdr->frame_control) &&
+	    !(info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) {
 		u8 *p = ieee80211_get_qos_ctl(hdr);
 		skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK;
 	}
@@ -2280,8 +2287,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 	 * we handle as though they are non-injected frames.
 	 * This code here isn't entirely correct, the local MAC address
 	 * isn't always enough to find the interface to use; for proper
-	 * VLAN/WDS support we will need a different mechanism (which
-	 * likely isn't going to be monitor interfaces).
+	 * VLAN support we have an nl80211-based mechanism.
 	 *
 	 * This is necessary, for example, for old hostapd versions that
 	 * don't use nl80211-based management TX/RX.
@@ -2292,8 +2298,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 		if (!ieee80211_sdata_running(tmp_sdata))
 			continue;
 		if (tmp_sdata->vif.type == NL80211_IFTYPE_MONITOR ||
-		    tmp_sdata->vif.type == NL80211_IFTYPE_AP_VLAN ||
-		    tmp_sdata->vif.type == NL80211_IFTYPE_WDS)
+		    tmp_sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 			continue;
 		if (ether_addr_equal(tmp_sdata->vif.addr, hdr->addr2)) {
 			sdata = tmp_sdata;
@@ -2387,9 +2392,6 @@ int ieee80211_lookup_ra_sta(struct ieee80211_sub_if_data *sdata,
 		}
 		sta = sta_info_get_bss(sdata, skb->data);
 		break;
-	case NL80211_IFTYPE_WDS:
-		sta = sta_info_get(sdata, sdata->u.wds.remote_addr);
-		break;
 #ifdef CONFIG_MAC80211_MESH
 	case NL80211_IFTYPE_MESH_POINT:
 		/* determined much later */
@@ -2473,7 +2475,9 @@ static u16 ieee80211_store_ack_skb(struct ieee80211_local *local,
  * @sdata: virtual interface to build the header for
  * @skb: the skb to build the header in
  * @info_flags: skb flags to set
+ * @sta: the station pointer
  * @ctrl_flags: info control flags to set
+ * @cookie: cookie pointer to fill (if not %NULL)
  *
  * This function takes the skb with 802.3 header and reformats the header to
  * the appropriate IEEE 802.11 header based on which interface the packet is
@@ -2563,20 +2567,6 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 		hdrlen = 24;
 		band = chanctx_conf->def.chan->band;
 		break;
-	case NL80211_IFTYPE_WDS:
-		fc |= cpu_to_le16(IEEE80211_FCTL_FROMDS | IEEE80211_FCTL_TODS);
-		/* RA TA DA SA */
-		memcpy(hdr.addr1, sdata->u.wds.remote_addr, ETH_ALEN);
-		memcpy(hdr.addr2, sdata->vif.addr, ETH_ALEN);
-		memcpy(hdr.addr3, skb->data, ETH_ALEN);
-		memcpy(hdr.addr4, skb->data + ETH_ALEN, ETH_ALEN);
-		hdrlen = 30;
-		/*
-		 * This is the exception! WDS style interfaces are prohibited
-		 * when channel contexts are in used so this must be valid
-		 */
-		band = local->hw.conf.chandef.chan->band;
-		break;
 #ifdef CONFIG_MAC80211_MESH
 	case NL80211_IFTYPE_MESH_POINT:
 		if (!is_multicast_ether_addr(skb->data)) {
@@ -2822,7 +2812,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
 		head_need += sdata->encrypt_headroom;
 		head_need += local->tx_headroom;
 		head_need = max_t(int, 0, head_need);
-		if (ieee80211_skb_resize(sdata, skb, head_need, true)) {
+		if (ieee80211_skb_resize(sdata, skb, head_need, ENCRYPT_DATA)) {
 			ieee80211_free_txskb(&local->hw, skb);
 			skb = NULL;
 			return ERR_PTR(-ENOMEM);
@@ -3386,7 +3376,7 @@ static void ieee80211_xmit_fast_finish(struct ieee80211_sub_if_data *sdata,
 	if (key)
 		info->control.hw_key = &key->conf;
 
-	ieee80211_tx_stats(skb->dev, skb->len);
+	dev_sw_netstats_tx_add(skb->dev, 1, skb->len);
 
 	if (hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) {
 		tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
@@ -3496,7 +3486,7 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata,
 	if (unlikely(ieee80211_skb_resize(sdata, skb,
 					  max_t(int, extra_head + hw_headroom -
 						     skb_headroom(skb), 0),
-					  false))) {
+					  ENCRYPT_NO))) {
 		kfree_skb(skb);
 		return true;
 	}
@@ -3613,13 +3603,14 @@ begin:
 	tx.skb = skb;
 	tx.sdata = vif_to_sdata(info->control.vif);
 
-	if (txq->sta && !(info->flags & IEEE80211_TX_CTL_INJECTED)) {
+	if (txq->sta) {
 		tx.sta = container_of(txq->sta, struct sta_info, sta);
 		/*
 		 * Drop unicast frames to unauthorised stations unless they are
-		 * EAPOL frames from the local station.
+		 * injected frames or EAPOL frames from the local station.
 		 */
-		if (unlikely(ieee80211_is_data(hdr->frame_control) &&
+		if (unlikely(!(info->flags & IEEE80211_TX_CTL_INJECTED) &&
+			     ieee80211_is_data(hdr->frame_control) &&
 			     !ieee80211_vif_is_mesh(&tx.sdata->vif) &&
 			     tx.sdata->vif.type != NL80211_IFTYPE_OCB &&
 			     !is_multicast_ether_addr(hdr->addr1) &&
@@ -3649,7 +3640,7 @@ begin:
 	else
 		info->flags &= ~IEEE80211_TX_CTL_AMPDU;
 
-	if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP)
+	if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP)
 		goto encap_out;
 
 	if (info->control.flags & IEEE80211_TX_CTRL_FAST_XMIT) {
@@ -3818,7 +3809,7 @@ void __ieee80211_schedule_txq(struct ieee80211_hw *hw,
 		 * get immediately moved to the back of the list on the next
 		 * call to ieee80211_next_txq().
 		 */
-		if (txqi->txq.sta &&
+		if (txqi->txq.sta && local->airtime_flags &&
 		    wiphy_ext_feature_isset(local->hw.wiphy,
 					    NL80211_EXT_FEATURE_AIRTIME_FAIRNESS))
 			list_add(&txqi->schedule_order,
@@ -4003,7 +3994,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 			goto out;
 		}
 
-		ieee80211_tx_stats(dev, skb->len);
+		dev_sw_netstats_tx_add(dev, 1, skb->len);
 
 		ieee80211_xmit(sdata, sta, skb);
 	}
@@ -4190,38 +4181,18 @@ static bool ieee80211_tx_8023(struct ieee80211_sub_if_data *sdata,
 
 static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
 				struct net_device *dev, struct sta_info *sta,
-				struct sk_buff *skb)
+				struct ieee80211_key *key, struct sk_buff *skb)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ethhdr *ehdr = (struct ethhdr *)skb->data;
 	struct ieee80211_local *local = sdata->local;
-	bool authorized = false;
-	bool multicast;
-	unsigned char *ra = ehdr->h_dest;
-
-	if (IS_ERR(sta) || (sta && !sta->uploaded))
-		sta = NULL;
-
-	if (sdata->vif.type == NL80211_IFTYPE_STATION &&
-	    (!sta || !test_sta_flag(sta, WLAN_STA_TDLS_PEER)))
-		ra = sdata->u.mgd.bssid;
-
-	if (is_zero_ether_addr(ra))
-		goto out_free;
+	struct tid_ampdu_tx *tid_tx;
+	u8 tid;
 
-	multicast = is_multicast_ether_addr(ra);
-
-	if (sta)
-		authorized = test_sta_flag(sta, WLAN_STA_AUTHORIZED);
-
-	if (!multicast && !authorized &&
-	    (ehdr->h_proto != sdata->control_port_protocol ||
-	     !ether_addr_equal(sdata->vif.addr, ehdr->h_source)))
-		goto out_free;
-
-	if (multicast && sdata->vif.type == NL80211_IFTYPE_AP &&
-	    !atomic_read(&sdata->u.ap.num_mcast_sta))
-		goto out_free;
+	if (local->ops->wake_tx_queue) {
+		u16 queue = __ieee80211_select_queue(sdata, sta, skb);
+		skb_set_queue_mapping(skb, queue);
+		skb_get_hash(skb);
+	}
 
 	if (unlikely(test_bit(SCAN_SW_SCANNING, &local->scanning)) &&
 	    test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state))
@@ -4229,36 +4200,42 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata,
 
 	memset(info, 0, sizeof(*info));
 
-	if (unlikely(!multicast && skb->sk &&
-		     skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS))
-		info->ack_frame_id = ieee80211_store_ack_skb(local, skb,
-							     &info->flags, NULL);
+	tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
+	tid_tx = rcu_dereference(sta->ampdu_mlme.tid_tx[tid]);
+	if (tid_tx) {
+		if (!test_bit(HT_AGG_STATE_OPERATIONAL, &tid_tx->state)) {
+			/* fall back to non-offload slow path */
+			__ieee80211_subif_start_xmit(skb, dev, 0, 0, NULL);
+			return;
+		}
 
-	if (unlikely(sdata->control_port_protocol == ehdr->h_proto)) {
-		if (sdata->control_port_no_encrypt)
-			info->flags |= IEEE80211_TX_INTFL_DONT_ENCRYPT;
-		info->control.flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO;
+		info->flags |= IEEE80211_TX_CTL_AMPDU;
+		if (tid_tx->timeout)
+			tid_tx->last_tx = jiffies;
 	}
 
-	if (multicast)
-		info->flags |= IEEE80211_TX_CTL_NO_ACK;
+	if (unlikely(skb->sk &&
+		     skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS))
+		info->ack_frame_id = ieee80211_store_ack_skb(local, skb,
+							     &info->flags, NULL);
 
 	info->hw_queue = sdata->vif.hw_queue[skb_get_queue_mapping(skb)];
 
-	ieee80211_tx_stats(dev, skb->len);
+	dev_sw_netstats_tx_add(dev, 1, skb->len);
 
-	if (sta) {
-		sta->tx_stats.bytes[skb_get_queue_mapping(skb)] += skb->len;
-		sta->tx_stats.packets[skb_get_queue_mapping(skb)]++;
-	}
+	sta->tx_stats.bytes[skb_get_queue_mapping(skb)] += skb->len;
+	sta->tx_stats.packets[skb_get_queue_mapping(skb)]++;
 
 	if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
 		sdata = container_of(sdata->bss,
 				     struct ieee80211_sub_if_data, u.ap);
 
-	info->control.flags |= IEEE80211_TX_CTRL_HW_80211_ENCAP;
+	info->flags |= IEEE80211_TX_CTL_HW_80211_ENCAP;
 	info->control.vif = &sdata->vif;
 
+	if (key)
+		info->control.hw_key = &key->conf;
+
 	ieee80211_tx_8023(sdata, skb, skb->len, sta, false);
 
 	return;
@@ -4271,13 +4248,10 @@ netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb,
 					    struct net_device *dev)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+	struct ethhdr *ehdr = (struct ethhdr *)skb->data;
+	struct ieee80211_key *key;
 	struct sta_info *sta;
 
-	if (WARN_ON(!sdata->hw_80211_encap)) {
-		kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
 	if (unlikely(skb->len < ETH_HLEN)) {
 		kfree_skb(skb);
 		return NETDEV_TX_OK;
@@ -4285,11 +4259,30 @@ netdev_tx_t ieee80211_subif_start_xmit_8023(struct sk_buff *skb,
 
 	rcu_read_lock();
 
-	if (ieee80211_lookup_ra_sta(sdata, skb, &sta))
+	if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) {
 		kfree_skb(skb);
-	else
-		ieee80211_8023_xmit(sdata, dev, sta, skb);
+		goto out;
+	}
+
+	if (unlikely(IS_ERR_OR_NULL(sta) || !sta->uploaded ||
+	    !test_sta_flag(sta, WLAN_STA_AUTHORIZED) ||
+	    sdata->control_port_protocol == ehdr->h_proto))
+		goto skip_offload;
+
+	key = rcu_dereference(sta->ptk[sta->ptk_idx]);
+	if (!key)
+		key = rcu_dereference(sdata->default_unicast_key);
 
+	if (key && (!(key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) ||
+		    key->conf.cipher == WLAN_CIPHER_SUITE_TKIP))
+		goto skip_offload;
+
+	ieee80211_8023_xmit(sdata, dev, sta, key, skb);
+	goto out;
+
+skip_offload:
+	ieee80211_subif_start_xmit(skb, dev);
+out:
 	rcu_read_unlock();
 
 	return NETDEV_TX_OK;
@@ -4365,7 +4358,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 
 	sdata = vif_to_sdata(info->control.vif);
 
-	if (info->flags & IEEE80211_TX_INTFL_NEED_TXPROCESSING) {
+	if (info->control.flags & IEEE80211_TX_INTCFL_NEED_TXPROCESSING) {
 		chanctx_conf = rcu_dereference(sdata->vif.chanctx_conf);
 		if (unlikely(!chanctx_conf)) {
 			dev_kfree_skb(skb);
@@ -4373,7 +4366,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 		}
 		info->band = chanctx_conf->def.chan->band;
 		result = ieee80211_tx(sdata, NULL, skb, true);
-	} else if (info->control.flags & IEEE80211_TX_CTRL_HW_80211_ENCAP) {
+	} else if (info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) {
 		if (ieee80211_lookup_ra_sta(sdata, skb, &sta)) {
 			dev_kfree_skb(skb);
 			return true;
@@ -4401,9 +4394,10 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 /*
  * Transmit all pending packets. Called from tasklet.
  */
-void ieee80211_tx_pending(unsigned long data)
+void ieee80211_tx_pending(struct tasklet_struct *t)
 {
-	struct ieee80211_local *local = (struct ieee80211_local *)data;
+	struct ieee80211_local *local = from_tasklet(local, t,
+						     tx_pending_tasklet);
 	unsigned long flags;
 	int i;
 	bool txok;
@@ -4538,14 +4532,14 @@ static int ieee80211_beacon_add_tim(struct ieee80211_sub_if_data *sdata,
 	return 0;
 }
 
-static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata,
-			      struct beacon_data *beacon)
+static void ieee80211_set_beacon_cntdwn(struct ieee80211_sub_if_data *sdata,
+					struct beacon_data *beacon)
 {
 	struct probe_resp *resp;
 	u8 *beacon_data;
 	size_t beacon_data_len;
 	int i;
-	u8 count = beacon->csa_current_counter;
+	u8 count = beacon->cntdwn_current_counter;
 
 	switch (sdata->vif.type) {
 	case NL80211_IFTYPE_AP:
@@ -4565,36 +4559,36 @@ static void ieee80211_set_csa(struct ieee80211_sub_if_data *sdata,
 	}
 
 	rcu_read_lock();
-	for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; ++i) {
+	for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; ++i) {
 		resp = rcu_dereference(sdata->u.ap.probe_resp);
 
-		if (beacon->csa_counter_offsets[i]) {
-			if (WARN_ON_ONCE(beacon->csa_counter_offsets[i] >=
+		if (beacon->cntdwn_counter_offsets[i]) {
+			if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[i] >=
 					 beacon_data_len)) {
 				rcu_read_unlock();
 				return;
 			}
 
-			beacon_data[beacon->csa_counter_offsets[i]] = count;
+			beacon_data[beacon->cntdwn_counter_offsets[i]] = count;
 		}
 
 		if (sdata->vif.type == NL80211_IFTYPE_AP && resp)
-			resp->data[resp->csa_counter_offsets[i]] = count;
+			resp->data[resp->cntdwn_counter_offsets[i]] = count;
 	}
 	rcu_read_unlock();
 }
 
-static u8 __ieee80211_csa_update_counter(struct beacon_data *beacon)
+static u8 __ieee80211_beacon_update_cntdwn(struct beacon_data *beacon)
 {
-	beacon->csa_current_counter--;
+	beacon->cntdwn_current_counter--;
 
 	/* the counter should never reach 0 */
-	WARN_ON_ONCE(!beacon->csa_current_counter);
+	WARN_ON_ONCE(!beacon->cntdwn_current_counter);
 
-	return beacon->csa_current_counter;
+	return beacon->cntdwn_current_counter;
 }
 
-u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif)
+u8 ieee80211_beacon_update_cntdwn(struct ieee80211_vif *vif)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct beacon_data *beacon = NULL;
@@ -4612,15 +4606,15 @@ u8 ieee80211_csa_update_counter(struct ieee80211_vif *vif)
 	if (!beacon)
 		goto unlock;
 
-	count = __ieee80211_csa_update_counter(beacon);
+	count = __ieee80211_beacon_update_cntdwn(beacon);
 
 unlock:
 	rcu_read_unlock();
 	return count;
 }
-EXPORT_SYMBOL(ieee80211_csa_update_counter);
+EXPORT_SYMBOL(ieee80211_beacon_update_cntdwn);
 
-void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter)
+void ieee80211_beacon_set_cntdwn(struct ieee80211_vif *vif, u8 counter)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct beacon_data *beacon = NULL;
@@ -4637,15 +4631,15 @@ void ieee80211_csa_set_counter(struct ieee80211_vif *vif, u8 counter)
 	if (!beacon)
 		goto unlock;
 
-	if (counter < beacon->csa_current_counter)
-		beacon->csa_current_counter = counter;
+	if (counter < beacon->cntdwn_current_counter)
+		beacon->cntdwn_current_counter = counter;
 
 unlock:
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(ieee80211_csa_set_counter);
+EXPORT_SYMBOL(ieee80211_beacon_set_cntdwn);
 
-bool ieee80211_csa_is_complete(struct ieee80211_vif *vif)
+bool ieee80211_beacon_cntdwn_is_complete(struct ieee80211_vif *vif)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct beacon_data *beacon = NULL;
@@ -4688,20 +4682,21 @@ bool ieee80211_csa_is_complete(struct ieee80211_vif *vif)
 		goto out;
 	}
 
-	if (!beacon->csa_counter_offsets[0])
+	if (!beacon->cntdwn_counter_offsets[0])
 		goto out;
 
-	if (WARN_ON_ONCE(beacon->csa_counter_offsets[0] > beacon_data_len))
+	if (WARN_ON_ONCE(beacon->cntdwn_counter_offsets[0] > beacon_data_len))
 		goto out;
 
-	if (beacon_data[beacon->csa_counter_offsets[0]] == 1)
+	if (beacon_data[beacon->cntdwn_counter_offsets[0]] == 1)
 		ret = true;
+
  out:
 	rcu_read_unlock();
 
 	return ret;
 }
-EXPORT_SYMBOL(ieee80211_csa_is_complete);
+EXPORT_SYMBOL(ieee80211_beacon_cntdwn_is_complete);
 
 static int ieee80211_beacon_protect(struct sk_buff *skb,
 				    struct ieee80211_local *local,
@@ -4761,11 +4756,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 
 		beacon = rcu_dereference(ap->beacon);
 		if (beacon) {
-			if (beacon->csa_counter_offsets[0]) {
+			if (beacon->cntdwn_counter_offsets[0]) {
 				if (!is_template)
-					__ieee80211_csa_update_counter(beacon);
+					ieee80211_beacon_update_cntdwn(vif);
 
-				ieee80211_set_csa(sdata, beacon);
+				ieee80211_set_beacon_cntdwn(sdata, beacon);
 			}
 
 			/*
@@ -4809,11 +4804,11 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 		if (!beacon)
 			goto out;
 
-		if (beacon->csa_counter_offsets[0]) {
+		if (beacon->cntdwn_counter_offsets[0]) {
 			if (!is_template)
-				__ieee80211_csa_update_counter(beacon);
+				__ieee80211_beacon_update_cntdwn(beacon);
 
-			ieee80211_set_csa(sdata, beacon);
+			ieee80211_set_beacon_cntdwn(sdata, beacon);
 		}
 
 		skb = dev_alloc_skb(local->tx_headroom + beacon->head_len +
@@ -4833,16 +4828,16 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 		if (!beacon)
 			goto out;
 
-		if (beacon->csa_counter_offsets[0]) {
+		if (beacon->cntdwn_counter_offsets[0]) {
 			if (!is_template)
 				/* TODO: For mesh csa_counter is in TU, so
 				 * decrementing it by one isn't correct, but
 				 * for now we leave it consistent with overall
 				 * mac80211's behavior.
 				 */
-				__ieee80211_csa_update_counter(beacon);
+				__ieee80211_beacon_update_cntdwn(beacon);
 
-			ieee80211_set_csa(sdata, beacon);
+			ieee80211_set_beacon_cntdwn(sdata, beacon);
 		}
 
 		if (ifmsh->sync_ops)
@@ -4874,13 +4869,13 @@ __ieee80211_beacon_get(struct ieee80211_hw *hw,
 	if (offs && beacon) {
 		int i;
 
-		for (i = 0; i < IEEE80211_MAX_CSA_COUNTERS_NUM; i++) {
-			u16 csa_off = beacon->csa_counter_offsets[i];
+		for (i = 0; i < IEEE80211_MAX_CNTDWN_COUNTERS_NUM; i++) {
+			u16 csa_off = beacon->cntdwn_counter_offsets[i];
 
 			if (!csa_off)
 				continue;
 
-			offs->csa_counter_offs[i] = csa_off_base + csa_off;
+			offs->cntdwn_counter_offs[i] = csa_off_base + csa_off;
 		}
 	}
 
@@ -4999,6 +4994,63 @@ out:
 }
 EXPORT_SYMBOL(ieee80211_proberesp_get);
 
+struct sk_buff *ieee80211_get_fils_discovery_tmpl(struct ieee80211_hw *hw,
+						  struct ieee80211_vif *vif)
+{
+	struct sk_buff *skb = NULL;
+	struct fils_discovery_data *tmpl = NULL;
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	if (sdata->vif.type != NL80211_IFTYPE_AP)
+		return NULL;
+
+	rcu_read_lock();
+	tmpl = rcu_dereference(sdata->u.ap.fils_discovery);
+	if (!tmpl) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	skb = dev_alloc_skb(sdata->local->hw.extra_tx_headroom + tmpl->len);
+	if (skb) {
+		skb_reserve(skb, sdata->local->hw.extra_tx_headroom);
+		skb_put_data(skb, tmpl->data, tmpl->len);
+	}
+
+	rcu_read_unlock();
+	return skb;
+}
+EXPORT_SYMBOL(ieee80211_get_fils_discovery_tmpl);
+
+struct sk_buff *
+ieee80211_get_unsol_bcast_probe_resp_tmpl(struct ieee80211_hw *hw,
+					  struct ieee80211_vif *vif)
+{
+	struct sk_buff *skb = NULL;
+	struct unsol_bcast_probe_resp_data *tmpl = NULL;
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	if (sdata->vif.type != NL80211_IFTYPE_AP)
+		return NULL;
+
+	rcu_read_lock();
+	tmpl = rcu_dereference(sdata->u.ap.unsol_bcast_probe_resp);
+	if (!tmpl) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	skb = dev_alloc_skb(sdata->local->hw.extra_tx_headroom + tmpl->len);
+	if (skb) {
+		skb_reserve(skb, sdata->local->hw.extra_tx_headroom);
+		skb_put_data(skb, tmpl->data, tmpl->len);
+	}
+
+	rcu_read_unlock();
+	return skb;
+}
+EXPORT_SYMBOL(ieee80211_get_unsol_bcast_probe_resp_tmpl);
+
 struct sk_buff *ieee80211_pspoll_get(struct ieee80211_hw *hw,
 				     struct ieee80211_vif *vif)
 {
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 8d3bfc0fe176..8d3ae6b2f95f 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -45,6 +45,58 @@ struct ieee80211_hw *wiphy_to_ieee80211_hw(struct wiphy *wiphy)
 }
 EXPORT_SYMBOL(wiphy_to_ieee80211_hw);
 
+u8 *ieee80211_get_bssid(struct ieee80211_hdr *hdr, size_t len,
+			enum nl80211_iftype type)
+{
+	__le16 fc = hdr->frame_control;
+
+	if (ieee80211_is_data(fc)) {
+		if (len < 24) /* drop incorrect hdr len (data) */
+			return NULL;
+
+		if (ieee80211_has_a4(fc))
+			return NULL;
+		if (ieee80211_has_tods(fc))
+			return hdr->addr1;
+		if (ieee80211_has_fromds(fc))
+			return hdr->addr2;
+
+		return hdr->addr3;
+	}
+
+	if (ieee80211_is_s1g_beacon(fc)) {
+		struct ieee80211_ext *ext = (void *) hdr;
+
+		return ext->u.s1g_beacon.sa;
+	}
+
+	if (ieee80211_is_mgmt(fc)) {
+		if (len < 24) /* drop incorrect hdr len (mgmt) */
+			return NULL;
+		return hdr->addr3;
+	}
+
+	if (ieee80211_is_ctl(fc)) {
+		if (ieee80211_is_pspoll(fc))
+			return hdr->addr1;
+
+		if (ieee80211_is_back_req(fc)) {
+			switch (type) {
+			case NL80211_IFTYPE_STATION:
+				return hdr->addr2;
+			case NL80211_IFTYPE_AP:
+			case NL80211_IFTYPE_AP_VLAN:
+				return hdr->addr1;
+			default:
+				break; /* fall through to the return */
+			}
+		}
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(ieee80211_get_bssid);
+
 void ieee80211_tx_set_protected(struct ieee80211_tx_data *tx)
 {
 	struct sk_buff *skb;
@@ -334,9 +386,10 @@ _ieee80211_wake_txqs(struct ieee80211_local *local, unsigned long *flags)
 	rcu_read_unlock();
 }
 
-void ieee80211_wake_txqs(unsigned long data)
+void ieee80211_wake_txqs(struct tasklet_struct *t)
 {
-	struct ieee80211_local *local = (struct ieee80211_local *)data;
+	struct ieee80211_local *local = from_tasklet(local, t,
+						     wake_txqs_tasklet);
 	unsigned long flags;
 
 	spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
@@ -733,6 +786,9 @@ static void __iterate_interfaces(struct ieee80211_local *local,
 		if (!(iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL) &&
 		    active_only && !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
 			continue;
+		if ((iter_flags & IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER) &&
+		    !(sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+			continue;
 		if (ieee80211_sdata_running(sdata) || !active_only)
 			iterator(data, sdata->vif.addr,
 				 &sdata->vif);
@@ -1003,6 +1059,11 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 		case WLAN_EID_LINK_ID:
 		case WLAN_EID_BSS_MAX_IDLE_PERIOD:
 		case WLAN_EID_RSNX:
+		case WLAN_EID_S1G_BCN_COMPAT:
+		case WLAN_EID_S1G_CAPABILITIES:
+		case WLAN_EID_S1G_OPERATION:
+		case WLAN_EID_AID_RESPONSE:
+		case WLAN_EID_S1G_SHORT_BCN_INTERVAL:
 		/*
 		 * not listing WLAN_EID_CHANNEL_SWITCH_WRAPPER -- it seems possible
 		 * that if the content gets bigger it might be needed more than once
@@ -1288,6 +1349,30 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 								&crc : NULL,
 							  elem, elems);
 			break;
+		case WLAN_EID_S1G_CAPABILITIES:
+			if (elen == sizeof(*elems->s1g_capab))
+				elems->s1g_capab = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
+		case WLAN_EID_S1G_OPERATION:
+			if (elen == sizeof(*elems->s1g_oper))
+				elems->s1g_oper = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
+		case WLAN_EID_S1G_BCN_COMPAT:
+			if (elen == sizeof(*elems->s1g_bcn_compat))
+				elems->s1g_bcn_compat = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
+		case WLAN_EID_AID_RESPONSE:
+			if (elen == sizeof(struct ieee80211_aid_response_ie))
+				elems->aid_resp = (void *)pos;
+			else
+				elem_parse_failed = true;
+			break;
 		default:
 			break;
 		}
@@ -2429,7 +2514,6 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 				return res;
 			}
 			break;
-		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_AP_VLAN:
 		case NL80211_IFTYPE_MONITOR:
 		case NL80211_IFTYPE_P2P_DEVICE:
@@ -2439,6 +2523,7 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		case NUM_NL80211_IFTYPES:
 		case NL80211_IFTYPE_P2P_CLIENT:
 		case NL80211_IFTYPE_P2P_GO:
+		case NL80211_IFTYPE_WDS:
 			WARN_ON(1);
 			break;
 		}
@@ -3374,6 +3459,42 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata,
 	return true;
 }
 
+bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper,
+				struct cfg80211_chan_def *chandef)
+{
+	u32 oper_freq;
+
+	if (!oper)
+		return false;
+
+	switch (FIELD_GET(S1G_OPER_CH_WIDTH_OPER, oper->ch_width)) {
+	case IEEE80211_S1G_CHANWIDTH_1MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_1;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_2MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_2;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_4MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_4;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_8MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_8;
+		break;
+	case IEEE80211_S1G_CHANWIDTH_16MHZ:
+		chandef->width = NL80211_CHAN_WIDTH_16;
+		break;
+	default:
+		return false;
+	}
+
+	oper_freq = ieee80211_channel_to_freq_khz(oper->oper_ch,
+						  NL80211_BAND_S1GHZ);
+	chandef->center_freq1 = KHZ_TO_MHZ(oper_freq);
+	chandef->freq1_offset = oper_freq % 1000;
+
+	return true;
+}
+
 int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef,
 			     const struct ieee80211_supported_band *sband,
 			     const u8 *srates, int srates_len, u32 *rates)
@@ -3545,6 +3666,7 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 	u64 ts = status->mactime;
 	struct rate_info ri;
 	u16 rate;
+	u8 n_ltf;
 
 	if (WARN_ON(!ieee80211_have_rx_timestamp(status)))
 		return 0;
@@ -3555,11 +3677,58 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 
 	/* Fill cfg80211 rate info */
 	switch (status->encoding) {
+	case RX_ENC_HE:
+		ri.flags |= RATE_INFO_FLAGS_HE_MCS;
+		ri.mcs = status->rate_idx;
+		ri.nss = status->nss;
+		ri.he_ru_alloc = status->he_ru;
+		if (status->enc_flags & RX_ENC_FLAG_SHORT_GI)
+			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
+
+		/*
+		 * See P802.11ax_D6.0, section 27.3.4 for
+		 * VHT PPDU format.
+		 */
+		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+			mpdu_offset += 2;
+			ts += 36;
+
+			/*
+			 * TODO:
+			 * For HE MU PPDU, add the HE-SIG-B.
+			 * For HE ER PPDU, add 8us for the HE-SIG-A.
+			 * For HE TB PPDU, add 4us for the HE-STF.
+			 * Add the HE-LTF durations - variable.
+			 */
+		}
+
+		break;
 	case RX_ENC_HT:
 		ri.mcs = status->rate_idx;
 		ri.flags |= RATE_INFO_FLAGS_MCS;
 		if (status->enc_flags & RX_ENC_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
+
+		/*
+		 * See P802.11REVmd_D3.0, section 19.3.2 for
+		 * HT PPDU format.
+		 */
+		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+			mpdu_offset += 2;
+			if (status->enc_flags & RX_ENC_FLAG_HT_GF)
+				ts += 24;
+			else
+				ts += 32;
+
+			/*
+			 * Add Data HT-LTFs per streams
+			 * TODO: add Extension HT-LTFs, 4us per LTF
+			 */
+			n_ltf = ((ri.mcs >> 3) & 3) + 1;
+			n_ltf = n_ltf == 3 ? 4 : n_ltf;
+			ts += n_ltf * 4;
+		}
+
 		break;
 	case RX_ENC_VHT:
 		ri.flags |= RATE_INFO_FLAGS_VHT_MCS;
@@ -3567,6 +3736,23 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		ri.nss = status->nss;
 		if (status->enc_flags & RX_ENC_FLAG_SHORT_GI)
 			ri.flags |= RATE_INFO_FLAGS_SHORT_GI;
+
+		/*
+		 * See P802.11REVmd_D3.0, section 21.3.2 for
+		 * VHT PPDU format.
+		 */
+		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
+			mpdu_offset += 2;
+			ts += 36;
+
+			/*
+			 * Add VHT-LTFs per streams
+			 */
+			n_ltf = (ri.nss != 1) && (ri.nss % 2) ?
+				ri.nss + 1 : ri.nss;
+			ts += 4 * n_ltf;
+		}
+
 		break;
 	default:
 		WARN_ON(1);
@@ -3590,7 +3776,6 @@ u64 ieee80211_calculate_rx_timestamp(struct ieee80211_local *local,
 		ri.legacy = DIV_ROUND_UP(bitrate, (1 << shift));
 
 		if (status->flag & RX_FLAG_MACTIME_PLCP_START) {
-			/* TODO: handle HT/VHT preambles */
 			if (status->band == NL80211_BAND_5GHZ) {
 				ts += 20 << shift;
 				mpdu_offset += 2;
@@ -4277,6 +4462,58 @@ int ieee80211_max_num_channels(struct ieee80211_local *local)
 	return max_num_different_channels;
 }
 
+void ieee80211_add_s1g_capab_ie(struct ieee80211_sub_if_data *sdata,
+				struct ieee80211_sta_s1g_cap *caps,
+				struct sk_buff *skb)
+{
+	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
+	struct ieee80211_s1g_cap s1g_capab;
+	u8 *pos;
+	int i;
+
+	if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION))
+		return;
+
+	if (!caps->s1g)
+		return;
+
+	memcpy(s1g_capab.capab_info, caps->cap, sizeof(caps->cap));
+	memcpy(s1g_capab.supp_mcs_nss, caps->nss_mcs, sizeof(caps->nss_mcs));
+
+	/* override the capability info */
+	for (i = 0; i < sizeof(ifmgd->s1g_capa.capab_info); i++) {
+		u8 mask = ifmgd->s1g_capa_mask.capab_info[i];
+
+		s1g_capab.capab_info[i] &= ~mask;
+		s1g_capab.capab_info[i] |= ifmgd->s1g_capa.capab_info[i] & mask;
+	}
+
+	/* then MCS and NSS set */
+	for (i = 0; i < sizeof(ifmgd->s1g_capa.supp_mcs_nss); i++) {
+		u8 mask = ifmgd->s1g_capa_mask.supp_mcs_nss[i];
+
+		s1g_capab.supp_mcs_nss[i] &= ~mask;
+		s1g_capab.supp_mcs_nss[i] |=
+			ifmgd->s1g_capa.supp_mcs_nss[i] & mask;
+	}
+
+	pos = skb_put(skb, 2 + sizeof(s1g_capab));
+	*pos++ = WLAN_EID_S1G_CAPABILITIES;
+	*pos++ = sizeof(s1g_capab);
+
+	memcpy(pos, &s1g_capab, sizeof(s1g_capab));
+}
+
+void ieee80211_add_aid_request_ie(struct ieee80211_sub_if_data *sdata,
+				  struct sk_buff *skb)
+{
+	u8 *pos = skb_put(skb, 3);
+
+	*pos++ = WLAN_EID_AID_REQUEST;
+	*pos++ = 1;
+	*pos++ = 0;
+}
+
 u8 *ieee80211_add_wmm_info_ie(u8 *buf, u8 qosinfo)
 {
 	*buf++ = WLAN_EID_VENDOR_SPECIFIC;
@@ -4319,3 +4556,24 @@ const u8 ieee80211_ac_to_qos_mask[IEEE80211_NUM_ACS] = {
 	IEEE80211_WMM_IE_STA_QOSINFO_AC_BE,
 	IEEE80211_WMM_IE_STA_QOSINFO_AC_BK
 };
+
+u16 ieee80211_encode_usf(int listen_interval)
+{
+	static const int listen_int_usf[] = { 1, 10, 1000, 10000 };
+	u16 ui, usf = 0;
+
+	/* find greatest USF */
+	while (usf < IEEE80211_MAX_USF) {
+		if (listen_interval % listen_int_usf[usf + 1])
+			break;
+		usf += 1;
+	}
+	ui = listen_interval / listen_int_usf[usf];
+
+	/* error if there is a remainder. Should've been checked by user */
+	WARN_ON_ONCE(ui > IEEE80211_MAX_UI);
+	listen_interval = FIELD_PREP(LISTEN_INT_USF, usf) |
+			  FIELD_PREP(LISTEN_INT_UI, ui);
+
+	return (u16) listen_interval;
+}
diff --git a/net/mac80211/vht.c b/net/mac80211/vht.c
index d1b64d0751f2..c3ca97373774 100644
--- a/net/mac80211/vht.c
+++ b/net/mac80211/vht.c
@@ -315,10 +315,6 @@ ieee80211_vht_cap_ie_to_sta_vht_cap(struct ieee80211_sub_if_data *sdata,
 
 	sta->sta.bandwidth = ieee80211_sta_cur_vht_bw(sta);
 
-	/* If HT IE reported 3839 bytes only, stay with that size. */
-	if (sta->sta.max_amsdu_len == IEEE80211_MAX_MPDU_LEN_HT_3839)
-		return;
-
 	switch (vht_cap->cap & IEEE80211_VHT_CAP_MAX_MPDU_MASK) {
 	case IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454:
 		sta->sta.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_VHT_11454;
@@ -469,12 +465,18 @@ enum ieee80211_sta_rx_bandwidth ieee80211_sta_cur_vht_bw(struct sta_info *sta)
 	 * IEEE80211-2016 specification makes higher bandwidth operation
 	 * possible on the TDLS link if the peers have wider bandwidth
 	 * capability.
+	 *
+	 * However, in this case, and only if the TDLS peer is authorized,
+	 * limit to the tdls_chandef so that the configuration here isn't
+	 * wider than what's actually requested on the channel context.
 	 */
 	if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) &&
-	    test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW))
-		return bw;
-
-	bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width));
+	    test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW) &&
+	    test_sta_flag(sta, WLAN_STA_AUTHORIZED) &&
+	    sta->tdls_chandef.chan)
+		bw = min(bw, ieee80211_chan_width_to_rx_bw(sta->tdls_chandef.width));
+	else
+		bw = min(bw, ieee80211_chan_width_to_rx_bw(bss_width));
 
 	return bw;
 }
diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c
index 2fb99325135a..9ea6004abe1b 100644
--- a/net/mac80211/wme.c
+++ b/net/mac80211/wme.c
@@ -118,9 +118,11 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata,
 				 struct ieee80211_hdr *hdr)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	u8 *p;
 
-	if (local->hw.queues < IEEE80211_NUM_ACS)
+	if ((info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER) ||
+	    local->hw.queues < IEEE80211_NUM_ACS)
 		return 0;
 
 	if (!ieee80211_is_data(hdr->frame_control)) {
@@ -141,6 +143,7 @@ u16 ieee80211_select_queue_80211(struct ieee80211_sub_if_data *sdata,
 u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 			     struct sta_info *sta, struct sk_buff *skb)
 {
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct mac80211_qos_map *qos_map;
 	bool qos;
 
@@ -153,7 +156,7 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	else
 		qos = false;
 
-	if (!qos) {
+	if (!qos || (info->control.flags & IEEE80211_TX_CTRL_DONT_REORDER)) {
 		skb->priority = 0; /* required for correct WPA/11i MIC */
 		return IEEE80211_AC_BE;
 	}
@@ -202,9 +205,6 @@ u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata,
 	case NL80211_IFTYPE_AP:
 		ra = skb->data;
 		break;
-	case NL80211_IFTYPE_WDS:
-		ra = sdata->u.wds.remote_addr;
-		break;
 	case NL80211_IFTYPE_STATION:
 		/* might be a TDLS station */
 		sta = sta_info_get(sdata, skb->data);
@@ -249,6 +249,14 @@ void ieee80211_set_qos_hdr(struct ieee80211_sub_if_data *sdata,
 
 	p = ieee80211_get_qos_ctl(hdr);
 
+	/* don't overwrite the QoS field of injected frames */
+	if (info->flags & IEEE80211_TX_CTL_INJECTED) {
+		/* do take into account Ack policy of injected frames */
+		if (*p & IEEE80211_QOS_CTL_ACK_POLICY_NOACK)
+			info->flags |= IEEE80211_TX_CTL_NO_ACK;
+		return;
+	}
+
 	/* set up the first byte */
 
 	/*
diff --git a/net/mac802154/main.c b/net/mac802154/main.c
index 06ea0f8bfd5c..520cedc594e1 100644
--- a/net/mac802154/main.c
+++ b/net/mac802154/main.c
@@ -20,9 +20,9 @@
 #include "ieee802154_i.h"
 #include "cfg.h"
 
-static void ieee802154_tasklet_handler(unsigned long data)
+static void ieee802154_tasklet_handler(struct tasklet_struct *t)
 {
-	struct ieee802154_local *local = (struct ieee802154_local *)data;
+	struct ieee802154_local *local = from_tasklet(local, t, tasklet);
 	struct sk_buff *skb;
 
 	while ((skb = skb_dequeue(&local->skb_queue))) {
@@ -91,9 +91,7 @@ ieee802154_alloc_hw(size_t priv_data_len, const struct ieee802154_ops *ops)
 	INIT_LIST_HEAD(&local->interfaces);
 	mutex_init(&local->iflist_mtx);
 
-	tasklet_init(&local->tasklet,
-		     ieee802154_tasklet_handler,
-		     (unsigned long)local);
+	tasklet_setup(&local->tasklet, ieee802154_tasklet_handler);
 
 	skb_queue_head_init(&local->skb_queue);
 
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index f2868a8a50c3..47bab701555f 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -377,6 +377,8 @@ static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
 	if (!pskb_may_pull(skb, sizeof(*hdr)))
 		goto err;
 
+	skb_dst_drop(skb);
+
 	/* Read and decode the label */
 	hdr = mpls_hdr(skb);
 	dec = mpls_entry_decode(hdr);
diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 2def85718d94..ef59e25dc482 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -300,5 +300,6 @@ static void __exit mpls_iptunnel_exit(void)
 module_exit(mpls_iptunnel_exit);
 
 MODULE_ALIAS_RTNL_LWT(MPLS);
+MODULE_SOFTDEP("post: mpls_gso");
 MODULE_DESCRIPTION("MultiProtocol Label Switching IP Tunnels");
 MODULE_LICENSE("GPL v2");
diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig
index 698bc3525160..a014149aa323 100644
--- a/net/mptcp/Kconfig
+++ b/net/mptcp/Kconfig
@@ -19,14 +19,11 @@ config INET_MPTCP_DIAG
 
 config MPTCP_IPV6
 	bool "MPTCP: IPv6 support for Multipath TCP"
-	select IPV6
+	depends on IPV6=y
 	default y
 
-endif
-
 config MPTCP_KUNIT_TESTS
 	tristate "This builds the MPTCP KUnit tests" if !KUNIT_ALL_TESTS
-	select MPTCP
 	depends on KUNIT
 	default KUNIT_ALL_TESTS
 	help
@@ -39,3 +36,4 @@ config MPTCP_KUNIT_TESTS
 
 	  If unsure, say N.
 
+endif
diff --git a/net/mptcp/crypto.c b/net/mptcp/crypto.c
index 05d398d3fde4..b472dc149856 100644
--- a/net/mptcp/crypto.c
+++ b/net/mptcp/crypto.c
@@ -21,7 +21,7 @@
  */
 
 #include <linux/kernel.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <asm/unaligned.h>
 
 #include "protocol.h"
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 54b888f94009..96ba616f59bf 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -18,6 +18,7 @@ struct mptcp_pernet {
 	struct ctl_table_header *ctl_table_hdr;
 
 	int mptcp_enabled;
+	unsigned int add_addr_timeout;
 };
 
 static struct mptcp_pernet *mptcp_get_pernet(struct net *net)
@@ -30,6 +31,11 @@ int mptcp_is_enabled(struct net *net)
 	return mptcp_get_pernet(net)->mptcp_enabled;
 }
 
+unsigned int mptcp_get_add_addr_timeout(struct net *net)
+{
+	return mptcp_get_pernet(net)->add_addr_timeout;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -40,12 +46,19 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		 */
 		.proc_handler = proc_dointvec,
 	},
+	{
+		.procname = "add_addr_timeout",
+		.maxlen = sizeof(unsigned int),
+		.mode = 0644,
+		.proc_handler = proc_dointvec_jiffies,
+	},
 	{}
 };
 
 static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 {
 	pernet->mptcp_enabled = 1;
+	pernet->add_addr_timeout = TCP_RTO_MAX;
 }
 
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -61,6 +74,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	}
 
 	table[0].data = &pernet->mptcp_enabled;
+	table[1].data = &pernet->add_addr_timeout;
 
 	hdr = register_net_sysctl(net, MPTCP_SYSCTL_PATH, table);
 	if (!hdr)
diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index 0a6a15f3456d..b921cbdd9aaa 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -22,6 +22,15 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
 	SNMP_MIB_ITEM("DSSNotMatching", MPTCP_MIB_DSSNOMATCH),
 	SNMP_MIB_ITEM("InfiniteMapRx", MPTCP_MIB_INFINITEMAPRX),
+	SNMP_MIB_ITEM("OFOQueueTail", MPTCP_MIB_OFOQUEUETAIL),
+	SNMP_MIB_ITEM("OFOQueue", MPTCP_MIB_OFOQUEUE),
+	SNMP_MIB_ITEM("OFOMerge", MPTCP_MIB_OFOMERGE),
+	SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW),
+	SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA),
+	SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR),
+	SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD),
+	SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR),
+	SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW),
 	SNMP_MIB_SENTINEL
 };
 
@@ -58,6 +67,7 @@ void mptcp_seq_show(struct seq_file *seq)
 		for (i = 0; mptcp_snmp_list[i].name; i++)
 			seq_puts(seq, " 0");
 
+		seq_putc(seq, '\n');
 		return;
 	}
 
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index d7de340fc997..47bcecce1106 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -15,6 +15,15 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_JOINACKMAC,		/* HMAC was wrong on ACK + MP_JOIN */
 	MPTCP_MIB_DSSNOMATCH,		/* Received a new mapping that did not match the previous one */
 	MPTCP_MIB_INFINITEMAPRX,	/* Received an infinite mapping */
+	MPTCP_MIB_OFOQUEUETAIL,	/* Segments inserted into OoO queue tail */
+	MPTCP_MIB_OFOQUEUE,		/* Segments inserted into OoO queue */
+	MPTCP_MIB_OFOMERGE,		/* Segments merged in OoO queue */
+	MPTCP_MIB_NODSSWINDOW,		/* Segments not in MPTCP windows */
+	MPTCP_MIB_DUPDATA,		/* Segments discarded due to duplicate DSS */
+	MPTCP_MIB_ADDADDR,		/* Received ADD_ADDR with echo-flag=0 */
+	MPTCP_MIB_ECHOADD,		/* Received ADD_ADDR with echo-flag=1 */
+	MPTCP_MIB_RMADDR,		/* Received RM_ADDR */
+	MPTCP_MIB_RMSUBFLOW,		/* Remove a subflow */
 	__MPTCP_MIB_MAX
 };
 
diff --git a/net/mptcp/mptcp_diag.c b/net/mptcp/mptcp_diag.c
index 5f390a97f556..b70ae4ba3000 100644
--- a/net/mptcp/mptcp_diag.c
+++ b/net/mptcp/mptcp_diag.c
@@ -140,7 +140,7 @@ static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
 	info->mptcpi_flags = flags;
 	info->mptcpi_token = READ_ONCE(msk->token);
 	info->mptcpi_write_seq = READ_ONCE(msk->write_seq);
-	info->mptcpi_snd_una = atomic64_read(&msk->snd_una);
+	info->mptcpi_snd_una = READ_ONCE(msk->snd_una);
 	info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq);
 	unlock_sock_fast(sk, slow);
 }
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 888bbbbb3e8a..e0d21c0607e5 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -7,10 +7,11 @@
 #define pr_fmt(fmt) "MPTCP: " fmt
 
 #include <linux/kernel.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <net/tcp.h>
 #include <net/mptcp.h>
 #include "protocol.h"
+#include "mib.h"
 
 static bool mptcp_cap_flag_sha256(u8 flags)
 {
@@ -240,9 +241,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		}
 
 		mp_opt->add_addr = 1;
-		mp_opt->port = 0;
 		mp_opt->addr_id = *ptr++;
-		pr_debug("ADD_ADDR: id=%d", mp_opt->addr_id);
 		if (mp_opt->family == MPTCP_ADDR_IPVERSION_4) {
 			memcpy((u8 *)&mp_opt->addr.s_addr, (u8 *)ptr, 4);
 			ptr += 4;
@@ -267,6 +266,9 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			mp_opt->ahmac = get_unaligned_be64(ptr);
 			ptr += 8;
 		}
+		pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d",
+			 (mp_opt->family == MPTCP_ADDR_IPVERSION_6) ? "6" : "",
+			 mp_opt->addr_id, mp_opt->ahmac, mp_opt->echo, mp_opt->port);
 		break;
 
 	case MPTCPOPT_RM_ADDR:
@@ -280,6 +282,16 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		pr_debug("RM_ADDR: id=%d", mp_opt->rm_id);
 		break;
 
+	case MPTCPOPT_MP_FASTCLOSE:
+		if (opsize != TCPOLEN_MPTCP_FASTCLOSE)
+			break;
+
+		ptr += 2;
+		mp_opt->rcvr_key = get_unaligned_be64(ptr);
+		ptr += 8;
+		mp_opt->fastclose = 1;
+		break;
+
 	default:
 		break;
 	}
@@ -296,6 +308,9 @@ void mptcp_get_options(const struct sk_buff *skb,
 	mp_opt->mp_capable = 0;
 	mp_opt->mp_join = 0;
 	mp_opt->add_addr = 0;
+	mp_opt->ahmac = 0;
+	mp_opt->fastclose = 0;
+	mp_opt->port = 0;
 	mp_opt->rm_addr = 0;
 	mp_opt->dss = 0;
 
@@ -490,7 +505,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 	bool ret = false;
 
 	mpext = skb ? mptcp_get_ext(skb) : NULL;
-	snd_data_fin_enable = READ_ONCE(msk->snd_data_fin_enable);
+	snd_data_fin_enable = mptcp_data_fin_enabled(msk);
 
 	if (!skb || (mpext && mpext->use_map) || snd_data_fin_enable) {
 		unsigned int map_size;
@@ -516,7 +531,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 		return ret;
 	}
 
-	if (subflow->use_64bit_ack) {
+	if (READ_ONCE(msk->use_64bit_ack)) {
 		ack_size = TCPOLEN_MPTCP_DSS_ACK64;
 		opts->ext_copy.data_ack = READ_ONCE(msk->ack_seq);
 		opts->ext_copy.ack64 = 1;
@@ -526,6 +541,7 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 		opts->ext_copy.ack64 = 0;
 	}
 	opts->ext_copy.use_ack = 1;
+	WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk));
 
 	/* Add kind/length/subtype/flag overhead if mapping is not populated */
 	if (dss_size == 0)
@@ -571,45 +587,94 @@ static u64 add_addr6_generate_hmac(u64 key1, u64 key2, u8 addr_id,
 }
 #endif
 
-static bool mptcp_established_options_addr(struct sock *sk,
-					   unsigned int *size,
-					   unsigned int remaining,
-					   struct mptcp_out_options *opts)
+static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *skb,
+					       unsigned int *size,
+					       unsigned int remaining,
+					       struct mptcp_out_options *opts)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	bool drop_other_suboptions = false;
+	unsigned int opt_size = *size;
 	struct mptcp_addr_info saddr;
+	bool echo;
+	bool port;
 	int len;
 
-	if (!mptcp_pm_should_signal(msk) ||
-	    !(mptcp_pm_addr_signal(msk, remaining, &saddr)))
+	if ((mptcp_pm_should_add_signal_ipv6(msk) ||
+	     mptcp_pm_should_add_signal_port(msk)) &&
+	    skb && skb_is_tcp_pure_ack(skb)) {
+		pr_debug("drop other suboptions");
+		opts->suboptions = 0;
+		opts->ext_copy.use_ack = 0;
+		opts->ext_copy.use_map = 0;
+		remaining += opt_size;
+		drop_other_suboptions = true;
+	}
+
+	if (!mptcp_pm_should_add_signal(msk) ||
+	    !(mptcp_pm_add_addr_signal(msk, remaining, &saddr, &echo, &port)))
 		return false;
 
-	len = mptcp_add_addr_len(saddr.family);
+	len = mptcp_add_addr_len(saddr.family, echo, port);
 	if (remaining < len)
 		return false;
 
 	*size = len;
+	if (drop_other_suboptions)
+		*size -= opt_size;
 	opts->addr_id = saddr.id;
+	if (port)
+		opts->port = ntohs(saddr.port);
 	if (saddr.family == AF_INET) {
 		opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
 		opts->addr = saddr.addr;
-		opts->ahmac = add_addr_generate_hmac(msk->local_key,
-						     msk->remote_key,
-						     opts->addr_id,
-						     &opts->addr);
+		if (!echo) {
+			opts->ahmac = add_addr_generate_hmac(msk->local_key,
+							     msk->remote_key,
+							     opts->addr_id,
+							     &opts->addr);
+		}
 	}
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	else if (saddr.family == AF_INET6) {
 		opts->suboptions |= OPTION_MPTCP_ADD_ADDR6;
 		opts->addr6 = saddr.addr6;
-		opts->ahmac = add_addr6_generate_hmac(msk->local_key,
-						      msk->remote_key,
-						      opts->addr_id,
-						      &opts->addr6);
+		if (!echo) {
+			opts->ahmac = add_addr6_generate_hmac(msk->local_key,
+							      msk->remote_key,
+							      opts->addr_id,
+							      &opts->addr6);
+		}
 	}
 #endif
-	pr_debug("addr_id=%d, ahmac=%llu", opts->addr_id, opts->ahmac);
+	pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
+		 opts->addr_id, opts->ahmac, echo, opts->port);
+
+	return true;
+}
+
+static bool mptcp_established_options_rm_addr(struct sock *sk,
+					      unsigned int *size,
+					      unsigned int remaining,
+					      struct mptcp_out_options *opts)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+	u8 rm_id;
+
+	if (!mptcp_pm_should_rm_signal(msk) ||
+	    !(mptcp_pm_rm_addr_signal(msk, remaining, &rm_id)))
+		return false;
+
+	if (remaining < TCPOLEN_MPTCP_RM_ADDR_BASE)
+		return false;
+
+	*size = TCPOLEN_MPTCP_RM_ADDR_BASE;
+	opts->suboptions |= OPTION_MPTCP_RM_ADDR;
+	opts->rm_id = rm_id;
+
+	pr_debug("rm_id=%d", opts->rm_id);
 
 	return true;
 }
@@ -626,6 +691,12 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 	if (unlikely(mptcp_check_fallback(sk)))
 		return false;
 
+	/* prevent adding of any MPTCP related options on reset packet
+	 * until we support MP_TCPRST/MP_FASTCLOSE
+	 */
+	if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST))
+		return false;
+
 	if (mptcp_established_options_mp(sk, skb, &opt_size, remaining, opts))
 		ret = true;
 	else if (mptcp_established_options_dss(sk, skb, &opt_size, remaining,
@@ -640,7 +711,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 
 	*size += opt_size;
 	remaining -= opt_size;
-	if (mptcp_established_options_addr(sk, &opt_size, remaining, opts)) {
+	if (mptcp_established_options_add_addr(sk, skb, &opt_size, remaining, opts)) {
+		*size += opt_size;
+		remaining -= opt_size;
+		ret = true;
+	} else if (mptcp_established_options_rm_addr(sk, &opt_size, remaining, opts)) {
 		*size += opt_size;
 		remaining -= opt_size;
 		ret = true;
@@ -676,7 +751,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 	return false;
 }
 
-static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk,
+static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 				    struct mptcp_subflow_context *subflow,
 				    struct sk_buff *skb,
 				    struct mptcp_options_received *mp_opt)
@@ -693,15 +768,20 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk,
 		    TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq &&
 		    subflow->mp_join && mp_opt->mp_join &&
 		    READ_ONCE(msk->pm.server_side))
-			tcp_send_ack(sk);
+			tcp_send_ack(ssk);
 		goto fully_established;
 	}
 
-	/* we should process OoO packets before the first subflow is fully
-	 * established, but not expected for MP_JOIN subflows
+	/* we must process OoO packets before the first subflow is fully
+	 * established. OoO packets are instead a protocol violation
+	 * for MP_JOIN subflows as the peer must not send any data
+	 * before receiving the forth ack - cfr. RFC 8684 section 3.2.
 	 */
-	if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1)
+	if (TCP_SKB_CB(skb)->seq != subflow->ssn_offset + 1) {
+		if (subflow->mp_join)
+			goto reset;
 		return subflow->mp_capable;
+	}
 
 	if (mp_opt->dss && mp_opt->use_ack) {
 		/* subflows are fully established as soon as we get any
@@ -712,10 +792,18 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk,
 		goto fully_established;
 	}
 
+	if (mp_opt->add_addr) {
+		WRITE_ONCE(msk->fully_established, true);
+		return true;
+	}
+
 	/* If the first established packet does not contain MP_CAPABLE + data
-	 * then fallback to TCP
+	 * then fallback to TCP. Fallback scenarios requires a reset for
+	 * MP_JOIN subflows.
 	 */
 	if (!mp_opt->mp_capable) {
+		if (subflow->mp_join)
+			goto reset;
 		subflow->mp_capable = 0;
 		pr_fallback(msk);
 		__mptcp_do_fallback(msk);
@@ -727,17 +815,26 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *sk,
 	mptcp_subflow_fully_established(subflow, mp_opt);
 
 fully_established:
-	if (likely(subflow->pm_notified))
+	/* if the subflow is not already linked into the conn_list, we can't
+	 * notify the PM: this subflow is still on the listener queue
+	 * and the PM possibly acquiring the subflow lock could race with
+	 * the listener close
+	 */
+	if (likely(subflow->pm_notified) || list_empty(&subflow->node))
 		return true;
 
 	subflow->pm_notified = 1;
 	if (subflow->mp_join) {
-		clear_3rdack_retransmission(sk);
+		clear_3rdack_retransmission(ssk);
 		mptcp_pm_subflow_established(msk, subflow);
 	} else {
 		mptcp_pm_fully_established(msk);
 	}
 	return true;
+
+reset:
+	mptcp_subflow_reset(ssk);
+	return false;
 }
 
 static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
@@ -755,31 +852,42 @@ static u64 expand_ack(u64 old_ack, u64 cur_ack, bool use_64bit)
 	return cur_ack;
 }
 
-static void update_una(struct mptcp_sock *msk,
-		       struct mptcp_options_received *mp_opt)
+static void ack_update_msk(struct mptcp_sock *msk,
+			   struct sock *ssk,
+			   struct mptcp_options_received *mp_opt)
 {
-	u64 new_snd_una, snd_una, old_snd_una = atomic64_read(&msk->snd_una);
-	u64 write_seq = READ_ONCE(msk->write_seq);
+	u64 new_wnd_end, new_snd_una, snd_nxt = READ_ONCE(msk->snd_nxt);
+	struct sock *sk = (struct sock *)msk;
+	u64 old_snd_una;
+
+	mptcp_data_lock(sk);
 
 	/* avoid ack expansion on update conflict, to reduce the risk of
 	 * wrongly expanding to a future ack sequence number, which is way
 	 * more dangerous than missing an ack
 	 */
+	old_snd_una = msk->snd_una;
 	new_snd_una = expand_ack(old_snd_una, mp_opt->data_ack, mp_opt->ack64);
 
 	/* ACK for data not even sent yet? Ignore. */
-	if (after64(new_snd_una, write_seq))
+	if (after64(new_snd_una, snd_nxt))
 		new_snd_una = old_snd_una;
 
-	while (after64(new_snd_una, old_snd_una)) {
-		snd_una = old_snd_una;
-		old_snd_una = atomic64_cmpxchg(&msk->snd_una, snd_una,
-					       new_snd_una);
-		if (old_snd_una == snd_una) {
-			mptcp_data_acked((struct sock *)msk);
-			break;
-		}
+	new_wnd_end = new_snd_una + tcp_sk(ssk)->snd_wnd;
+
+	if (after64(new_wnd_end, msk->wnd_end))
+		msk->wnd_end = new_wnd_end;
+
+	/* this assumes mptcp_incoming_options() is invoked after tcp_ack() */
+	if (after64(msk->wnd_end, READ_ONCE(msk->snd_nxt)) &&
+	    sk_stream_memory_free(ssk))
+		__mptcp_check_push(sk, ssk);
+
+	if (after64(new_snd_una, old_snd_una)) {
+		msk->snd_una = new_snd_una;
+		__mptcp_data_acked(sk);
 	}
+	mptcp_data_unlock(sk);
 }
 
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit)
@@ -825,21 +933,37 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
 	return hmac == mp_opt->ahmac;
 }
 
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
-			    struct tcp_options_received *opt_rx)
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	struct mptcp_options_received mp_opt;
 	struct mptcp_ext *mpext;
 
-	if (__mptcp_check_fallback(msk))
+	if (__mptcp_check_fallback(msk)) {
+		/* Keep it simple and unconditionally trigger send data cleanup and
+		 * pending queue spooling. We will need to acquire the data lock
+		 * for more accurate checks, and once the lock is acquired, such
+		 * helpers are cheap.
+		 */
+		mptcp_data_lock(subflow->conn);
+		if (sk_stream_memory_free(sk))
+			__mptcp_check_push(subflow->conn, sk);
+		__mptcp_data_acked(subflow->conn);
+		mptcp_data_unlock(subflow->conn);
 		return;
+	}
 
 	mptcp_get_options(skb, &mp_opt);
 	if (!check_fully_established(msk, sk, subflow, skb, &mp_opt))
 		return;
 
+	if (mp_opt.fastclose &&
+	    msk->local_key == mp_opt.rcvr_key) {
+		WRITE_ONCE(msk->rcv_fastclose, true);
+		mptcp_schedule_work((struct sock *)msk);
+	}
+
 	if (mp_opt.add_addr && add_addr_hmac_valid(msk, &mp_opt)) {
 		struct mptcp_addr_info addr;
 
@@ -855,11 +979,21 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 			addr.addr6 = mp_opt.addr6;
 		}
 #endif
-		if (!mp_opt.echo)
+		if (!mp_opt.echo) {
 			mptcp_pm_add_addr_received(msk, &addr);
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
+		} else {
+			mptcp_pm_del_add_timer(msk, &addr);
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADD);
+		}
 		mp_opt.add_addr = 0;
 	}
 
+	if (mp_opt.rm_addr) {
+		mptcp_pm_rm_addr_received(msk, mp_opt.rm_id);
+		mp_opt.rm_addr = 0;
+	}
+
 	if (!mp_opt.dss)
 		return;
 
@@ -867,7 +1001,7 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 	 * monodirectional flows will stuck
 	 */
 	if (mp_opt.use_ack)
-		update_una(msk, &mp_opt);
+		ack_update_msk(msk, sk, &mp_opt);
 
 	/* Zero-data-length packets are dropped by the caller and not
 	 * propagated to the MPTCP layer, so the skb extension does not
@@ -912,7 +1046,24 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
 	}
 }
 
-void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
+static void mptcp_set_rwin(const struct tcp_sock *tp)
+{
+	const struct sock *ssk = (const struct sock *)tp;
+	const struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk;
+	u64 ack_seq;
+
+	subflow = mptcp_subflow_ctx(ssk);
+	msk = mptcp_sk(subflow->conn);
+
+	ack_seq = READ_ONCE(msk->ack_seq) + tp->rcv_wnd;
+
+	if (after64(ack_seq, READ_ONCE(msk->rcv_wnd_sent)))
+		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
+}
+
+void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
+			 struct mptcp_out_options *opts)
 {
 	if ((OPTION_MPTCP_MPC_SYN | OPTION_MPTCP_MPC_SYNACK |
 	     OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
@@ -951,44 +1102,66 @@ void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
 	}
 
 mp_capable_done:
-	if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
-		if (opts->ahmac)
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR, 0,
-					      opts->addr_id);
-		else
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR_BASE,
-					      MPTCP_ADDR_ECHO,
-					      opts->addr_id);
-		memcpy((u8 *)ptr, (u8 *)&opts->addr.s_addr, 4);
-		ptr += 1;
+	if ((OPTION_MPTCP_ADD_ADDR
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	     | OPTION_MPTCP_ADD_ADDR6
+#endif
+	    ) & opts->suboptions) {
+		u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
+		u8 echo = MPTCP_ADDR_ECHO;
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions)
+			len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
+#endif
+
+		if (opts->port)
+			len += TCPOLEN_MPTCP_PORT_LEN;
+
 		if (opts->ahmac) {
-			put_unaligned_be64(opts->ahmac, ptr);
-			ptr += 2;
+			len += sizeof(opts->ahmac);
+			echo = 0;
 		}
-	}
 
+		*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
+				      len, echo, opts->addr_id);
+		if (OPTION_MPTCP_ADD_ADDR & opts->suboptions) {
+			memcpy((u8 *)ptr, (u8 *)&opts->addr.s_addr, 4);
+			ptr += 1;
+		}
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions) {
-		if (opts->ahmac)
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR6, 0,
-					      opts->addr_id);
-		else
-			*ptr++ = mptcp_option(MPTCPOPT_ADD_ADDR,
-					      TCPOLEN_MPTCP_ADD_ADDR6_BASE,
-					      MPTCP_ADDR_ECHO,
-					      opts->addr_id);
-		memcpy((u8 *)ptr, opts->addr6.s6_addr, 16);
-		ptr += 4;
-		if (opts->ahmac) {
-			put_unaligned_be64(opts->ahmac, ptr);
-			ptr += 2;
+		else if (OPTION_MPTCP_ADD_ADDR6 & opts->suboptions) {
+			memcpy((u8 *)ptr, opts->addr6.s6_addr, 16);
+			ptr += 4;
 		}
-	}
 #endif
 
+		if (!opts->port) {
+			if (opts->ahmac) {
+				put_unaligned_be64(opts->ahmac, ptr);
+				ptr += 2;
+			}
+		} else {
+			if (opts->ahmac) {
+				u8 *bptr = (u8 *)ptr;
+
+				put_unaligned_be16(opts->port, bptr);
+				bptr += 2;
+				put_unaligned_be64(opts->ahmac, bptr);
+				bptr += 8;
+				put_unaligned_be16(TCPOPT_NOP << 8 |
+						   TCPOPT_NOP, bptr);
+
+				ptr += 3;
+			} else {
+				put_unaligned_be32(opts->port << 16 |
+						   TCPOPT_NOP << 8 |
+						   TCPOPT_NOP, ptr);
+				ptr += 1;
+			}
+		}
+	}
+
 	if (OPTION_MPTCP_RM_ADDR & opts->suboptions) {
 		*ptr++ = mptcp_option(MPTCPOPT_RM_ADDR,
 				      TCPOLEN_MPTCP_RM_ADDR_BASE,
@@ -1069,4 +1242,7 @@ mp_capable_done:
 					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
 		}
 	}
+
+	if (tp)
+		mptcp_set_rwin(tp);
 }
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index a8ad20559aaa..da2ed576f289 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -13,23 +13,55 @@
 /* path manager command handlers */
 
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
-			   const struct mptcp_addr_info *addr)
+			   const struct mptcp_addr_info *addr,
+			   bool echo, bool port)
 {
+	u8 add_addr = READ_ONCE(msk->pm.addr_signal);
+
 	pr_debug("msk=%p, local_id=%d", msk, addr->id);
 
+	if (add_addr) {
+		pr_warn("addr_signal error, add_addr=%d", add_addr);
+		return -EINVAL;
+	}
+
 	msk->pm.local = *addr;
-	WRITE_ONCE(msk->pm.addr_signal, true);
+	add_addr |= BIT(MPTCP_ADD_ADDR_SIGNAL);
+	if (echo)
+		add_addr |= BIT(MPTCP_ADD_ADDR_ECHO);
+	if (addr->family == AF_INET6)
+		add_addr |= BIT(MPTCP_ADD_ADDR_IPV6);
+	if (port)
+		add_addr |= BIT(MPTCP_ADD_ADDR_PORT);
+	WRITE_ONCE(msk->pm.addr_signal, add_addr);
 	return 0;
 }
 
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id)
 {
-	return -ENOTSUPP;
+	u8 rm_addr = READ_ONCE(msk->pm.addr_signal);
+
+	pr_debug("msk=%p, local_id=%d", msk, local_id);
+
+	if (rm_addr) {
+		pr_warn("addr_signal error, rm_addr=%d", rm_addr);
+		return -EINVAL;
+	}
+
+	msk->pm.rm_id = local_id;
+	rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL);
+	WRITE_ONCE(msk->pm.addr_signal, rm_addr);
+	return 0;
 }
 
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 remote_id)
+int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id)
 {
-	return -ENOTSUPP;
+	pr_debug("msk=%p, local_id=%d", msk, local_id);
+
+	spin_lock_bh(&msk->pm.lock);
+	mptcp_pm_nl_rm_subflow_received(msk, local_id);
+	spin_unlock_bh(&msk->pm.lock);
+	return 0;
 }
 
 /* path manager event handlers */
@@ -46,7 +78,7 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, int server_side)
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
-	int ret;
+	int ret = 0;
 
 	pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows,
 		 pm->subflows_max, READ_ONCE(pm->accept_subflow));
@@ -56,9 +88,11 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
 		return false;
 
 	spin_lock_bh(&pm->lock);
-	ret = pm->subflows < pm->subflows_max;
-	if (ret && ++pm->subflows == pm->subflows_max)
-		WRITE_ONCE(pm->accept_subflow, false);
+	if (READ_ONCE(pm->accept_subflow)) {
+		ret = pm->subflows < pm->subflows_max;
+		if (ret && ++pm->subflows == pm->subflows_max)
+			WRITE_ONCE(pm->accept_subflow, false);
+	}
 	spin_unlock_bh(&pm->lock);
 
 	return ret;
@@ -76,8 +110,7 @@ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk,
 		return false;
 
 	msk->pm.status |= BIT(new_status);
-	if (schedule_work(&msk->work))
-		sock_hold((struct sock *)msk);
+	mptcp_schedule_work((struct sock *)msk);
 	return true;
 }
 
@@ -93,8 +126,14 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk)
 
 	spin_lock_bh(&pm->lock);
 
-	if (READ_ONCE(pm->work_pending))
+	/* mptcp_pm_fully_established() can be invoked by multiple
+	 * racing paths - accept() and check_fully_established()
+	 * be sure to serve this event only once.
+	 */
+	if (READ_ONCE(pm->work_pending) &&
+	    !(msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)))
 		mptcp_pm_schedule_work(msk, MPTCP_PM_ESTABLISHED);
+	msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED);
 
 	spin_unlock_bh(&pm->lock);
 }
@@ -135,38 +174,83 @@ void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 	pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id,
 		 READ_ONCE(pm->accept_addr));
 
-	/* avoid acquiring the lock if there is no room for fouther addresses */
-	if (!READ_ONCE(pm->accept_addr))
-		return;
-
 	spin_lock_bh(&pm->lock);
 
-	/* be sure there is something to signal re-checking under PM lock */
-	if (READ_ONCE(pm->accept_addr) &&
-	    mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED))
+	if (!READ_ONCE(pm->accept_addr)) {
+		mptcp_pm_announce_addr(msk, addr, true, addr->port);
+		mptcp_pm_add_addr_send_ack(msk);
+	} else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
 		pm->remote = *addr;
+	}
+
+	spin_unlock_bh(&pm->lock);
+}
+
+void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk)
+{
+	if (!mptcp_pm_should_add_signal_ipv6(msk) &&
+	    !mptcp_pm_should_add_signal_port(msk))
+		return;
+
+	mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_SEND_ACK);
+}
+
+void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id)
+{
+	struct mptcp_pm_data *pm = &msk->pm;
+
+	pr_debug("msk=%p remote_id=%d", msk, rm_id);
 
+	spin_lock_bh(&pm->lock);
+	mptcp_pm_schedule_work(msk, MPTCP_PM_RM_ADDR_RECEIVED);
+	pm->rm_id = rm_id;
 	spin_unlock_bh(&pm->lock);
 }
 
 /* path manager helpers */
 
-bool mptcp_pm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
-			  struct mptcp_addr_info *saddr)
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
+			      struct mptcp_addr_info *saddr, bool *echo, bool *port)
 {
 	int ret = false;
 
 	spin_lock_bh(&msk->pm.lock);
 
 	/* double check after the lock is acquired */
-	if (!mptcp_pm_should_signal(msk))
+	if (!mptcp_pm_should_add_signal(msk))
 		goto out_unlock;
 
-	if (remaining < mptcp_add_addr_len(msk->pm.local.family))
+	*echo = mptcp_pm_should_add_signal_echo(msk);
+	*port = mptcp_pm_should_add_signal_port(msk);
+
+	if (remaining < mptcp_add_addr_len(msk->pm.local.family, *echo, *port))
 		goto out_unlock;
 
 	*saddr = msk->pm.local;
-	WRITE_ONCE(msk->pm.addr_signal, false);
+	WRITE_ONCE(msk->pm.addr_signal, 0);
+	ret = true;
+
+out_unlock:
+	spin_unlock_bh(&msk->pm.lock);
+	return ret;
+}
+
+bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
+			     u8 *rm_id)
+{
+	int ret = false;
+
+	spin_lock_bh(&msk->pm.lock);
+
+	/* double check after the lock is acquired */
+	if (!mptcp_pm_should_rm_signal(msk))
+		goto out_unlock;
+
+	if (remaining < TCPOLEN_MPTCP_RM_ADDR_BASE)
+		goto out_unlock;
+
+	*rm_id = msk->pm.rm_id;
+	WRITE_ONCE(msk->pm.addr_signal, 0);
 	ret = true;
 
 out_unlock:
@@ -185,13 +269,15 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 	msk->pm.add_addr_accepted = 0;
 	msk->pm.local_addr_used = 0;
 	msk->pm.subflows = 0;
+	msk->pm.rm_id = 0;
 	WRITE_ONCE(msk->pm.work_pending, false);
-	WRITE_ONCE(msk->pm.addr_signal, false);
+	WRITE_ONCE(msk->pm.addr_signal, 0);
 	WRITE_ONCE(msk->pm.accept_addr, false);
 	WRITE_ONCE(msk->pm.accept_subflow, false);
 	msk->pm.status = 0;
 
 	spin_lock_init(&msk->pm.lock);
+	INIT_LIST_HEAD(&msk->pm.anno_list);
 
 	mptcp_pm_nl_data_init(msk);
 }
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 770da3627848..a6d983d80576 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -15,6 +15,7 @@
 #include <uapi/linux/mptcp.h>
 
 #include "protocol.h"
+#include "mib.h"
 
 /* forward declaration */
 static struct genl_family mptcp_genl_family;
@@ -23,12 +24,18 @@ static int pm_nl_pernet_id;
 
 struct mptcp_pm_addr_entry {
 	struct list_head	list;
-	unsigned int		flags;
-	int			ifindex;
 	struct mptcp_addr_info	addr;
 	struct rcu_head		rcu;
 };
 
+struct mptcp_pm_add_entry {
+	struct list_head	list;
+	struct mptcp_addr_info	addr;
+	struct timer_list	add_timer;
+	struct mptcp_sock	*sock;
+	u8			retrans_times;
+};
+
 struct pm_nl_pernet {
 	/* protects pernet updates */
 	spinlock_t		lock;
@@ -42,6 +49,7 @@ struct pm_nl_pernet {
 };
 
 #define MPTCP_PM_ADDR_MAX	8
+#define ADD_ADDR_RETRANS_MAX	3
 
 static bool addresses_equal(const struct mptcp_addr_info *a,
 			    struct mptcp_addr_info *b, bool use_port)
@@ -127,22 +135,20 @@ select_local_address(const struct pm_nl_pernet *pernet,
 	struct mptcp_pm_addr_entry *entry, *ret = NULL;
 
 	rcu_read_lock();
-	spin_lock_bh(&msk->join_list_lock);
+	__mptcp_flush_join_list(msk);
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
-		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
+		if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
 			continue;
 
 		/* avoid any address already in use by subflows and
 		 * pending join
 		 */
 		if (entry->addr.family == ((struct sock *)msk)->sk_family &&
-		    !lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
-		    !lookup_subflow_by_saddr(&msk->join_list, &entry->addr)) {
+		    !lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) {
 			ret = entry;
 			break;
 		}
 	}
-	spin_unlock_bh(&msk->join_list_lock);
 	rcu_read_unlock();
 	return ret;
 }
@@ -160,7 +166,7 @@ select_signal_address(struct pm_nl_pernet *pernet, unsigned int pos)
 	 * can lead to additional addresses not being announced.
 	 */
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
-		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
+		if (!(entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
 			continue;
 		if (i++ == pos) {
 			ret = entry;
@@ -179,6 +185,125 @@ static void check_work_pending(struct mptcp_sock *msk)
 		WRITE_ONCE(msk->pm.work_pending, false);
 }
 
+static struct mptcp_pm_add_entry *
+lookup_anno_list_by_saddr(struct mptcp_sock *msk,
+			  struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *entry;
+
+	list_for_each_entry(entry, &msk->pm.anno_list, list) {
+		if (addresses_equal(&entry->addr, addr, false))
+			return entry;
+	}
+
+	return NULL;
+}
+
+static void mptcp_pm_add_timer(struct timer_list *timer)
+{
+	struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer);
+	struct mptcp_sock *msk = entry->sock;
+	struct sock *sk = (struct sock *)msk;
+
+	pr_debug("msk=%p", msk);
+
+	if (!msk)
+		return;
+
+	if (inet_sk_state_load(sk) == TCP_CLOSE)
+		return;
+
+	if (!entry->addr.id)
+		return;
+
+	if (mptcp_pm_should_add_signal(msk)) {
+		sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8);
+		goto out;
+	}
+
+	spin_lock_bh(&msk->pm.lock);
+
+	if (!mptcp_pm_should_add_signal(msk)) {
+		pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
+		mptcp_pm_announce_addr(msk, &entry->addr, false, entry->addr.port);
+		mptcp_pm_add_addr_send_ack(msk);
+		entry->retrans_times++;
+	}
+
+	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
+		sk_reset_timer(sk, timer,
+			       jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));
+
+	spin_unlock_bh(&msk->pm.lock);
+
+out:
+	__sock_put(sk);
+}
+
+struct mptcp_pm_add_entry *
+mptcp_pm_del_add_timer(struct mptcp_sock *msk,
+		       struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *entry;
+	struct sock *sk = (struct sock *)msk;
+
+	spin_lock_bh(&msk->pm.lock);
+	entry = lookup_anno_list_by_saddr(msk, addr);
+	if (entry)
+		entry->retrans_times = ADD_ADDR_RETRANS_MAX;
+	spin_unlock_bh(&msk->pm.lock);
+
+	if (entry)
+		sk_stop_timer_sync(sk, &entry->add_timer);
+
+	return entry;
+}
+
+static bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
+				     struct mptcp_pm_addr_entry *entry)
+{
+	struct mptcp_pm_add_entry *add_entry = NULL;
+	struct sock *sk = (struct sock *)msk;
+	struct net *net = sock_net(sk);
+
+	if (lookup_anno_list_by_saddr(msk, &entry->addr))
+		return false;
+
+	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
+	if (!add_entry)
+		return false;
+
+	list_add(&add_entry->list, &msk->pm.anno_list);
+
+	add_entry->addr = entry->addr;
+	add_entry->sock = msk;
+	add_entry->retrans_times = 0;
+
+	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
+	sk_reset_timer(sk, &add_entry->add_timer,
+		       jiffies + mptcp_get_add_addr_timeout(net));
+
+	return true;
+}
+
+void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_add_entry *entry, *tmp;
+	struct sock *sk = (struct sock *)msk;
+	LIST_HEAD(free_list);
+
+	pr_debug("msk=%p", msk);
+
+	spin_lock_bh(&msk->pm.lock);
+	list_splice_init(&msk->pm.anno_list, &free_list);
+	spin_unlock_bh(&msk->pm.lock);
+
+	list_for_each_entry_safe(entry, tmp, &free_list, list) {
+		sk_stop_timer_sync(sk, &entry->add_timer);
+		kfree(entry);
+	}
+}
+
 static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 {
 	struct mptcp_addr_info remote = { 0 };
@@ -186,7 +311,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 	struct mptcp_pm_addr_entry *local;
 	struct pm_nl_pernet *pernet;
 
-	pernet = net_generic(sock_net((struct sock *)msk), pm_nl_pernet_id);
+	pernet = net_generic(sock_net(sk), pm_nl_pernet_id);
 
 	pr_debug("local %d:%d signal %d:%d subflows %d:%d\n",
 		 msk->pm.local_addr_used, msk->pm.local_addr_max,
@@ -199,8 +324,11 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 					      msk->pm.add_addr_signaled);
 
 		if (local) {
-			msk->pm.add_addr_signaled++;
-			mptcp_pm_announce_addr(msk, &local->addr);
+			if (mptcp_pm_alloc_anno_list(msk, local)) {
+				msk->pm.add_addr_signaled++;
+				mptcp_pm_announce_addr(msk, &local->addr, false, local->addr.port);
+				mptcp_pm_nl_add_addr_send_ack(msk);
+			}
 		} else {
 			/* pick failed, avoid fourther attempts later */
 			msk->pm.local_addr_used = msk->pm.add_addr_signal_max;
@@ -220,8 +348,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 			msk->pm.subflows++;
 			check_work_pending(msk);
 			spin_unlock_bh(&msk->pm.lock);
-			__mptcp_subflow_connect(sk, local->ifindex,
-						&local->addr, &remote);
+			__mptcp_subflow_connect(sk, &local->addr, &remote);
 			spin_lock_bh(&msk->pm.lock);
 			return;
 		}
@@ -247,6 +374,7 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	struct sock *sk = (struct sock *)msk;
 	struct mptcp_addr_info remote;
 	struct mptcp_addr_info local;
+	bool use_port = false;
 
 	pr_debug("accepted %d:%d remote family %d",
 		 msk->pm.add_addr_accepted, msk->pm.add_addr_accept_max,
@@ -263,17 +391,125 @@ void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	remote = msk->pm.remote;
 	if (!remote.port)
 		remote.port = sk->sk_dport;
+	else
+		use_port = true;
 	memset(&local, 0, sizeof(local));
 	local.family = remote.family;
 
 	spin_unlock_bh(&msk->pm.lock);
-	__mptcp_subflow_connect((struct sock *)msk, 0, &local, &remote);
+	__mptcp_subflow_connect(sk, &local, &remote);
 	spin_lock_bh(&msk->pm.lock);
+
+	mptcp_pm_announce_addr(msk, &remote, true, use_port);
+	mptcp_pm_nl_add_addr_send_ack(msk);
+}
+
+void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+
+	if (!mptcp_pm_should_add_signal_ipv6(msk) &&
+	    !mptcp_pm_should_add_signal_port(msk))
+		return;
+
+	__mptcp_flush_join_list(msk);
+	subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
+	if (subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		u8 add_addr;
+
+		spin_unlock_bh(&msk->pm.lock);
+		if (mptcp_pm_should_add_signal_ipv6(msk))
+			pr_debug("send ack for add_addr6");
+		if (mptcp_pm_should_add_signal_port(msk))
+			pr_debug("send ack for add_addr_port");
+
+		lock_sock(ssk);
+		tcp_send_ack(ssk);
+		release_sock(ssk);
+		spin_lock_bh(&msk->pm.lock);
+
+		add_addr = READ_ONCE(msk->pm.addr_signal);
+		if (mptcp_pm_should_add_signal_ipv6(msk))
+			add_addr &= ~BIT(MPTCP_ADD_ADDR_IPV6);
+		if (mptcp_pm_should_add_signal_port(msk))
+			add_addr &= ~BIT(MPTCP_ADD_ADDR_PORT);
+		WRITE_ONCE(msk->pm.addr_signal, add_addr);
+	}
+}
+
+void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct sock *sk = (struct sock *)msk;
+
+	pr_debug("address rm_id %d", msk->pm.rm_id);
+
+	if (!msk->pm.rm_id)
+		return;
+
+	if (list_empty(&msk->conn_list))
+		return;
+
+	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
+
+		if (msk->pm.rm_id != subflow->remote_id)
+			continue;
+
+		spin_unlock_bh(&msk->pm.lock);
+		mptcp_subflow_shutdown(sk, ssk, how);
+		__mptcp_close_ssk(sk, ssk, subflow);
+		spin_lock_bh(&msk->pm.lock);
+
+		msk->pm.add_addr_accepted--;
+		msk->pm.subflows--;
+		WRITE_ONCE(msk->pm.accept_addr, true);
+
+		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMADDR);
+
+		break;
+	}
+}
+
+void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct sock *sk = (struct sock *)msk;
+
+	pr_debug("subflow rm_id %d", rm_id);
+
+	if (!rm_id)
+		return;
+
+	if (list_empty(&msk->conn_list))
+		return;
+
+	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
+
+		if (rm_id != subflow->local_id)
+			continue;
+
+		spin_unlock_bh(&msk->pm.lock);
+		mptcp_subflow_shutdown(sk, ssk, how);
+		__mptcp_close_ssk(sk, ssk, subflow);
+		spin_lock_bh(&msk->pm.lock);
+
+		msk->pm.local_addr_used--;
+		msk->pm.subflows--;
+
+		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW);
+
+		break;
+	}
 }
 
 static bool address_use_port(struct mptcp_pm_addr_entry *entry)
 {
-	return (entry->flags &
+	return (entry->addr.flags &
 		(MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) ==
 		MPTCP_PM_ADDR_FLAG_SIGNAL;
 }
@@ -303,9 +539,9 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 			goto out;
 	}
 
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)
+	if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)
 		pernet->add_addr_signal_max++;
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+	if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
 		pernet->local_addr_max++;
 
 	entry->addr.id = pernet->next_id++;
@@ -358,8 +594,9 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	if (!entry)
 		return -ENOMEM;
 
-	entry->flags = 0;
 	entry->addr = skc_local;
+	entry->addr.ifindex = 0;
+	entry->addr.flags = 0;
 	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry);
 	if (ret < 0)
 		kfree(entry);
@@ -397,8 +634,8 @@ mptcp_pm_addr_policy[MPTCP_PM_ADDR_ATTR_MAX + 1] = {
 	[MPTCP_PM_ADDR_ATTR_FAMILY]	= { .type	= NLA_U16,	},
 	[MPTCP_PM_ADDR_ATTR_ID]		= { .type	= NLA_U8,	},
 	[MPTCP_PM_ADDR_ATTR_ADDR4]	= { .type	= NLA_U32,	},
-	[MPTCP_PM_ADDR_ATTR_ADDR6]	= { .type	= NLA_EXACT_LEN,
-					    .len   = sizeof(struct in6_addr), },
+	[MPTCP_PM_ADDR_ATTR_ADDR6]	=
+		NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
 	[MPTCP_PM_ADDR_ATTR_PORT]	= { .type	= NLA_U16	},
 	[MPTCP_PM_ADDR_ATTR_FLAGS]	= { .type	= NLA_U32	},
 	[MPTCP_PM_ADDR_ATTR_IF_IDX]     = { .type	= NLA_S32	},
@@ -473,14 +710,17 @@ static int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info,
 		entry->addr.addr.s_addr = nla_get_in_addr(tb[addr_addr]);
 
 skip_family:
-	if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX])
-		entry->ifindex = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]);
+	if (tb[MPTCP_PM_ADDR_ATTR_IF_IDX]) {
+		u32 val = nla_get_s32(tb[MPTCP_PM_ADDR_ATTR_IF_IDX]);
+
+		entry->addr.ifindex = val;
+	}
 
 	if (tb[MPTCP_PM_ADDR_ATTR_ID])
 		entry->addr.id = nla_get_u8(tb[MPTCP_PM_ADDR_ATTR_ID]);
 
 	if (tb[MPTCP_PM_ADDR_ATTR_FLAGS])
-		entry->flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]);
+		entry->addr.flags = nla_get_u32(tb[MPTCP_PM_ADDR_ATTR_FLAGS]);
 
 	return 0;
 }
@@ -530,6 +770,68 @@ __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
 	return NULL;
 }
 
+static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
+				      struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *entry;
+
+	entry = mptcp_pm_del_add_timer(msk, addr);
+	if (entry) {
+		list_del(&entry->list);
+		kfree(entry);
+		return true;
+	}
+
+	return false;
+}
+
+static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
+				      struct mptcp_addr_info *addr,
+				      bool force)
+{
+	bool ret;
+
+	ret = remove_anno_list_by_saddr(msk, addr);
+	if (ret || force) {
+		spin_lock_bh(&msk->pm.lock);
+		mptcp_pm_remove_addr(msk, addr->id);
+		spin_unlock_bh(&msk->pm.lock);
+	}
+	return ret;
+}
+
+static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
+						   struct mptcp_addr_info *addr)
+{
+	struct mptcp_sock *msk;
+	long s_slot = 0, s_num = 0;
+
+	pr_debug("remove_id=%d", addr->id);
+
+	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
+		struct sock *sk = (struct sock *)msk;
+		bool remove_subflow;
+
+		if (list_empty(&msk->conn_list)) {
+			mptcp_pm_remove_anno_addr(msk, addr, false);
+			goto next;
+		}
+
+		lock_sock(sk);
+		remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
+		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow);
+		if (remove_subflow)
+			mptcp_pm_remove_subflow(msk, addr->id);
+		release_sock(sk);
+
+next:
+		sock_put(sk);
+		cond_resched();
+	}
+
+	return 0;
+}
+
 static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
@@ -545,29 +847,32 @@ static int mptcp_nl_cmd_del_addr(struct sk_buff *skb, struct genl_info *info)
 	entry = __lookup_addr_by_id(pernet, addr.addr.id);
 	if (!entry) {
 		GENL_SET_ERR_MSG(info, "address not found");
-		ret = -EINVAL;
-		goto out;
+		spin_unlock_bh(&pernet->lock);
+		return -EINVAL;
 	}
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)
+	if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)
 		pernet->add_addr_signal_max--;
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+	if (entry->addr.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
 		pernet->local_addr_max--;
 
 	pernet->addrs--;
 	list_del_rcu(&entry->list);
-	kfree_rcu(entry, rcu);
-out:
 	spin_unlock_bh(&pernet->lock);
+
+	mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), &entry->addr);
+	kfree_rcu(entry, rcu);
+
 	return ret;
 }
 
-static void __flush_addrs(struct pm_nl_pernet *pernet)
+static void __flush_addrs(struct net *net, struct list_head *list)
 {
-	while (!list_empty(&pernet->local_addr_list)) {
+	while (!list_empty(list)) {
 		struct mptcp_pm_addr_entry *cur;
 
-		cur = list_entry(pernet->local_addr_list.next,
+		cur = list_entry(list->next,
 				 struct mptcp_pm_addr_entry, list);
+		mptcp_nl_remove_subflow_and_signal_addr(net, &cur->addr);
 		list_del_rcu(&cur->list);
 		kfree_rcu(cur, rcu);
 	}
@@ -584,11 +889,13 @@ static void __reset_counters(struct pm_nl_pernet *pernet)
 static int mptcp_nl_cmd_flush_addrs(struct sk_buff *skb, struct genl_info *info)
 {
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
+	LIST_HEAD(free_list);
 
 	spin_lock_bh(&pernet->lock);
-	__flush_addrs(pernet);
+	list_splice_init(&pernet->local_addr_list, &free_list);
 	__reset_counters(pernet);
 	spin_unlock_bh(&pernet->lock);
+	__flush_addrs(sock_net(skb->sk), &free_list);
 	return 0;
 }
 
@@ -606,10 +913,10 @@ static int mptcp_nl_fill_addr(struct sk_buff *skb,
 		goto nla_put_failure;
 	if (nla_put_u8(skb, MPTCP_PM_ADDR_ATTR_ID, addr->id))
 		goto nla_put_failure;
-	if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->flags))
+	if (nla_put_u32(skb, MPTCP_PM_ADDR_ATTR_FLAGS, entry->addr.flags))
 		goto nla_put_failure;
-	if (entry->ifindex &&
-	    nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->ifindex))
+	if (entry->addr.ifindex &&
+	    nla_put_s32(skb, MPTCP_PM_ADDR_ATTR_IF_IDX, entry->addr.ifindex))
 		goto nla_put_failure;
 
 	if (addr->family == AF_INET &&
@@ -789,7 +1096,7 @@ fail:
 	return -EMSGSIZE;
 }
 
-static struct genl_ops mptcp_pm_ops[] = {
+static const struct genl_small_ops mptcp_pm_ops[] = {
 	{
 		.cmd    = MPTCP_PM_CMD_ADD_ADDR,
 		.doit   = mptcp_nl_cmd_add_addr,
@@ -828,8 +1135,8 @@ static struct genl_family mptcp_genl_family __ro_after_init = {
 	.policy		= mptcp_pm_policy,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= mptcp_pm_ops,
-	.n_ops		= ARRAY_SIZE(mptcp_pm_ops),
+	.small_ops	= mptcp_pm_ops,
+	.n_small_ops	= ARRAY_SIZE(mptcp_pm_ops),
 	.mcgrps		= mptcp_pm_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(mptcp_pm_mcgrps),
 };
@@ -850,10 +1157,12 @@ static void __net_exit pm_nl_exit_net(struct list_head *net_list)
 	struct net *net;
 
 	list_for_each_entry(net, net_list, exit_list) {
+		struct pm_nl_pernet *pernet = net_generic(net, pm_nl_pernet_id);
+
 		/* net is removed from namespace list, can't race with
 		 * other modifiers
 		 */
-		__flush_addrs(net_generic(net, pm_nl_pernet_id));
+		__flush_addrs(net, &pernet->local_addr_list);
 	}
 }
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 5d747c6a610e..f998a077c7dd 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -21,11 +21,10 @@
 #include <net/transp_v6.h>
 #endif
 #include <net/mptcp.h>
+#include <net/xfrm.h>
 #include "protocol.h"
 #include "mib.h"
 
-#define MPTCP_SAME_STATE TCP_MAX_STATES
-
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 struct mptcp6_sock {
 	struct mptcp_sock msk;
@@ -34,6 +33,8 @@ struct mptcp6_sock {
 #endif
 
 struct mptcp_skb_cb {
+	u64 map_seq;
+	u64 end_seq;
 	u32 offset;
 };
 
@@ -41,6 +42,9 @@ struct mptcp_skb_cb {
 
 static struct percpu_counter mptcp_sockets_allocated;
 
+static void __mptcp_destroy_sock(struct sock *sk);
+static void __mptcp_check_send_data_fin(struct sock *sk);
+
 /* If msk has an initial subflow socket, and the MP_CAPABLE handshake has not
  * completed yet or has failed, return the subflow socket.
  * Otherwise return NULL.
@@ -53,6 +57,12 @@ static struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk)
 	return msk->subflow;
 }
 
+/* Returns end sequence number of the receiver's advertised window */
+static u64 mptcp_wnd_end(const struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->wnd_end);
+}
+
 static bool mptcp_is_tcpsk(struct sock *sk)
 {
 	struct socket *sock = sk->sk_socket;
@@ -102,6 +112,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	msk->subflow = ssock;
 	subflow = mptcp_subflow_ctx(ssock->sk);
 	list_add(&subflow->node, &msk->conn_list);
+	sock_hold(ssock->sk);
 	subflow->request_mptcp = 1;
 
 	/* accept() will wait on first subflow sk_wq, and we always wakes up
@@ -112,35 +123,208 @@ static int __mptcp_socket_create(struct mptcp_sock *msk)
 	return 0;
 }
 
-static void __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
-			     struct sk_buff *skb,
-			     unsigned int offset, size_t copy_len)
+static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
+{
+	sk_drops_add(sk, skb);
+	__kfree_skb(skb);
+}
+
+static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
+			       struct sk_buff *from)
+{
+	bool fragstolen;
+	int delta;
+
+	if (MPTCP_SKB_CB(from)->offset ||
+	    !skb_try_coalesce(to, from, &fragstolen, &delta))
+		return false;
+
+	pr_debug("colesced seq %llx into %llx new len %d new end seq %llx",
+		 MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
+		 to->len, MPTCP_SKB_CB(from)->end_seq);
+	MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
+	kfree_skb_partial(from, fragstolen);
+	atomic_add(delta, &sk->sk_rmem_alloc);
+	sk_mem_charge(sk, delta);
+	return true;
+}
+
+static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
+				   struct sk_buff *from)
+{
+	if (MPTCP_SKB_CB(from)->map_seq != MPTCP_SKB_CB(to)->end_seq)
+		return false;
+
+	return mptcp_try_coalesce((struct sock *)msk, to, from);
+}
+
+/* "inspired" by tcp_data_queue_ofo(), main differences:
+ * - use mptcp seqs
+ * - don't cope with sacks
+ */
+static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 {
 	struct sock *sk = (struct sock *)msk;
-	struct sk_buff *tail;
+	struct rb_node **p, *parent;
+	u64 seq, end_seq, max_seq;
+	struct sk_buff *skb1;
+
+	seq = MPTCP_SKB_CB(skb)->map_seq;
+	end_seq = MPTCP_SKB_CB(skb)->end_seq;
+	max_seq = READ_ONCE(msk->rcv_wnd_sent);
+
+	pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
+		 RB_EMPTY_ROOT(&msk->out_of_order_queue));
+	if (after64(end_seq, max_seq)) {
+		/* out of window */
+		mptcp_drop(sk, skb);
+		pr_debug("oow by %lld, rcv_wnd_sent %llu\n",
+			 (unsigned long long)end_seq - (unsigned long)max_seq,
+			 (unsigned long long)msk->rcv_wnd_sent);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW);
+		return;
+	}
 
-	__skb_unlink(skb, &ssk->sk_receive_queue);
+	p = &msk->out_of_order_queue.rb_node;
+	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUE);
+	if (RB_EMPTY_ROOT(&msk->out_of_order_queue)) {
+		rb_link_node(&skb->rbnode, NULL, p);
+		rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);
+		msk->ooo_last_skb = skb;
+		goto end;
+	}
 
-	skb_ext_reset(skb);
-	skb_orphan(skb);
-	WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len);
+	/* with 2 subflows, adding at end of ooo queue is quite likely
+	 * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup.
+	 */
+	if (mptcp_ooo_try_coalesce(msk, msk->ooo_last_skb, skb)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL);
+		return;
+	}
 
-	tail = skb_peek_tail(&sk->sk_receive_queue);
-	if (offset == 0 && tail) {
-		bool fragstolen;
-		int delta;
+	/* Can avoid an rbtree lookup if we are adding skb after ooo_last_skb */
+	if (!before64(seq, MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOQUEUETAIL);
+		parent = &msk->ooo_last_skb->rbnode;
+		p = &parent->rb_right;
+		goto insert;
+	}
 
-		if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) {
-			kfree_skb_partial(skb, fragstolen);
-			atomic_add(delta, &sk->sk_rmem_alloc);
-			sk_mem_charge(sk, delta);
+	/* Find place to insert this segment. Handle overlaps on the way. */
+	parent = NULL;
+	while (*p) {
+		parent = *p;
+		skb1 = rb_to_skb(parent);
+		if (before64(seq, MPTCP_SKB_CB(skb1)->map_seq)) {
+			p = &parent->rb_left;
+			continue;
+		}
+		if (before64(seq, MPTCP_SKB_CB(skb1)->end_seq)) {
+			if (!after64(end_seq, MPTCP_SKB_CB(skb1)->end_seq)) {
+				/* All the bits are present. Drop. */
+				mptcp_drop(sk, skb);
+				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+				return;
+			}
+			if (after64(seq, MPTCP_SKB_CB(skb1)->map_seq)) {
+				/* partial overlap:
+				 *     |     skb      |
+				 *  |     skb1    |
+				 * continue traversing
+				 */
+			} else {
+				/* skb's seq == skb1's seq and skb covers skb1.
+				 * Replace skb1 with skb.
+				 */
+				rb_replace_node(&skb1->rbnode, &skb->rbnode,
+						&msk->out_of_order_queue);
+				mptcp_drop(sk, skb1);
+				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+				goto merge_right;
+			}
+		} else if (mptcp_ooo_try_coalesce(msk, skb1, skb)) {
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_OFOMERGE);
 			return;
 		}
+		p = &parent->rb_right;
 	}
 
+insert:
+	/* Insert segment into RB tree. */
+	rb_link_node(&skb->rbnode, parent, p);
+	rb_insert_color(&skb->rbnode, &msk->out_of_order_queue);
+
+merge_right:
+	/* Remove other segments covered by skb. */
+	while ((skb1 = skb_rb_next(skb)) != NULL) {
+		if (before64(end_seq, MPTCP_SKB_CB(skb1)->end_seq))
+			break;
+		rb_erase(&skb1->rbnode, &msk->out_of_order_queue);
+		mptcp_drop(sk, skb1);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+	}
+	/* If there is no skb after us, we are the last_skb ! */
+	if (!skb1)
+		msk->ooo_last_skb = skb;
+
+end:
+	skb_condense(skb);
 	skb_set_owner_r(skb, sk);
-	__skb_queue_tail(&sk->sk_receive_queue, skb);
+}
+
+static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
+			     struct sk_buff *skb, unsigned int offset,
+			     size_t copy_len)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct sock *sk = (struct sock *)msk;
+	struct sk_buff *tail;
+
+	__skb_unlink(skb, &ssk->sk_receive_queue);
+
+	skb_ext_reset(skb);
+	skb_orphan(skb);
+
+	/* try to fetch required memory from subflow */
+	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
+		if (ssk->sk_forward_alloc < skb->truesize)
+			goto drop;
+		__sk_mem_reclaim(ssk, skb->truesize);
+		if (!sk_rmem_schedule(sk, skb, skb->truesize))
+			goto drop;
+	}
+
+	/* the skb map_seq accounts for the skb offset:
+	 * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
+	 * value
+	 */
+	MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow);
+	MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len;
 	MPTCP_SKB_CB(skb)->offset = offset;
+
+	if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
+		/* in sequence */
+		WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len);
+		tail = skb_peek_tail(&sk->sk_receive_queue);
+		if (tail && mptcp_try_coalesce(sk, tail, skb))
+			return true;
+
+		skb_set_owner_r(skb, sk);
+		__skb_queue_tail(&sk->sk_receive_queue, skb);
+		return true;
+	} else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) {
+		mptcp_data_queue_ofo(msk, skb);
+		return false;
+	}
+
+	/* old data, keep it simple and drop the whole pkt, sender
+	 * will retransmit as needed, if needed.
+	 */
+	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+drop:
+	mptcp_drop(sk, skb);
+	return false;
 }
 
 static void mptcp_stop_timer(struct sock *sk)
@@ -151,38 +335,35 @@ static void mptcp_stop_timer(struct sock *sk)
 	mptcp_sk(sk)->timer_ival = 0;
 }
 
-/* both sockets must be locked */
-static bool mptcp_subflow_dsn_valid(const struct mptcp_sock *msk,
-				    struct sock *ssk)
+static void mptcp_close_wake_up(struct sock *sk)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
-	u64 dsn = mptcp_subflow_get_mapped_dsn(subflow);
+	if (sock_flag(sk, SOCK_DEAD))
+		return;
 
-	/* revalidate data sequence number.
-	 *
-	 * mptcp_subflow_data_available() is usually called
-	 * without msk lock.  Its unlikely (but possible)
-	 * that msk->ack_seq has been advanced since the last
-	 * call found in-sequence data.
-	 */
-	if (likely(dsn == msk->ack_seq))
-		return true;
+	sk->sk_state_change(sk);
+	if (sk->sk_shutdown == SHUTDOWN_MASK ||
+	    sk->sk_state == TCP_CLOSE)
+		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
+	else
+		sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+}
+
+static bool mptcp_pending_data_fin_ack(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	subflow->data_avail = 0;
-	return mptcp_subflow_data_available(ssk);
+	return !__mptcp_check_fallback(msk) &&
+	       ((1 << sk->sk_state) &
+		(TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
+	       msk->write_seq == READ_ONCE(msk->snd_una);
 }
 
 static void mptcp_check_data_fin_ack(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	if (__mptcp_check_fallback(msk))
-		return;
-
 	/* Look for an acknowledged DATA_FIN */
-	if (((1 << sk->sk_state) &
-	     (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK)) &&
-	    msk->write_seq == atomic64_read(&msk->snd_una)) {
+	if (mptcp_pending_data_fin_ack(sk)) {
 		mptcp_stop_timer(sk);
 
 		WRITE_ONCE(msk->snd_data_fin_enable, 0);
@@ -190,20 +371,14 @@ static void mptcp_check_data_fin_ack(struct sock *sk)
 		switch (sk->sk_state) {
 		case TCP_FIN_WAIT1:
 			inet_sk_state_store(sk, TCP_FIN_WAIT2);
-			sk->sk_state_change(sk);
 			break;
 		case TCP_CLOSING:
 		case TCP_LAST_ACK:
 			inet_sk_state_store(sk, TCP_CLOSE);
-			sk->sk_state_change(sk);
 			break;
 		}
 
-		if (sk->sk_shutdown == SHUTDOWN_MASK ||
-		    sk->sk_state == TCP_CLOSE)
-			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
-		else
-			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+		mptcp_close_wake_up(sk);
 	}
 }
 
@@ -237,13 +412,79 @@ static void mptcp_set_timeout(const struct sock *sk, const struct sock *ssk)
 	mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN;
 }
 
-static void mptcp_check_data_fin(struct sock *sk)
+static bool mptcp_subflow_active(struct mptcp_subflow_context *subflow)
+{
+	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+	/* can't send if JOIN hasn't completed yet (i.e. is usable for mptcp) */
+	if (subflow->request_join && !subflow->fully_established)
+		return false;
+
+	/* only send if our side has not closed yet */
+	return ((1 << ssk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT));
+}
+
+static bool tcp_can_send_ack(const struct sock *ssk)
+{
+	return !((1 << inet_sk_state_load(ssk)) &
+	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
+}
+
+static void mptcp_send_ack(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		lock_sock(ssk);
+		if (tcp_can_send_ack(ssk))
+			tcp_send_ack(ssk);
+		release_sock(ssk);
+	}
+}
+
+static bool mptcp_subflow_cleanup_rbuf(struct sock *ssk)
+{
+	int ret;
+
+	lock_sock(ssk);
+	ret = tcp_can_send_ack(ssk);
+	if (ret)
+		tcp_cleanup_rbuf(ssk, 1);
+	release_sock(ssk);
+	return ret;
+}
+
+static void mptcp_cleanup_rbuf(struct mptcp_sock *msk)
+{
+	struct sock *ack_hint = READ_ONCE(msk->ack_hint);
+	struct mptcp_subflow_context *subflow;
+
+	/* if the hinted ssk is still active, try to use it */
+	if (likely(ack_hint)) {
+		mptcp_for_each_subflow(msk, subflow) {
+			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+			if (ack_hint == ssk && mptcp_subflow_cleanup_rbuf(ssk))
+				return;
+		}
+	}
+
+	/* otherwise pick the first active subflow */
+	mptcp_for_each_subflow(msk, subflow)
+		if (mptcp_subflow_cleanup_rbuf(mptcp_subflow_tcp_sock(subflow)))
+			return;
+}
+
+static bool mptcp_check_data_fin(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	u64 rcv_data_fin_seq;
+	bool ret = false;
 
 	if (__mptcp_check_fallback(msk) || !msk->first)
-		return;
+		return ret;
 
 	/* Need to ack a DATA_FIN received from a peer while this side
 	 * of the connection is in ESTABLISHED, FIN_WAIT1, or FIN_WAIT2.
@@ -259,8 +500,6 @@ static void mptcp_check_data_fin(struct sock *sk)
 	 */
 
 	if (mptcp_pending_data_fin(sk, &rcv_data_fin_seq)) {
-		struct mptcp_subflow_context *subflow;
-
 		WRITE_ONCE(msk->ack_seq, msk->ack_seq + 1);
 		WRITE_ONCE(msk->rcv_data_fin, 0);
 
@@ -277,7 +516,6 @@ static void mptcp_check_data_fin(struct sock *sk)
 			break;
 		case TCP_FIN_WAIT2:
 			inet_sk_state_store(sk, TCP_CLOSE);
-			// @@ Close subflows now?
 			break;
 		default:
 			/* Other states not expected */
@@ -285,23 +523,12 @@ static void mptcp_check_data_fin(struct sock *sk)
 			break;
 		}
 
+		ret = true;
 		mptcp_set_timeout(sk, NULL);
-		mptcp_for_each_subflow(msk, subflow) {
-			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-			lock_sock(ssk);
-			tcp_send_ack(ssk);
-			release_sock(ssk);
-		}
-
-		sk->sk_state_change(sk);
-
-		if (sk->sk_shutdown == SHUTDOWN_MASK ||
-		    sk->sk_state == TCP_CLOSE)
-			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_HUP);
-		else
-			sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN);
+		mptcp_send_ack(msk);
+		mptcp_close_wake_up(sk);
 	}
+	return ret;
 }
 
 static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
@@ -314,12 +541,20 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 	bool more_data_avail;
 	struct tcp_sock *tp;
 	bool done = false;
+	int sk_rbuf;
 
-	if (!mptcp_subflow_dsn_valid(msk, ssk)) {
-		*bytes = 0;
-		return false;
+	sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+
+	if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+		int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+
+		if (unlikely(ssk_rbuf > sk_rbuf)) {
+			WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf);
+			sk_rbuf = ssk_rbuf;
+		}
 	}
 
+	pr_debug("msk=%p ssk=%p", msk, ssk);
 	tp = tcp_sk(ssk);
 	do {
 		u32 map_remaining, offset;
@@ -332,8 +567,15 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 				mptcp_subflow_get_map_offset(subflow);
 
 		skb = skb_peek(&ssk->sk_receive_queue);
-		if (!skb)
+		if (!skb) {
+			/* if no data is found, a racing workqueue/recvmsg
+			 * already processed the new data, stop here or we
+			 * can enter an infinite loop
+			 */
+			if (!moved)
+				done = true;
 			break;
+		}
 
 		if (__mptcp_check_fallback(msk)) {
 			/* if we are running under the workqueue, TCP could have
@@ -357,9 +599,9 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 			if (tp->urg_data)
 				done = true;
 
-			__mptcp_move_skb(msk, ssk, skb, offset, len);
+			if (__mptcp_move_skb(msk, ssk, skb, offset, len))
+				moved += len;
 			seq += len;
-			moved += len;
 
 			if (WARN_ON_ONCE(map_remaining < len))
 				break;
@@ -372,78 +614,125 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 		WRITE_ONCE(tp->copied_seq, seq);
 		more_data_avail = mptcp_subflow_data_available(ssk);
 
-		if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf)) {
+		if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) {
 			done = true;
 			break;
 		}
 	} while (more_data_avail);
+	WRITE_ONCE(msk->ack_hint, ssk);
 
-	*bytes = moved;
+	*bytes += moved;
+	return done;
+}
 
-	/* If the moves have caught up with the DATA_FIN sequence number
-	 * it's time to ack the DATA_FIN and change socket state, but
-	 * this is not a good place to change state. Let the workqueue
-	 * do it.
-	 */
-	if (mptcp_pending_data_fin(sk, NULL) &&
-	    schedule_work(&msk->work))
-		sock_hold(sk);
+static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
+{
+	struct sock *sk = (struct sock *)msk;
+	struct sk_buff *skb, *tail;
+	bool moved = false;
+	struct rb_node *p;
+	u64 end_seq;
+
+	p = rb_first(&msk->out_of_order_queue);
+	pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
+	while (p) {
+		skb = rb_to_skb(p);
+		if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq))
+			break;
 
-	return done;
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, &msk->out_of_order_queue);
+
+		if (unlikely(!after64(MPTCP_SKB_CB(skb)->end_seq,
+				      msk->ack_seq))) {
+			mptcp_drop(sk, skb);
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_DUPDATA);
+			continue;
+		}
+
+		end_seq = MPTCP_SKB_CB(skb)->end_seq;
+		tail = skb_peek_tail(&sk->sk_receive_queue);
+		if (!tail || !mptcp_ooo_try_coalesce(msk, tail, skb)) {
+			int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
+
+			/* skip overlapping data, if any */
+			pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d",
+				 MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
+				 delta);
+			MPTCP_SKB_CB(skb)->offset += delta;
+			__skb_queue_tail(&sk->sk_receive_queue, skb);
+		}
+		msk->ack_seq = end_seq;
+		moved = true;
+	}
+	return moved;
 }
 
 /* In most cases we will be able to lock the mptcp socket.  If its already
  * owned, we need to defer to the work queue to avoid ABBA deadlock.
  */
-static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
+static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct sock *sk = (struct sock *)msk;
 	unsigned int moved = 0;
 
-	if (READ_ONCE(sk->sk_lock.owned))
-		return false;
-
-	if (unlikely(!spin_trylock_bh(&sk->sk_lock.slock)))
-		return false;
+	if (inet_sk_state_load(sk) == TCP_CLOSE)
+		return;
 
-	/* must re-check after taking the lock */
-	if (!READ_ONCE(sk->sk_lock.owned))
-		__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
+	mptcp_data_lock(sk);
 
-	spin_unlock_bh(&sk->sk_lock.slock);
+	__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
+	__mptcp_ofo_queue(msk);
 
-	return moved > 0;
+	/* If the moves have caught up with the DATA_FIN sequence number
+	 * it's time to ack the DATA_FIN and change socket state, but
+	 * this is not a good place to change state. Let the workqueue
+	 * do it.
+	 */
+	if (mptcp_pending_data_fin(sk, NULL))
+		mptcp_schedule_work(sk);
+	mptcp_data_unlock(sk);
 }
 
 void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 {
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct mptcp_sock *msk = mptcp_sk(sk);
+	int sk_rbuf, ssk_rbuf;
+	bool wake;
 
-	set_bit(MPTCP_DATA_READY, &msk->flags);
+	/* The peer can send data while we are shutting down this
+	 * subflow at msk destruction time, but we must avoid enqueuing
+	 * more data to the msk receive queue
+	 */
+	if (unlikely(subflow->disposable))
+		return;
 
-	if (atomic_read(&sk->sk_rmem_alloc) < READ_ONCE(sk->sk_rcvbuf) &&
-	    move_skbs_to_msk(msk, ssk))
-		goto wake;
+	/* move_skbs_to_msk below can legitly clear the data_avail flag,
+	 * but we will need later to properly woke the reader, cache its
+	 * value
+	 */
+	wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL;
+	if (wake)
+		set_bit(MPTCP_DATA_READY, &msk->flags);
 
-	/* don't schedule if mptcp sk is (still) over limit */
-	if (atomic_read(&sk->sk_rmem_alloc) > READ_ONCE(sk->sk_rcvbuf))
+	ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
+	sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
+	if (unlikely(ssk_rbuf > sk_rbuf))
+		sk_rbuf = ssk_rbuf;
+
+	/* over limit? can't append more skbs to msk */
+	if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf)
 		goto wake;
 
-	/* mptcp socket is owned, release_cb should retry */
-	if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
-			      &sk->sk_tsq_flags)) {
-		sock_hold(sk);
+	move_skbs_to_msk(msk, ssk);
 
-		/* need to try again, its possible release_cb() has already
-		 * been called after the test_and_set_bit() above.
-		 */
-		move_skbs_to_msk(msk, ssk);
-	}
 wake:
-	sk->sk_data_ready(sk);
+	if (wake)
+		sk->sk_data_ready(sk);
 }
 
-static void __mptcp_flush_join_list(struct mptcp_sock *msk)
+void __mptcp_flush_join_list(struct mptcp_sock *msk)
 {
 	if (likely(list_empty(&msk->join_list)))
 		return;
@@ -463,6 +752,10 @@ static void mptcp_reset_timer(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	unsigned long tout;
 
+	/* prevent rescheduling on close */
+	if (unlikely(inet_sk_state_load(sk) == TCP_CLOSE))
+		return;
+
 	/* should never be called with mptcp level timer cleared */
 	tout = READ_ONCE(mptcp_sk(sk)->timer_ival);
 	if (WARN_ON_ONCE(!tout))
@@ -470,23 +763,23 @@ static void mptcp_reset_timer(struct sock *sk)
 	sk_reset_timer(sk, &icsk->icsk_retransmit_timer, jiffies + tout);
 }
 
-void mptcp_data_acked(struct sock *sk)
+bool mptcp_schedule_work(struct sock *sk)
 {
-	mptcp_reset_timer(sk);
-
-	if ((!sk_stream_is_writeable(sk) ||
-	     (inet_sk_state_load(sk) != TCP_ESTABLISHED)) &&
-	    schedule_work(&mptcp_sk(sk)->work))
+	if (inet_sk_state_load(sk) != TCP_CLOSE &&
+	    schedule_work(&mptcp_sk(sk)->work)) {
+		/* each subflow already holds a reference to the sk, and the
+		 * workqueue is invoked by a subflow, so sk can't go away here.
+		 */
 		sock_hold(sk);
+		return true;
+	}
+	return false;
 }
 
 void mptcp_subflow_eof(struct sock *sk)
 {
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	if (!test_and_set_bit(MPTCP_WORK_EOF, &msk->flags) &&
-	    schedule_work(&msk->work))
-		sock_hold(sk);
+	if (!test_and_set_bit(MPTCP_WORK_EOF, &mptcp_sk(sk)->flags))
+		mptcp_schedule_work(sk);
 }
 
 static void mptcp_check_for_eof(struct mptcp_sock *msk)
@@ -497,8 +790,10 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
 
 	mptcp_for_each_subflow(msk, subflow)
 		receivers += !subflow->rx_eof;
+	if (receivers)
+		return;
 
-	if (!receivers && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
+	if (!(sk->sk_shutdown & RCV_SHUTDOWN)) {
 		/* hopefully temporary hack: propagate shutdown status
 		 * to msk, when all subflows agree on it
 		 */
@@ -508,16 +803,21 @@ static void mptcp_check_for_eof(struct mptcp_sock *msk)
 		set_bit(MPTCP_DATA_READY, &msk->flags);
 		sk->sk_data_ready(sk);
 	}
-}
-
-static bool mptcp_ext_cache_refill(struct mptcp_sock *msk)
-{
-	const struct sock *sk = (const struct sock *)msk;
 
-	if (!msk->cached_ext)
-		msk->cached_ext = __skb_ext_alloc(sk->sk_allocation);
-
-	return !!msk->cached_ext;
+	switch (sk->sk_state) {
+	case TCP_ESTABLISHED:
+		inet_sk_state_store(sk, TCP_CLOSE_WAIT);
+		break;
+	case TCP_FIN_WAIT1:
+		inet_sk_state_store(sk, TCP_CLOSING);
+		break;
+	case TCP_FIN_WAIT2:
+		inet_sk_state_store(sk, TCP_CLOSE);
+		break;
+	default:
+		return;
+	}
+	mptcp_close_wake_up(sk);
 }
 
 static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
@@ -542,8 +842,11 @@ static bool mptcp_skb_can_collapse_to(u64 write_seq,
 	if (!tcp_skb_can_collapse_to(skb))
 		return false;
 
-	/* can collapse only if MPTCP level sequence is in order */
-	return mpext && mpext->data_seq + mpext->data_len == write_seq;
+	/* can collapse only if MPTCP level sequence is in order and this
+	 * mapping has not been xmitted yet
+	 */
+	return mpext && mpext->data_seq + mpext->data_len == write_seq &&
+	       !mpext->frozen;
 }
 
 static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
@@ -551,9 +854,128 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
 				       const struct mptcp_data_frag *df)
 {
 	return df && pfrag->page == df->page &&
+		pfrag->size - pfrag->offset > 0 &&
 		df->data_seq + df->data_len == msk->write_seq;
 }
 
+static int mptcp_wmem_with_overhead(struct sock *sk, int size)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	int ret, skbs;
+
+	ret = size + ((sizeof(struct mptcp_data_frag) * size) >> PAGE_SHIFT);
+	skbs = (msk->tx_pending_data + size) / msk->size_goal_cache;
+	if (skbs < msk->skb_tx_cache.qlen)
+		return ret;
+
+	return ret + (skbs - msk->skb_tx_cache.qlen) * SKB_TRUESIZE(MAX_TCP_HEADER);
+}
+
+static void __mptcp_wmem_reserve(struct sock *sk, int size)
+{
+	int amount = mptcp_wmem_with_overhead(sk, size);
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	WARN_ON_ONCE(msk->wmem_reserved);
+	if (WARN_ON_ONCE(amount < 0))
+		amount = 0;
+
+	if (amount <= sk->sk_forward_alloc)
+		goto reserve;
+
+	/* under memory pressure try to reserve at most a single page
+	 * otherwise try to reserve the full estimate and fallback
+	 * to a single page before entering the error path
+	 */
+	if ((tcp_under_memory_pressure(sk) && amount > PAGE_SIZE) ||
+	    !sk_wmem_schedule(sk, amount)) {
+		if (amount <= PAGE_SIZE)
+			goto nomem;
+
+		amount = PAGE_SIZE;
+		if (!sk_wmem_schedule(sk, amount))
+			goto nomem;
+	}
+
+reserve:
+	msk->wmem_reserved = amount;
+	sk->sk_forward_alloc -= amount;
+	return;
+
+nomem:
+	/* we will wait for memory on next allocation */
+	msk->wmem_reserved = -1;
+}
+
+static void __mptcp_update_wmem(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (!msk->wmem_reserved)
+		return;
+
+	if (msk->wmem_reserved < 0)
+		msk->wmem_reserved = 0;
+	if (msk->wmem_reserved > 0) {
+		sk->sk_forward_alloc += msk->wmem_reserved;
+		msk->wmem_reserved = 0;
+	}
+}
+
+static bool mptcp_wmem_alloc(struct sock *sk, int size)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	/* check for pre-existing error condition */
+	if (msk->wmem_reserved < 0)
+		return false;
+
+	if (msk->wmem_reserved >= size)
+		goto account;
+
+	mptcp_data_lock(sk);
+	if (!sk_wmem_schedule(sk, size)) {
+		mptcp_data_unlock(sk);
+		return false;
+	}
+
+	sk->sk_forward_alloc -= size;
+	msk->wmem_reserved += size;
+	mptcp_data_unlock(sk);
+
+account:
+	msk->wmem_reserved -= size;
+	return true;
+}
+
+static void mptcp_wmem_uncharge(struct sock *sk, int size)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (msk->wmem_reserved < 0)
+		msk->wmem_reserved = 0;
+	msk->wmem_reserved += size;
+}
+
+static void mptcp_mem_reclaim_partial(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	/* if we are experiencing a transint allocation error,
+	 * the forward allocation memory has been already
+	 * released
+	 */
+	if (msk->wmem_reserved < 0)
+		return;
+
+	mptcp_data_lock(sk);
+	sk->sk_forward_alloc += msk->wmem_reserved;
+	sk_mem_reclaim_partial(sk);
+	msk->wmem_reserved = sk->sk_forward_alloc;
+	sk->sk_forward_alloc = 0;
+	mptcp_data_unlock(sk);
+}
+
 static void dfrag_uncharge(struct sock *sk, int len)
 {
 	sk_mem_uncharge(sk, len);
@@ -569,7 +991,7 @@ static void dfrag_clear(struct sock *sk, struct mptcp_data_frag *dfrag)
 	put_page(dfrag->page);
 }
 
-static void mptcp_clean_una(struct sock *sk)
+static void __mptcp_clean_una(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_data_frag *dtmp, *dfrag;
@@ -580,13 +1002,15 @@ static void mptcp_clean_una(struct sock *sk)
 	 * plain TCP
 	 */
 	if (__mptcp_check_fallback(msk))
-		atomic64_set(&msk->snd_una, msk->write_seq);
-	snd_una = atomic64_read(&msk->snd_una);
+		msk->snd_una = READ_ONCE(msk->snd_nxt);
 
+	snd_una = msk->snd_una;
 	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) {
 		if (after64(dfrag->data_seq + dfrag->data_len, snd_una))
 			break;
 
+		if (WARN_ON_ONCE(dfrag == msk->first_pending))
+			break;
 		dfrag_clear(sk, dfrag);
 		cleaned = true;
 	}
@@ -595,12 +1019,13 @@ static void mptcp_clean_una(struct sock *sk)
 	if (dfrag && after64(snd_una, dfrag->data_seq)) {
 		u64 delta = snd_una - dfrag->data_seq;
 
-		if (WARN_ON_ONCE(delta > dfrag->data_len))
+		if (WARN_ON_ONCE(delta > dfrag->already_sent))
 			goto out;
 
 		dfrag->data_seq += delta;
 		dfrag->offset += delta;
 		dfrag->data_len -= delta;
+		dfrag->already_sent -= delta;
 
 		dfrag_uncharge(sk, delta);
 		cleaned = true;
@@ -608,11 +1033,41 @@ static void mptcp_clean_una(struct sock *sk)
 
 out:
 	if (cleaned) {
-		sk_mem_reclaim_partial(sk);
+		if (tcp_under_memory_pressure(sk)) {
+			__mptcp_update_wmem(sk);
+			sk_mem_reclaim_partial(sk);
+		}
 
-		/* Only wake up writers if a subflow is ready */
-		if (test_bit(MPTCP_SEND_SPACE, &msk->flags))
-			sk_stream_write_space(sk);
+		if (sk_stream_is_writeable(sk)) {
+			/* pairs with memory barrier in mptcp_poll */
+			smp_mb();
+			if (test_and_clear_bit(MPTCP_NOSPACE, &msk->flags))
+				sk_stream_write_space(sk);
+		}
+	}
+
+	if (snd_una == READ_ONCE(msk->snd_nxt)) {
+		if (msk->timer_ival)
+			mptcp_stop_timer(sk);
+	} else {
+		mptcp_reset_timer(sk);
+	}
+}
+
+static void mptcp_enter_memory_pressure(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	bool first = true;
+
+	sk_stream_moderate_sndbuf(sk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		if (first)
+			tcp_enter_memory_pressure(ssk);
+		sk_stream_moderate_sndbuf(ssk);
+		first = false;
 	}
 }
 
@@ -625,8 +1080,7 @@ static bool mptcp_page_frag_refill(struct sock *sk, struct page_frag *pfrag)
 					pfrag, sk->sk_allocation)))
 		return true;
 
-	sk->sk_prot->enter_memory_pressure(sk);
-	sk_stream_moderate_sndbuf(sk);
+	mptcp_enter_memory_pressure(sk);
 	return false;
 }
 
@@ -642,149 +1096,241 @@ mptcp_carve_data_frag(const struct mptcp_sock *msk, struct page_frag *pfrag,
 	dfrag->data_seq = msk->write_seq;
 	dfrag->overhead = offset - orig_offset + sizeof(struct mptcp_data_frag);
 	dfrag->offset = offset + sizeof(struct mptcp_data_frag);
+	dfrag->already_sent = 0;
 	dfrag->page = pfrag->page;
 
 	return dfrag;
 }
 
-static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
-			      struct msghdr *msg, struct mptcp_data_frag *dfrag,
-			      long *timeo, int *pmss_now,
-			      int *ps_goal)
+struct mptcp_sendmsg_info {
+	int mss_now;
+	int size_goal;
+	u16 limit;
+	u16 sent;
+	unsigned int flags;
+};
+
+static int mptcp_check_allowed_size(struct mptcp_sock *msk, u64 data_seq,
+				    int avail_size)
+{
+	u64 window_end = mptcp_wnd_end(msk);
+
+	if (__mptcp_check_fallback(msk))
+		return avail_size;
+
+	if (!before64(data_seq + avail_size, window_end)) {
+		u64 allowed_size = window_end - data_seq;
+
+		return min_t(unsigned int, allowed_size, avail_size);
+	}
+
+	return avail_size;
+}
+
+static bool __mptcp_add_ext(struct sk_buff *skb, gfp_t gfp)
+{
+	struct skb_ext *mpext = __skb_ext_alloc(gfp);
+
+	if (!mpext)
+		return false;
+	__skb_ext_set(skb, SKB_EXT_MPTCP, mpext);
+	return true;
+}
+
+static struct sk_buff *__mptcp_do_alloc_tx_skb(struct sock *sk, gfp_t gfp)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb_fclone(MAX_TCP_HEADER, gfp);
+	if (likely(skb)) {
+		if (likely(__mptcp_add_ext(skb, gfp))) {
+			skb_reserve(skb, MAX_TCP_HEADER);
+			skb->reserved_tailroom = skb->end - skb->tail;
+			return skb;
+		}
+		__kfree_skb(skb);
+	} else {
+		mptcp_enter_memory_pressure(sk);
+	}
+	return NULL;
+}
+
+static bool mptcp_tx_cache_refill(struct sock *sk, int size,
+				  struct sk_buff_head *skbs, int *total_ts)
 {
-	int mss_now, avail_size, size_goal, offset, ret, frag_truesize = 0;
-	bool dfrag_collapsed, can_collapse = false;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	struct mptcp_ext *mpext = NULL;
-	bool retransmission = !!dfrag;
-	struct sk_buff *skb, *tail;
-	struct page_frag *pfrag;
-	struct page *page;
-	u64 *write_seq;
-	size_t psize;
-
-	/* use the mptcp page cache so that we can easily move the data
-	 * from one substream to another, but do per subflow memory accounting
-	 * Note: pfrag is used only !retransmission, but the compiler if
-	 * fooled into a warning if we don't init here
-	 */
-	pfrag = sk_page_frag(sk);
-	if (!retransmission) {
-		write_seq = &msk->write_seq;
-		page = pfrag->page;
+	struct sk_buff *skb;
+	int space_needed;
+
+	if (unlikely(tcp_under_memory_pressure(sk))) {
+		mptcp_mem_reclaim_partial(sk);
+
+		/* under pressure pre-allocate at most a single skb */
+		if (msk->skb_tx_cache.qlen)
+			return true;
+		space_needed = msk->size_goal_cache;
 	} else {
-		write_seq = &dfrag->data_seq;
-		page = dfrag->page;
+		space_needed = msk->tx_pending_data + size -
+			       msk->skb_tx_cache.qlen * msk->size_goal_cache;
 	}
 
-	/* compute copy limit */
-	mss_now = tcp_send_mss(ssk, &size_goal, msg->msg_flags);
-	*pmss_now = mss_now;
-	*ps_goal = size_goal;
-	avail_size = size_goal;
-	skb = tcp_write_queue_tail(ssk);
+	while (space_needed > 0) {
+		skb = __mptcp_do_alloc_tx_skb(sk, sk->sk_allocation);
+		if (unlikely(!skb)) {
+			/* under memory pressure, try to pass the caller a
+			 * single skb to allow forward progress
+			 */
+			while (skbs->qlen > 1) {
+				skb = __skb_dequeue_tail(skbs);
+				__kfree_skb(skb);
+			}
+			return skbs->qlen > 0;
+		}
+
+		*total_ts += skb->truesize;
+		__skb_queue_tail(skbs, skb);
+		space_needed -= msk->size_goal_cache;
+	}
+	return true;
+}
+
+static bool __mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, gfp_t gfp)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct sk_buff *skb;
+
+	if (ssk->sk_tx_skb_cache) {
+		skb = ssk->sk_tx_skb_cache;
+		if (unlikely(!skb_ext_find(skb, SKB_EXT_MPTCP) &&
+			     !__mptcp_add_ext(skb, gfp)))
+			return false;
+		return true;
+	}
+
+	skb = skb_peek(&msk->skb_tx_cache);
 	if (skb) {
-		mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
+		if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
+			skb = __skb_dequeue(&msk->skb_tx_cache);
+			if (WARN_ON_ONCE(!skb))
+				return false;
+
+			mptcp_wmem_uncharge(sk, skb->truesize);
+			ssk->sk_tx_skb_cache = skb;
+			return true;
+		}
+
+		/* over memory limit, no point to try to allocate a new skb */
+		return false;
+	}
 
+	skb = __mptcp_do_alloc_tx_skb(sk, gfp);
+	if (!skb)
+		return false;
+
+	if (likely(sk_wmem_schedule(ssk, skb->truesize))) {
+		ssk->sk_tx_skb_cache = skb;
+		return true;
+	}
+	kfree_skb(skb);
+	return false;
+}
+
+static bool mptcp_must_reclaim_memory(struct sock *sk, struct sock *ssk)
+{
+	return !ssk->sk_tx_skb_cache &&
+	       !skb_peek(&mptcp_sk(sk)->skb_tx_cache) &&
+	       tcp_under_memory_pressure(sk);
+}
+
+static bool mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk)
+{
+	if (unlikely(mptcp_must_reclaim_memory(sk, ssk)))
+		mptcp_mem_reclaim_partial(sk);
+	return __mptcp_alloc_tx_skb(sk, ssk, sk->sk_allocation);
+}
+
+static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
+			      struct mptcp_data_frag *dfrag,
+			      struct mptcp_sendmsg_info *info)
+{
+	u64 data_seq = dfrag->data_seq + info->sent;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	bool zero_window_probe = false;
+	struct mptcp_ext *mpext = NULL;
+	struct sk_buff *skb, *tail;
+	bool can_collapse = false;
+	int size_bias = 0;
+	int avail_size;
+	size_t ret = 0;
+
+	pr_debug("msk=%p ssk=%p sending dfrag at seq=%lld len=%d already sent=%d",
+		 msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
+
+	/* compute send limit */
+	info->mss_now = tcp_send_mss(ssk, &info->size_goal, info->flags);
+	avail_size = info->size_goal;
+	msk->size_goal_cache = info->size_goal;
+	skb = tcp_write_queue_tail(ssk);
+	if (skb) {
 		/* Limit the write to the size available in the
 		 * current skb, if any, so that we create at most a new skb.
 		 * Explicitly tells TCP internals to avoid collapsing on later
 		 * queue management operation, to avoid breaking the ext <->
 		 * SSN association set here
 		 */
-		can_collapse = (size_goal - skb->len > 0) &&
-			      mptcp_skb_can_collapse_to(*write_seq, skb, mpext);
-		if (!can_collapse)
+		mpext = skb_ext_find(skb, SKB_EXT_MPTCP);
+		can_collapse = (info->size_goal - skb->len > 0) &&
+			 mptcp_skb_can_collapse_to(data_seq, skb, mpext);
+		if (!can_collapse) {
 			TCP_SKB_CB(skb)->eor = 1;
-		else
-			avail_size = size_goal - skb->len;
-	}
-
-	if (!retransmission) {
-		/* reuse tail pfrag, if possible, or carve a new one from the
-		 * page allocator
-		 */
-		dfrag = mptcp_rtx_tail(sk);
-		offset = pfrag->offset;
-		dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
-		if (!dfrag_collapsed) {
-			dfrag = mptcp_carve_data_frag(msk, pfrag, offset);
-			offset = dfrag->offset;
-			frag_truesize = dfrag->overhead;
-		}
-		psize = min_t(size_t, pfrag->size - offset, avail_size);
-
-		/* Copy to page */
-		pr_debug("left=%zu", msg_data_left(msg));
-		psize = copy_page_from_iter(pfrag->page, offset,
-					    min_t(size_t, msg_data_left(msg),
-						  psize),
-					    &msg->msg_iter);
-		pr_debug("left=%zu", msg_data_left(msg));
-		if (!psize)
-			return -EINVAL;
-
-		if (!sk_wmem_schedule(sk, psize + dfrag->overhead)) {
-			iov_iter_revert(&msg->msg_iter, psize);
-			return -ENOMEM;
+		} else {
+			size_bias = skb->len;
+			avail_size = info->size_goal - skb->len;
 		}
-	} else {
-		offset = dfrag->offset;
-		psize = min_t(size_t, dfrag->data_len, avail_size);
 	}
 
-	/* tell the TCP stack to delay the push so that we can safely
-	 * access the skb after the sendpages call
-	 */
-	ret = do_tcp_sendpages(ssk, page, offset, psize,
-			       msg->msg_flags | MSG_SENDPAGE_NOTLAST | MSG_DONTWAIT);
-	if (ret <= 0) {
-		if (!retransmission)
-			iov_iter_revert(&msg->msg_iter, psize);
-		return ret;
-	}
+	/* Zero window and all data acked? Probe. */
+	avail_size = mptcp_check_allowed_size(msk, data_seq, avail_size);
+	if (avail_size == 0) {
+		u64 snd_una = READ_ONCE(msk->snd_una);
 
-	frag_truesize += ret;
-	if (!retransmission) {
-		if (unlikely(ret < psize))
-			iov_iter_revert(&msg->msg_iter, psize - ret);
+		if (skb || snd_una != msk->snd_nxt)
+			return 0;
+		zero_window_probe = true;
+		data_seq = snd_una - 1;
+		avail_size = 1;
+	}
 
-		/* send successful, keep track of sent data for mptcp-level
-		 * retransmission
-		 */
-		dfrag->data_len += ret;
-		if (!dfrag_collapsed) {
-			get_page(dfrag->page);
-			list_add_tail(&dfrag->list, &msk->rtx_queue);
-			sk_wmem_queued_add(sk, frag_truesize);
-		} else {
-			sk_wmem_queued_add(sk, ret);
-		}
+	if (WARN_ON_ONCE(info->sent > info->limit ||
+			 info->limit > dfrag->data_len))
+		return 0;
 
-		/* charge data on mptcp rtx queue to the master socket
-		 * Note: we charge such data both to sk and ssk
-		 */
-		sk->sk_forward_alloc -= frag_truesize;
+	ret = info->limit - info->sent;
+	tail = tcp_build_frag(ssk, avail_size + size_bias, info->flags,
+			      dfrag->page, dfrag->offset + info->sent, &ret);
+	if (!tail) {
+		tcp_remove_empty_skb(sk, tcp_write_queue_tail(ssk));
+		return -ENOMEM;
 	}
 
-	/* if the tail skb extension is still the cached one, collapsing
-	 * really happened. Note: we can't check for 'same skb' as the sk_buff
-	 * hdr on tail can be transmitted, freed and re-allocated by the
-	 * do_tcp_sendpages() call
+	/* if the tail skb is still the cached one, collapsing really happened.
 	 */
-	tail = tcp_write_queue_tail(ssk);
-	if (mpext && tail && mpext == skb_ext_find(tail, SKB_EXT_MPTCP)) {
-		WARN_ON_ONCE(!can_collapse);
+	if (skb == tail) {
+		TCP_SKB_CB(tail)->tcp_flags &= ~TCPHDR_PSH;
 		mpext->data_len += ret;
+		WARN_ON_ONCE(!can_collapse);
+		WARN_ON_ONCE(zero_window_probe);
 		goto out;
 	}
 
-	skb = tcp_write_queue_tail(ssk);
-	mpext = __skb_ext_set(skb, SKB_EXT_MPTCP, msk->cached_ext);
-	msk->cached_ext = NULL;
+	mpext = skb_ext_find(tail, SKB_EXT_MPTCP);
+	if (WARN_ON_ONCE(!mpext)) {
+		/* should never reach here, stream corrupted */
+		return -EINVAL;
+	}
 
 	memset(mpext, 0, sizeof(*mpext));
-	mpext->data_seq = *write_seq;
+	mpext->data_seq = data_seq;
 	mpext->subflow_seq = mptcp_subflow_ctx(ssk)->rel_write_seq;
 	mpext->data_len = ret;
 	mpext->use_map = 1;
@@ -794,85 +1340,257 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		 mpext->data_seq, mpext->subflow_seq, mpext->data_len,
 		 mpext->dsn64);
 
+	if (zero_window_probe) {
+		mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
+		mpext->frozen = 1;
+		ret = 0;
+		tcp_push_pending_frames(ssk);
+	}
 out:
-	if (!retransmission)
-		pfrag->offset += frag_truesize;
-	WRITE_ONCE(*write_seq, *write_seq + ret);
 	mptcp_subflow_ctx(ssk)->rel_write_seq += ret;
-
 	return ret;
 }
 
-static void mptcp_nospace(struct mptcp_sock *msk, struct socket *sock)
-{
-	clear_bit(MPTCP_SEND_SPACE, &msk->flags);
-	smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
+#define MPTCP_SEND_BURST_SIZE		((1 << 16) - \
+					 sizeof(struct tcphdr) - \
+					 MAX_TCP_OPTION_SPACE - \
+					 sizeof(struct ipv6hdr) - \
+					 sizeof(struct frag_hdr))
 
-	/* enables sk->write_space() callbacks */
-	set_bit(SOCK_NOSPACE, &sock->flags);
-}
+struct subflow_send_info {
+	struct sock *ssk;
+	u64 ratio;
+};
 
-static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
+static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk,
+					   u32 *sndbuf)
 {
+	struct subflow_send_info send_info[2];
 	struct mptcp_subflow_context *subflow;
-	struct sock *backup = NULL;
+	int i, nr_active = 0;
+	struct sock *ssk;
+	u64 ratio;
+	u32 pace;
 
-	sock_owned_by_me((const struct sock *)msk);
+	sock_owned_by_me((struct sock *)msk);
 
-	if (!mptcp_ext_cache_refill(msk))
-		return NULL;
+	*sndbuf = 0;
+	if (__mptcp_check_fallback(msk)) {
+		if (!msk->first)
+			return NULL;
+		*sndbuf = msk->first->sk_sndbuf;
+		return sk_stream_memory_free(msk->first) ? msk->first : NULL;
+	}
+
+	/* re-use last subflow, if the burst allow that */
+	if (msk->last_snd && msk->snd_burst > 0 &&
+	    sk_stream_memory_free(msk->last_snd) &&
+	    mptcp_subflow_active(mptcp_subflow_ctx(msk->last_snd))) {
+		mptcp_for_each_subflow(msk, subflow) {
+			ssk =  mptcp_subflow_tcp_sock(subflow);
+			*sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
+		}
+		return msk->last_snd;
+	}
 
+	/* pick the subflow with the lower wmem/wspace ratio */
+	for (i = 0; i < 2; ++i) {
+		send_info[i].ssk = NULL;
+		send_info[i].ratio = -1;
+	}
 	mptcp_for_each_subflow(msk, subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		ssk =  mptcp_subflow_tcp_sock(subflow);
+		if (!mptcp_subflow_active(subflow))
+			continue;
 
-		if (!sk_stream_memory_free(ssk)) {
-			struct socket *sock = ssk->sk_socket;
+		nr_active += !subflow->backup;
+		*sndbuf = max(tcp_sk(ssk)->snd_wnd, *sndbuf);
+		if (!sk_stream_memory_free(subflow->tcp_sock))
+			continue;
 
-			if (sock)
-				mptcp_nospace(msk, sock);
+		pace = READ_ONCE(ssk->sk_pacing_rate);
+		if (!pace)
+			continue;
 
-			return NULL;
+		ratio = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32,
+				pace);
+		if (ratio < send_info[subflow->backup].ratio) {
+			send_info[subflow->backup].ssk = ssk;
+			send_info[subflow->backup].ratio = ratio;
 		}
+	}
 
-		if (subflow->backup) {
-			if (!backup)
-				backup = ssk;
+	pr_debug("msk=%p nr_active=%d ssk=%p:%lld backup=%p:%lld",
+		 msk, nr_active, send_info[0].ssk, send_info[0].ratio,
+		 send_info[1].ssk, send_info[1].ratio);
 
-			continue;
-		}
+	/* pick the best backup if no other subflow is active */
+	if (!nr_active)
+		send_info[0].ssk = send_info[1].ssk;
 
-		return ssk;
+	if (send_info[0].ssk) {
+		msk->last_snd = send_info[0].ssk;
+		msk->snd_burst = min_t(int, MPTCP_SEND_BURST_SIZE,
+				       sk_stream_wspace(msk->last_snd));
+		return msk->last_snd;
 	}
+	return NULL;
+}
 
-	return backup;
+static void mptcp_push_release(struct sock *sk, struct sock *ssk,
+			       struct mptcp_sendmsg_info *info)
+{
+	mptcp_set_timeout(sk, ssk);
+	tcp_push(ssk, 0, info->mss_now, tcp_sk(ssk)->nonagle, info->size_goal);
+	release_sock(ssk);
 }
 
-static void ssk_check_wmem(struct mptcp_sock *msk, struct sock *ssk)
+static void mptcp_push_pending(struct sock *sk, unsigned int flags)
 {
-	struct socket *sock;
+	struct sock *prev_ssk = NULL, *ssk = NULL;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_sendmsg_info info = {
+				.flags = flags,
+	};
+	struct mptcp_data_frag *dfrag;
+	int len, copied = 0;
+	u32 sndbuf;
+
+	while ((dfrag = mptcp_send_head(sk))) {
+		info.sent = dfrag->already_sent;
+		info.limit = dfrag->data_len;
+		len = dfrag->data_len - dfrag->already_sent;
+		while (len > 0) {
+			int ret = 0;
+
+			prev_ssk = ssk;
+			__mptcp_flush_join_list(msk);
+			ssk = mptcp_subflow_get_send(msk, &sndbuf);
+
+			/* do auto tuning */
+			if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
+			    sndbuf > READ_ONCE(sk->sk_sndbuf))
+				WRITE_ONCE(sk->sk_sndbuf, sndbuf);
+
+			/* try to keep the subflow socket lock across
+			 * consecutive xmit on the same socket
+			 */
+			if (ssk != prev_ssk && prev_ssk)
+				mptcp_push_release(sk, prev_ssk, &info);
+			if (!ssk)
+				goto out;
 
-	if (likely(sk_stream_is_writeable(ssk)))
-		return;
+			if (ssk != prev_ssk || !prev_ssk)
+				lock_sock(ssk);
+
+			/* keep it simple and always provide a new skb for the
+			 * subflow, even if we will not use it when collapsing
+			 * on the pending one
+			 */
+			if (!mptcp_alloc_tx_skb(sk, ssk)) {
+				mptcp_push_release(sk, ssk, &info);
+				goto out;
+			}
+
+			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+			if (ret <= 0) {
+				mptcp_push_release(sk, ssk, &info);
+				goto out;
+			}
 
-	sock = READ_ONCE(ssk->sk_socket);
-	if (sock)
-		mptcp_nospace(msk, sock);
+			info.sent += ret;
+			dfrag->already_sent += ret;
+			msk->snd_nxt += ret;
+			msk->snd_burst -= ret;
+			msk->tx_pending_data -= ret;
+			copied += ret;
+			len -= ret;
+		}
+		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+	}
+
+	/* at this point we held the socket lock for the last subflow we used */
+	if (ssk)
+		mptcp_push_release(sk, ssk, &info);
+
+out:
+	if (copied) {
+		/* start the timer, if it's not pending */
+		if (!mptcp_timer_pending(sk))
+			mptcp_reset_timer(sk);
+		__mptcp_check_send_data_fin(sk);
+	}
+}
+
+static void __mptcp_subflow_push_pending(struct sock *sk, struct sock *ssk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_sendmsg_info info;
+	struct mptcp_data_frag *dfrag;
+	int len, copied = 0;
+
+	info.flags = 0;
+	while ((dfrag = mptcp_send_head(sk))) {
+		info.sent = dfrag->already_sent;
+		info.limit = dfrag->data_len;
+		len = dfrag->data_len - dfrag->already_sent;
+		while (len > 0) {
+			int ret = 0;
+
+			/* do auto tuning */
+			if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK) &&
+			    ssk->sk_sndbuf > READ_ONCE(sk->sk_sndbuf))
+				WRITE_ONCE(sk->sk_sndbuf, ssk->sk_sndbuf);
+
+			if (unlikely(mptcp_must_reclaim_memory(sk, ssk))) {
+				__mptcp_update_wmem(sk);
+				sk_mem_reclaim_partial(sk);
+			}
+			if (!__mptcp_alloc_tx_skb(sk, ssk, GFP_ATOMIC))
+				goto out;
+
+			ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+			if (ret <= 0)
+				goto out;
+
+			info.sent += ret;
+			dfrag->already_sent += ret;
+			msk->snd_nxt += ret;
+			msk->snd_burst -= ret;
+			msk->tx_pending_data -= ret;
+			copied += ret;
+			len -= ret;
+		}
+		WRITE_ONCE(msk->first_pending, mptcp_send_next(sk));
+	}
+
+out:
+	/* __mptcp_alloc_tx_skb could have released some wmem and we are
+	 * not going to flush it via release_sock()
+	 */
+	__mptcp_update_wmem(sk);
+	if (copied) {
+		mptcp_set_timeout(sk, ssk);
+		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+			 info.size_goal);
+		if (msk->snd_data_fin_enable &&
+		    msk->snd_nxt + 1 == msk->write_seq)
+			mptcp_schedule_work(sk);
+	}
 }
 
 static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
-	int mss_now = 0, size_goal = 0, ret = 0;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct page_frag *pfrag;
 	size_t copied = 0;
-	struct sock *ssk;
-	bool tx_ok;
+	int ret = 0;
 	long timeo;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -EOPNOTSUPP;
 
-	lock_sock(sk);
+	mptcp_lock_sock(sk, __mptcp_wmem_reserve(sk, min_t(size_t, 1 << 20, len)));
 
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
@@ -883,120 +1601,95 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	pfrag = sk_page_frag(sk);
-restart:
-	mptcp_clean_una(sk);
 
-	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
-		ret = -EPIPE;
-		goto out;
-	}
+	while (msg_data_left(msg)) {
+		int total_ts, frag_truesize = 0;
+		struct mptcp_data_frag *dfrag;
+		struct sk_buff_head skbs;
+		bool dfrag_collapsed;
+		size_t psize, offset;
 
-	__mptcp_flush_join_list(msk);
-	ssk = mptcp_subflow_get_send(msk);
-	while (!sk_stream_memory_free(sk) ||
-	       !ssk ||
-	       !mptcp_page_frag_refill(ssk, pfrag)) {
-		if (ssk) {
-			/* make sure retransmit timer is
-			 * running before we wait for memory.
-			 *
-			 * The retransmit timer might be needed
-			 * to make the peer send an up-to-date
-			 * MPTCP Ack.
-			 */
-			mptcp_set_timeout(sk, ssk);
-			if (!mptcp_timer_pending(sk))
-				mptcp_reset_timer(sk);
+		if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) {
+			ret = -EPIPE;
+			goto out;
 		}
 
-		ret = sk_stream_wait_memory(sk, &timeo);
-		if (ret)
-			goto out;
+		/* reuse tail pfrag, if possible, or carve a new one from the
+		 * page allocator
+		 */
+		dfrag = mptcp_pending_tail(sk);
+		dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
+		if (!dfrag_collapsed) {
+			if (!sk_stream_memory_free(sk))
+				goto wait_for_memory;
 
-		mptcp_clean_una(sk);
+			if (!mptcp_page_frag_refill(sk, pfrag))
+				goto wait_for_memory;
 
-		ssk = mptcp_subflow_get_send(msk);
-		if (list_empty(&msk->conn_list)) {
-			ret = -ENOTCONN;
-			goto out;
+			dfrag = mptcp_carve_data_frag(msk, pfrag, pfrag->offset);
+			frag_truesize = dfrag->overhead;
 		}
-	}
-
-	pr_debug("conn_list->subflow=%p", ssk);
 
-	lock_sock(ssk);
-	tx_ok = msg_data_left(msg);
-	while (tx_ok) {
-		ret = mptcp_sendmsg_frag(sk, ssk, msg, NULL, &timeo, &mss_now,
-					 &size_goal);
-		if (ret < 0) {
-			if (ret == -EAGAIN && timeo > 0) {
-				mptcp_set_timeout(sk, ssk);
-				release_sock(ssk);
-				goto restart;
-			}
-			break;
+		/* we do not bound vs wspace, to allow a single packet.
+		 * memory accounting will prevent execessive memory usage
+		 * anyway
+		 */
+		offset = dfrag->offset + dfrag->data_len;
+		psize = pfrag->size - offset;
+		psize = min_t(size_t, psize, msg_data_left(msg));
+		total_ts = psize + frag_truesize;
+		__skb_queue_head_init(&skbs);
+		if (!mptcp_tx_cache_refill(sk, psize, &skbs, &total_ts))
+			goto wait_for_memory;
+
+		if (!mptcp_wmem_alloc(sk, total_ts)) {
+			__skb_queue_purge(&skbs);
+			goto wait_for_memory;
 		}
 
-		copied += ret;
-
-		tx_ok = msg_data_left(msg);
-		if (!tx_ok)
-			break;
-
-		if (!sk_stream_memory_free(ssk) ||
-		    !mptcp_page_frag_refill(ssk, pfrag) ||
-		    !mptcp_ext_cache_refill(msk)) {
-			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-			tcp_push(ssk, msg->msg_flags, mss_now,
-				 tcp_sk(ssk)->nonagle, size_goal);
-			mptcp_set_timeout(sk, ssk);
-			release_sock(ssk);
-			goto restart;
+		skb_queue_splice_tail(&skbs, &msk->skb_tx_cache);
+		if (copy_page_from_iter(dfrag->page, offset, psize,
+					&msg->msg_iter) != psize) {
+			mptcp_wmem_uncharge(sk, psize + frag_truesize);
+			ret = -EFAULT;
+			goto out;
 		}
 
-		/* memory is charged to mptcp level socket as well, i.e.
-		 * if msg is very large, mptcp socket may run out of buffer
-		 * space.  mptcp_clean_una() will release data that has
-		 * been acked at mptcp level in the mean time, so there is
-		 * a good chance we can continue sending data right away.
-		 *
-		 * Normally, when the tcp subflow can accept more data, then
-		 * so can the MPTCP socket.  However, we need to cope with
-		 * peers that might lag behind in their MPTCP-level
-		 * acknowledgements, i.e.  data might have been acked at
-		 * tcp level only.  So, we must also check the MPTCP socket
-		 * limits before we send more data.
+		/* data successfully copied into the write queue */
+		copied += psize;
+		dfrag->data_len += psize;
+		frag_truesize += psize;
+		pfrag->offset += frag_truesize;
+		WRITE_ONCE(msk->write_seq, msk->write_seq + psize);
+		msk->tx_pending_data += psize;
+
+		/* charge data on mptcp pending queue to the msk socket
+		 * Note: we charge such data both to sk and ssk
 		 */
-		if (unlikely(!sk_stream_memory_free(sk))) {
-			tcp_push(ssk, msg->msg_flags, mss_now,
-				 tcp_sk(ssk)->nonagle, size_goal);
-			mptcp_clean_una(sk);
-			if (!sk_stream_memory_free(sk)) {
-				/* can't send more for now, need to wait for
-				 * MPTCP-level ACKs from peer.
-				 *
-				 * Wakeup will happen via mptcp_clean_una().
-				 */
-				mptcp_set_timeout(sk, ssk);
-				release_sock(ssk);
-				goto restart;
-			}
+		sk_wmem_queued_add(sk, frag_truesize);
+		if (!dfrag_collapsed) {
+			get_page(dfrag->page);
+			list_add_tail(&dfrag->list, &msk->rtx_queue);
+			if (!msk->first_pending)
+				WRITE_ONCE(msk->first_pending, dfrag);
 		}
-	}
+		pr_debug("msk=%p dfrag at seq=%lld len=%d sent=%d new=%d", msk,
+			 dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
+			 !dfrag_collapsed);
 
-	mptcp_set_timeout(sk, ssk);
-	if (copied) {
-		tcp_push(ssk, msg->msg_flags, mss_now, tcp_sk(ssk)->nonagle,
-			 size_goal);
+		continue;
 
-		/* start the timer, if it's not pending */
-		if (!mptcp_timer_pending(sk))
-			mptcp_reset_timer(sk);
+wait_for_memory:
+		set_bit(MPTCP_NOSPACE, &msk->flags);
+		mptcp_push_pending(sk, msg->msg_flags);
+		ret = sk_stream_wait_memory(sk, &timeo);
+		if (ret)
+			goto out;
 	}
 
-	ssk_check_wmem(msk, ssk);
-	release_sock(ssk);
+	if (copied)
+		mptcp_push_pending(sk, msg->msg_flags);
+
 out:
 	release_sock(sk);
 	return copied ? : ret;
@@ -1021,11 +1714,10 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 				struct msghdr *msg,
 				size_t len)
 {
-	struct sock *sk = (struct sock *)msk;
 	struct sk_buff *skb;
 	int copied = 0;
 
-	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
+	while ((skb = skb_peek(&msk->receive_queue)) != NULL) {
 		u32 offset = MPTCP_SKB_CB(skb)->offset;
 		u32 data_len = skb->len - offset;
 		u32 count = min_t(size_t, len - copied, data_len);
@@ -1045,7 +1737,10 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 			break;
 		}
 
-		__skb_unlink(skb, &sk->sk_receive_queue);
+		/* we will bulk release the skb memory later */
+		skb->destructor = NULL;
+		msk->rmem_released += skb->truesize;
+		__skb_unlink(skb, &msk->receive_queue);
 		__kfree_skb(skb);
 
 		if (copied >= len)
@@ -1135,10 +1830,14 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 			 */
 			mptcp_for_each_subflow(msk, subflow) {
 				struct sock *ssk;
+				bool slow;
 
 				ssk = mptcp_subflow_tcp_sock(subflow);
+				slow = lock_sock_fast(ssk);
 				WRITE_ONCE(ssk->sk_rcvbuf, rcvbuf);
 				tcp_sk(ssk)->window_clamp = window_clamp;
+				tcp_cleanup_rbuf(ssk, 1);
+				unlock_sock_fast(ssk, slow);
 			}
 		}
 	}
@@ -1149,23 +1848,68 @@ new_measure:
 	msk->rcvq_space.time = mstamp;
 }
 
-static bool __mptcp_move_skbs(struct mptcp_sock *msk)
+static void __mptcp_update_rmem(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (!msk->rmem_released)
+		return;
+
+	atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
+	sk_mem_uncharge(sk, msk->rmem_released);
+	msk->rmem_released = 0;
+}
+
+static void __mptcp_splice_receive_queue(struct sock *sk)
 {
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	skb_queue_splice_tail_init(&sk->sk_receive_queue, &msk->receive_queue);
+}
+
+static bool __mptcp_move_skbs(struct mptcp_sock *msk, unsigned int rcv)
+{
+	struct sock *sk = (struct sock *)msk;
 	unsigned int moved = 0;
-	bool done;
+	bool ret, done;
 
+	__mptcp_flush_join_list(msk);
 	do {
 		struct sock *ssk = mptcp_subflow_recv_lookup(msk);
+		bool slowpath;
 
-		if (!ssk)
+		/* we can have data pending in the subflows only if the msk
+		 * receive buffer was full at subflow_data_ready() time,
+		 * that is an unlikely slow path.
+		 */
+		if (likely(!ssk))
 			break;
 
-		lock_sock(ssk);
+		slowpath = lock_sock_fast(ssk);
+		mptcp_data_lock(sk);
 		done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
-		release_sock(ssk);
+		mptcp_data_unlock(sk);
+		if (moved && rcv) {
+			WRITE_ONCE(msk->rmem_pending, min(rcv, moved));
+			tcp_cleanup_rbuf(ssk, 1);
+			WRITE_ONCE(msk->rmem_pending, 0);
+		}
+		unlock_sock_fast(ssk, slowpath);
 	} while (!done);
 
-	return moved > 0;
+	/* acquire the data lock only if some input data is pending */
+	ret = moved > 0;
+	if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) ||
+	    !skb_queue_empty_lockless(&sk->sk_receive_queue)) {
+		mptcp_data_lock(sk);
+		__mptcp_update_rmem(sk);
+		ret |= __mptcp_ofo_queue(msk);
+		__mptcp_splice_receive_queue(sk);
+		mptcp_data_unlock(sk);
+	}
+	if (ret)
+		mptcp_check_data_fin((struct sock *)msk);
+	return !skb_queue_empty(&msk->receive_queue);
 }
 
 static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
@@ -1179,15 +1923,19 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	if (msg->msg_flags & ~(MSG_WAITALL | MSG_DONTWAIT))
 		return -EOPNOTSUPP;
 
-	lock_sock(sk);
+	mptcp_lock_sock(sk, __mptcp_splice_receive_queue(sk));
+	if (unlikely(sk->sk_state == TCP_LISTEN)) {
+		copied = -ENOTCONN;
+		goto out_err;
+	}
+
 	timeo = sock_rcvtimeo(sk, nonblock);
 
 	len = min_t(size_t, len, INT_MAX);
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
-	__mptcp_flush_join_list(msk);
 
-	while (len > (size_t)copied) {
-		int bytes_read;
+	while (copied < len) {
+		int bytes_read, old_space;
 
 		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied);
 		if (unlikely(bytes_read < 0)) {
@@ -1198,10 +1946,15 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 		copied += bytes_read;
 
-		if (skb_queue_empty(&sk->sk_receive_queue) &&
-		    __mptcp_move_skbs(msk))
+		if (skb_queue_empty(&msk->receive_queue) &&
+		    __mptcp_move_skbs(msk, len - copied))
 			continue;
 
+		/* be sure to advertise window change */
+		old_space = READ_ONCE(msk->old_wspace);
+		if ((tcp_space(sk) - old_space) >= old_space)
+			mptcp_cleanup_rbuf(msk);
+
 		/* only the master socket status is relevant here. The exit
 		 * conditions mirror closely tcp_recvmsg()
 		 */
@@ -1224,8 +1977,14 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 			if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
 				mptcp_check_for_eof(msk);
 
-			if (sk->sk_shutdown & RCV_SHUTDOWN)
+			if (sk->sk_shutdown & RCV_SHUTDOWN) {
+				/* race breaker: the shutdown could be after the
+				 * previous receive queue check
+				 */
+				if (__mptcp_move_skbs(msk, len - copied))
+					continue;
 				break;
+			}
 
 			if (sk->sk_state == TCP_CLOSE) {
 				copied = -ENOTCONN;
@@ -1247,20 +2006,24 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		mptcp_wait_data(sk, &timeo);
 	}
 
-	if (skb_queue_empty(&sk->sk_receive_queue)) {
+	if (skb_queue_empty_lockless(&sk->sk_receive_queue) &&
+	    skb_queue_empty(&msk->receive_queue)) {
 		/* entire backlog drained, clear DATA_READY. */
 		clear_bit(MPTCP_DATA_READY, &msk->flags);
 
 		/* .. race-breaker: ssk might have gotten new data
 		 * after last __mptcp_move_skbs() returned false.
 		 */
-		if (unlikely(__mptcp_move_skbs(msk)))
+		if (unlikely(__mptcp_move_skbs(msk, 0)))
 			set_bit(MPTCP_DATA_READY, &msk->flags);
 	} else if (unlikely(!test_bit(MPTCP_DATA_READY, &msk->flags))) {
 		/* data to read but mptcp_wait_data() cleared DATA_READY */
 		set_bit(MPTCP_DATA_READY, &msk->flags);
 	}
 out_err:
+	pr_debug("msk=%p data_ready=%d rx queue empty=%d copied=%d",
+		 msk, test_bit(MPTCP_DATA_READY, &msk->flags),
+		 skb_queue_empty_lockless(&sk->sk_receive_queue), copied);
 	mptcp_rcv_space_adjust(msk, copied);
 
 	release_sock(sk);
@@ -1271,13 +2034,8 @@ static void mptcp_retransmit_handler(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	if (atomic64_read(&msk->snd_una) == READ_ONCE(msk->write_seq)) {
-		mptcp_stop_timer(sk);
-	} else {
-		set_bit(MPTCP_WORK_RTX, &msk->flags);
-		if (schedule_work(&msk->work))
-			sock_hold(sk);
-	}
+	set_bit(MPTCP_WORK_RTX, &msk->flags);
+	mptcp_schedule_work(sk);
 }
 
 static void mptcp_retransmit_timer(struct timer_list *t)
@@ -1299,6 +2057,14 @@ static void mptcp_retransmit_timer(struct timer_list *t)
 	sock_put(sk);
 }
 
+static void mptcp_timeout_timer(struct timer_list *t)
+{
+	struct sock *sk = from_timer(sk, t, sk_timer);
+
+	mptcp_schedule_work(sk);
+	sock_put(sk);
+}
+
 /* Find an idle subflow.  Return NULL if there is unacked data at tcp
  * level.
  *
@@ -1311,12 +2077,21 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
 
 	sock_owned_by_me((const struct sock *)msk);
 
+	if (__mptcp_check_fallback(msk))
+		return NULL;
+
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
+		if (!mptcp_subflow_active(subflow))
+			continue;
+
 		/* still data outstanding at TCP level?  Don't retransmit. */
-		if (!tcp_write_queue_empty(ssk))
+		if (!tcp_write_queue_empty(ssk)) {
+			if (inet_csk(ssk)->icsk_ca_state >= TCP_CA_Loss)
+				continue;
 			return NULL;
+		}
 
 		if (subflow->backup) {
 			if (!backup)
@@ -1338,21 +2113,45 @@ static struct sock *mptcp_subflow_get_retrans(const struct mptcp_sock *msk)
  * so we need to use tcp_close() after detaching them from the mptcp
  * parent socket.
  */
-static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
-			      struct mptcp_subflow_context *subflow,
-			      long timeout)
+void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+		       struct mptcp_subflow_context *subflow)
 {
-	struct socket *sock = READ_ONCE(ssk->sk_socket);
+	bool dispose_socket = false;
+	struct socket *sock;
 
 	list_del(&subflow->node);
 
-	if (sock && sock != sk->sk_socket) {
-		/* outgoing subflow */
-		sock_release(sock);
+	lock_sock_nested(ssk, SINGLE_DEPTH_NESTING);
+
+	/* if we are invoked by the msk cleanup code, the subflow is
+	 * already orphaned
+	 */
+	sock = ssk->sk_socket;
+	if (sock) {
+		dispose_socket = sock != sk->sk_socket;
+		sock_orphan(ssk);
+	}
+
+	subflow->disposable = 1;
+
+	/* if ssk hit tcp_done(), tcp_cleanup_ulp() cleared the related ops
+	 * the ssk has been already destroyed, we just need to release the
+	 * reference owned by msk;
+	 */
+	if (!inet_csk(ssk)->icsk_ulp_ops) {
+		kfree_rcu(subflow, rcu);
 	} else {
-		/* incoming subflow */
-		tcp_close(ssk, timeout);
+		/* otherwise tcp will dispose of the ssk and subflow ctx */
+		__tcp_close(ssk, 0);
+
+		/* close acquired an extra ref */
+		__sock_put(ssk);
 	}
+	release_sock(ssk);
+	if (dispose_socket)
+		iput(SOCK_INODE(sock));
+
+	sock_put(ssk);
 }
 
 static unsigned int mptcp_sync_mss(struct sock *sk, u32 pmtu)
@@ -1371,6 +2170,14 @@ static void pm_work(struct mptcp_sock *msk)
 		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
 		mptcp_pm_nl_add_addr_received(msk);
 	}
+	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
+		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
+		mptcp_pm_nl_add_addr_send_ack(msk);
+	}
+	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
+		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
+		mptcp_pm_nl_rm_addr_received(msk);
+	}
 	if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) {
 		pm->status &= ~BIT(MPTCP_PM_ESTABLISHED);
 		mptcp_pm_nl_fully_established(msk);
@@ -1383,24 +2190,90 @@ static void pm_work(struct mptcp_sock *msk)
 	spin_unlock_bh(&msk->pm.lock);
 }
 
+static void __mptcp_close_subflow(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+
+	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		if (inet_sk_state_load(ssk) != TCP_CLOSE)
+			continue;
+
+		__mptcp_close_ssk((struct sock *)msk, ssk, subflow);
+	}
+}
+
+static bool mptcp_check_close_timeout(const struct sock *sk)
+{
+	s32 delta = tcp_jiffies32 - inet_csk(sk)->icsk_mtup.probe_timestamp;
+	struct mptcp_subflow_context *subflow;
+
+	if (delta >= TCP_TIMEWAIT_LEN)
+		return true;
+
+	/* if all subflows are in closed status don't bother with additional
+	 * timeout
+	 */
+	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+		if (inet_sk_state_load(mptcp_subflow_tcp_sock(subflow)) !=
+		    TCP_CLOSE)
+			return false;
+	}
+	return true;
+}
+
+static void mptcp_check_fastclose(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct sock *sk = &msk->sk.icsk_inet.sk;
+
+	if (likely(!READ_ONCE(msk->rcv_fastclose)))
+		return;
+
+	mptcp_token_destroy(msk);
+
+	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
+		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
+
+		lock_sock(tcp_sk);
+		if (tcp_sk->sk_state != TCP_CLOSE) {
+			tcp_send_active_reset(tcp_sk, GFP_ATOMIC);
+			tcp_set_state(tcp_sk, TCP_CLOSE);
+		}
+		release_sock(tcp_sk);
+	}
+
+	inet_sk_state_store(sk, TCP_CLOSE);
+	sk->sk_shutdown = SHUTDOWN_MASK;
+	smp_mb__before_atomic(); /* SHUTDOWN must be visible first */
+	set_bit(MPTCP_DATA_READY, &msk->flags);
+	set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags);
+
+	mptcp_close_wake_up(sk);
+}
+
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
 	struct sock *ssk, *sk = &msk->sk.icsk_inet.sk;
-	int orig_len, orig_offset, mss_now = 0, size_goal = 0;
+	struct mptcp_sendmsg_info info = {};
 	struct mptcp_data_frag *dfrag;
-	u64 orig_write_seq;
 	size_t copied = 0;
-	struct msghdr msg = {
-		.msg_flags = MSG_DONTWAIT,
-	};
-	long timeo = 0;
+	int state, ret;
 
 	lock_sock(sk);
-	mptcp_clean_una(sk);
+	state = sk->sk_state;
+	if (unlikely(state == TCP_CLOSE))
+		goto unlock;
+
 	mptcp_check_data_fin_ack(sk);
 	__mptcp_flush_join_list(msk);
-	__mptcp_move_skbs(msk);
+
+	mptcp_check_fastclose(msk);
+
+	if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+		__mptcp_close_subflow(msk);
 
 	if (msk->pm.status)
 		pm_work(msk);
@@ -1408,8 +2281,21 @@ static void mptcp_worker(struct work_struct *work)
 	if (test_and_clear_bit(MPTCP_WORK_EOF, &msk->flags))
 		mptcp_check_for_eof(msk);
 
+	__mptcp_check_send_data_fin(sk);
 	mptcp_check_data_fin(sk);
 
+	/* if the msk data is completely acked, or the socket timedout,
+	 * there is no point in keeping around an orphaned sk
+	 */
+	if (sock_flag(sk, SOCK_DEAD) &&
+	    (mptcp_check_close_timeout(sk) ||
+	    (state != sk->sk_state &&
+	    ((1 << inet_sk_state_load(sk)) & (TCPF_CLOSE | TCPF_FIN_WAIT2))))) {
+		inet_sk_state_store(sk, TCP_CLOSE);
+		__mptcp_destroy_sock(sk);
+		goto unlock;
+	}
+
 	if (!test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
 		goto unlock;
 
@@ -1417,39 +2303,30 @@ static void mptcp_worker(struct work_struct *work)
 	if (!dfrag)
 		goto unlock;
 
-	if (!mptcp_ext_cache_refill(msk))
-		goto reset_unlock;
-
 	ssk = mptcp_subflow_get_retrans(msk);
 	if (!ssk)
 		goto reset_unlock;
 
 	lock_sock(ssk);
 
-	orig_len = dfrag->data_len;
-	orig_offset = dfrag->offset;
-	orig_write_seq = dfrag->data_seq;
-	while (dfrag->data_len > 0) {
-		int ret = mptcp_sendmsg_frag(sk, ssk, &msg, dfrag, &timeo,
-					     &mss_now, &size_goal);
-		if (ret < 0)
+	/* limit retransmission to the bytes already sent on some subflows */
+	info.sent = 0;
+	info.limit = dfrag->already_sent;
+	while (info.sent < dfrag->already_sent) {
+		if (!mptcp_alloc_tx_skb(sk, ssk))
+			break;
+
+		ret = mptcp_sendmsg_frag(sk, ssk, dfrag, &info);
+		if (ret <= 0)
 			break;
 
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RETRANSSEGS);
 		copied += ret;
-		dfrag->data_len -= ret;
-		dfrag->offset += ret;
-
-		if (!mptcp_ext_cache_refill(msk))
-			break;
+		info.sent += ret;
 	}
 	if (copied)
-		tcp_push(ssk, msg.msg_flags, mss_now, tcp_sk(ssk)->nonagle,
-			 size_goal);
-
-	dfrag->data_seq = orig_write_seq;
-	dfrag->offset = orig_offset;
-	dfrag->data_len = orig_len;
+		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
+			 info.size_goal);
 
 	mptcp_set_timeout(sk, ssk);
 	release_sock(ssk);
@@ -1472,9 +2349,17 @@ static int __mptcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&msk->conn_list);
 	INIT_LIST_HEAD(&msk->join_list);
 	INIT_LIST_HEAD(&msk->rtx_queue);
-	__set_bit(MPTCP_SEND_SPACE, &msk->flags);
 	INIT_WORK(&msk->work, mptcp_worker);
-
+	__skb_queue_head_init(&msk->receive_queue);
+	__skb_queue_head_init(&msk->skb_tx_cache);
+	msk->out_of_order_queue = RB_ROOT;
+	msk->first_pending = NULL;
+	msk->wmem_reserved = 0;
+	msk->rmem_released = 0;
+	msk->tx_pending_data = 0;
+	msk->size_goal_cache = TCP_BASE_MSS;
+
+	msk->ack_hint = NULL;
 	msk->first = NULL;
 	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
 
@@ -1482,7 +2367,7 @@ static int __mptcp_init_sock(struct sock *sk)
 
 	/* re-use the csk retrans timer for MPTCP-level retrans */
 	timer_setup(&msk->sk.icsk_retransmit_timer, mptcp_retransmit_timer, 0);
-
+	timer_setup(&sk->sk_timer, mptcp_timeout_timer, 0);
 	return 0;
 }
 
@@ -1491,23 +2376,23 @@ static int mptcp_init_sock(struct sock *sk)
 	struct net *net = sock_net(sk);
 	int ret;
 
+	ret = __mptcp_init_sock(sk);
+	if (ret)
+		return ret;
+
 	if (!mptcp_is_enabled(net))
 		return -ENOPROTOOPT;
 
 	if (unlikely(!net->mib.mptcp_statistics) && !mptcp_mib_alloc(net))
 		return -ENOMEM;
 
-	ret = __mptcp_init_sock(sk);
-	if (ret)
-		return ret;
-
 	ret = __mptcp_socket_create(mptcp_sk(sk));
 	if (ret)
 		return ret;
 
 	sk_sockets_allocated_inc(sk);
 	sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1];
-	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[2];
+	sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1];
 
 	return 0;
 }
@@ -1516,11 +2401,15 @@ static void __mptcp_clear_xmit(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_data_frag *dtmp, *dfrag;
+	struct sk_buff *skb;
 
-	sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
-
+	WRITE_ONCE(msk->first_pending, NULL);
 	list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list)
 		dfrag_clear(sk, dfrag);
+	while ((skb = __skb_dequeue(&msk->skb_tx_cache)) != NULL) {
+		sk->sk_forward_alloc += skb->truesize;
+		kfree_skb(skb);
+	}
 }
 
 static void mptcp_cancel_work(struct sock *sk)
@@ -1528,10 +2417,10 @@ static void mptcp_cancel_work(struct sock *sk)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	if (cancel_work_sync(&msk->work))
-		sock_put(sk);
+		__sock_put(sk);
 }
 
-static void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
+void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
 {
 	lock_sock(ssk);
 
@@ -1586,42 +2475,67 @@ static int mptcp_close_state(struct sock *sk)
 	return next & TCP_ACTION_FIN;
 }
 
-static void mptcp_close(struct sock *sk, long timeout)
+static void __mptcp_check_send_data_fin(struct sock *sk)
 {
-	struct mptcp_subflow_context *subflow, *tmp;
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	LIST_HEAD(conn_list);
 
-	lock_sock(sk);
-	sk->sk_shutdown = SHUTDOWN_MASK;
+	pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
+		 msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
+		 msk->snd_nxt, msk->write_seq);
 
-	if (sk->sk_state == TCP_LISTEN) {
-		inet_sk_state_store(sk, TCP_CLOSE);
-		goto cleanup;
-	} else if (sk->sk_state == TCP_CLOSE) {
-		goto cleanup;
-	}
+	/* we still need to enqueue subflows or not really shutting down,
+	 * skip this
+	 */
+	if (!msk->snd_data_fin_enable || msk->snd_nxt + 1 != msk->write_seq ||
+	    mptcp_send_head(sk))
+		return;
+
+	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 
+	/* fallback socket will not get data_fin/ack, can move to the next
+	 * state now
+	 */
 	if (__mptcp_check_fallback(msk)) {
-		goto update_state;
-	} else if (mptcp_close_state(sk)) {
-		pr_debug("Sending DATA_FIN sk=%p", sk);
-		WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
-		WRITE_ONCE(msk->snd_data_fin_enable, 1);
+		if ((1 << sk->sk_state) & (TCPF_CLOSING | TCPF_LAST_ACK)) {
+			inet_sk_state_store(sk, TCP_CLOSE);
+			mptcp_close_wake_up(sk);
+		} else if (sk->sk_state == TCP_FIN_WAIT1) {
+			inet_sk_state_store(sk, TCP_FIN_WAIT2);
+		}
+	}
 
-		mptcp_for_each_subflow(msk, subflow) {
-			struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
+	__mptcp_flush_join_list(msk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
 
-			mptcp_subflow_shutdown(sk, tcp_sk, SHUTDOWN_MASK);
-		}
+		mptcp_subflow_shutdown(sk, tcp_sk, SEND_SHUTDOWN);
 	}
+}
 
-	sk_stream_wait_close(sk, timeout);
+static void __mptcp_wr_shutdown(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
 
-update_state:
-	inet_sk_state_store(sk, TCP_CLOSE);
+	pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
+		 msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
+		 !!mptcp_send_head(sk));
+
+	/* will be ignored by fallback sockets */
+	WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
+	WRITE_ONCE(msk->snd_data_fin_enable, 1);
+
+	__mptcp_check_send_data_fin(sk);
+}
+
+static void __mptcp_destroy_sock(struct sock *sk)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	LIST_HEAD(conn_list);
+
+	pr_debug("msk=%p", msk);
 
-cleanup:
 	/* be sure to always acquire the join list lock, to sync vs
 	 * mptcp_finish_join().
 	 */
@@ -1630,20 +2544,77 @@ cleanup:
 	spin_unlock_bh(&msk->join_list_lock);
 	list_splice_init(&msk->conn_list, &conn_list);
 
-	__mptcp_clear_xmit(sk);
-
-	release_sock(sk);
+	sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
+	msk->pm.status = 0;
 
 	list_for_each_entry_safe(subflow, tmp, &conn_list, node) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		__mptcp_close_ssk(sk, ssk, subflow, timeout);
+		__mptcp_close_ssk(sk, ssk, subflow);
+	}
+
+	sk->sk_prot->destroy(sk);
+
+	WARN_ON_ONCE(msk->wmem_reserved);
+	WARN_ON_ONCE(msk->rmem_released);
+	sk_stream_kill_queues(sk);
+	xfrm_sk_free_policy(sk);
+	sk_refcnt_debug_release(sk);
+	sock_put(sk);
+}
+
+static void mptcp_close(struct sock *sk, long timeout)
+{
+	struct mptcp_subflow_context *subflow;
+	bool do_cancel_work = false;
+
+	lock_sock(sk);
+	sk->sk_shutdown = SHUTDOWN_MASK;
+
+	if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) {
+		inet_sk_state_store(sk, TCP_CLOSE);
+		goto cleanup;
 	}
 
-	mptcp_cancel_work(sk);
+	if (mptcp_close_state(sk))
+		__mptcp_wr_shutdown(sk);
 
-	__skb_queue_purge(&sk->sk_receive_queue);
+	sk_stream_wait_close(sk, timeout);
 
-	sk_common_release(sk);
+cleanup:
+	/* orphan all the subflows */
+	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
+	list_for_each_entry(subflow, &mptcp_sk(sk)->conn_list, node) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		bool slow, dispose_socket;
+		struct socket *sock;
+
+		slow = lock_sock_fast(ssk);
+		sock = ssk->sk_socket;
+		dispose_socket = sock && sock != sk->sk_socket;
+		sock_orphan(ssk);
+		unlock_sock_fast(ssk, slow);
+
+		/* for the outgoing subflows we additionally need to free
+		 * the associated socket
+		 */
+		if (dispose_socket)
+			iput(SOCK_INODE(sock));
+	}
+	sock_orphan(sk);
+
+	sock_hold(sk);
+	pr_debug("msk=%p state=%d", sk, sk->sk_state);
+	if (sk->sk_state == TCP_CLOSE) {
+		__mptcp_destroy_sock(sk);
+		do_cancel_work = true;
+	} else {
+		sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);
+	}
+	release_sock(sk);
+	if (do_cancel_work)
+		mptcp_cancel_work(sk);
+	sock_put(sk);
 }
 
 static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
@@ -1671,11 +2642,17 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
 
 static int mptcp_disconnect(struct sock *sk, int flags)
 {
-	/* Should never be called.
-	 * inet_stream_connect() calls ->disconnect, but that
-	 * refers to the subflow socket, not the mptcp one.
-	 */
-	WARN_ON_ONCE(1);
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	__mptcp_flush_join_list(msk);
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		lock_sock(ssk);
+		tcp_disconnect(ssk, flags);
+		release_sock(ssk);
+	}
 	return 0;
 }
 
@@ -1714,18 +2691,24 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 	WRITE_ONCE(msk->fully_established, false);
 
 	msk->write_seq = subflow_req->idsn + 1;
-	atomic64_set(&msk->snd_una, msk->write_seq);
+	msk->snd_nxt = msk->write_seq;
+	msk->snd_una = msk->write_seq;
+	msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd;
+
 	if (mp_opt->mp_capable) {
 		msk->can_ack = true;
 		msk->remote_key = mp_opt->sndr_key;
 		mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
 		ack_seq++;
 		WRITE_ONCE(msk->ack_seq, ack_seq);
+		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 	}
 
 	sock_reset_flag(nsk, SOCK_RCU_FREE);
 	/* will be fully established after successful MPC subflow creation */
 	inet_sk_state_store(nsk, TCP_SYN_RECV);
+
+	security_inet_csk_clone(nsk, req);
 	bh_unlock_sock(nsk);
 
 	/* keep a single reference */
@@ -1747,6 +2730,8 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk)
 				      TCP_INIT_CWND * tp->advmss);
 	if (msk->rcvq_space.space == 0)
 		msk->rcvq_space.space = TCP_INIT_CWND * TCP_MSS_DEFAULT;
+
+	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
 }
 
 static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
@@ -1771,7 +2756,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 	if (sk_is_mptcp(newsk)) {
 		struct mptcp_subflow_context *subflow;
 		struct sock *new_mptcp_sock;
-		struct sock *ssk = newsk;
 
 		subflow = mptcp_subflow_ctx(newsk);
 		new_mptcp_sock = subflow->conn;
@@ -1786,21 +2770,8 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 
 		/* acquire the 2nd reference for the owning socket */
 		sock_hold(new_mptcp_sock);
-
-		local_bh_disable();
-		bh_lock_sock(new_mptcp_sock);
-		msk = mptcp_sk(new_mptcp_sock);
-		msk->first = newsk;
-
 		newsk = new_mptcp_sock;
-		mptcp_copy_inaddrs(newsk, ssk);
-		list_add(&subflow->node, &msk->conn_list);
-
-		mptcp_rcv_space_init(msk, ssk);
-		bh_unlock_sock(new_mptcp_sock);
-
-		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
-		local_bh_enable();
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK);
 	} else {
 		MPTCP_INC_STATS(sock_net(sk),
 				MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK);
@@ -1809,14 +2780,25 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err,
 	return newsk;
 }
 
-static void mptcp_destroy(struct sock *sk)
+void mptcp_destroy_common(struct mptcp_sock *msk)
 {
-	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct sock *sk = (struct sock *)msk;
+
+	__mptcp_clear_xmit(sk);
+
+	/* move to sk_receive_queue, sk_stream_kill_queues will purge it */
+	skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue);
 
+	skb_rbtree_purge(&msk->out_of_order_queue);
 	mptcp_token_destroy(msk);
-	if (msk->cached_ext)
-		__skb_ext_put(msk->cached_ext);
+	mptcp_pm_free_anno_list(msk);
+}
 
+static void mptcp_destroy(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	mptcp_destroy_common(msk);
 	sk_sockets_allocated_dec(sk);
 }
 
@@ -1930,16 +2912,58 @@ static int mptcp_getsockopt(struct sock *sk, int level, int optname,
 	return -EOPNOTSUPP;
 }
 
-#define MPTCP_DEFERRED_ALL (TCPF_DELACK_TIMER_DEFERRED | \
-			    TCPF_WRITE_TIMER_DEFERRED)
+void __mptcp_data_acked(struct sock *sk)
+{
+	if (!sock_owned_by_user(sk))
+		__mptcp_clean_una(sk);
+	else
+		set_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags);
 
-/* this is very alike tcp_release_cb() but we must handle differently a
- * different set of events
- */
+	if (mptcp_pending_data_fin_ack(sk))
+		mptcp_schedule_work(sk);
+}
+
+void __mptcp_check_push(struct sock *sk, struct sock *ssk)
+{
+	if (!mptcp_send_head(sk))
+		return;
+
+	if (!sock_owned_by_user(sk))
+		__mptcp_subflow_push_pending(sk, ssk);
+	else
+		set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags);
+}
+
+#define MPTCP_DEFERRED_ALL (TCPF_WRITE_TIMER_DEFERRED)
+
+/* processes deferred events and flush wmem */
 static void mptcp_release_cb(struct sock *sk)
 {
 	unsigned long flags, nflags;
 
+	/* push_pending may touch wmem_reserved, do it before the later
+	 * cleanup
+	 */
+	if (test_and_clear_bit(MPTCP_CLEAN_UNA, &mptcp_sk(sk)->flags))
+		__mptcp_clean_una(sk);
+	if (test_and_clear_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) {
+		/* mptcp_push_pending() acquires the subflow socket lock
+		 *
+		 * 1) can't be invoked in atomic scope
+		 * 2) must avoid ABBA deadlock with msk socket spinlock: the RX
+		 *    datapath acquires the msk socket spinlock while helding
+		 *    the subflow socket lock
+		 */
+
+		spin_unlock_bh(&sk->sk_lock.slock);
+		mptcp_push_pending(sk, 0);
+		spin_lock_bh(&sk->sk_lock.slock);
+	}
+
+	/* clear any wmem reservation and errors */
+	__mptcp_update_wmem(sk);
+	__mptcp_update_rmem(sk);
+
 	do {
 		flags = sk->sk_tsq_flags;
 		if (!(flags & MPTCP_DEFERRED_ALL))
@@ -1949,15 +2973,6 @@ static void mptcp_release_cb(struct sock *sk)
 
 	sock_release_ownership(sk);
 
-	if (flags & TCPF_DELACK_TIMER_DEFERRED) {
-		struct mptcp_sock *msk = mptcp_sk(sk);
-		struct sock *ssk;
-
-		ssk = mptcp_subflow_recv_lookup(msk);
-		if (!ssk || !schedule_work(&msk->work))
-			__sock_put(sk);
-	}
-
 	if (flags & TCPF_WRITE_TIMER_DEFERRED) {
 		mptcp_retransmit_handler(sk);
 		__sock_put(sk);
@@ -2015,9 +3030,11 @@ void mptcp_finish_connect(struct sock *ssk)
 	WRITE_ONCE(msk->remote_key, subflow->remote_key);
 	WRITE_ONCE(msk->local_key, subflow->local_key);
 	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
+	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 	WRITE_ONCE(msk->ack_seq, ack_seq);
+	WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 	WRITE_ONCE(msk->can_ack, 1);
-	atomic64_set(&msk->snd_una, msk->write_seq);
+	WRITE_ONCE(msk->snd_una, msk->write_seq);
 
 	mptcp_pm_new_connection(msk, 0);
 
@@ -2033,9 +3050,9 @@ static void mptcp_sock_graft(struct sock *sk, struct socket *parent)
 	write_unlock_bh(&sk->sk_callback_lock);
 }
 
-bool mptcp_finish_join(struct sock *sk)
+bool mptcp_finish_join(struct sock *ssk)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	struct sock *parent = (void *)msk;
 	struct socket *parent_sock;
@@ -2056,12 +3073,14 @@ bool mptcp_finish_join(struct sock *sk)
 	/* active connections are already on conn_list, and we can't acquire
 	 * msk lock here.
 	 * use the join list lock as synchronization point and double-check
-	 * msk status to avoid racing with mptcp_close()
+	 * msk status to avoid racing with __mptcp_destroy_sock()
 	 */
 	spin_lock_bh(&msk->join_list_lock);
 	ret = inet_sk_state_load(parent) == TCP_ESTABLISHED;
-	if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node)))
+	if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node))) {
 		list_add_tail(&subflow->node, &msk->join_list);
+		sock_hold(ssk);
+	}
 	spin_unlock_bh(&msk->join_list_lock);
 	if (!ret)
 		return false;
@@ -2070,17 +3089,18 @@ bool mptcp_finish_join(struct sock *sk)
 	 * at close time
 	 */
 	parent_sock = READ_ONCE(parent->sk_socket);
-	if (parent_sock && !sk->sk_socket)
-		mptcp_sock_graft(sk, parent_sock);
+	if (parent_sock && !ssk->sk_socket)
+		mptcp_sock_graft(ssk, parent_sock);
 	subflow->map_seq = READ_ONCE(msk->ack_seq);
 	return true;
 }
 
-static bool mptcp_memory_free(const struct sock *sk, int wake)
+static void mptcp_shutdown(struct sock *sk, int how)
 {
-	struct mptcp_sock *msk = mptcp_sk(sk);
+	pr_debug("sk=%p, how=%d", sk, how);
 
-	return wake ? test_bit(MPTCP_SEND_SPACE, &msk->flags) : true;
+	if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
+		__mptcp_wr_shutdown(sk);
 }
 
 static struct proto mptcp_prot = {
@@ -2092,7 +3112,7 @@ static struct proto mptcp_prot = {
 	.accept		= mptcp_accept,
 	.setsockopt	= mptcp_setsockopt,
 	.getsockopt	= mptcp_getsockopt,
-	.shutdown	= tcp_shutdown,
+	.shutdown	= mptcp_shutdown,
 	.destroy	= mptcp_destroy,
 	.sendmsg	= mptcp_sendmsg,
 	.recvmsg	= mptcp_recvmsg,
@@ -2103,8 +3123,8 @@ static struct proto mptcp_prot = {
 	.sockets_allocated	= &mptcp_sockets_allocated,
 	.memory_allocated	= &tcp_memory_allocated,
 	.memory_pressure	= &tcp_memory_pressure,
-	.stream_memory_free	= mptcp_memory_free,
 	.sysctl_wmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_wmem),
+	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_rmem),
 	.sysctl_mem	= sysctl_tcp_mem,
 	.obj_size	= sizeof(struct mptcp_sock),
 	.slab_flags	= SLAB_TYPESAFE_BY_RCU,
@@ -2247,6 +3267,23 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 	if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) {
 		struct mptcp_sock *msk = mptcp_sk(newsock->sk);
 		struct mptcp_subflow_context *subflow;
+		struct sock *newsk = newsock->sk;
+		bool slowpath;
+
+		slowpath = lock_sock_fast(newsk);
+
+		/* PM/worker can now acquire the first subflow socket
+		 * lock without racing with listener queue cleanup,
+		 * we can notify it, if needed.
+		 */
+		subflow = mptcp_subflow_ctx(msk->first);
+		list_add(&subflow->node, &msk->conn_list);
+		sock_hold(msk->first);
+		if (mptcp_is_fully_established(newsk))
+			mptcp_pm_fully_established(msk);
+
+		mptcp_copy_inaddrs(newsk, msk->first);
+		mptcp_rcv_space_init(msk, msk->first);
 
 		/* set ssk->sk_socket of accept()ed flows to mptcp socket.
 		 * This is needed so NOSPACE flag can be set from tcp stack.
@@ -2258,6 +3295,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
 			if (!ssk->sk_socket)
 				mptcp_sock_graft(ssk, newsock);
 		}
+		unlock_sock_fast(newsk, slowpath);
 	}
 
 	if (inet_csk_listen_poll(ssock->sk))
@@ -2276,6 +3314,24 @@ static __poll_t mptcp_check_readable(struct mptcp_sock *msk)
 	       0;
 }
 
+static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
+{
+	struct sock *sk = (struct sock *)msk;
+
+	if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
+		return 0;
+
+	if (sk_stream_is_writeable(sk))
+		return EPOLLOUT | EPOLLWRNORM;
+
+	set_bit(MPTCP_NOSPACE, &msk->flags);
+	smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
+	if (sk_stream_is_writeable(sk))
+		return EPOLLOUT | EPOLLWRNORM;
+
+	return 0;
+}
+
 static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 			   struct poll_table_struct *wait)
 {
@@ -2288,14 +3344,13 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	sock_poll_wait(file, sock, wait);
 
 	state = inet_sk_state_load(sk);
+	pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
 	if (state == TCP_LISTEN)
 		return mptcp_check_readable(msk);
 
 	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
 		mask |= mptcp_check_readable(msk);
-		if (sk_stream_is_writeable(sk) &&
-		    test_bit(MPTCP_SEND_SPACE, &msk->flags))
-			mask |= EPOLLOUT | EPOLLWRNORM;
+		mask |= mptcp_check_writeable(msk);
 	}
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
@@ -2303,66 +3358,6 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	return mask;
 }
 
-static int mptcp_shutdown(struct socket *sock, int how)
-{
-	struct mptcp_sock *msk = mptcp_sk(sock->sk);
-	struct mptcp_subflow_context *subflow;
-	int ret = 0;
-
-	pr_debug("sk=%p, how=%d", msk, how);
-
-	lock_sock(sock->sk);
-
-	how++;
-	if ((how & ~SHUTDOWN_MASK) || !how) {
-		ret = -EINVAL;
-		goto out_unlock;
-	}
-
-	if (sock->state == SS_CONNECTING) {
-		if ((1 << sock->sk->sk_state) &
-		    (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
-			sock->state = SS_DISCONNECTING;
-		else
-			sock->state = SS_CONNECTED;
-	}
-
-	/* If we've already sent a FIN, or it's a closed state, skip this. */
-	if (__mptcp_check_fallback(msk)) {
-		if (how == SHUT_WR || how == SHUT_RDWR)
-			inet_sk_state_store(sock->sk, TCP_FIN_WAIT1);
-
-		mptcp_for_each_subflow(msk, subflow) {
-			struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
-			mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
-		}
-	} else if ((how & SEND_SHUTDOWN) &&
-		   ((1 << sock->sk->sk_state) &
-		    (TCPF_ESTABLISHED | TCPF_SYN_SENT |
-		     TCPF_SYN_RECV | TCPF_CLOSE_WAIT)) &&
-		   mptcp_close_state(sock->sk)) {
-		__mptcp_flush_join_list(msk);
-
-		WRITE_ONCE(msk->write_seq, msk->write_seq + 1);
-		WRITE_ONCE(msk->snd_data_fin_enable, 1);
-
-		mptcp_for_each_subflow(msk, subflow) {
-			struct sock *tcp_sk = mptcp_subflow_tcp_sock(subflow);
-
-			mptcp_subflow_shutdown(sock->sk, tcp_sk, how);
-		}
-	}
-
-	/* Wake up anyone sleeping in poll. */
-	sock->sk->sk_state_change(sock->sk);
-
-out_unlock:
-	release_sock(sock->sk);
-
-	return ret;
-}
-
 static const struct proto_ops mptcp_stream_ops = {
 	.family		   = PF_INET,
 	.owner		   = THIS_MODULE,
@@ -2376,7 +3371,7 @@ static const struct proto_ops mptcp_stream_ops = {
 	.ioctl		   = inet_ioctl,
 	.gettstamp	   = sock_gettstamp,
 	.listen		   = mptcp_listen,
-	.shutdown	   = mptcp_shutdown,
+	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
 	.getsockopt	   = sock_common_getsockopt,
 	.sendmsg	   = inet_sendmsg,
@@ -2426,7 +3421,7 @@ static const struct proto_ops mptcp_v6_stream_ops = {
 	.ioctl		   = inet6_ioctl,
 	.gettstamp	   = sock_gettstamp,
 	.listen		   = mptcp_listen,
-	.shutdown	   = mptcp_shutdown,
+	.shutdown	   = inet_shutdown,
 	.setsockopt	   = sock_common_setsockopt,
 	.getsockopt	   = sock_common_getsockopt,
 	.sendmsg	   = inet6_sendmsg,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 20f04ac85409..d67de793d363 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -23,6 +23,7 @@
 #define OPTION_MPTCP_ADD_ADDR	BIT(6)
 #define OPTION_MPTCP_ADD_ADDR6	BIT(7)
 #define OPTION_MPTCP_RM_ADDR	BIT(8)
+#define OPTION_MPTCP_FASTCLOSE	BIT(9)
 
 /* MPTCP option subtypes */
 #define MPTCPOPT_MP_CAPABLE	0
@@ -49,15 +50,16 @@
 #define TCPOLEN_MPTCP_DSS_MAP64		14
 #define TCPOLEN_MPTCP_DSS_CHECKSUM	2
 #define TCPOLEN_MPTCP_ADD_ADDR		16
-#define TCPOLEN_MPTCP_ADD_ADDR_PORT	18
+#define TCPOLEN_MPTCP_ADD_ADDR_PORT	20
 #define TCPOLEN_MPTCP_ADD_ADDR_BASE	8
-#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT	10
+#define TCPOLEN_MPTCP_ADD_ADDR_BASE_PORT	12
 #define TCPOLEN_MPTCP_ADD_ADDR6		28
-#define TCPOLEN_MPTCP_ADD_ADDR6_PORT	30
+#define TCPOLEN_MPTCP_ADD_ADDR6_PORT	32
 #define TCPOLEN_MPTCP_ADD_ADDR6_BASE	20
-#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT	22
-#define TCPOLEN_MPTCP_PORT_LEN		2
+#define TCPOLEN_MPTCP_ADD_ADDR6_BASE_PORT	24
+#define TCPOLEN_MPTCP_PORT_LEN		4
 #define TCPOLEN_MPTCP_RM_ADDR_BASE	4
+#define TCPOLEN_MPTCP_FASTCLOSE		12
 
 /* MPTCP MP_JOIN flags */
 #define MPTCPOPT_BACKUP		BIT(0)
@@ -86,10 +88,20 @@
 
 /* MPTCP socket flags */
 #define MPTCP_DATA_READY	0
-#define MPTCP_SEND_SPACE	1
+#define MPTCP_NOSPACE		1
 #define MPTCP_WORK_RTX		2
 #define MPTCP_WORK_EOF		3
 #define MPTCP_FALLBACK_DONE	4
+#define MPTCP_WORK_CLOSE_SUBFLOW 5
+#define MPTCP_PUSH_PENDING	6
+#define MPTCP_CLEAN_UNA		7
+
+static inline bool before64(__u64 seq1, __u64 seq2)
+{
+	return (__s64)(seq1 - seq2) < 0;
+}
+
+#define after64(seq2, seq1)	before64(seq1, seq2)
 
 struct mptcp_options_received {
 	u64	sndr_key;
@@ -100,6 +112,7 @@ struct mptcp_options_received {
 	u16	data_len;
 	u16	mp_capable : 1,
 		mp_join : 1,
+		fastclose : 1,
 		dss : 1,
 		add_addr : 1,
 		rm_addr : 1,
@@ -109,7 +122,7 @@ struct mptcp_options_received {
 	u32	token;
 	u32	nonce;
 	u64	thmac;
-	u8	hmac[20];
+	u8	hmac[MPTCPOPT_HMAC_LEN];
 	u8	join_id;
 	u8	use_map:1,
 		dsn64:1,
@@ -140,6 +153,8 @@ struct mptcp_addr_info {
 	sa_family_t		family;
 	__be16			port;
 	u8			id;
+	u8			flags;
+	int			ifindex;
 	union {
 		struct in_addr addr;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -150,17 +165,29 @@ struct mptcp_addr_info {
 
 enum mptcp_pm_status {
 	MPTCP_PM_ADD_ADDR_RECEIVED,
+	MPTCP_PM_ADD_ADDR_SEND_ACK,
+	MPTCP_PM_RM_ADDR_RECEIVED,
 	MPTCP_PM_ESTABLISHED,
+	MPTCP_PM_ALREADY_ESTABLISHED,	/* persistent status, set after ESTABLISHED event */
 	MPTCP_PM_SUBFLOW_ESTABLISHED,
 };
 
+enum mptcp_addr_signal_status {
+	MPTCP_ADD_ADDR_SIGNAL,
+	MPTCP_ADD_ADDR_ECHO,
+	MPTCP_ADD_ADDR_IPV6,
+	MPTCP_ADD_ADDR_PORT,
+	MPTCP_RM_ADDR_SIGNAL,
+};
+
 struct mptcp_pm_data {
 	struct mptcp_addr_info local;
 	struct mptcp_addr_info remote;
+	struct list_head anno_list;
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
-	bool		addr_signal;
+	u8		addr_signal;
 	bool		server_side;
 	bool		work_pending;
 	bool		accept_addr;
@@ -174,14 +201,16 @@ struct mptcp_pm_data {
 	u8		local_addr_max;
 	u8		subflows_max;
 	u8		status;
+	u8		rm_id;
 };
 
 struct mptcp_data_frag {
 	struct list_head list;
 	u64 data_seq;
-	int data_len;
-	int offset;
-	int overhead;
+	u16 data_len;
+	u16 offset;
+	u16 overhead;
+	u16 already_sent;
 	struct page *page;
 };
 
@@ -192,22 +221,40 @@ struct mptcp_sock {
 	u64		local_key;
 	u64		remote_key;
 	u64		write_seq;
+	u64		snd_nxt;
 	u64		ack_seq;
+	u64		rcv_wnd_sent;
 	u64		rcv_data_fin_seq;
-	atomic64_t	snd_una;
+	int		wmem_reserved;
+	struct sock	*last_snd;
+	int		snd_burst;
+	int		old_wspace;
+	u64		snd_una;
+	u64		wnd_end;
 	unsigned long	timer_ival;
 	u32		token;
+	int		rmem_pending;
+	int		rmem_released;
 	unsigned long	flags;
 	bool		can_ack;
 	bool		fully_established;
 	bool		rcv_data_fin;
 	bool		snd_data_fin_enable;
+	bool		rcv_fastclose;
+	bool		use_64bit_ack; /* Set when we received a 64-bit DSN */
 	spinlock_t	join_list_lock;
+	struct sock	*ack_hint;
 	struct work_struct work;
+	struct sk_buff  *ooo_last_skb;
+	struct rb_root  out_of_order_queue;
+	struct sk_buff_head receive_queue;
+	struct sk_buff_head skb_tx_cache;	/* this is wmem accounted */
+	int		tx_pending_data;
+	int		size_goal_cache;
 	struct list_head conn_list;
 	struct list_head rtx_queue;
+	struct mptcp_data_frag *first_pending;
 	struct list_head join_list;
-	struct skb_ext	*cached_ext;	/* for the next sendmsg */
 	struct socket	*subflow; /* outgoing connect/listener/!mp_capable */
 	struct sock	*first;
 	struct mptcp_pm_data	pm;
@@ -219,6 +266,22 @@ struct mptcp_sock {
 	} rcvq_space;
 };
 
+#define mptcp_lock_sock(___sk, cb) do {					\
+	struct sock *__sk = (___sk); /* silence macro reuse warning */	\
+	might_sleep();							\
+	spin_lock_bh(&__sk->sk_lock.slock);				\
+	if (__sk->sk_lock.owned)					\
+		__lock_sock(__sk);					\
+	cb;								\
+	__sk->sk_lock.owned = 1;					\
+	spin_unlock(&__sk->sk_lock.slock);				\
+	mutex_acquire(&__sk->sk_lock.dep_map, 0, 0, _RET_IP_);		\
+	local_bh_enable();						\
+} while (0)
+
+#define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock)
+#define mptcp_data_unlock(sk) spin_unlock_bh(&(sk)->sk_lock.slock)
+
 #define mptcp_for_each_subflow(__msk, __subflow)			\
 	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
 
@@ -227,11 +290,46 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk)
 	return (struct mptcp_sock *)sk;
 }
 
+static inline int __mptcp_space(const struct sock *sk)
+{
+	return tcp_space(sk) + READ_ONCE(mptcp_sk(sk)->rmem_pending);
+}
+
+static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)
+{
+	const struct mptcp_sock *msk = mptcp_sk(sk);
+
+	return READ_ONCE(msk->first_pending);
+}
+
+static inline struct mptcp_data_frag *mptcp_send_next(struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+	struct mptcp_data_frag *cur;
+
+	cur = msk->first_pending;
+	return list_is_last(&cur->list, &msk->rtx_queue) ? NULL :
+						     list_next_entry(cur, list);
+}
+
+static inline struct mptcp_data_frag *mptcp_pending_tail(const struct sock *sk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	if (!msk->first_pending)
+		return NULL;
+
+	if (WARN_ON_ONCE(list_empty(&msk->rtx_queue)))
+		return NULL;
+
+	return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
+}
+
 static inline struct mptcp_data_frag *mptcp_rtx_tail(const struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
-	if (list_empty(&msk->rtx_queue))
+	if (!before64(msk->snd_nxt, READ_ONCE(msk->snd_una)))
 		return NULL;
 
 	return list_last_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
@@ -268,6 +366,12 @@ mptcp_subflow_rsk(const struct request_sock *rsk)
 	return (struct mptcp_subflow_request_sock *)rsk;
 }
 
+enum mptcp_data_avail {
+	MPTCP_SUBFLOW_NODATA,
+	MPTCP_SUBFLOW_DATA_AVAIL,
+	MPTCP_SUBFLOW_OOO_DATA
+};
+
 /* MPTCP subflow context */
 struct mptcp_subflow_context {
 	struct	list_head node;/* conn_list of subflows */
@@ -292,10 +396,10 @@ struct mptcp_subflow_context {
 		map_valid : 1,
 		mpc_map : 1,
 		backup : 1,
-		data_avail : 1,
 		rx_eof : 1,
-		use_64bit_ack : 1, /* Set when we received a 64-bit DSN */
-		can_ack : 1;	    /* only after processing the remote a key */
+		can_ack : 1,        /* only after processing the remote a key */
+		disposable : 1;	    /* ctx can be free at ulp release time */
+	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;
 	u32	local_nonce;
@@ -343,15 +447,28 @@ mptcp_subflow_get_mapped_dsn(const struct mptcp_subflow_context *subflow)
 	return subflow->map_seq + mptcp_subflow_get_map_offset(subflow);
 }
 
+static inline void mptcp_add_pending_subflow(struct mptcp_sock *msk,
+					     struct mptcp_subflow_context *subflow)
+{
+	sock_hold(mptcp_subflow_tcp_sock(subflow));
+	spin_lock_bh(&msk->join_list_lock);
+	list_add_tail(&subflow->node, &msk->join_list);
+	spin_unlock_bh(&msk->join_list_lock);
+}
+
 int mptcp_is_enabled(struct net *net);
+unsigned int mptcp_get_add_addr_timeout(struct net *net);
 void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow,
 				     struct mptcp_options_received *mp_opt);
 bool mptcp_subflow_data_available(struct sock *sk);
 void __init mptcp_subflow_init(void);
+void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
+void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+		       struct mptcp_subflow_context *subflow);
+void mptcp_subflow_reset(struct sock *ssk);
 
 /* called with sk socket lock held */
-int __mptcp_subflow_connect(struct sock *sk, int ifindex,
-			    const struct mptcp_addr_info *loc,
+int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 			    const struct mptcp_addr_info *remote);
 int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock);
 
@@ -385,9 +502,19 @@ static inline bool mptcp_is_fully_established(struct sock *sk)
 void mptcp_rcv_space_init(struct mptcp_sock *msk, const struct sock *ssk);
 void mptcp_data_ready(struct sock *sk, struct sock *ssk);
 bool mptcp_finish_join(struct sock *sk);
-void mptcp_data_acked(struct sock *sk);
+bool mptcp_schedule_work(struct sock *sk);
+void __mptcp_check_push(struct sock *sk, struct sock *ssk);
+void __mptcp_data_acked(struct sock *sk);
 void mptcp_subflow_eof(struct sock *sk);
 bool mptcp_update_rcv_data_fin(struct mptcp_sock *msk, u64 data_fin_seq, bool use_64bit);
+void __mptcp_flush_join_list(struct mptcp_sock *msk);
+static inline bool mptcp_data_fin_enabled(const struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->snd_data_fin_enable) &&
+	       READ_ONCE(msk->write_seq) == READ_ONCE(msk->snd_nxt);
+}
+
+void mptcp_destroy_common(struct mptcp_sock *msk);
 
 void __init mptcp_token_init(void);
 static inline void mptcp_token_init_request(struct request_sock *req)
@@ -421,26 +548,62 @@ void mptcp_pm_subflow_established(struct mptcp_sock *msk,
 void mptcp_pm_subflow_closed(struct mptcp_sock *msk, u8 id);
 void mptcp_pm_add_addr_received(struct mptcp_sock *msk,
 				const struct mptcp_addr_info *addr);
+void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
+void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, u8 rm_id);
+void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
+struct mptcp_pm_add_entry *
+mptcp_pm_del_add_timer(struct mptcp_sock *msk,
+		       struct mptcp_addr_info *addr);
 
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
-			   const struct mptcp_addr_info *addr);
+			   const struct mptcp_addr_info *addr,
+			   bool echo, bool port);
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, u8 local_id);
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 remote_id);
+int mptcp_pm_remove_subflow(struct mptcp_sock *msk, u8 local_id);
+
+static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_SIGNAL);
+}
+
+static inline bool mptcp_pm_should_add_signal_echo(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_ECHO);
+}
 
-static inline bool mptcp_pm_should_signal(struct mptcp_sock *msk)
+static inline bool mptcp_pm_should_add_signal_ipv6(struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.addr_signal);
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_IPV6);
 }
 
-static inline unsigned int mptcp_add_addr_len(int family)
+static inline bool mptcp_pm_should_add_signal_port(struct mptcp_sock *msk)
 {
-	if (family == AF_INET)
-		return TCPOLEN_MPTCP_ADD_ADDR;
-	return TCPOLEN_MPTCP_ADD_ADDR6;
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_ADD_ADDR_PORT);
 }
 
-bool mptcp_pm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
-			  struct mptcp_addr_info *saddr);
+static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
+{
+	return READ_ONCE(msk->pm.addr_signal) & BIT(MPTCP_RM_ADDR_SIGNAL);
+}
+
+static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port)
+{
+	u8 len = TCPOLEN_MPTCP_ADD_ADDR_BASE;
+
+	if (family == AF_INET6)
+		len = TCPOLEN_MPTCP_ADD_ADDR6_BASE;
+	if (!echo)
+		len += MPTCPOPT_THMAC_LEN;
+	if (port)
+		len += TCPOLEN_MPTCP_PORT_LEN;
+
+	return len;
+}
+
+bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
+			      struct mptcp_addr_info *saddr, bool *echo, bool *port);
+bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
+			     u8 *rm_id);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 
 void __init mptcp_pm_nl_init(void);
@@ -448,6 +611,9 @@ void mptcp_pm_nl_data_init(struct mptcp_sock *msk);
 void mptcp_pm_nl_fully_established(struct mptcp_sock *msk);
 void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk);
 void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk);
+void mptcp_pm_nl_add_addr_send_ack(struct mptcp_sock *msk);
+void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk);
+void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 
 static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
@@ -455,21 +621,14 @@ static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
 	return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
 }
 
-static inline bool before64(__u64 seq1, __u64 seq2)
-{
-	return (__s64)(seq1 - seq2) < 0;
-}
-
-#define after64(seq2, seq1)	before64(seq1, seq2)
-
 void mptcp_diag_subflow_init(struct tcp_ulp_ops *ops);
 
-static inline bool __mptcp_check_fallback(struct mptcp_sock *msk)
+static inline bool __mptcp_check_fallback(const struct mptcp_sock *msk)
 {
 	return test_bit(MPTCP_FALLBACK_DONE, &msk->flags);
 }
 
-static inline bool mptcp_check_fallback(struct sock *sk)
+static inline bool mptcp_check_fallback(const struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 6f035af1c9d2..278cbe3e539e 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -10,7 +10,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <crypto/algapi.h>
-#include <crypto/sha.h>
+#include <crypto/sha2.h>
 #include <net/sock.h>
 #include <net/inet_common.h>
 #include <net/inet_hashtables.h>
@@ -20,6 +20,7 @@
 #include <net/ip6_route.h>
 #endif
 #include <net/mptcp.h>
+#include <uapi/linux/mptcp.h>
 #include "protocol.h"
 #include "mib.h"
 
@@ -111,9 +112,14 @@ static int __subflow_init_req(struct request_sock *req, const struct sock *sk_li
 	return 0;
 }
 
-static void subflow_init_req(struct request_sock *req,
-			     const struct sock *sk_listener,
-			     struct sk_buff *skb)
+/* Init mptcp request socket.
+ *
+ * Returns an error code if a JOIN has failed and a TCP reset
+ * should be sent.
+ */
+static int subflow_init_req(struct request_sock *req,
+			    const struct sock *sk_listener,
+			    struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *listener = mptcp_subflow_ctx(sk_listener);
 	struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
@@ -124,7 +130,7 @@ static void subflow_init_req(struct request_sock *req,
 
 	ret = __subflow_init_req(req, sk_listener);
 	if (ret)
-		return;
+		return 0;
 
 	mptcp_get_options(skb, &mp_opt);
 
@@ -132,7 +138,7 @@ static void subflow_init_req(struct request_sock *req,
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
 		if (mp_opt.mp_join)
-			return;
+			return 0;
 	} else if (mp_opt.mp_join) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
 	}
@@ -156,7 +162,7 @@ again:
 			} else {
 				subflow_req->mp_capable = 1;
 			}
-			return;
+			return 0;
 		}
 
 		err = mptcp_token_new_request(req);
@@ -174,7 +180,11 @@ again:
 		subflow_req->remote_nonce = mp_opt.nonce;
 		subflow_req->msk = subflow_token_join_request(req, skb);
 
-		if (unlikely(req->syncookie) && subflow_req->msk) {
+		/* Can't fall back to TCP in this case. */
+		if (!subflow_req->msk)
+			return -EPERM;
+
+		if (unlikely(req->syncookie)) {
 			if (mptcp_can_accept_new_subflow(subflow_req->msk))
 				subflow_init_req_cookie_join_save(subflow_req, skb);
 		}
@@ -182,6 +192,8 @@ again:
 		pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
 			 subflow_req->remote_nonce, subflow_req->msk);
 	}
+
+	return 0;
 }
 
 int mptcp_subflow_init_cookie_req(struct request_sock *req,
@@ -227,27 +239,53 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req,
 }
 EXPORT_SYMBOL_GPL(mptcp_subflow_init_cookie_req);
 
-static void subflow_v4_init_req(struct request_sock *req,
-				const struct sock *sk_listener,
-				struct sk_buff *skb)
+static struct dst_entry *subflow_v4_route_req(const struct sock *sk,
+					      struct sk_buff *skb,
+					      struct flowi *fl,
+					      struct request_sock *req)
 {
+	struct dst_entry *dst;
+	int err;
+
 	tcp_rsk(req)->is_mptcp = 1;
 
-	tcp_request_sock_ipv4_ops.init_req(req, sk_listener, skb);
+	dst = tcp_request_sock_ipv4_ops.route_req(sk, skb, fl, req);
+	if (!dst)
+		return NULL;
+
+	err = subflow_init_req(req, sk, skb);
+	if (err == 0)
+		return dst;
 
-	subflow_init_req(req, sk_listener, skb);
+	dst_release(dst);
+	if (!req->syncookie)
+		tcp_request_sock_ops.send_reset(sk, skb);
+	return NULL;
 }
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
-static void subflow_v6_init_req(struct request_sock *req,
-				const struct sock *sk_listener,
-				struct sk_buff *skb)
+static struct dst_entry *subflow_v6_route_req(const struct sock *sk,
+					      struct sk_buff *skb,
+					      struct flowi *fl,
+					      struct request_sock *req)
 {
+	struct dst_entry *dst;
+	int err;
+
 	tcp_rsk(req)->is_mptcp = 1;
 
-	tcp_request_sock_ipv6_ops.init_req(req, sk_listener, skb);
+	dst = tcp_request_sock_ipv6_ops.route_req(sk, skb, fl, req);
+	if (!dst)
+		return NULL;
+
+	err = subflow_init_req(req, sk, skb);
+	if (err == 0)
+		return dst;
 
-	subflow_init_req(req, sk_listener, skb);
+	dst_release(dst);
+	if (!req->syncookie)
+		tcp6_request_sock_ops.send_reset(sk, skb);
+	return NULL;
 }
 #endif
 
@@ -270,6 +308,24 @@ static bool subflow_thmac_valid(struct mptcp_subflow_context *subflow)
 	return thmac == subflow->thmac;
 }
 
+void mptcp_subflow_reset(struct sock *ssk)
+{
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	struct sock *sk = subflow->conn;
+
+	/* must hold: tcp_done() could drop last reference on parent */
+	sock_hold(sk);
+
+	tcp_set_state(ssk, TCP_CLOSE);
+	tcp_send_active_reset(ssk, GFP_ATOMIC);
+	tcp_done(ssk);
+	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) &&
+	    schedule_work(&mptcp_sk(sk)->work))
+		return; /* worker will put sk for us */
+
+	sock_put(sk);
+}
+
 static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -342,8 +398,7 @@ fallback:
 	return;
 
 do_reset:
-	tcp_send_active_reset(sk, GFP_ATOMIC);
-	tcp_done(sk);
+	mptcp_subflow_reset(sk);
 }
 
 struct request_sock_ops mptcp_subflow_request_sock_ops;
@@ -434,7 +489,7 @@ static void mptcp_sock_destruct(struct sock *sk)
 		sock_orphan(sk);
 	}
 
-	mptcp_token_destroy(mptcp_sk(sk));
+	mptcp_destroy_common(mptcp_sk(sk));
 	inet_sock_destruct(sk);
 }
 
@@ -530,9 +585,8 @@ create_msk:
 			fallback = true;
 	} else if (subflow_req->mp_join) {
 		mptcp_get_options(skb, &mp_opt);
-		if (!mp_opt.mp_join ||
-		    !mptcp_can_accept_new_subflow(subflow_req->msk) ||
-		    !subflow_hmac_valid(req, &mp_opt)) {
+		if (!mp_opt.mp_join || !subflow_hmac_valid(req, &mp_opt) ||
+		    !mptcp_can_accept_new_subflow(subflow_req->msk)) {
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKMAC);
 			fallback = true;
 		}
@@ -565,6 +619,11 @@ create_child:
 			 */
 			inet_sk_state_store((void *)new_msk, TCP_ESTABLISHED);
 
+			/* record the newly created socket as the first msk
+			 * subflow, but don't link it yet into conn_list
+			 */
+			WRITE_ONCE(mptcp_sk(new_msk)->first, child);
+
 			/* new mpc subflow takes ownership of the newly
 			 * created mptcp socket
 			 */
@@ -769,12 +828,11 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 	if (!mpext->dsn64) {
 		map_seq = expand_seq(subflow->map_seq, subflow->map_data_len,
 				     mpext->data_seq);
-		subflow->use_64bit_ack = 0;
 		pr_debug("expanded seq=%llu", subflow->map_seq);
 	} else {
 		map_seq = mpext->data_seq;
-		subflow->use_64bit_ack = 1;
 	}
+	WRITE_ONCE(mptcp_sk(subflow->conn)->use_64bit_ack, !!mpext->dsn64);
 
 	if (subflow->map_valid) {
 		/* Allow replacing only with an identical map */
@@ -817,16 +875,23 @@ validate_seq:
 	return MAPPING_OK;
 }
 
-static int subflow_read_actor(read_descriptor_t *desc,
-			      struct sk_buff *skb,
-			      unsigned int offset, size_t len)
+static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
+				       u64 limit)
 {
-	size_t copy_len = min(desc->count, len);
-
-	desc->count -= copy_len;
-
-	pr_debug("flushed %zu bytes, %zu left", copy_len, desc->count);
-	return copy_len;
+	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+	bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
+	u32 incr;
+
+	incr = limit >= skb->len ? skb->len + fin : limit;
+
+	pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
+		 subflow->map_subflow_seq);
+	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
+	tcp_sk(ssk)->copied_seq += incr;
+	if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
+		sk_eat_skb(ssk, skb);
+	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
+		subflow->map_valid = 0;
 }
 
 static bool subflow_check_data_avail(struct sock *ssk)
@@ -838,13 +903,13 @@ static bool subflow_check_data_avail(struct sock *ssk)
 
 	pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk,
 		 subflow->data_avail, skb_peek(&ssk->sk_receive_queue));
+	if (!skb_peek(&ssk->sk_receive_queue))
+		subflow->data_avail = 0;
 	if (subflow->data_avail)
 		return true;
 
 	msk = mptcp_sk(subflow->conn);
 	for (;;) {
-		u32 map_remaining;
-		size_t delta;
 		u64 ack_seq;
 		u64 old_ack;
 
@@ -862,6 +927,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 			subflow->map_data_len = skb->len;
 			subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq -
 						   subflow->ssn_offset;
+			subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
 			return true;
 		}
 
@@ -889,42 +955,18 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
 		pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
 			 ack_seq);
-		if (ack_seq == old_ack)
+		if (ack_seq == old_ack) {
+			subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL;
+			break;
+		} else if (after64(ack_seq, old_ack)) {
+			subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA;
 			break;
+		}
 
 		/* only accept in-sequence mapping. Old values are spurious
-		 * retransmission; we can hit "future" values on active backup
-		 * subflow switch, we relay on retransmissions to get
-		 * in-sequence data.
-		 * Cuncurrent subflows support will require subflow data
-		 * reordering
+		 * retransmission
 		 */
-		map_remaining = subflow->map_data_len -
-				mptcp_subflow_get_map_offset(subflow);
-		if (before64(ack_seq, old_ack))
-			delta = min_t(size_t, old_ack - ack_seq, map_remaining);
-		else
-			delta = min_t(size_t, ack_seq - old_ack, map_remaining);
-
-		/* discard mapped data */
-		pr_debug("discarding %zu bytes, current map len=%d", delta,
-			 map_remaining);
-		if (delta) {
-			read_descriptor_t desc = {
-				.count = delta,
-			};
-			int ret;
-
-			ret = tcp_read_sock(ssk, &desc, subflow_read_actor);
-			if (ret < 0) {
-				ssk->sk_err = -ret;
-				goto fatal;
-			}
-			if (ret < delta)
-				return false;
-			if (delta == map_remaining)
-				subflow->map_valid = 0;
-		}
+		mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
 	}
 	return true;
 
@@ -935,13 +977,13 @@ fatal:
 	ssk->sk_error_report(ssk);
 	tcp_set_state(ssk, TCP_CLOSE);
 	tcp_send_active_reset(ssk, GFP_ATOMIC);
+	subflow->data_avail = 0;
 	return false;
 }
 
 bool mptcp_subflow_data_available(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct sk_buff *skb;
 
 	/* check if current mapping is still valid */
 	if (subflow->map_valid &&
@@ -954,15 +996,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
 			 subflow->map_data_len);
 	}
 
-	if (!subflow_check_data_avail(sk)) {
-		subflow->data_avail = 0;
-		return false;
-	}
-
-	skb = skb_peek(&sk->sk_receive_queue);
-	subflow->data_avail = skb &&
-		       before(tcp_sk(sk)->copied_seq, TCP_SKB_CB(skb)->end_seq);
-	return subflow->data_avail;
+	return subflow_check_data_avail(sk);
 }
 
 /* If ssk has an mptcp parent socket, use the mptcp rcvbuf occupancy,
@@ -979,7 +1013,7 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space)
 	const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	const struct sock *sk = subflow->conn;
 
-	*space = tcp_space(sk);
+	*space = __mptcp_space(sk);
 	*full_space = tcp_full_space(sk);
 }
 
@@ -1004,18 +1038,9 @@ static void subflow_data_ready(struct sock *sk)
 		mptcp_data_ready(parent, sk);
 }
 
-static void subflow_write_space(struct sock *sk)
+static void subflow_write_space(struct sock *ssk)
 {
-	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
-	struct sock *parent = subflow->conn;
-
-	sk_stream_write_space(sk);
-	if (sk_stream_is_writeable(sk)) {
-		set_bit(MPTCP_SEND_SPACE, &mptcp_sk(parent)->flags);
-		smp_mb__after_atomic();
-		/* set SEND_SPACE before sk_stream_write_space clears NOSPACE */
-		sk_stream_write_space(parent);
-	}
+	/* we take action in __mptcp_clean_una() */
 }
 
 static struct inet_connection_sock_af_ops *
@@ -1069,8 +1094,7 @@ static void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 #endif
 }
 
-int __mptcp_subflow_connect(struct sock *sk, int ifindex,
-			    const struct mptcp_addr_info *loc,
+int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 			    const struct mptcp_addr_info *remote)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1115,7 +1139,7 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex,
 	if (loc->family == AF_INET6)
 		addrlen = sizeof(struct sockaddr_in6);
 #endif
-	ssk->sk_bound_dev_if = ifindex;
+	ssk->sk_bound_dev_if = loc->ifindex;
 	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
 	if (err)
 		goto failed;
@@ -1127,24 +1151,51 @@ int __mptcp_subflow_connect(struct sock *sk, int ifindex,
 	subflow->local_id = local_id;
 	subflow->remote_id = remote_id;
 	subflow->request_join = 1;
-	subflow->request_bkup = 1;
+	subflow->request_bkup = !!(loc->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	mptcp_info2sockaddr(remote, &addr);
 
+	mptcp_add_pending_subflow(msk, subflow);
 	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);
 	if (err && err != -EINPROGRESS)
-		goto failed;
+		goto failed_unlink;
 
+	return err;
+
+failed_unlink:
 	spin_lock_bh(&msk->join_list_lock);
-	list_add_tail(&subflow->node, &msk->join_list);
+	list_del(&subflow->node);
 	spin_unlock_bh(&msk->join_list_lock);
 
-	return err;
-
 failed:
+	subflow->disposable = 1;
 	sock_release(sf);
 	return err;
 }
 
+static void mptcp_attach_cgroup(struct sock *parent, struct sock *child)
+{
+#ifdef CONFIG_SOCK_CGROUP_DATA
+	struct sock_cgroup_data *parent_skcd = &parent->sk_cgrp_data,
+				*child_skcd = &child->sk_cgrp_data;
+
+	/* only the additional subflows created by kworkers have to be modified */
+	if (cgroup_id(sock_cgroup_ptr(parent_skcd)) !=
+	    cgroup_id(sock_cgroup_ptr(child_skcd))) {
+#ifdef CONFIG_MEMCG
+		struct mem_cgroup *memcg = parent->sk_memcg;
+
+		mem_cgroup_sk_free(child);
+		if (memcg && css_tryget(&memcg->css))
+			child->sk_memcg = memcg;
+#endif /* CONFIG_MEMCG */
+
+		cgroup_sk_free(child_skcd);
+		*child_skcd = *parent_skcd;
+		cgroup_sk_clone(child_skcd);
+	}
+#endif /* CONFIG_SOCK_CGROUP_DATA */
+}
+
 int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 {
 	struct mptcp_subflow_context *subflow;
@@ -1165,6 +1216,9 @@ int mptcp_subflow_create_socket(struct sock *sk, struct socket **new_sock)
 
 	lock_sock(sf->sk);
 
+	/* the newly created socket has to be in the same cgroup as its parent */
+	mptcp_attach_cgroup(sk, sf->sk);
+
 	/* kernel sockets do not by default acquire net ref, but TCP timer
 	 * needs it.
 	 */
@@ -1263,7 +1317,6 @@ static void subflow_state_change(struct sock *sk)
 		mptcp_data_ready(parent, sk);
 
 	if (__mptcp_check_fallback(mptcp_sk(parent)) &&
-	    !(parent->sk_shutdown & RCV_SHUTDOWN) &&
 	    !subflow->rx_eof && subflow_is_done(sk)) {
 		subflow->rx_eof = 1;
 		mptcp_subflow_eof(parent);
@@ -1306,17 +1359,27 @@ out:
 	return err;
 }
 
-static void subflow_ulp_release(struct sock *sk)
+static void subflow_ulp_release(struct sock *ssk)
 {
-	struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(sk);
+	struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
+	bool release = true;
+	struct sock *sk;
 
 	if (!ctx)
 		return;
 
-	if (ctx->conn)
-		sock_put(ctx->conn);
+	sk = ctx->conn;
+	if (sk) {
+		/* if the msk has been orphaned, keep the ctx
+		 * alive, will be freed by __mptcp_close_ssk(),
+		 * when the subflow is still unaccepted
+		 */
+		release = ctx->disposable || list_empty(&ctx->node);
+		sock_put(sk);
+	}
 
-	kfree_rcu(ctx, rcu);
+	if (release)
+		kfree_rcu(ctx, rcu);
 }
 
 static void subflow_ulp_clone(const struct request_sock *req,
@@ -1401,7 +1464,7 @@ void __init mptcp_subflow_init(void)
 		panic("MPTCP: failed to init subflow request sock ops\n");
 
 	subflow_request_sock_ipv4_ops = tcp_request_sock_ipv4_ops;
-	subflow_request_sock_ipv4_ops.init_req = subflow_v4_init_req;
+	subflow_request_sock_ipv4_ops.route_req = subflow_v4_route_req;
 
 	subflow_specific = ipv4_specific;
 	subflow_specific.conn_request = subflow_v4_conn_request;
@@ -1410,7 +1473,7 @@ void __init mptcp_subflow_init(void)
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	subflow_request_sock_ipv6_ops = tcp_request_sock_ipv6_ops;
-	subflow_request_sock_ipv6_ops.init_req = subflow_v6_init_req;
+	subflow_request_sock_ipv6_ops.route_req = subflow_v6_route_req;
 
 	subflow_v6_specific = ipv6_specific;
 	subflow_v6_specific.conn_request = subflow_v6_conn_request;
diff --git a/net/mptcp/token.c b/net/mptcp/token.c
index 8b47c4bb1c6b..feb4b9ffd462 100644
--- a/net/mptcp/token.c
+++ b/net/mptcp/token.c
@@ -291,7 +291,7 @@ struct mptcp_sock *mptcp_token_iter_next(const struct net *net, long *s_slot,
 {
 	struct mptcp_sock *ret = NULL;
 	struct hlist_nulls_node *pos;
-	int slot, num;
+	int slot, num = 0;
 
 	for (slot = *s_slot; slot <= token_mask; *s_num = 0, slot++) {
 		struct token_bucket *bucket = &token_hash[slot];
diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c
index f1be3e3f6425..a9cb355324d1 100644
--- a/net/ncsi/ncsi-manage.c
+++ b/net/ncsi/ncsi-manage.c
@@ -1726,9 +1726,6 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev,
 	ndp->ptype.dev = dev;
 	dev_add_pack(&ndp->ptype);
 
-	/* Set up generic netlink interface */
-	ncsi_init_netlink(dev);
-
 	pdev = to_platform_device(dev->dev.parent);
 	if (pdev) {
 		np = pdev->dev.of_node;
@@ -1892,8 +1889,6 @@ void ncsi_unregister_dev(struct ncsi_dev *nd)
 	list_del_rcu(&ndp->node);
 	spin_unlock_irqrestore(&ncsi_dev_lock, flags);
 
-	ncsi_unregister_netlink(nd->dev);
-
 	kfree(ndp);
 }
 EXPORT_SYMBOL_GPL(ncsi_unregister_dev);
diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c
index 8b386d766e7d..bb5f1650f11c 100644
--- a/net/ncsi/ncsi-netlink.c
+++ b/net/ncsi/ncsi-netlink.c
@@ -716,7 +716,7 @@ static int ncsi_set_channel_mask_nl(struct sk_buff *msg,
 	return 0;
 }
 
-static const struct genl_ops ncsi_ops[] = {
+static const struct genl_small_ops ncsi_ops[] = {
 	{
 		.cmd = NCSI_CMD_PKG_INFO,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -762,28 +762,12 @@ static struct genl_family ncsi_genl_family __ro_after_init = {
 	.maxattr = NCSI_ATTR_MAX,
 	.policy = ncsi_genl_policy,
 	.module = THIS_MODULE,
-	.ops = ncsi_ops,
-	.n_ops = ARRAY_SIZE(ncsi_ops),
+	.small_ops = ncsi_ops,
+	.n_small_ops = ARRAY_SIZE(ncsi_ops),
 };
 
-int ncsi_init_netlink(struct net_device *dev)
+static int __init ncsi_init_netlink(void)
 {
-	int rc;
-
-	rc = genl_register_family(&ncsi_genl_family);
-	if (rc)
-		netdev_err(dev, "ncsi: failed to register netlink family\n");
-
-	return rc;
-}
-
-int ncsi_unregister_netlink(struct net_device *dev)
-{
-	int rc;
-
-	rc = genl_unregister_family(&ncsi_genl_family);
-	if (rc)
-		netdev_err(dev, "ncsi: failed to unregister netlink family\n");
-
-	return rc;
+	return genl_register_family(&ncsi_genl_family);
 }
+subsys_initcall(ncsi_init_netlink);
diff --git a/net/ncsi/ncsi-netlink.h b/net/ncsi/ncsi-netlink.h
index 7502723fba83..39a1a9d7bf77 100644
--- a/net/ncsi/ncsi-netlink.h
+++ b/net/ncsi/ncsi-netlink.h
@@ -22,7 +22,4 @@ int ncsi_send_netlink_err(struct net_device *dev,
 			  struct nlmsghdr *nlhdr,
 			  int err);
 
-int ncsi_init_netlink(struct net_device *dev);
-int ncsi_unregister_netlink(struct net_device *dev);
-
 #endif /* __NCSI_NETLINK_H__ */
diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c
index 5b1f4ec66dd9..888ccc2d4e34 100644
--- a/net/ncsi/ncsi-rsp.c
+++ b/net/ncsi/ncsi-rsp.c
@@ -1120,7 +1120,7 @@ int ncsi_rcv_rsp(struct sk_buff *skb, struct net_device *dev,
 	int payload, i, ret;
 
 	/* Find the NCSI device */
-	nd = ncsi_find_dev(dev);
+	nd = ncsi_find_dev(orig_dev);
 	ndp = nd ? TO_NCSI_DEV_PRIV(nd) : NULL;
 	if (!ndp)
 		return -ENODEV;
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 25313c29d799..49fbef0d99be 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -441,6 +441,7 @@ endif # NF_CONNTRACK
 
 config NF_TABLES
 	select NETFILTER_NETLINK
+	select LIBCRC32C
 	tristate "Netfilter nf_tables support"
 	help
 	  nftables is the new packet classification framework that intends to
@@ -681,6 +682,16 @@ config NFT_FIB_NETDEV
 	  The lookup will be delegated to the IPv4 or IPv6 FIB depending
 	  on the protocol of the packet.
 
+config NFT_REJECT_NETDEV
+	depends on NFT_REJECT_IPV4
+	depends on NFT_REJECT_IPV6
+	tristate "Netfilter nf_tables netdev REJECT support"
+	help
+	  This option enables the REJECT support from the netdev table.
+	  The return packet generation will be delegated to the IPv4
+	  or IPv6 ICMP or TCP RST implementation depending on the
+	  protocol of the packet.
+
 endif # NF_TABLES_NETDEV
 
 endif # NF_TABLES
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 0e0ded87e27b..33da7bf1b68e 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -101,6 +101,7 @@ obj-$(CONFIG_NFT_QUEUE)		+= nft_queue.o
 obj-$(CONFIG_NFT_QUOTA)		+= nft_quota.o
 obj-$(CONFIG_NFT_REJECT) 	+= nft_reject.o
 obj-$(CONFIG_NFT_REJECT_INET)	+= nft_reject_inet.o
+obj-$(CONFIG_NFT_REJECT_NETDEV)	+= nft_reject_netdev.o
 obj-$(CONFIG_NFT_TUNNEL)	+= nft_tunnel.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 3ac7c8c1548d..63d032191e62 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -282,6 +282,16 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum,
 			return NULL;
 		return net->nf.hooks_bridge + hooknum;
 #endif
+#ifdef CONFIG_NETFILTER_INGRESS
+	case NFPROTO_INET:
+		if (WARN_ON_ONCE(hooknum != NF_INET_INGRESS))
+			return NULL;
+		if (!dev || dev_net(dev) != net) {
+			WARN_ON_ONCE(1);
+			return NULL;
+		}
+		return &dev->nf_hooks_ingress;
+#endif
 	case NFPROTO_IPV4:
 		if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv4) <= hooknum))
 			return NULL;
@@ -311,20 +321,80 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum,
 	return NULL;
 }
 
+static int nf_ingress_check(struct net *net, const struct nf_hook_ops *reg,
+			    int hooknum)
+{
+#ifndef CONFIG_NETFILTER_INGRESS
+	if (reg->hooknum == hooknum)
+		return -EOPNOTSUPP;
+#endif
+	if (reg->hooknum != hooknum ||
+	    !reg->dev || dev_net(reg->dev) != net)
+		return -EINVAL;
+
+	return 0;
+}
+
+static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf)
+{
+	if ((pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) ||
+	    (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS))
+		return true;
+
+	return false;
+}
+
+static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf)
+{
+#ifdef CONFIG_JUMP_LABEL
+	int hooknum;
+
+	if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) {
+		pf = NFPROTO_NETDEV;
+		hooknum = NF_NETDEV_INGRESS;
+	} else {
+		hooknum = reg->hooknum;
+	}
+	static_key_slow_inc(&nf_hooks_needed[pf][hooknum]);
+#endif
+}
+
+static void nf_static_key_dec(const struct nf_hook_ops *reg, int pf)
+{
+#ifdef CONFIG_JUMP_LABEL
+	int hooknum;
+
+	if (pf == NFPROTO_INET && reg->hooknum == NF_INET_INGRESS) {
+		pf = NFPROTO_NETDEV;
+		hooknum = NF_NETDEV_INGRESS;
+	} else {
+		hooknum = reg->hooknum;
+	}
+	static_key_slow_dec(&nf_hooks_needed[pf][hooknum]);
+#endif
+}
+
 static int __nf_register_net_hook(struct net *net, int pf,
 				  const struct nf_hook_ops *reg)
 {
 	struct nf_hook_entries *p, *new_hooks;
 	struct nf_hook_entries __rcu **pp;
+	int err;
 
-	if (pf == NFPROTO_NETDEV) {
-#ifndef CONFIG_NETFILTER_INGRESS
-		if (reg->hooknum == NF_NETDEV_INGRESS)
-			return -EOPNOTSUPP;
-#endif
-		if (reg->hooknum != NF_NETDEV_INGRESS ||
-		    !reg->dev || dev_net(reg->dev) != net)
-			return -EINVAL;
+	switch (pf) {
+	case NFPROTO_NETDEV:
+		err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS);
+		if (err < 0)
+			return err;
+		break;
+	case NFPROTO_INET:
+		if (reg->hooknum != NF_INET_INGRESS)
+			break;
+
+		err = nf_ingress_check(net, reg, NF_INET_INGRESS);
+		if (err < 0)
+			return err;
+		break;
 	}
 
 	pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev);
@@ -345,12 +415,11 @@ static int __nf_register_net_hook(struct net *net, int pf,
 
 	hooks_validate(new_hooks);
 #ifdef CONFIG_NETFILTER_INGRESS
-	if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS)
+	if (nf_ingress_hook(reg, pf))
 		net_inc_ingress_queue();
 #endif
-#ifdef CONFIG_JUMP_LABEL
-	static_key_slow_inc(&nf_hooks_needed[pf][reg->hooknum]);
-#endif
+	nf_static_key_inc(reg, pf);
+
 	BUG_ON(p == new_hooks);
 	nf_hook_entries_free(p);
 	return 0;
@@ -403,12 +472,10 @@ static void __nf_unregister_net_hook(struct net *net, int pf,
 
 	if (nf_remove_net_hook(p, reg)) {
 #ifdef CONFIG_NETFILTER_INGRESS
-		if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS)
+		if (nf_ingress_hook(reg, pf))
 			net_dec_ingress_queue();
 #endif
-#ifdef CONFIG_JUMP_LABEL
-		static_key_slow_dec(&nf_hooks_needed[pf][reg->hooknum]);
-#endif
+		nf_static_key_dec(reg, pf);
 	} else {
 		WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum);
 	}
@@ -425,8 +492,12 @@ static void __nf_unregister_net_hook(struct net *net, int pf,
 void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg)
 {
 	if (reg->pf == NFPROTO_INET) {
-		__nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
-		__nf_unregister_net_hook(net, NFPROTO_IPV6, reg);
+		if (reg->hooknum == NF_INET_INGRESS) {
+			__nf_unregister_net_hook(net, NFPROTO_INET, reg);
+		} else {
+			__nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
+			__nf_unregister_net_hook(net, NFPROTO_IPV6, reg);
+		}
 	} else {
 		__nf_unregister_net_hook(net, reg->pf, reg);
 	}
@@ -451,14 +522,20 @@ int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg)
 	int err;
 
 	if (reg->pf == NFPROTO_INET) {
-		err = __nf_register_net_hook(net, NFPROTO_IPV4, reg);
-		if (err < 0)
-			return err;
-
-		err = __nf_register_net_hook(net, NFPROTO_IPV6, reg);
-		if (err < 0) {
-			__nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
-			return err;
+		if (reg->hooknum == NF_INET_INGRESS) {
+			err = __nf_register_net_hook(net, NFPROTO_INET, reg);
+			if (err < 0)
+				return err;
+		} else {
+			err = __nf_register_net_hook(net, NFPROTO_IPV4, reg);
+			if (err < 0)
+				return err;
+
+			err = __nf_register_net_hook(net, NFPROTO_IPV6, reg);
+			if (err < 0) {
+				__nf_unregister_net_hook(net, NFPROTO_IPV4, reg);
+				return err;
+			}
 		}
 	} else {
 		err = __nf_register_net_hook(net, reg->pf, reg);
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 920b7c4331f0..89009c82a6b2 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -250,22 +250,7 @@ EXPORT_SYMBOL_GPL(ip_set_type_unregister);
 void *
 ip_set_alloc(size_t size)
 {
-	void *members = NULL;
-
-	if (size < KMALLOC_MAX_SIZE)
-		members = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
-
-	if (members) {
-		pr_debug("%p: allocated with kmalloc\n", members);
-		return members;
-	}
-
-	members = vzalloc(size);
-	if (!members)
-		return NULL;
-	pr_debug("%p: allocated with vmalloc\n", members);
-
-	return members;
+	return kvzalloc(size, GFP_KERNEL_ACCOUNT);
 }
 EXPORT_SYMBOL_GPL(ip_set_alloc);
 
@@ -286,8 +271,7 @@ flag_nested(const struct nlattr *nla)
 
 static const struct nla_policy ipaddr_policy[IPSET_ATTR_IPADDR_MAX + 1] = {
 	[IPSET_ATTR_IPADDR_IPV4]	= { .type = NLA_U32 },
-	[IPSET_ATTR_IPADDR_IPV6]	= { .type = NLA_BINARY,
-					    .len = sizeof(struct in6_addr) },
+	[IPSET_ATTR_IPADDR_IPV6]	= NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
 };
 
 int
@@ -652,13 +636,14 @@ ip_set_match_extensions(struct ip_set *set, const struct ip_set_ext *ext,
 	if (SET_WITH_COUNTER(set)) {
 		struct ip_set_counter *counter = ext_counter(data, set);
 
+		ip_set_update_counter(counter, ext, flags);
+
 		if (flags & IPSET_FLAG_MATCH_COUNTERS &&
 		    !(ip_set_match_counter(ip_set_get_packets(counter),
 				mext->packets, mext->packets_op) &&
 		      ip_set_match_counter(ip_set_get_bytes(counter),
 				mext->bytes, mext->bytes_op)))
 			return false;
-		ip_set_update_counter(counter, ext, flags);
 	}
 	if (SET_WITH_SKBINFO(set))
 		ip_set_get_skbinfo(ext_skbinfo(data, set),
@@ -1124,6 +1109,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
 		ret = -IPSET_ERR_PROTOCOL;
 		goto put_out;
 	}
+	/* Set create flags depending on the type revision */
+	set->flags |= set->type->create_flags[revision];
 
 	ret = set->type->create(net, set, tb, flags);
 	if (ret != 0)
@@ -1254,10 +1241,12 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl,
 		/* Modified by ip_set_destroy() only, which is serialized */
 		inst->is_destroyed = false;
 	} else {
+		u32 flags = flag_exist(nlh);
 		s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
 				    &i);
 		if (!s) {
-			ret = -ENOENT;
+			if (!(flags & IPSET_FLAG_EXIST))
+				ret = -ENOENT;
 			goto out;
 		} else if (s->ref || s->ref_netlink) {
 			ret = -IPSET_ERR_BUSY;
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index 521e970be402..6186358eac7c 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -37,18 +37,18 @@
  */
 
 /* Number of elements to store in an initial array block */
-#define AHASH_INIT_SIZE			4
+#define AHASH_INIT_SIZE			2
 /* Max number of elements to store in an array block */
-#define AHASH_MAX_SIZE			(3 * AHASH_INIT_SIZE)
+#define AHASH_MAX_SIZE			(6 * AHASH_INIT_SIZE)
 /* Max muber of elements in the array block when tuned */
 #define AHASH_MAX_TUNED			64
 
+#define AHASH_MAX(h)			((h)->bucketsize)
+
 /* Max number of elements can be tuned */
 #ifdef IP_SET_HASH_WITH_MULTI
-#define AHASH_MAX(h)			((h)->ahash_max)
-
 static u8
-tune_ahash_max(u8 curr, u32 multi)
+tune_bucketsize(u8 curr, u32 multi)
 {
 	u32 n;
 
@@ -61,12 +61,10 @@ tune_ahash_max(u8 curr, u32 multi)
 	 */
 	return n > curr && n <= AHASH_MAX_TUNED ? n : curr;
 }
-
-#define TUNE_AHASH_MAX(h, multi)	\
-	((h)->ahash_max = tune_ahash_max((h)->ahash_max, multi))
+#define TUNE_BUCKETSIZE(h, multi)	\
+	((h)->bucketsize = tune_bucketsize((h)->bucketsize, multi))
 #else
-#define AHASH_MAX(h)			AHASH_MAX_SIZE
-#define TUNE_AHASH_MAX(h, multi)
+#define TUNE_BUCKETSIZE(h, multi)
 #endif
 
 /* A hash bucket */
@@ -143,20 +141,6 @@ htable_size(u8 hbits)
 	return hsize * sizeof(struct hbucket *) + sizeof(struct htable);
 }
 
-/* Compute htable_bits from the user input parameter hashsize */
-static u8
-htable_bits(u32 hashsize)
-{
-	/* Assume that hashsize == 2^htable_bits */
-	u8 bits = fls(hashsize - 1);
-
-	if (jhash_size(bits) != hashsize)
-		/* Round up to the first 2^n value */
-		bits = fls(hashsize);
-
-	return bits;
-}
-
 #ifdef IP_SET_HASH_WITH_NETS
 #if IPSET_NET_COUNT > 1
 #define __CIDR(cidr, i)		(cidr[i])
@@ -321,9 +305,7 @@ struct htype {
 #ifdef IP_SET_HASH_WITH_MARKMASK
 	u32 markmask;		/* markmask value for mark mask to store */
 #endif
-#ifdef IP_SET_HASH_WITH_MULTI
-	u8 ahash_max;		/* max elements in an array block */
-#endif
+	u8 bucketsize;		/* max elements in an array block */
 #ifdef IP_SET_HASH_WITH_NETMASK
 	u8 netmask;		/* netmask value for subnets to store */
 #endif
@@ -644,7 +626,7 @@ mtype_resize(struct ip_set *set, bool retried)
 	struct htype *h = set->data;
 	struct htable *t, *orig;
 	u8 htable_bits;
-	size_t dsize = set->dsize;
+	size_t hsize, dsize = set->dsize;
 #ifdef IP_SET_HASH_WITH_NETS
 	u8 flags;
 	struct mtype_elem *tmp;
@@ -668,14 +650,12 @@ mtype_resize(struct ip_set *set, bool retried)
 retry:
 	ret = 0;
 	htable_bits++;
-	if (!htable_bits) {
-		/* In case we have plenty of memory :-) */
-		pr_warn("Cannot increase the hashsize of set %s further\n",
-			set->name);
-		ret = -IPSET_ERR_HASH_FULL;
-		goto out;
-	}
-	t = ip_set_alloc(htable_size(htable_bits));
+	if (!htable_bits)
+		goto hbwarn;
+	hsize = htable_size(htable_bits);
+	if (!hsize)
+		goto hbwarn;
+	t = ip_set_alloc(hsize);
 	if (!t) {
 		ret = -ENOMEM;
 		goto out;
@@ -817,6 +797,12 @@ cleanup:
 	if (ret == -EAGAIN)
 		goto retry;
 	goto out;
+
+hbwarn:
+	/* In case we have plenty of memory :-) */
+	pr_warn("Cannot increase the hashsize of set %s further\n", set->name);
+	ret = -IPSET_ERR_HASH_FULL;
+	goto out;
 }
 
 /* Get the current number of elements and ext_size in the set  */
@@ -950,7 +936,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 		goto set_full;
 	/* Create a new slot */
 	if (n->pos >= n->size) {
-		TUNE_AHASH_MAX(h, multi);
+		TUNE_BUCKETSIZE(h, multi);
 		if (n->size >= AHASH_MAX(h)) {
 			/* Trigger rehashing */
 			mtype_data_next(&h->next, d);
@@ -1305,6 +1291,11 @@ mtype_head(struct ip_set *set, struct sk_buff *skb)
 	if (nla_put_u32(skb, IPSET_ATTR_MARKMASK, h->markmask))
 		goto nla_put_failure;
 #endif
+	if (set->flags & IPSET_CREATE_FLAG_BUCKETSIZE) {
+		if (nla_put_u8(skb, IPSET_ATTR_BUCKETSIZE, h->bucketsize) ||
+		    nla_put_net32(skb, IPSET_ATTR_INITVAL, htonl(h->initval)))
+			goto nla_put_failure;
+	}
 	if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) ||
 	    nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) ||
 	    nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements)))
@@ -1520,7 +1511,11 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 	if (!h)
 		return -ENOMEM;
 
-	hbits = htable_bits(hashsize);
+	/* Compute htable_bits from the user input parameter hashsize.
+	 * Assume that hashsize == 2^htable_bits,
+	 * otherwise round up to the first 2^n value.
+	 */
+	hbits = fls(hashsize - 1);
 	hsize = htable_size(hbits);
 	if (hsize == 0) {
 		kfree(h);
@@ -1547,8 +1542,20 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set,
 #ifdef IP_SET_HASH_WITH_MARKMASK
 	h->markmask = markmask;
 #endif
-	get_random_bytes(&h->initval, sizeof(h->initval));
-
+	if (tb[IPSET_ATTR_INITVAL])
+		h->initval = ntohl(nla_get_be32(tb[IPSET_ATTR_INITVAL]));
+	else
+		get_random_bytes(&h->initval, sizeof(h->initval));
+	h->bucketsize = AHASH_MAX_SIZE;
+	if (tb[IPSET_ATTR_BUCKETSIZE]) {
+		h->bucketsize = nla_get_u8(tb[IPSET_ATTR_BUCKETSIZE]);
+		if (h->bucketsize < AHASH_INIT_SIZE)
+			h->bucketsize = AHASH_INIT_SIZE;
+		else if (h->bucketsize > AHASH_MAX_SIZE)
+			h->bucketsize = AHASH_MAX_SIZE;
+		else if (h->bucketsize % 2)
+			h->bucketsize += 1;
+	}
 	t->htable_bits = hbits;
 	t->maxelem = h->maxelem / ahash_numof_locks(hbits);
 	RCU_INIT_POINTER(h->table, t);
diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c
index 5d6d68eaf6a9..d1bef23fd4f5 100644
--- a/net/netfilter/ipset/ip_set_hash_ip.c
+++ b/net/netfilter/ipset/ip_set_hash_ip.c
@@ -23,7 +23,8 @@
 /*				1	   Counters support */
 /*				2	   Comments support */
 /*				3	   Forceadd support */
-#define IPSET_TYPE_REV_MAX	4	/* skbinfo support  */
+/*				4	   skbinfo support */
+#define IPSET_TYPE_REV_MAX	5	/* bucketsize, initval support  */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -277,11 +278,13 @@ static struct ip_set_type hash_ip_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ip_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_NETMASK]	= { .type = NLA_U8  },
diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c
index eceb7bc4a93a..467c59a83c0a 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmac.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmac.c
@@ -23,7 +23,7 @@
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
 #define IPSET_TYPE_REV_MIN	0
-#define IPSET_TYPE_REV_MAX	0
+#define IPSET_TYPE_REV_MAX	1	/* bucketsize, initval support  */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Tomasz Chilinski <tomasz.chilinski@chilan.com>");
@@ -268,11 +268,13 @@ static struct ip_set_type hash_ipmac_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipmac_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipmark.c b/net/netfilter/ipset/ip_set_hash_ipmark.c
index aba1df617d6e..18346d18aa16 100644
--- a/net/netfilter/ipset/ip_set_hash_ipmark.c
+++ b/net/netfilter/ipset/ip_set_hash_ipmark.c
@@ -21,7 +21,8 @@
 
 #define IPSET_TYPE_REV_MIN	0
 /*				1	   Forceadd support */
-#define IPSET_TYPE_REV_MAX	2	/* skbinfo support  */
+/*				2	   skbinfo support */
+#define IPSET_TYPE_REV_MAX	3	/* bucketsize, initval support  */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Vytas Dauksa <vytas.dauksa@smoothwall.net>");
@@ -274,12 +275,14 @@ static struct ip_set_type hash_ipmark_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipmark_create,
 	.create_policy	= {
 		[IPSET_ATTR_MARKMASK]	= { .type = NLA_U32 },
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c
index 1ff228717e29..e1ca11196515 100644
--- a/net/netfilter/ipset/ip_set_hash_ipport.c
+++ b/net/netfilter/ipset/ip_set_hash_ipport.c
@@ -25,7 +25,8 @@
 /*				2    Counters support added */
 /*				3    Comments support added */
 /*				4    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	5 /* skbinfo support added */
+/*				5    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	6 /* bucketsize, initval support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -341,11 +342,13 @@ static struct ip_set_type hash_ipport_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipport_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_PROTO]	= { .type = NLA_U8 },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c
index fa88afd812fa..ab179e064597 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportip.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportip.c
@@ -25,7 +25,8 @@
 /*				2    Counters support added */
 /*				3    Comments support added */
 /*				4    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	5 /* skbinfo support added */
+/*				5    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	6 /* bucketsize, initval support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -356,11 +357,13 @@ static struct ip_set_type hash_ipportip_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipportip_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c
index eef6ecfcb409..8f075b44cf64 100644
--- a/net/netfilter/ipset/ip_set_hash_ipportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c
@@ -27,7 +27,8 @@
 /*				4    Counters support added */
 /*				5    Comments support added */
 /*				6    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	7 /* skbinfo support added */
+/*				7    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	8 /* bucketsize, initval support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -513,11 +514,13 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_ipportnet_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_mac.c b/net/netfilter/ipset/ip_set_hash_mac.c
index 0b61593165ef..718814730acf 100644
--- a/net/netfilter/ipset/ip_set_hash_mac.c
+++ b/net/netfilter/ipset/ip_set_hash_mac.c
@@ -16,7 +16,7 @@
 #include <linux/netfilter/ipset/ip_set_hash.h>
 
 #define IPSET_TYPE_REV_MIN	0
-#define IPSET_TYPE_REV_MAX	0
+#define IPSET_TYPE_REV_MAX	1	/* bucketsize, initval support */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -125,11 +125,13 @@ static struct ip_set_type hash_mac_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_mac_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c
index 136cf0781d3a..c1a11f041ac6 100644
--- a/net/netfilter/ipset/ip_set_hash_net.c
+++ b/net/netfilter/ipset/ip_set_hash_net.c
@@ -24,7 +24,8 @@
 /*				3    Counters support added */
 /*				4    Comments support added */
 /*				5    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	6 /* skbinfo mapping support added */
+/*				6    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	7 /* bucketsize, initval support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -354,11 +355,13 @@ static struct ip_set_type hash_net_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_net_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c
index be5e95a0d876..ddd51c2e1cb3 100644
--- a/net/netfilter/ipset/ip_set_hash_netiface.c
+++ b/net/netfilter/ipset/ip_set_hash_netiface.c
@@ -26,7 +26,8 @@
 /*				4    Comments support added */
 /*				5    Forceadd support added */
 /*				6    skbinfo support added */
-#define IPSET_TYPE_REV_MAX	7 /* interface wildcard support added */
+/*				7    interface wildcard support added */
+#define IPSET_TYPE_REV_MAX	8 /* bucketsize, initval support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -225,7 +226,7 @@ hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[],
 		if (e.cidr > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
-	nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
+	nla_strscpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
 
 	if (tb[IPSET_ATTR_CADT_FLAGS]) {
 		u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
@@ -442,7 +443,7 @@ hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	ip6_netmask(&e.ip, e.cidr);
 
-	nla_strlcpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
+	nla_strscpy(e.iface, tb[IPSET_ATTR_IFACE], IFNAMSIZ);
 
 	if (tb[IPSET_ATTR_CADT_FLAGS]) {
 		u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]);
@@ -470,11 +471,13 @@ static struct ip_set_type hash_netiface_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_netiface_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_PROTO]	= { .type = NLA_U8 },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index da4ef910b12d..6532f0505e66 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -22,7 +22,8 @@
 
 #define IPSET_TYPE_REV_MIN	0
 /*				1	   Forceadd support added */
-#define IPSET_TYPE_REV_MAX	2	/* skbinfo support added */
+/*				2	   skbinfo support added */
+#define IPSET_TYPE_REV_MAX	3	/* bucketsize, initval support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
@@ -459,11 +460,13 @@ static struct ip_set_type hash_netnet_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_netnet_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c
index 34448df80fb9..ec1564a1cb5a 100644
--- a/net/netfilter/ipset/ip_set_hash_netport.c
+++ b/net/netfilter/ipset/ip_set_hash_netport.c
@@ -26,7 +26,8 @@
 /*				4    Counters support added */
 /*				5    Comments support added */
 /*				6    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	7 /* skbinfo support added */
+/*				7    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	8 /* bucketsize, initval support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@netfilter.org>");
@@ -460,11 +461,13 @@ static struct ip_set_type hash_netport_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_netport_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_PROTO]	= { .type = NLA_U8 },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 934c1712cba8..0e91d1e82f1c 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -23,7 +23,8 @@
 #define IPSET_TYPE_REV_MIN	0
 /*				0    Comments support added */
 /*				1    Forceadd support added */
-#define IPSET_TYPE_REV_MAX	2 /* skbinfo support added */
+/*				2    skbinfo support added */
+#define IPSET_TYPE_REV_MAX	3 /* bucketsize, initval support added */
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Oliver Smith <oliver@8.c.9.b.0.7.4.0.1.0.0.2.ip6.arpa>");
@@ -558,11 +559,13 @@ static struct ip_set_type hash_netportnet_type __read_mostly = {
 	.family		= NFPROTO_UNSPEC,
 	.revision_min	= IPSET_TYPE_REV_MIN,
 	.revision_max	= IPSET_TYPE_REV_MAX,
+	.create_flags[IPSET_TYPE_REV_MAX] = IPSET_CREATE_FLAG_BUCKETSIZE,
 	.create		= hash_netportnet_create,
 	.create_policy	= {
 		[IPSET_ATTR_HASHSIZE]	= { .type = NLA_U32 },
 		[IPSET_ATTR_MAXELEM]	= { .type = NLA_U32 },
-		[IPSET_ATTR_PROBES]	= { .type = NLA_U8 },
+		[IPSET_ATTR_INITVAL]	= { .type = NLA_U32 },
+		[IPSET_ATTR_BUCKETSIZE]	= { .type = NLA_U8 },
 		[IPSET_ATTR_RESIZE]	= { .type = NLA_U8  },
 		[IPSET_ATTR_TIMEOUT]	= { .type = NLA_U32 },
 		[IPSET_ATTR_CADT_FLAGS]	= { .type = NLA_U32 },
diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig
index 2c1593089ede..eb0e329f9b8d 100644
--- a/net/netfilter/ipvs/Kconfig
+++ b/net/netfilter/ipvs/Kconfig
@@ -29,7 +29,6 @@ if IP_VS
 config	IP_VS_IPV6
 	bool "IPv6 support for IPVS"
 	depends on IPV6 = y || IP_VS = IPV6
-	select IP6_NF_IPTABLES
 	select NF_DEFRAG_IPV6
 	help
 	  Add IPv6 support to IPVS.
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index a90b8eac16ac..c100c6b112c8 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -402,6 +402,8 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 {
 	unsigned int hash;
 	struct ip_vs_conn *cp, *ret=NULL;
+	const union nf_inet_addr *saddr;
+	__be16 sport;
 
 	/*
 	 *	Check for "full" addressed entries
@@ -411,10 +413,20 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p)
 	rcu_read_lock();
 
 	hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
-		if (p->vport == cp->cport && p->cport == cp->dport &&
-		    cp->af == p->af &&
+		if (p->vport != cp->cport)
+			continue;
+
+		if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) {
+			sport = cp->vport;
+			saddr = &cp->vaddr;
+		} else {
+			sport = cp->dport;
+			saddr = &cp->daddr;
+		}
+
+		if (p->cport == sport && cp->af == p->af &&
 		    ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) &&
-		    ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) &&
+		    ip_vs_addr_equal(p->af, p->caddr, saddr) &&
 		    p->protocol == cp->protocol &&
 		    cp->ipvs == p->ipvs) {
 			if (!__ip_vs_conn_get(cp))
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index e3668a6e54e4..54e086c65721 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -742,12 +742,12 @@ static int ip_vs_route_me_harder(struct netns_ipvs *ipvs, int af,
 		struct dst_entry *dst = skb_dst(skb);
 
 		if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
-		    ip6_route_me_harder(ipvs->net, skb) != 0)
+		    ip6_route_me_harder(ipvs->net, skb->sk, skb) != 0)
 			return 1;
 	} else
 #endif
 		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
-		    ip_route_me_harder(ipvs->net, skb, RTN_LOCAL) != 0)
+		    ip_route_me_harder(ipvs->net, skb->sk, skb, RTN_LOCAL) != 0)
 			return 1;
 
 	return 0;
@@ -875,7 +875,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 	unsigned int verdict = NF_DROP;
 
 	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
-		goto ignore_cp;
+		goto after_nat;
 
 	/* Ensure the checksum is correct */
 	if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) {
@@ -901,6 +901,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 	if (ip_vs_route_me_harder(cp->ipvs, af, skb, hooknum))
 		goto out;
 
+after_nat:
 	/* do the statistics and put it back */
 	ip_vs_out_stats(cp, skb);
 
@@ -909,8 +910,6 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 		ip_vs_notrack(skb);
 	else
 		ip_vs_update_conntrack(skb, cp, 0);
-
-ignore_cp:
 	verdict = NF_ACCEPT;
 
 out:
@@ -1276,6 +1275,9 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 {
 	struct ip_vs_protocol *pp = pd->pp;
 
+	if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
+		goto after_nat;
+
 	IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet");
 
 	if (skb_ensure_writable(skb, iph->len))
@@ -1316,6 +1318,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
 
 	IP_VS_DBG_PKT(10, af, pp, skb, iph->off, "After SNAT");
 
+after_nat:
 	ip_vs_out_stats(cp, skb);
 	ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd);
 	skb->ipvs_property = 1;
@@ -1412,11 +1415,8 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
 	cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto,
 			     ipvs, af, skb, &iph);
 
-	if (likely(cp)) {
-		if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ)
-			goto ignore_cp;
+	if (likely(cp))
 		return handle_response(af, skb, pd, cp, &iph, hooknum);
-	}
 
 	/* Check for real-server-started requests */
 	if (atomic_read(&ipvs->conn_out_counter)) {
@@ -1475,14 +1475,9 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in
 		}
 	}
 
-out:
 	IP_VS_DBG_PKT(12, af, pp, skb, iph.off,
 		      "ip_vs_out: packet continues traversal as normal");
 	return NF_ACCEPT;
-
-ignore_cp:
-	__ip_vs_conn_put(cp);
-	goto out;
 }
 
 /*
@@ -2142,7 +2137,7 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int
 	if (cp->flags & IP_VS_CONN_F_ONE_PACKET)
 		pkts = sysctl_sync_threshold(ipvs);
 	else
-		pkts = atomic_add_return(1, &cp->in_pkts);
+		pkts = atomic_inc_return(&cp->in_pkts);
 
 	if (ipvs->sync_state & IP_VS_STATE_MASTER)
 		ip_vs_sync_conn(ipvs, cp, pkts);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 678c5b14841c..d45dbcba8b49 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2508,6 +2508,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len)
 		/* Set timeout values for (tcp tcpfin udp) */
 		ret = ip_vs_set_timeout(ipvs, (struct ip_vs_timeout_user *)arg);
 		goto out_unlock;
+	} else if (!len) {
+		/* No more commands with len == 0 below */
+		ret = -EINVAL;
+		goto out_unlock;
 	}
 
 	usvc_compat = (struct ip_vs_service_user *)arg;
@@ -2584,9 +2588,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, sockptr_t ptr, unsigned int len)
 		break;
 	case IP_VS_SO_SET_DELDEST:
 		ret = ip_vs_del_dest(svc, &udest);
-		break;
-	default:
-		ret = -EINVAL;
 	}
 
   out_unlock:
@@ -3892,7 +3893,7 @@ out:
 }
 
 
-static const struct genl_ops ip_vs_genl_ops[] = {
+static const struct genl_small_ops ip_vs_genl_ops[] = {
 	{
 		.cmd	= IPVS_CMD_NEW_SERVICE,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -4000,8 +4001,8 @@ static struct genl_family ip_vs_genl_family __ro_after_init = {
 	.policy = ip_vs_cmd_policy,
 	.netnsok        = true,         /* Make ipvsadm to work on netns */
 	.module		= THIS_MODULE,
-	.ops		= ip_vs_genl_ops,
-	.n_ops		= ARRAY_SIZE(ip_vs_genl_ops),
+	.small_ops	= ip_vs_genl_ops,
+	.n_small_ops	= ARRAY_SIZE(ip_vs_genl_ops),
 };
 
 static int __init ip_vs_genl_register(void)
@@ -4166,12 +4167,18 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
 
 	spin_lock_init(&ipvs->tot_stats.lock);
 
-	proc_create_net("ip_vs", 0, ipvs->net->proc_net, &ip_vs_info_seq_ops,
-			sizeof(struct ip_vs_iter));
-	proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net,
-			ip_vs_stats_show, NULL);
-	proc_create_net_single("ip_vs_stats_percpu", 0, ipvs->net->proc_net,
-			ip_vs_stats_percpu_show, NULL);
+#ifdef CONFIG_PROC_FS
+	if (!proc_create_net("ip_vs", 0, ipvs->net->proc_net,
+			     &ip_vs_info_seq_ops, sizeof(struct ip_vs_iter)))
+		goto err_vs;
+	if (!proc_create_net_single("ip_vs_stats", 0, ipvs->net->proc_net,
+				    ip_vs_stats_show, NULL))
+		goto err_stats;
+	if (!proc_create_net_single("ip_vs_stats_percpu", 0,
+				    ipvs->net->proc_net,
+				    ip_vs_stats_percpu_show, NULL))
+		goto err_percpu;
+#endif
 
 	if (ip_vs_control_net_init_sysctl(ipvs))
 		goto err;
@@ -4179,6 +4186,17 @@ int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
 	return 0;
 
 err:
+#ifdef CONFIG_PROC_FS
+	remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net);
+
+err_percpu:
+	remove_proc_entry("ip_vs_stats", ipvs->net->proc_net);
+
+err_stats:
+	remove_proc_entry("ip_vs", ipvs->net->proc_net);
+
+err_vs:
+#endif
 	free_percpu(ipvs->tot_stats.cpustats);
 	return -ENOMEM;
 }
@@ -4187,9 +4205,11 @@ void __net_exit ip_vs_control_net_cleanup(struct netns_ipvs *ipvs)
 {
 	ip_vs_trash_cleanup(ipvs);
 	ip_vs_control_net_cleanup_sysctl(ipvs);
+#ifdef CONFIG_PROC_FS
 	remove_proc_entry("ip_vs_stats_percpu", ipvs->net->proc_net);
 	remove_proc_entry("ip_vs_stats", ipvs->net->proc_net);
 	remove_proc_entry("ip_vs", ipvs->net->proc_net);
+#endif
 	free_percpu(ipvs->tot_stats.cpustats);
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index dc2e7da2742a..7da51390cea6 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -539,8 +539,8 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 	if (new_state != cp->state) {
 		struct ip_vs_dest *dest = cp->dest;
 
-		IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] %s:%d->"
-			      "%s:%d state: %s->%s conn->refcnt:%d\n",
+		IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] c:%s:%d v:%s:%d "
+			      "d:%s:%d state: %s->%s conn->refcnt:%d\n",
 			      pd->pp->name,
 			      ((state_off == TCP_DIR_OUTPUT) ?
 			       "output " : "input "),
@@ -548,10 +548,12 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 			      th->fin ? 'F' : '.',
 			      th->ack ? 'A' : '.',
 			      th->rst ? 'R' : '.',
-			      IP_VS_DBG_ADDR(cp->daf, &cp->daddr),
-			      ntohs(cp->dport),
 			      IP_VS_DBG_ADDR(cp->af, &cp->caddr),
 			      ntohs(cp->cport),
+			      IP_VS_DBG_ADDR(cp->af, &cp->vaddr),
+			      ntohs(cp->vport),
+			      IP_VS_DBG_ADDR(cp->daf, &cp->daddr),
+			      ntohs(cp->dport),
 			      tcp_state_name(cp->state),
 			      tcp_state_name(new_state),
 			      refcount_read(&cp->refcnt));
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 2b8abbfe018c..9d43277b8b4f 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -242,9 +242,6 @@ struct ip_vs_sync_thread_data {
       |                    IPVS Sync Connection (1)                   |
 */
 
-#define SYNC_MESG_HEADER_LEN	4
-#define MAX_CONNS_PER_SYNCBUFF	255 /* nr_conns in ip_vs_sync_mesg is 8 bit */
-
 /* Version 0 header */
 struct ip_vs_sync_mesg_v0 {
 	__u8                    nr_conns;
@@ -618,7 +615,7 @@ static void ip_vs_sync_conn_v0(struct netns_ipvs *ipvs, struct ip_vs_conn *cp,
 	cp = cp->control;
 	if (cp) {
 		if (cp->flags & IP_VS_CONN_F_TEMPLATE)
-			pkts = atomic_add_return(1, &cp->in_pkts);
+			pkts = atomic_inc_return(&cp->in_pkts);
 		else
 			pkts = sysctl_sync_threshold(ipvs);
 		ip_vs_sync_conn(ipvs, cp, pkts);
@@ -779,7 +776,7 @@ control:
 	if (!cp)
 		return;
 	if (cp->flags & IP_VS_CONN_F_TEMPLATE)
-		pkts = atomic_add_return(1, &cp->in_pkts);
+		pkts = atomic_inc_return(&cp->in_pkts);
 	else
 		pkts = sysctl_sync_threshold(ipvs);
 	goto sloop;
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index b00866d777fe..d2e5a8f644b8 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -609,6 +609,8 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb,
 	if (ret == NF_ACCEPT) {
 		nf_reset_ct(skb);
 		skb_forward_csum(skb);
+		if (skb->dev)
+			skb->tstamp = 0;
 	}
 	return ret;
 }
@@ -649,6 +651,8 @@ static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
 
 	if (!local) {
 		skb_forward_csum(skb);
+		if (skb->dev)
+			skb->tstamp = 0;
 		NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
 			NULL, skb_dst(skb)->dev, dst_output);
 	} else
@@ -669,6 +673,8 @@ static inline int ip_vs_send_or_cont(int pf, struct sk_buff *skb,
 	if (!local) {
 		ip_vs_drop_early_demux_sk(skb);
 		skb_forward_csum(skb);
+		if (skb->dev)
+			skb->tstamp = 0;
 		NF_HOOK(pf, NF_INET_LOCAL_OUT, cp->ipvs->net, NULL, skb,
 			NULL, skb_dst(skb)->dev, dst_output);
 	} else
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5b97d233f89b..ff0168736f6e 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -859,7 +859,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 
 out:
 	nf_conntrack_double_unlock(hash, reply_hash);
-	NF_CT_STAT_INC(net, insert_failed);
 	local_bh_enable();
 	return -EEXIST;
 }
@@ -909,6 +908,7 @@ static void __nf_conntrack_insert_prepare(struct nf_conn *ct)
 		tstamp->start = ktime_get_real_ns();
 }
 
+/* caller must hold locks to prevent concurrent changes */
 static int __nf_ct_resolve_clash(struct sk_buff *skb,
 				 struct nf_conntrack_tuple_hash *h)
 {
@@ -922,23 +922,21 @@ static int __nf_ct_resolve_clash(struct sk_buff *skb,
 	if (nf_ct_is_dying(ct))
 		return NF_DROP;
 
-	if (!atomic_inc_not_zero(&ct->ct_general.use))
-		return NF_DROP;
-
 	if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
 	    nf_ct_match(ct, loser_ct)) {
 		struct net *net = nf_ct_net(ct);
 
+		nf_conntrack_get(&ct->ct_general);
+
 		nf_ct_acct_merge(ct, ctinfo, loser_ct);
 		nf_ct_add_to_dying_list(loser_ct);
 		nf_conntrack_put(&loser_ct->ct_general);
 		nf_ct_set(skb, ct, ctinfo);
 
-		NF_CT_STAT_INC(net, insert_failed);
+		NF_CT_STAT_INC(net, clash_resolve);
 		return NF_ACCEPT;
 	}
 
-	nf_ct_put(ct);
 	return NF_DROP;
 }
 
@@ -998,6 +996,8 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
 
 	hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode,
 				 &nf_conntrack_hash[repl_idx]);
+
+	NF_CT_STAT_INC(net, clash_resolve);
 	return NF_ACCEPT;
 }
 
@@ -1027,10 +1027,10 @@ static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx)
  *
  * Failing that, the new, unconfirmed conntrack is still added to the table
  * provided that the collision only occurs in the ORIGINAL direction.
- * The new entry will be added after the existing one in the hash list,
+ * The new entry will be added only in the non-clashing REPLY direction,
  * so packets in the ORIGINAL direction will continue to match the existing
  * entry.  The new entry will also have a fixed timeout so it expires --
- * due to the collision, it will not see bidirectional traffic.
+ * due to the collision, it will only see reply traffic.
  *
  * Returns NF_DROP if the clash could not be resolved.
  */
@@ -1229,7 +1229,8 @@ nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
 			 * Let nf_ct_resolve_clash() deal with this later.
 			 */
 			if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
-					      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple))
+					      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple) &&
+					      nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL))
 				continue;
 
 			NF_CT_STAT_INC_ATOMIC(net, found);
@@ -1725,10 +1726,8 @@ nf_conntrack_handle_icmp(struct nf_conn *tmpl,
 	else
 		return NF_ACCEPT;
 
-	if (ret <= 0) {
+	if (ret <= 0)
 		NF_CT_STAT_INC_ATOMIC(state->net, error);
-		NF_CT_STAT_INC_ATOMIC(state->net, invalid);
-	}
 
 	return ret;
 }
@@ -1802,10 +1801,8 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state)
 	if (tmpl || ctinfo == IP_CT_UNTRACKED) {
 		/* Previously seen (loopback or untracked)?  Ignore. */
 		if ((tmpl && !nf_ct_is_template(tmpl)) ||
-		     ctinfo == IP_CT_UNTRACKED) {
-			NF_CT_STAT_INC_ATOMIC(state->net, ignore);
+		     ctinfo == IP_CT_UNTRACKED)
 			return NF_ACCEPT;
-		}
 		skb->_nfct = 0;
 	}
 
@@ -1813,7 +1810,6 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state)
 	dataoff = get_l4proto(skb, skb_network_offset(skb), state->pf, &protonum);
 	if (dataoff <= 0) {
 		pr_debug("not prepared to track yet or error occurred\n");
-		NF_CT_STAT_INC_ATOMIC(state->net, error);
 		NF_CT_STAT_INC_ATOMIC(state->net, invalid);
 		ret = NF_ACCEPT;
 		goto out;
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index c3a4214dc958..84caf3316946 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -167,10 +167,14 @@ nla_put_failure:
 	return -1;
 }
 
-static int ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct)
+static int ctnetlink_dump_timeout(struct sk_buff *skb, const struct nf_conn *ct,
+				  bool skip_zero)
 {
 	long timeout = nf_ct_expires(ct) / HZ;
 
+	if (skip_zero && timeout == 0)
+		return 0;
+
 	if (nla_put_be32(skb, CTA_TIMEOUT, htonl(timeout)))
 		goto nla_put_failure;
 	return 0;
@@ -179,7 +183,8 @@ nla_put_failure:
 	return -1;
 }
 
-static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct)
+static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct,
+				    bool destroy)
 {
 	const struct nf_conntrack_l4proto *l4proto;
 	struct nlattr *nest_proto;
@@ -193,7 +198,7 @@ static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct)
 	if (!nest_proto)
 		goto nla_put_failure;
 
-	ret = l4proto->to_nlattr(skb, nest_proto, ct);
+	ret = l4proto->to_nlattr(skb, nest_proto, ct, destroy);
 
 	nla_nest_end(skb, nest_proto);
 
@@ -537,8 +542,8 @@ static int ctnetlink_dump_info(struct sk_buff *skb, struct nf_conn *ct)
 		return -1;
 
 	if (!test_bit(IPS_OFFLOAD_BIT, &ct->status) &&
-	    (ctnetlink_dump_timeout(skb, ct) < 0 ||
-	     ctnetlink_dump_protoinfo(skb, ct) < 0))
+	    (ctnetlink_dump_timeout(skb, ct, false) < 0 ||
+	     ctnetlink_dump_protoinfo(skb, ct, false) < 0))
 		return -1;
 
 	return 0;
@@ -780,15 +785,19 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 		goto nla_put_failure;
 
 	if (events & (1 << IPCT_DESTROY)) {
+		if (ctnetlink_dump_timeout(skb, ct, true) < 0)
+			goto nla_put_failure;
+
 		if (ctnetlink_dump_acct(skb, ct, type) < 0 ||
-		    ctnetlink_dump_timestamp(skb, ct) < 0)
+		    ctnetlink_dump_timestamp(skb, ct) < 0 ||
+		    ctnetlink_dump_protoinfo(skb, ct, true) < 0)
 			goto nla_put_failure;
 	} else {
-		if (ctnetlink_dump_timeout(skb, ct) < 0)
+		if (ctnetlink_dump_timeout(skb, ct, false) < 0)
 			goto nla_put_failure;
 
-		if (events & (1 << IPCT_PROTOINFO)
-		    && ctnetlink_dump_protoinfo(skb, ct) < 0)
+		if (events & (1 << IPCT_PROTOINFO) &&
+		    ctnetlink_dump_protoinfo(skb, ct, false) < 0)
 			goto nla_put_failure;
 
 		if ((events & (1 << IPCT_HELPER) || nfct_help(ct))
@@ -2497,7 +2506,6 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 
 	if (nla_put_be32(skb, CTA_STATS_FOUND, htonl(st->found)) ||
 	    nla_put_be32(skb, CTA_STATS_INVALID, htonl(st->invalid)) ||
-	    nla_put_be32(skb, CTA_STATS_IGNORE, htonl(st->ignore)) ||
 	    nla_put_be32(skb, CTA_STATS_INSERT, htonl(st->insert)) ||
 	    nla_put_be32(skb, CTA_STATS_INSERT_FAILED,
 				htonl(st->insert_failed)) ||
@@ -2505,7 +2513,9 @@ ctnetlink_ct_stat_cpu_fill_info(struct sk_buff *skb, u32 portid, u32 seq,
 	    nla_put_be32(skb, CTA_STATS_EARLY_DROP, htonl(st->early_drop)) ||
 	    nla_put_be32(skb, CTA_STATS_ERROR, htonl(st->error)) ||
 	    nla_put_be32(skb, CTA_STATS_SEARCH_RESTART,
-				htonl(st->search_restart)))
+				htonl(st->search_restart)) ||
+	    nla_put_be32(skb, CTA_STATS_CLASH_RESOLVE,
+				htonl(st->clash_resolve)))
 		goto nla_put_failure;
 
 	nlmsg_end(skb, nlh);
@@ -2719,10 +2729,10 @@ static int __ctnetlink_glue_build(struct sk_buff *skb, struct nf_conn *ct)
 	if (ctnetlink_dump_status(skb, ct) < 0)
 		goto nla_put_failure;
 
-	if (ctnetlink_dump_timeout(skb, ct) < 0)
+	if (ctnetlink_dump_timeout(skb, ct, false) < 0)
 		goto nla_put_failure;
 
-	if (ctnetlink_dump_protoinfo(skb, ct) < 0)
+	if (ctnetlink_dump_protoinfo(skb, ct, false) < 0)
 		goto nla_put_failure;
 
 	if (ctnetlink_dump_helpinfo(skb, ct) < 0)
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index b3f4a334f9d7..db7479db8512 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -589,7 +589,7 @@ static void dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
 static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
-			  struct nf_conn *ct)
+			  struct nf_conn *ct, bool destroy)
 {
 	struct nlattr *nest_parms;
 
@@ -597,15 +597,22 @@ static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP);
 	if (!nest_parms)
 		goto nla_put_failure;
-	if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state) ||
-	    nla_put_u8(skb, CTA_PROTOINFO_DCCP_ROLE,
+	if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state))
+		goto nla_put_failure;
+
+	if (destroy)
+		goto skip_state;
+
+	if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_ROLE,
 		       ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]) ||
 	    nla_put_be64(skb, CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ,
 			 cpu_to_be64(ct->proto.dccp.handshake_seq),
 			 CTA_PROTOINFO_DCCP_PAD))
 		goto nla_put_failure;
+skip_state:
 	nla_nest_end(skb, nest_parms);
 	spin_unlock_bh(&ct->lock);
+
 	return 0;
 
 nla_put_failure:
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 810cca24b399..fb8dc02e502f 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -543,7 +543,7 @@ static bool sctp_can_early_drop(const struct nf_conn *ct)
 #include <linux/netfilter/nfnetlink_conntrack.h>
 
 static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
-			  struct nf_conn *ct)
+			  struct nf_conn *ct, bool destroy)
 {
 	struct nlattr *nest_parms;
 
@@ -552,15 +552,20 @@ static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 	if (!nest_parms)
 		goto nla_put_failure;
 
-	if (nla_put_u8(skb, CTA_PROTOINFO_SCTP_STATE, ct->proto.sctp.state) ||
-	    nla_put_be32(skb, CTA_PROTOINFO_SCTP_VTAG_ORIGINAL,
+	if (nla_put_u8(skb, CTA_PROTOINFO_SCTP_STATE, ct->proto.sctp.state))
+		goto nla_put_failure;
+
+	if (destroy)
+		goto skip_state;
+
+	if (nla_put_be32(skb, CTA_PROTOINFO_SCTP_VTAG_ORIGINAL,
 			 ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL]) ||
 	    nla_put_be32(skb, CTA_PROTOINFO_SCTP_VTAG_REPLY,
 			 ct->proto.sctp.vtag[IP_CT_DIR_REPLY]))
 		goto nla_put_failure;
 
+skip_state:
 	spin_unlock_bh(&ct->lock);
-
 	nla_nest_end(skb, nest_parms);
 
 	return 0;
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index e8c86ee4c1c4..1d7e1c595546 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -541,13 +541,20 @@ static bool tcp_in_window(const struct nf_conn *ct,
 			swin = win << sender->td_scale;
 			sender->td_maxwin = (swin == 0 ? 1 : swin);
 			sender->td_maxend = end + sender->td_maxwin;
-			/*
-			 * We haven't seen traffic in the other direction yet
-			 * but we have to tweak window tracking to pass III
-			 * and IV until that happens.
-			 */
-			if (receiver->td_maxwin == 0)
+			if (receiver->td_maxwin == 0) {
+				/* We haven't seen traffic in the other
+				 * direction yet but we have to tweak window
+				 * tracking to pass III and IV until that
+				 * happens.
+				 */
 				receiver->td_end = receiver->td_maxend = sack;
+			} else if (sack == receiver->td_end + 1) {
+				/* Likely a reply to a keepalive.
+				 * Needed for III.
+				 */
+				receiver->td_end++;
+			}
+
 		}
 	} else if (((state->state == TCP_CONNTRACK_SYN_SENT
 		     && dir == IP_CT_DIR_ORIGINAL)
@@ -827,12 +834,6 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	return true;
 }
 
-static bool nf_conntrack_tcp_established(const struct nf_conn *ct)
-{
-	return ct->proto.tcp.state == TCP_CONNTRACK_ESTABLISHED &&
-	       test_bit(IPS_ASSURED_BIT, &ct->status);
-}
-
 /* Returns verdict for packet, or -1 for invalid. */
 int nf_conntrack_tcp_packet(struct nf_conn *ct,
 			    struct sk_buff *skb,
@@ -1185,7 +1186,7 @@ static bool tcp_can_early_drop(const struct nf_conn *ct)
 #include <linux/netfilter/nfnetlink_conntrack.h>
 
 static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
-			 struct nf_conn *ct)
+			 struct nf_conn *ct, bool destroy)
 {
 	struct nlattr *nest_parms;
 	struct nf_ct_tcp_flags tmp = {};
@@ -1195,8 +1196,13 @@ static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 	if (!nest_parms)
 		goto nla_put_failure;
 
-	if (nla_put_u8(skb, CTA_PROTOINFO_TCP_STATE, ct->proto.tcp.state) ||
-	    nla_put_u8(skb, CTA_PROTOINFO_TCP_WSCALE_ORIGINAL,
+	if (nla_put_u8(skb, CTA_PROTOINFO_TCP_STATE, ct->proto.tcp.state))
+		goto nla_put_failure;
+
+	if (destroy)
+		goto skip_state;
+
+	if (nla_put_u8(skb, CTA_PROTOINFO_TCP_WSCALE_ORIGINAL,
 		       ct->proto.tcp.seen[0].td_scale) ||
 	    nla_put_u8(skb, CTA_PROTOINFO_TCP_WSCALE_REPLY,
 		       ct->proto.tcp.seen[1].td_scale))
@@ -1211,8 +1217,8 @@ static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 	if (nla_put(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY,
 		    sizeof(struct nf_ct_tcp_flags), &tmp))
 		goto nla_put_failure;
+skip_state:
 	spin_unlock_bh(&ct->lock);
-
 	nla_nest_end(skb, nest_parms);
 
 	return 0;
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index a604f43e3e6b..0ee702d374b0 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -428,18 +428,18 @@ static int ct_cpu_seq_show(struct seq_file *seq, void *v)
 	const struct ip_conntrack_stat *st = v;
 
 	if (v == SEQ_START_TOKEN) {
-		seq_puts(seq, "entries  searched found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error  expect_new expect_create expect_delete search_restart\n");
+		seq_puts(seq, "entries  clashres found new invalid ignore delete delete_list insert insert_failed drop early_drop icmp_error  expect_new expect_create expect_delete search_restart\n");
 		return 0;
 	}
 
 	seq_printf(seq, "%08x  %08x %08x %08x %08x %08x %08x %08x "
 			"%08x %08x %08x %08x %08x  %08x %08x %08x %08x\n",
 		   nr_conntracks,
-		   0,
+		   st->clash_resolve,
 		   st->found,
 		   0,
 		   st->invalid,
-		   st->ignore,
+		   0,
 		   0,
 		   0,
 		   st->insert,
@@ -523,6 +523,9 @@ nf_conntrack_hash_sysctl(struct ctl_table *table, int write,
 {
 	int ret;
 
+	/* module_param hashsize could have changed value */
+	nf_conntrack_htable_size_user = nf_conntrack_htable_size;
+
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 	if (ret < 0 || !write)
 		return ret;
diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c
index 2b01a151eaa8..a579e59ee5c5 100644
--- a/net/netfilter/nf_dup_netdev.c
+++ b/net/netfilter/nf_dup_netdev.c
@@ -19,6 +19,7 @@ static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev)
 		skb_push(skb, skb->mac_len);
 
 	skb->dev = dev;
+	skb->tstamp = 0;
 	dev_queue_xmit(skb);
 }
 
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 4f7a567c536e..4a4acbba78ff 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -395,12 +395,11 @@ static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
 {
 	struct tcphdr *tcph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+	if (skb_try_make_writable(skb, thoff + sizeof(*tcph)))
 		return -1;
 
 	tcph = (void *)(skb_network_header(skb) + thoff);
-	inet_proto_csum_replace2(&tcph->check, skb, port, new_port, true);
+	inet_proto_csum_replace2(&tcph->check, skb, port, new_port, false);
 
 	return 0;
 }
@@ -410,14 +409,13 @@ static int nf_flow_nat_port_udp(struct sk_buff *skb, unsigned int thoff,
 {
 	struct udphdr *udph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
+	if (skb_try_make_writable(skb, thoff + sizeof(*udph)))
 		return -1;
 
 	udph = (void *)(skb_network_header(skb) + thoff);
 	if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) {
 		inet_proto_csum_replace2(&udph->check, skb, port,
-					 new_port, true);
+					 new_port, false);
 		if (!udph->check)
 			udph->check = CSUM_MANGLED_0;
 	}
@@ -449,8 +447,7 @@ int nf_flow_snat_port(const struct flow_offload *flow,
 	struct flow_ports *hdr;
 	__be16 port, new_port;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*hdr)))
+	if (skb_try_make_writable(skb, thoff + sizeof(*hdr)))
 		return -1;
 
 	hdr = (void *)(skb_network_header(skb) + thoff);
@@ -481,8 +478,7 @@ int nf_flow_dnat_port(const struct flow_offload *flow,
 	struct flow_ports *hdr;
 	__be16 port, new_port;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*hdr)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*hdr)))
+	if (skb_try_make_writable(skb, thoff + sizeof(*hdr)))
 		return -1;
 
 	hdr = (void *)(skb_network_header(skb) + thoff);
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index a3bca758b849..a698dbe28ef5 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -25,9 +25,6 @@ static int nf_flow_state_check(struct flow_offload *flow, int proto,
 	if (proto != IPPROTO_TCP)
 		return 0;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)))
-		return -1;
-
 	tcph = (void *)(skb_network_header(skb) + thoff);
 	if (unlikely(tcph->fin || tcph->rst)) {
 		flow_offload_teardown(flow);
@@ -42,8 +39,7 @@ static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff,
 {
 	struct tcphdr *tcph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+	if (skb_try_make_writable(skb, thoff + sizeof(*tcph)))
 		return -1;
 
 	tcph = (void *)(skb_network_header(skb) + thoff);
@@ -57,8 +53,7 @@ static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff,
 {
 	struct udphdr *udph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
+	if (skb_try_make_writable(skb, thoff + sizeof(*udph)))
 		return -1;
 
 	udph = (void *)(skb_network_header(skb) + thoff);
@@ -167,8 +162,8 @@ static bool ip_has_options(unsigned int thoff)
 static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
 			    struct flow_offload_tuple *tuple)
 {
+	unsigned int thoff, hdrsize;
 	struct flow_ports *ports;
-	unsigned int thoff;
 	struct iphdr *iph;
 
 	if (!pskb_may_pull(skb, sizeof(*iph)))
@@ -181,15 +176,22 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev,
 	    unlikely(ip_has_options(thoff)))
 		return -1;
 
-	if (iph->protocol != IPPROTO_TCP &&
-	    iph->protocol != IPPROTO_UDP)
+	switch (iph->protocol) {
+	case IPPROTO_TCP:
+		hdrsize = sizeof(struct tcphdr);
+		break;
+	case IPPROTO_UDP:
+		hdrsize = sizeof(struct udphdr);
+		break;
+	default:
 		return -1;
+	}
 
 	if (iph->ttl <= 1)
 		return -1;
 
 	thoff = iph->ihl * 4;
-	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+	if (!pskb_may_pull(skb, thoff + hdrsize))
 		return -1;
 
 	iph = ip_hdr(skb);
@@ -315,8 +317,7 @@ static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff,
 {
 	struct tcphdr *tcph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*tcph)))
+	if (skb_try_make_writable(skb, thoff + sizeof(*tcph)))
 		return -1;
 
 	tcph = (void *)(skb_network_header(skb) + thoff);
@@ -332,8 +333,7 @@ static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff,
 {
 	struct udphdr *udph;
 
-	if (!pskb_may_pull(skb, thoff + sizeof(*udph)) ||
-	    skb_try_make_writable(skb, thoff + sizeof(*udph)))
+	if (skb_try_make_writable(skb, thoff + sizeof(*udph)))
 		return -1;
 
 	udph = (void *)(skb_network_header(skb) + thoff);
@@ -439,24 +439,31 @@ static int nf_flow_nat_ipv6(const struct flow_offload *flow,
 static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev,
 			      struct flow_offload_tuple *tuple)
 {
+	unsigned int thoff, hdrsize;
 	struct flow_ports *ports;
 	struct ipv6hdr *ip6h;
-	unsigned int thoff;
 
 	if (!pskb_may_pull(skb, sizeof(*ip6h)))
 		return -1;
 
 	ip6h = ipv6_hdr(skb);
 
-	if (ip6h->nexthdr != IPPROTO_TCP &&
-	    ip6h->nexthdr != IPPROTO_UDP)
+	switch (ip6h->nexthdr) {
+	case IPPROTO_TCP:
+		hdrsize = sizeof(struct tcphdr);
+		break;
+	case IPPROTO_UDP:
+		hdrsize = sizeof(struct udphdr);
+		break;
+	default:
 		return -1;
+	}
 
 	if (ip6h->hop_limit <= 1)
 		return -1;
 
 	thoff = sizeof(*ip6h);
-	if (!pskb_may_pull(skb, thoff + sizeof(*ports)))
+	if (!pskb_may_pull(skb, thoff + hdrsize))
 		return -1;
 
 	ip6h = ipv6_hdr(skb);
diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c
index ae5628ddbe6d..fd7c5f0f5c25 100644
--- a/net/netfilter/nf_log_common.c
+++ b/net/netfilter/nf_log_common.c
@@ -171,6 +171,18 @@ nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
 }
 EXPORT_SYMBOL_GPL(nf_log_dump_packet_common);
 
+void nf_log_dump_vlan(struct nf_log_buf *m, const struct sk_buff *skb)
+{
+	u16 vid;
+
+	if (!skb_vlan_tag_present(skb))
+		return;
+
+	vid = skb_vlan_tag_get(skb);
+	nf_log_buf_add(m, "VPROTO=%04x VID=%u ", ntohs(skb->vlan_proto), vid);
+}
+EXPORT_SYMBOL_GPL(nf_log_dump_vlan);
+
 /* bridge and netdev logging families share this code. */
 void nf_log_l2packet(struct net *net, u_int8_t pf,
 		     __be16 protocol,
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index ea923f8cf9c4..b7c3c902290f 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1174,6 +1174,7 @@ static int __init nf_nat_init(void)
 	ret = register_pernet_subsys(&nat_net_ops);
 	if (ret < 0) {
 		nf_ct_extend_unregister(&nat_extend);
+		kvfree(nf_nat_bysource);
 		return ret;
 	}
 
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index 59151dc07fdc..e87b6bd6b3cd 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -715,7 +715,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
 
 		if (ct->tuplehash[dir].tuple.dst.u3.ip !=
 		    ct->tuplehash[!dir].tuple.src.u3.ip) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
@@ -953,7 +953,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb,
 
 		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
 				      &ct->tuplehash[!dir].tuple.src.u3)) {
-			err = nf_ip6_route_me_harder(state->net, skb);
+			err = nf_ip6_route_me_harder(state->net, state->sk, skb);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 9cca35d22927..b100c04a0e43 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -446,7 +446,7 @@ synproxy_send_tcp(struct net *net,
 
 	skb_dst_set_noref(nskb, skb_dst(skb));
 	nskb->protocol = htons(ETH_P_IP);
-	if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
+	if (ip_route_me_harder(net, nskb->sk, nskb, RTN_UNSPEC))
 		goto free_nskb;
 
 	if (nfct) {
@@ -849,7 +849,7 @@ synproxy_send_tcp_ipv6(struct net *net,
 	fl6.fl6_sport = nth->source;
 	fl6.fl6_dport = nth->dest;
 	security_skb_classify_flow((struct sk_buff *)skb,
-				   flowi6_to_flowi(&fl6));
+				   flowi6_to_flowi_common(&fl6));
 	err = nf_ip6_route(net, &dst, flowi6_to_flowi(&fl6), false);
 	if (err) {
 		goto free_nskb;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 4603b667973a..8ee9f40cc0ea 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -206,7 +206,7 @@ static int nf_tables_register_hook(struct net *net,
 	if (basechain->type->ops_register)
 		return basechain->type->ops_register(net, ops);
 
-	if (table->family == NFPROTO_NETDEV)
+	if (nft_base_chain_netdev(table->family, basechain->ops.hooknum))
 		return nft_netdev_register_hooks(net, &basechain->hook_list);
 
 	return nf_register_net_hook(net, &basechain->ops);
@@ -228,7 +228,7 @@ static void nf_tables_unregister_hook(struct net *net,
 	if (basechain->type->ops_unregister)
 		return basechain->type->ops_unregister(net, ops);
 
-	if (table->family == NFPROTO_NETDEV)
+	if (nft_base_chain_netdev(table->family, basechain->ops.hooknum))
 		nft_netdev_unregister_hooks(net, &basechain->hook_list);
 	else
 		nf_unregister_net_hook(net, &basechain->ops);
@@ -302,7 +302,7 @@ static void nft_rule_expr_activate(const struct nft_ctx *ctx,
 	struct nft_expr *expr;
 
 	expr = nft_expr_first(rule);
-	while (expr != nft_expr_last(rule) && expr->ops) {
+	while (nft_expr_more(rule, expr)) {
 		if (expr->ops->activate)
 			expr->ops->activate(ctx, expr);
 
@@ -317,7 +317,7 @@ static void nft_rule_expr_deactivate(const struct nft_ctx *ctx,
 	struct nft_expr *expr;
 
 	expr = nft_expr_first(rule);
-	while (expr != nft_expr_last(rule) && expr->ops) {
+	while (nft_expr_more(rule, expr)) {
 		if (expr->ops->deactivate)
 			expr->ops->deactivate(ctx, expr, phase);
 
@@ -581,7 +581,8 @@ struct nft_module_request {
 };
 
 #ifdef CONFIG_MODULES
-static int nft_request_module(struct net *net, const char *fmt, ...)
+static __printf(2, 3) int nft_request_module(struct net *net, const char *fmt,
+					     ...)
 {
 	char module_name[MODULE_NAME_LEN];
 	struct nft_module_request *req;
@@ -619,7 +620,8 @@ static int nft_request_module(struct net *net, const char *fmt, ...)
 static void lockdep_nfnl_nft_mutex_not_held(void)
 {
 #ifdef CONFIG_PROVE_LOCKING
-	WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES));
+	if (debug_locks)
+		WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES));
 #endif
 }
 
@@ -650,6 +652,8 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
 				    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_TABLE_FLAGS]	= { .type = NLA_U32 },
 	[NFTA_TABLE_HANDLE]	= { .type = NLA_U64 },
+	[NFTA_TABLE_USERDATA]	= { .type = NLA_BINARY,
+				    .len = NFT_USERDATA_MAXLEN }
 };
 
 static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
@@ -676,6 +680,11 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 			 NFTA_TABLE_PAD))
 		goto nla_put_failure;
 
+	if (table->udata) {
+		if (nla_put(skb, NFTA_TABLE_USERDATA, table->udlen, table->udata))
+			goto nla_put_failure;
+	}
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -988,8 +997,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 	int family = nfmsg->nfgen_family;
 	const struct nlattr *attr;
 	struct nft_table *table;
-	u32 flags = 0;
 	struct nft_ctx ctx;
+	u32 flags = 0;
 	int err;
 
 	lockdep_assert_held(&net->nft.commit_mutex);
@@ -1025,6 +1034,14 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 	if (table->name == NULL)
 		goto err_strdup;
 
+	if (nla[NFTA_TABLE_USERDATA]) {
+		table->udata = nla_memdup(nla[NFTA_TABLE_USERDATA], GFP_KERNEL);
+		if (table->udata == NULL)
+			goto err_table_udata;
+
+		table->udlen = nla_len(nla[NFTA_TABLE_USERDATA]);
+	}
+
 	err = rhltable_init(&table->chains_ht, &nft_chain_ht_params);
 	if (err)
 		goto err_chain_ht;
@@ -1047,6 +1064,8 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 err_trans:
 	rhltable_destroy(&table->chains_ht);
 err_chain_ht:
+	kfree(table->udata);
+err_table_udata:
 	kfree(table->name);
 err_strdup:
 	kfree(table);
@@ -1202,6 +1221,7 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx)
 
 	rhltable_destroy(&ctx->table->chains_ht);
 	kfree(ctx->table->name);
+	kfree(ctx->table->udata);
 	kfree(ctx->table);
 }
 
@@ -1263,7 +1283,7 @@ static struct nft_chain *nft_chain_lookup(struct net *net,
 	if (nla == NULL)
 		return ERR_PTR(-EINVAL);
 
-	nla_strlcpy(search, nla, sizeof(search));
+	nla_strscpy(search, nla, sizeof(search));
 
 	WARN_ON(!rcu_read_lock_held() &&
 		!lockdep_commit_lock_is_held(net));
@@ -1297,6 +1317,8 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
 	[NFTA_CHAIN_COUNTERS]	= { .type = NLA_NESTED },
 	[NFTA_CHAIN_FLAGS]	= { .type = NLA_U32 },
 	[NFTA_CHAIN_ID]		= { .type = NLA_U32 },
+	[NFTA_CHAIN_USERDATA]	= { .type = NLA_BINARY,
+				    .len = NFT_USERDATA_MAXLEN },
 };
 
 static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = {
@@ -1361,7 +1383,7 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family,
 	if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority)))
 		goto nla_put_failure;
 
-	if (family == NFPROTO_NETDEV) {
+	if (nft_base_chain_netdev(family, ops->hooknum)) {
 		nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS);
 		list_for_each_entry(hook, &basechain->hook_list, list) {
 			if (!first)
@@ -1438,6 +1460,10 @@ static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net,
 	if (nla_put_be32(skb, NFTA_CHAIN_USE, htonl(chain->use)))
 		goto nla_put_failure;
 
+	if (chain->udata &&
+	    nla_put(skb, NFTA_CHAIN_USERDATA, chain->udlen, chain->udata))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -1661,7 +1687,7 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx)
 	if (nft_is_base_chain(chain)) {
 		struct nft_base_chain *basechain = nft_base_chain(chain);
 
-		if (ctx->family == NFPROTO_NETDEV) {
+		if (nft_base_chain_netdev(ctx->family, basechain->ops.hooknum)) {
 			list_for_each_entry_safe(hook, next,
 						 &basechain->hook_list, list) {
 				list_del_rcu(&hook->list);
@@ -1674,9 +1700,11 @@ void nf_tables_chain_destroy(struct nft_ctx *ctx)
 			free_percpu(rcu_dereference_raw(basechain->stats));
 		}
 		kfree(chain->name);
+		kfree(chain->udata);
 		kfree(basechain);
 	} else {
 		kfree(chain->name);
+		kfree(chain->udata);
 		kfree(chain);
 	}
 }
@@ -1695,7 +1723,11 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net,
 		goto err_hook_alloc;
 	}
 
-	nla_strlcpy(ifname, attr, IFNAMSIZ);
+	nla_strscpy(ifname, attr, IFNAMSIZ);
+	/* nf_tables_netdev_event() is called under rtnl_mutex, this is
+	 * indirectly serializing all the other holders of the commit_mutex with
+	 * the rtnl_mutex.
+	 */
 	dev = __dev_get_by_name(net, ifname);
 	if (!dev) {
 		err = -ENOENT;
@@ -1838,7 +1870,7 @@ static int nft_chain_parse_hook(struct net *net,
 		if (IS_ERR(type))
 			return PTR_ERR(type);
 	}
-	if (hook->num > NF_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
+	if (hook->num >= NFT_MAX_HOOKS || !(type->hook_mask & (1 << hook->num)))
 		return -EOPNOTSUPP;
 
 	if (type->type == NFT_CHAIN_T_NAT &&
@@ -1851,7 +1883,7 @@ static int nft_chain_parse_hook(struct net *net,
 	hook->type = type;
 
 	INIT_LIST_HEAD(&hook->list);
-	if (family == NFPROTO_NETDEV) {
+	if (nft_base_chain_netdev(family, hook->num)) {
 		err = nft_chain_parse_netdev(net, ha, &hook->list);
 		if (err < 0) {
 			module_put(type->owner);
@@ -1918,7 +1950,7 @@ static int nft_basechain_init(struct nft_base_chain *basechain, u8 family,
 	INIT_LIST_HEAD(&basechain->hook_list);
 	chain = &basechain->chain;
 
-	if (family == NFPROTO_NETDEV) {
+	if (nft_base_chain_netdev(family, hook->num)) {
 		list_splice_init(&hook->list, &basechain->hook_list);
 		list_for_each_entry(h, &basechain->hook_list, list)
 			nft_basechain_hook_init(&h->ops, family, hook, chain);
@@ -2030,7 +2062,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	} else {
 		if (!(flags & NFT_CHAIN_BINDING)) {
 			err = -EINVAL;
-			goto err1;
+			goto err_destroy_chain;
 		}
 
 		snprintf(name, sizeof(name), "__chain%llu", ++chain_id);
@@ -2039,13 +2071,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 
 	if (!chain->name) {
 		err = -ENOMEM;
-		goto err1;
+		goto err_destroy_chain;
+	}
+
+	if (nla[NFTA_CHAIN_USERDATA]) {
+		chain->udata = nla_memdup(nla[NFTA_CHAIN_USERDATA], GFP_KERNEL);
+		if (chain->udata == NULL) {
+			err = -ENOMEM;
+			goto err_destroy_chain;
+		}
+		chain->udlen = nla_len(nla[NFTA_CHAIN_USERDATA]);
 	}
 
 	rules = nf_tables_chain_alloc_rules(chain, 0);
 	if (!rules) {
 		err = -ENOMEM;
-		goto err1;
+		goto err_destroy_chain;
 	}
 
 	*rules = NULL;
@@ -2054,12 +2095,12 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 
 	err = nf_tables_register_hook(net, table, chain);
 	if (err < 0)
-		goto err1;
+		goto err_destroy_chain;
 
 	trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN);
 	if (IS_ERR(trans)) {
 		err = PTR_ERR(trans);
-		goto err2;
+		goto err_unregister_hook;
 	}
 
 	nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET;
@@ -2069,15 +2110,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 	err = nft_chain_add(table, chain);
 	if (err < 0) {
 		nft_trans_destroy(trans);
-		goto err2;
+		goto err_unregister_hook;
 	}
 
 	table->use++;
 
 	return 0;
-err2:
+err_unregister_hook:
 	nf_tables_unregister_hook(net, table, chain);
-err1:
+err_destroy_chain:
 	nf_tables_chain_destroy(ctx);
 
 	return err;
@@ -2103,7 +2144,8 @@ static bool nft_hook_list_equal(struct list_head *hook_list1,
 }
 
 static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
-			      u32 flags)
+			      u32 flags, const struct nlattr *attr,
+			      struct netlink_ext_ack *extack)
 {
 	const struct nlattr * const *nla = ctx->nla;
 	struct nft_table *table = ctx->table;
@@ -2119,9 +2161,10 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 		return -EOPNOTSUPP;
 
 	if (nla[NFTA_CHAIN_HOOK]) {
-		if (!nft_is_base_chain(chain))
+		if (!nft_is_base_chain(chain)) {
+			NL_SET_BAD_ATTR(extack, attr);
 			return -EEXIST;
-
+		}
 		err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family,
 					   false);
 		if (err < 0)
@@ -2130,13 +2173,15 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 		basechain = nft_base_chain(chain);
 		if (basechain->type != hook.type) {
 			nft_chain_release_hook(&hook);
+			NL_SET_BAD_ATTR(extack, attr);
 			return -EEXIST;
 		}
 
-		if (ctx->family == NFPROTO_NETDEV) {
+		if (nft_base_chain_netdev(ctx->family, hook.num)) {
 			if (!nft_hook_list_equal(&basechain->hook_list,
 						 &hook.list)) {
 				nft_chain_release_hook(&hook);
+				NL_SET_BAD_ATTR(extack, attr);
 				return -EEXIST;
 			}
 		} else {
@@ -2144,6 +2189,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 			if (ops->hooknum != hook.num ||
 			    ops->priority != hook.priority) {
 				nft_chain_release_hook(&hook);
+				NL_SET_BAD_ATTR(extack, attr);
 				return -EEXIST;
 			}
 		}
@@ -2156,8 +2202,10 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 
 		chain2 = nft_chain_lookup(ctx->net, table,
 					  nla[NFTA_CHAIN_NAME], genmask);
-		if (!IS_ERR(chain2))
+		if (!IS_ERR(chain2)) {
+			NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]);
 			return -EEXIST;
+		}
 	}
 
 	if (nla[NFTA_CHAIN_COUNTERS]) {
@@ -2200,6 +2248,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 			    nft_trans_chain_update(tmp) &&
 			    nft_trans_chain_name(tmp) &&
 			    strcmp(name, nft_trans_chain_name(tmp)) == 0) {
+				NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]);
 				kfree(name);
 				goto err;
 			}
@@ -2322,7 +2371,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 			return -EOPNOTSUPP;
 
 		flags |= chain->flags & NFT_CHAIN_BASE;
-		return nf_tables_updchain(&ctx, genmask, policy, flags);
+		return nf_tables_updchain(&ctx, genmask, policy, flags, attr,
+					  extack);
 	}
 
 	return nf_tables_addchain(&ctx, family, genmask, policy, flags);
@@ -3036,7 +3086,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	 * is called on error from nf_tables_newrule().
 	 */
 	expr = nft_expr_first(rule);
-	while (expr != nft_expr_last(rule) && expr->ops) {
+	while (nft_expr_more(rule, expr)) {
 		next = nft_expr_next(expr);
 		nf_tables_expr_destroy(ctx, expr);
 		expr = next;
@@ -3521,6 +3571,7 @@ static const struct nla_policy nft_set_policy[NFTA_SET_MAX + 1] = {
 	[NFTA_SET_OBJ_TYPE]		= { .type = NLA_U32 },
 	[NFTA_SET_HANDLE]		= { .type = NLA_U64 },
 	[NFTA_SET_EXPR]			= { .type = NLA_NESTED },
+	[NFTA_SET_EXPRESSIONS]		= { .type = NLA_NESTED },
 };
 
 static const struct nla_policy nft_set_desc_policy[NFTA_SET_DESC_MAX + 1] = {
@@ -3674,7 +3725,7 @@ cont:
 	return 0;
 }
 
-static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
+int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
 {
 	u64 ms = be64_to_cpu(nla_get_be64(nla));
 	u64 max = (u64)(~((u64)0));
@@ -3688,7 +3739,7 @@ static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
 	return 0;
 }
 
-static __be64 nf_jiffies64_to_msecs(u64 input)
+__be64 nf_jiffies64_to_msecs(u64 input)
 {
 	return cpu_to_be64(jiffies64_to_msecs(input));
 }
@@ -3728,6 +3779,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 	u32 portid = ctx->portid;
 	struct nlattr *nest;
 	u32 seq = ctx->seq;
+	int i;
 
 	event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg),
@@ -3796,12 +3848,23 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
 
 	nla_nest_end(skb, nest);
 
-	if (set->expr) {
+	if (set->num_exprs == 1) {
 		nest = nla_nest_start_noflag(skb, NFTA_SET_EXPR);
-		if (nf_tables_fill_expr_info(skb, set->expr) < 0)
+		if (nf_tables_fill_expr_info(skb, set->exprs[0]) < 0)
 			goto nla_put_failure;
 
 		nla_nest_end(skb, nest);
+	} else if (set->num_exprs > 1) {
+		nest = nla_nest_start_noflag(skb, NFTA_SET_EXPRESSIONS);
+		if (nest == NULL)
+			goto nla_put_failure;
+
+		for (i = 0; i < set->num_exprs; i++) {
+			if (nft_expr_dump(skb, NFTA_LIST_ELEM,
+					  set->exprs[i]) < 0)
+				goto nla_put_failure;
+		}
+		nla_nest_end(skb, nest);
 	}
 
 	nlmsg_end(skb, nlh);
@@ -4099,7 +4162,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 		if (flags & ~(NFT_SET_ANONYMOUS | NFT_SET_CONSTANT |
 			      NFT_SET_INTERVAL | NFT_SET_TIMEOUT |
 			      NFT_SET_MAP | NFT_SET_EVAL |
-			      NFT_SET_OBJECT | NFT_SET_CONCAT))
+			      NFT_SET_OBJECT | NFT_SET_CONCAT | NFT_SET_EXPR))
 			return -EOPNOTSUPP;
 		/* Only one of these operations is supported */
 		if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) ==
@@ -4170,7 +4233,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 			return err;
 	}
 
-	if (nla[NFTA_SET_EXPR])
+	if (nla[NFTA_SET_EXPR] || nla[NFTA_SET_EXPRESSIONS])
 		desc.expr = true;
 
 	table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask);
@@ -4234,6 +4297,35 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 			err = PTR_ERR(expr);
 			goto err_set_alloc_name;
 		}
+		set->exprs[0] = expr;
+		set->num_exprs++;
+	} else if (nla[NFTA_SET_EXPRESSIONS]) {
+		struct nft_expr *expr;
+		struct nlattr *tmp;
+		int left;
+
+		if (!(flags & NFT_SET_EXPR)) {
+			err = -EINVAL;
+			goto err_set_alloc_name;
+		}
+		i = 0;
+		nla_for_each_nested(tmp, nla[NFTA_SET_EXPRESSIONS], left) {
+			if (i == NFT_SET_EXPR_MAX) {
+				err = -E2BIG;
+				goto err_set_init;
+			}
+			if (nla_type(tmp) != NFTA_LIST_ELEM) {
+				err = -EINVAL;
+				goto err_set_init;
+			}
+			expr = nft_set_elem_expr_alloc(&ctx, set, tmp);
+			if (IS_ERR(expr)) {
+				err = PTR_ERR(expr);
+				goto err_set_init;
+			}
+			set->exprs[i++] = expr;
+			set->num_exprs++;
+		}
 	}
 
 	udata = NULL;
@@ -4251,7 +4343,6 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 	set->dtype = dtype;
 	set->objtype = objtype;
 	set->dlen  = desc.dlen;
-	set->expr = expr;
 	set->flags = flags;
 	set->size  = desc.size;
 	set->policy = policy;
@@ -4280,8 +4371,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 err_set_trans:
 	ops->destroy(set);
 err_set_init:
-	if (expr)
-		nft_expr_destroy(&ctx, expr);
+	for (i = 0; i < set->num_exprs; i++)
+		nft_expr_destroy(&ctx, set->exprs[i]);
 err_set_alloc_name:
 	kfree(set->name);
 err_set_name:
@@ -4291,11 +4382,13 @@ err_set_name:
 
 static void nft_set_destroy(const struct nft_ctx *ctx, struct nft_set *set)
 {
+	int i;
+
 	if (WARN_ON(set->use > 0))
 		return;
 
-	if (set->expr)
-		nft_expr_destroy(ctx, set->expr);
+	for (i = 0; i < set->num_exprs; i++)
+		nft_expr_destroy(ctx, set->exprs[i]);
 
 	set->ops->destroy(set);
 	kfree(set->name);
@@ -4448,8 +4541,8 @@ const struct nft_set_ext_type nft_set_ext_types[] = {
 	[NFT_SET_EXT_DATA]		= {
 		.align	= __alignof__(u32),
 	},
-	[NFT_SET_EXT_EXPR]		= {
-		.align	= __alignof__(struct nft_expr),
+	[NFT_SET_EXT_EXPRESSIONS]	= {
+		.align	= __alignof__(struct nft_set_elem_expr),
 	},
 	[NFT_SET_EXT_OBJREF]		= {
 		.len	= sizeof(struct nft_object *),
@@ -4492,6 +4585,7 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = {
 	[NFTA_SET_ELEM_OBJREF]		= { .type = NLA_STRING,
 					    .len = NFT_OBJ_MAXNAMELEN - 1 },
 	[NFTA_SET_ELEM_KEY_END]		= { .type = NLA_NESTED },
+	[NFTA_SET_ELEM_EXPRESSIONS]	= { .type = NLA_NESTED },
 };
 
 static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = {
@@ -4525,6 +4619,43 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net,
 	return 0;
 }
 
+static int nft_set_elem_expr_dump(struct sk_buff *skb,
+				  const struct nft_set *set,
+				  const struct nft_set_ext *ext)
+{
+	struct nft_set_elem_expr *elem_expr;
+	u32 size, num_exprs = 0;
+	struct nft_expr *expr;
+	struct nlattr *nest;
+
+	elem_expr = nft_set_ext_expr(ext);
+	nft_setelem_expr_foreach(expr, elem_expr, size)
+		num_exprs++;
+
+	if (num_exprs == 1) {
+		expr = nft_setelem_expr_at(elem_expr, 0);
+		if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr) < 0)
+			return -1;
+
+		return 0;
+	} else if (num_exprs > 1) {
+		nest = nla_nest_start_noflag(skb, NFTA_SET_ELEM_EXPRESSIONS);
+		if (nest == NULL)
+			goto nla_put_failure;
+
+		nft_setelem_expr_foreach(expr, elem_expr, size) {
+			expr = nft_setelem_expr_at(elem_expr, size);
+			if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0)
+				goto nla_put_failure;
+		}
+		nla_nest_end(skb, nest);
+	}
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
 static int nf_tables_fill_setelem(struct sk_buff *skb,
 				  const struct nft_set *set,
 				  const struct nft_set_elem *elem)
@@ -4552,8 +4683,8 @@ static int nf_tables_fill_setelem(struct sk_buff *skb,
 			  set->dlen) < 0)
 		goto nla_put_failure;
 
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR) &&
-	    nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, nft_set_ext_expr(ext)) < 0)
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) &&
+	    nft_set_elem_expr_dump(skb, set, ext))
 		goto nla_put_failure;
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) &&
@@ -5048,8 +5179,8 @@ void *nft_set_elem_init(const struct nft_set *set,
 	return elem;
 }
 
-static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
-				      struct nft_expr *expr)
+static void __nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
+					struct nft_expr *expr)
 {
 	if (expr->ops->destroy_clone) {
 		expr->ops->destroy_clone(ctx, expr);
@@ -5059,6 +5190,16 @@ static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
 	}
 }
 
+static void nft_set_elem_expr_destroy(const struct nft_ctx *ctx,
+				      struct nft_set_elem_expr *elem_expr)
+{
+	struct nft_expr *expr;
+	u32 size;
+
+	nft_setelem_expr_foreach(expr, elem_expr, size)
+		__nft_set_elem_expr_destroy(ctx, expr);
+}
+
 void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 			  bool destroy_expr)
 {
@@ -5071,7 +5212,7 @@ void nft_set_elem_destroy(const struct nft_set *set, void *elem,
 	nft_data_release(nft_set_ext_key(ext), NFT_DATA_VALUE);
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA))
 		nft_data_release(nft_set_ext_data(ext), set->dtype);
-	if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
+	if (destroy_expr && nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS))
 		nft_set_elem_expr_destroy(&ctx, nft_set_ext_expr(ext));
 
 	if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF))
@@ -5088,32 +5229,72 @@ static void nf_tables_set_elem_destroy(const struct nft_ctx *ctx,
 {
 	struct nft_set_ext *ext = nft_set_elem_ext(set, elem);
 
-	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPR))
+	if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS))
 		nft_set_elem_expr_destroy(ctx, nft_set_ext_expr(ext));
 
 	kfree(elem);
 }
 
+int nft_set_elem_expr_clone(const struct nft_ctx *ctx, struct nft_set *set,
+			    struct nft_expr *expr_array[])
+{
+	struct nft_expr *expr;
+	int err, i, k;
+
+	for (i = 0; i < set->num_exprs; i++) {
+		expr = kzalloc(set->exprs[i]->ops->size, GFP_KERNEL);
+		if (!expr)
+			goto err_expr;
+
+		err = nft_expr_clone(expr, set->exprs[i]);
+		if (err < 0) {
+			nft_expr_destroy(ctx, expr);
+			goto err_expr;
+		}
+		expr_array[i] = expr;
+	}
+
+	return 0;
+
+err_expr:
+	for (k = i - 1; k >= 0; k--)
+		nft_expr_destroy(ctx, expr_array[k]);
+
+	return -ENOMEM;
+}
+
+static void nft_set_elem_expr_setup(const struct nft_set_ext *ext, int i,
+				    struct nft_expr *expr_array[])
+{
+	struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext);
+	struct nft_expr *expr = nft_setelem_expr_at(elem_expr, elem_expr->size);
+
+	memcpy(expr, expr_array[i], expr_array[i]->ops->size);
+	elem_expr->size += expr_array[i]->ops->size;
+	kfree(expr_array[i]);
+	expr_array[i] = NULL;
+}
+
 static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			    const struct nlattr *attr, u32 nlmsg_flags)
 {
+	struct nft_expr *expr_array[NFT_SET_EXPR_MAX] = {};
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
 	u8 genmask = nft_genmask_next(ctx->net);
+	u32 flags = 0, size = 0, num_exprs = 0;
 	struct nft_set_ext_tmpl tmpl;
 	struct nft_set_ext *ext, *ext2;
 	struct nft_set_elem elem;
 	struct nft_set_binding *binding;
 	struct nft_object *obj = NULL;
-	struct nft_expr *expr = NULL;
 	struct nft_userdata *udata;
 	struct nft_data_desc desc;
 	enum nft_registers dreg;
 	struct nft_trans *trans;
-	u32 flags = 0;
 	u64 timeout;
 	u64 expiration;
+	int err, i;
 	u8 ulen;
-	int err;
 
 	err = nla_parse_nested_deprecated(nla, NFTA_SET_ELEM_MAX, attr,
 					  nft_set_elem_policy, NULL);
@@ -5146,7 +5327,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 	      nla[NFTA_SET_ELEM_TIMEOUT] ||
 	      nla[NFTA_SET_ELEM_EXPIRATION] ||
 	      nla[NFTA_SET_ELEM_USERDATA] ||
-	      nla[NFTA_SET_ELEM_EXPR]))
+	      nla[NFTA_SET_ELEM_EXPR] ||
+	      nla[NFTA_SET_ELEM_EXPRESSIONS]))
 		return -EINVAL;
 
 	timeout = 0;
@@ -5171,23 +5353,64 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			return err;
 	}
 
-	if (nla[NFTA_SET_ELEM_EXPR] != NULL) {
+	if (nla[NFTA_SET_ELEM_EXPR]) {
+		struct nft_expr *expr;
+
+		if (set->num_exprs && set->num_exprs != 1)
+			return -EOPNOTSUPP;
+
 		expr = nft_set_elem_expr_alloc(ctx, set,
 					       nla[NFTA_SET_ELEM_EXPR]);
 		if (IS_ERR(expr))
 			return PTR_ERR(expr);
 
-		err = -EOPNOTSUPP;
-		if (set->expr && set->expr->ops != expr->ops)
+		expr_array[0] = expr;
+		num_exprs = 1;
+
+		if (set->num_exprs && set->exprs[0]->ops != expr->ops) {
+			err = -EOPNOTSUPP;
 			goto err_set_elem_expr;
-	} else if (set->expr) {
-		expr = kzalloc(set->expr->ops->size, GFP_KERNEL);
-		if (!expr)
-			return -ENOMEM;
+		}
+	} else if (nla[NFTA_SET_ELEM_EXPRESSIONS]) {
+		struct nft_expr *expr;
+		struct nlattr *tmp;
+		int left;
+
+		i = 0;
+		nla_for_each_nested(tmp, nla[NFTA_SET_ELEM_EXPRESSIONS], left) {
+			if (i == NFT_SET_EXPR_MAX ||
+			    (set->num_exprs && set->num_exprs == i)) {
+				err = -E2BIG;
+				goto err_set_elem_expr;
+			}
+			if (nla_type(tmp) != NFTA_LIST_ELEM) {
+				err = -EINVAL;
+				goto err_set_elem_expr;
+			}
+			expr = nft_set_elem_expr_alloc(ctx, set, tmp);
+			if (IS_ERR(expr)) {
+				err = PTR_ERR(expr);
+				goto err_set_elem_expr;
+			}
+			expr_array[i] = expr;
+			num_exprs++;
 
-		err = nft_expr_clone(expr, set->expr);
-		if (err < 0)
+			if (set->num_exprs && expr->ops != set->exprs[i]->ops) {
+				err = -EOPNOTSUPP;
+				goto err_set_elem_expr;
+			}
+			i++;
+		}
+		if (set->num_exprs && set->num_exprs != i) {
+			err = -EOPNOTSUPP;
 			goto err_set_elem_expr;
+		}
+	} else if (set->num_exprs > 0) {
+		err = nft_set_elem_expr_clone(ctx, set, expr_array);
+		if (err < 0)
+			goto err_set_elem_expr_clone;
+
+		num_exprs = set->num_exprs;
 	}
 
 	err = nft_setelem_parse_key(ctx, set, &elem.key.val,
@@ -5212,9 +5435,14 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
 	}
 
-	if (expr)
-		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPR,
-				       expr->ops->size);
+	if (num_exprs) {
+		for (i = 0; i < num_exprs; i++)
+			size += expr_array[i]->ops->size;
+
+		nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS,
+				       sizeof(struct nft_set_elem_expr) +
+				       size);
+	}
 
 	if (nla[NFTA_SET_ELEM_OBJREF] != NULL) {
 		if (!(set->flags & NFT_SET_OBJECT)) {
@@ -5296,11 +5524,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		*nft_set_ext_obj(ext) = obj;
 		obj->use++;
 	}
-	if (expr) {
-		memcpy(nft_set_ext_expr(ext), expr, expr->ops->size);
-		kfree(expr);
-		expr = NULL;
-	}
+	for (i = 0; i < num_exprs; i++)
+		nft_set_elem_expr_setup(ext, i, expr_array);
 
 	trans = nft_trans_elem_alloc(ctx, NFT_MSG_NEWSETELEM, set);
 	if (trans == NULL)
@@ -5361,9 +5586,9 @@ err_parse_key_end:
 err_parse_key:
 	nft_data_release(&elem.key.val, NFT_DATA_VALUE);
 err_set_elem_expr:
-	if (expr != NULL)
-		nft_expr_destroy(ctx, expr);
-
+	for (i = 0; i < num_exprs && expr_array[i]; i++)
+		nft_expr_destroy(ctx, expr_array[i]);
+err_set_elem_expr_clone:
 	return err;
 }
 
@@ -5690,7 +5915,7 @@ struct nft_object *nft_obj_lookup(const struct net *net,
 	struct rhlist_head *tmp, *list;
 	struct nft_object *obj;
 
-	nla_strlcpy(search, nla, sizeof(search));
+	nla_strscpy(search, nla, sizeof(search));
 	k.name = search;
 
 	WARN_ON_ONCE(!rcu_read_lock_held() &&
@@ -5737,6 +5962,8 @@ static const struct nla_policy nft_obj_policy[NFTA_OBJ_MAX + 1] = {
 	[NFTA_OBJ_TYPE]		= { .type = NLA_U32 },
 	[NFTA_OBJ_DATA]		= { .type = NLA_NESTED },
 	[NFTA_OBJ_HANDLE]	= { .type = NLA_U64},
+	[NFTA_OBJ_USERDATA]	= { .type = NLA_BINARY,
+				    .len = NFT_USERDATA_MAXLEN },
 };
 
 static struct nft_object *nft_obj_init(const struct nft_ctx *ctx,
@@ -5928,7 +6155,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	obj = nft_obj_init(&ctx, type, nla[NFTA_OBJ_DATA]);
 	if (IS_ERR(obj)) {
 		err = PTR_ERR(obj);
-		goto err1;
+		goto err_init;
 	}
 	obj->key.table = table;
 	obj->handle = nf_tables_alloc_handle(table);
@@ -5936,32 +6163,42 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 	obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL);
 	if (!obj->key.name) {
 		err = -ENOMEM;
-		goto err2;
+		goto err_strdup;
+	}
+
+	if (nla[NFTA_OBJ_USERDATA]) {
+		obj->udata = nla_memdup(nla[NFTA_OBJ_USERDATA], GFP_KERNEL);
+		if (obj->udata == NULL)
+			goto err_userdata;
+
+		obj->udlen = nla_len(nla[NFTA_OBJ_USERDATA]);
 	}
 
 	err = nft_trans_obj_add(&ctx, NFT_MSG_NEWOBJ, obj);
 	if (err < 0)
-		goto err3;
+		goto err_trans;
 
 	err = rhltable_insert(&nft_objname_ht, &obj->rhlhead,
 			      nft_objname_ht_params);
 	if (err < 0)
-		goto err4;
+		goto err_obj_ht;
 
 	list_add_tail_rcu(&obj->list, &table->objects);
 	table->use++;
 	return 0;
-err4:
+err_obj_ht:
 	/* queued in transaction log */
 	INIT_LIST_HEAD(&obj->list);
 	return err;
-err3:
+err_trans:
 	kfree(obj->key.name);
-err2:
+err_userdata:
+	kfree(obj->udata);
+err_strdup:
 	if (obj->ops->destroy)
 		obj->ops->destroy(&ctx, obj);
 	kfree(obj);
-err1:
+err_init:
 	module_put(type->owner);
 	return err;
 }
@@ -5993,6 +6230,10 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net,
 			 NFTA_OBJ_PAD))
 		goto nla_put_failure;
 
+	if (obj->udata &&
+	    nla_put(skb, NFTA_OBJ_USERDATA, obj->udlen, obj->udata))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -6199,6 +6440,7 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj)
 
 	module_put(obj->ops->type->owner);
 	kfree(obj->key.name);
+	kfree(obj->udata);
 	kfree(obj);
 }
 
@@ -7076,7 +7318,7 @@ static void nf_tables_flowtable_notify(struct nft_ctx *ctx,
 			GFP_KERNEL);
 	kfree(buf);
 
-	if (ctx->report &&
+	if (!ctx->report &&
 	    !nfnetlink_has_listeners(ctx->net, NFNLGRP_NFTABLES))
 		return;
 
@@ -7198,7 +7440,7 @@ static void nf_tables_gen_notify(struct net *net, struct sk_buff *skb,
 	audit_log_nfcfg("?:0;?:0", 0, net->nft.base_seq,
 			AUDIT_NFT_OP_GEN_REGISTER, GFP_KERNEL);
 
-	if (nlmsg_report(nlh) &&
+	if (!nlmsg_report(nlh) &&
 	    !nfnetlink_has_listeners(net, NFNLGRP_NFTABLES))
 		return;
 
@@ -7992,12 +8234,16 @@ static void nf_tables_abort_release(struct nft_trans *trans)
 	kfree(trans);
 }
 
-static int __nf_tables_abort(struct net *net, bool autoload)
+static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action)
 {
 	struct nft_trans *trans, *next;
 	struct nft_trans_elem *te;
 	struct nft_hook *hook;
 
+	if (action == NFNL_ABORT_VALIDATE &&
+	    nf_tables_validate(net) < 0)
+		return -EAGAIN;
+
 	list_for_each_entry_safe_reverse(trans, next, &net->nft.commit_list,
 					 list) {
 		switch (trans->msg_type) {
@@ -8129,7 +8375,7 @@ static int __nf_tables_abort(struct net *net, bool autoload)
 		nf_tables_abort_release(trans);
 	}
 
-	if (autoload)
+	if (action == NFNL_ABORT_AUTOLOAD)
 		nf_tables_module_autoload(net);
 	else
 		nf_tables_module_autoload_cleanup(net);
@@ -8142,9 +8388,10 @@ static void nf_tables_cleanup(struct net *net)
 	nft_validate_state_update(net, NFT_VALIDATE_SKIP);
 }
 
-static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload)
+static int nf_tables_abort(struct net *net, struct sk_buff *skb,
+			   enum nfnl_abort_action action)
 {
-	int ret = __nf_tables_abort(net, autoload);
+	int ret = __nf_tables_abort(net, action);
 
 	mutex_unlock(&net->nft.commit_mutex);
 
@@ -8704,6 +8951,17 @@ int __nft_release_basechain(struct nft_ctx *ctx)
 }
 EXPORT_SYMBOL_GPL(__nft_release_basechain);
 
+static void __nft_release_hooks(struct net *net)
+{
+	struct nft_table *table;
+	struct nft_chain *chain;
+
+	list_for_each_entry(table, &net->nft.tables, list) {
+		list_for_each_entry(chain, &table->chains, list)
+			nf_tables_unregister_hook(net, table, chain);
+	}
+}
+
 static void __nft_release_tables(struct net *net)
 {
 	struct nft_flowtable *flowtable, *nf;
@@ -8719,10 +8977,6 @@ static void __nft_release_tables(struct net *net)
 
 	list_for_each_entry_safe(table, nt, &net->nft.tables, list) {
 		ctx.family = table->family;
-
-		list_for_each_entry(chain, &table->chains, list)
-			nf_tables_unregister_hook(net, table, chain);
-		/* No packets are walking on these chains anymore. */
 		ctx.table = table;
 		list_for_each_entry(chain, &table->chains, list) {
 			ctx.chain = chain;
@@ -8771,11 +9025,16 @@ static int __net_init nf_tables_init_net(struct net *net)
 	return 0;
 }
 
+static void __net_exit nf_tables_pre_exit_net(struct net *net)
+{
+	__nft_release_hooks(net);
+}
+
 static void __net_exit nf_tables_exit_net(struct net *net)
 {
 	mutex_lock(&net->nft.commit_mutex);
 	if (!list_empty(&net->nft.commit_list))
-		__nf_tables_abort(net, false);
+		__nf_tables_abort(net, NFNL_ABORT_NONE);
 	__nft_release_tables(net);
 	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
@@ -8784,8 +9043,9 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 }
 
 static struct pernet_operations nf_tables_net_ops = {
-	.init	= nf_tables_init_net,
-	.exit	= nf_tables_exit_net,
+	.init		= nf_tables_init_net,
+	.pre_exit	= nf_tables_pre_exit_net,
+	.exit		= nf_tables_exit_net,
 };
 
 static int __init nf_tables_module_init(void)
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 587897a2498b..dbc2e945c98e 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -47,13 +47,22 @@ static inline void nft_trace_packet(struct nft_traceinfo *info,
 	}
 }
 
+static void nft_bitwise_fast_eval(const struct nft_expr *expr,
+				  struct nft_regs *regs)
+{
+	const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr);
+	u32 *src = &regs->data[priv->sreg];
+	u32 *dst = &regs->data[priv->dreg];
+
+	*dst = (*src & priv->mask) ^ priv->xor;
+}
+
 static void nft_cmp_fast_eval(const struct nft_expr *expr,
 			      struct nft_regs *regs)
 {
 	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
-	u32 mask = nft_cmp_fast_mask(priv->len);
 
-	if ((regs->data[priv->sreg] & mask) == priv->data)
+	if (((regs->data[priv->sreg] & priv->mask) == priv->data) ^ priv->inv)
 		return;
 	regs->verdict.code = NFT_BREAK;
 }
@@ -176,6 +185,8 @@ next_rule:
 		nft_rule_for_each_expr(expr, last, rule) {
 			if (expr->ops == &nft_cmp_fast_ops)
 				nft_cmp_fast_eval(expr, &regs);
+			else if (expr->ops == &nft_bitwise_fast_ops)
+				nft_bitwise_fast_eval(expr, &regs);
 			else if (expr->ops != &nft_payload_fast_ops ||
 				 !nft_payload_fast_eval(expr, &regs, pkt))
 				expr_call_ops_eval(expr, &regs, pkt);
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 9ef37c1b7b3b..9ae14270c543 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -28,6 +28,23 @@ static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions)
 	return flow;
 }
 
+void nft_flow_rule_set_addr_type(struct nft_flow_rule *flow,
+				 enum flow_dissector_key_id addr_type)
+{
+	struct nft_flow_match *match = &flow->match;
+	struct nft_flow_key *mask = &match->mask;
+	struct nft_flow_key *key = &match->key;
+
+	if (match->dissector.used_keys & BIT(FLOW_DISSECTOR_KEY_CONTROL))
+		return;
+
+	key->control.addr_type = addr_type;
+	mask->control.addr_type = 0xffff;
+	match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL);
+	match->dissector.offset[FLOW_DISSECTOR_KEY_CONTROL] =
+		offsetof(struct nft_flow_key, control);
+}
+
 struct nft_flow_rule *nft_flow_rule_create(struct net *net,
 					   const struct nft_rule *rule)
 {
@@ -37,7 +54,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net,
 	struct nft_expr *expr;
 
 	expr = nft_expr_first(rule);
-	while (expr->ops && expr != nft_expr_last(rule)) {
+	while (nft_expr_more(rule, expr)) {
 		if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION)
 			num_actions++;
 
@@ -61,7 +78,7 @@ struct nft_flow_rule *nft_flow_rule_create(struct net *net,
 	ctx->net = net;
 	ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC;
 
-	while (expr->ops && expr != nft_expr_last(rule)) {
+	while (nft_expr_more(rule, expr)) {
 		if (!expr->ops->offload) {
 			err = -EOPNOTSUPP;
 			goto err_out;
@@ -323,8 +340,6 @@ static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain,
 	return nft_block_setup(basechain, &bo, cmd);
 }
 
-#define FLOW_SETUP_BLOCK TC_SETUP_BLOCK
-
 static int nft_chain_offload_cmd(struct nft_base_chain *basechain,
 				 struct net_device *dev,
 				 enum flow_block_command cmd)
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 3a2e64e13b22..d3df66a39b5e 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -46,6 +46,23 @@ static struct {
 	const struct nfnetlink_subsystem __rcu	*subsys;
 } table[NFNL_SUBSYS_COUNT];
 
+static struct lock_class_key nfnl_lockdep_keys[NFNL_SUBSYS_COUNT];
+
+static const char *const nfnl_lockdep_names[NFNL_SUBSYS_COUNT] = {
+	[NFNL_SUBSYS_NONE] = "nfnl_subsys_none",
+	[NFNL_SUBSYS_CTNETLINK] = "nfnl_subsys_ctnetlink",
+	[NFNL_SUBSYS_CTNETLINK_EXP] = "nfnl_subsys_ctnetlink_exp",
+	[NFNL_SUBSYS_QUEUE] = "nfnl_subsys_queue",
+	[NFNL_SUBSYS_ULOG] = "nfnl_subsys_ulog",
+	[NFNL_SUBSYS_OSF] = "nfnl_subsys_osf",
+	[NFNL_SUBSYS_IPSET] = "nfnl_subsys_ipset",
+	[NFNL_SUBSYS_ACCT] = "nfnl_subsys_acct",
+	[NFNL_SUBSYS_CTNETLINK_TIMEOUT] = "nfnl_subsys_cttimeout",
+	[NFNL_SUBSYS_CTHELPER] = "nfnl_subsys_cthelper",
+	[NFNL_SUBSYS_NFTABLES] = "nfnl_subsys_nftables",
+	[NFNL_SUBSYS_NFT_COMPAT] = "nfnl_subsys_nftcompat",
+};
+
 static const int nfnl_group2type[NFNLGRP_MAX+1] = {
 	[NFNLGRP_CONNTRACK_NEW]		= NFNL_SUBSYS_CTNETLINK,
 	[NFNLGRP_CONNTRACK_UPDATE]	= NFNL_SUBSYS_CTNETLINK,
@@ -316,7 +333,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return netlink_ack(skb, nlh, -EINVAL, NULL);
 replay:
 	status = 0;
-
+replay_abort:
 	skb = netlink_skb_clone(oskb, GFP_KERNEL);
 	if (!skb)
 		return netlink_ack(oskb, nlh, -ENOMEM, NULL);
@@ -482,7 +499,7 @@ ack:
 	}
 done:
 	if (status & NFNL_BATCH_REPLAY) {
-		ss->abort(net, oskb, true);
+		ss->abort(net, oskb, NFNL_ABORT_AUTOLOAD);
 		nfnl_err_reset(&err_list);
 		kfree_skb(skb);
 		module_put(ss->owner);
@@ -493,11 +510,25 @@ done:
 			status |= NFNL_BATCH_REPLAY;
 			goto done;
 		} else if (err) {
-			ss->abort(net, oskb, false);
+			ss->abort(net, oskb, NFNL_ABORT_NONE);
 			netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
 		}
 	} else {
-		ss->abort(net, oskb, false);
+		enum nfnl_abort_action abort_action;
+
+		if (status & NFNL_BATCH_FAILURE)
+			abort_action = NFNL_ABORT_NONE;
+		else
+			abort_action = NFNL_ABORT_VALIDATE;
+
+		err = ss->abort(net, oskb, abort_action);
+		if (err == -EAGAIN) {
+			nfnl_err_reset(&err_list);
+			kfree_skb(skb);
+			module_put(ss->owner);
+			status |= NFNL_BATCH_FAILURE;
+			goto replay_abort;
+		}
 	}
 	if (ss->cleanup)
 		ss->cleanup(net);
@@ -632,7 +663,7 @@ static int __init nfnetlink_init(void)
 		BUG_ON(nfnl_group2type[i] == NFNL_SUBSYS_NONE);
 
 	for (i=0; i<NFNL_SUBSYS_COUNT; i++)
-		mutex_init(&table[i].mutex);
+		__mutex_init(&table[i].mutex, nfnl_lockdep_names[i], &nfnl_lockdep_keys[i]);
 
 	return register_pernet_subsys(&nfnetlink_net_ops);
 }
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 5bfec829c12f..0fa1653b5f19 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -16,6 +16,7 @@
 #include <linux/errno.h>
 #include <net/netlink.h>
 #include <net/sock.h>
+#include <net/netns/generic.h>
 
 #include <linux/netfilter.h>
 #include <linux/netfilter/nfnetlink.h>
@@ -41,6 +42,17 @@ struct nfacct_filter {
 	u32 mask;
 };
 
+struct nfnl_acct_net {
+	struct list_head        nfnl_acct_list;
+};
+
+static unsigned int nfnl_acct_net_id __read_mostly;
+
+static inline struct nfnl_acct_net *nfnl_acct_pernet(struct net *net)
+{
+	return net_generic(net, nfnl_acct_net_id);
+}
+
 #define NFACCT_F_QUOTA (NFACCT_F_QUOTA_PKTS | NFACCT_F_QUOTA_BYTES)
 #define NFACCT_OVERQUOTA_BIT	2	/* NFACCT_F_OVERQUOTA */
 
@@ -49,6 +61,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
 			 const struct nlattr * const tb[],
 			 struct netlink_ext_ack *extack)
 {
+	struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net);
 	struct nf_acct *nfacct, *matching = NULL;
 	char *acct_name;
 	unsigned int size = 0;
@@ -61,7 +74,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
 	if (strlen(acct_name) == 0)
 		return -EINVAL;
 
-	list_for_each_entry(nfacct, &net->nfnl_acct_list, head) {
+	list_for_each_entry(nfacct, &nfnl_acct_net->nfnl_acct_list, head) {
 		if (strncmp(nfacct->name, acct_name, NFACCT_NAME_MAX) != 0)
 			continue;
 
@@ -112,7 +125,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
 		nfacct->flags = flags;
 	}
 
-	nla_strlcpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
+	nla_strscpy(nfacct->name, tb[NFACCT_NAME], NFACCT_NAME_MAX);
 
 	if (tb[NFACCT_BYTES]) {
 		atomic64_set(&nfacct->bytes,
@@ -123,7 +136,7 @@ static int nfnl_acct_new(struct net *net, struct sock *nfnl,
 			     be64_to_cpu(nla_get_be64(tb[NFACCT_PKTS])));
 	}
 	refcount_set(&nfacct->refcnt, 1);
-	list_add_tail_rcu(&nfacct->head, &net->nfnl_acct_list);
+	list_add_tail_rcu(&nfacct->head, &nfnl_acct_net->nfnl_acct_list);
 	return 0;
 }
 
@@ -188,6 +201,7 @@ static int
 nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
+	struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net);
 	struct nf_acct *cur, *last;
 	const struct nfacct_filter *filter = cb->data;
 
@@ -199,7 +213,7 @@ nfnl_acct_dump(struct sk_buff *skb, struct netlink_callback *cb)
 		cb->args[1] = 0;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(cur, &net->nfnl_acct_list, head) {
+	list_for_each_entry_rcu(cur, &nfnl_acct_net->nfnl_acct_list, head) {
 		if (last) {
 			if (cur != last)
 				continue;
@@ -269,6 +283,7 @@ static int nfnl_acct_get(struct net *net, struct sock *nfnl,
 			 const struct nlattr * const tb[],
 			 struct netlink_ext_ack *extack)
 {
+	struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net);
 	int ret = -ENOENT;
 	struct nf_acct *cur;
 	char *acct_name;
@@ -288,7 +303,7 @@ static int nfnl_acct_get(struct net *net, struct sock *nfnl,
 		return -EINVAL;
 	acct_name = nla_data(tb[NFACCT_NAME]);
 
-	list_for_each_entry(cur, &net->nfnl_acct_list, head) {
+	list_for_each_entry(cur, &nfnl_acct_net->nfnl_acct_list, head) {
 		struct sk_buff *skb2;
 
 		if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0)
@@ -342,19 +357,20 @@ static int nfnl_acct_del(struct net *net, struct sock *nfnl,
 			 const struct nlattr * const tb[],
 			 struct netlink_ext_ack *extack)
 {
+	struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net);
 	struct nf_acct *cur, *tmp;
 	int ret = -ENOENT;
 	char *acct_name;
 
 	if (!tb[NFACCT_NAME]) {
-		list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head)
+		list_for_each_entry_safe(cur, tmp, &nfnl_acct_net->nfnl_acct_list, head)
 			nfnl_acct_try_del(cur);
 
 		return 0;
 	}
 	acct_name = nla_data(tb[NFACCT_NAME]);
 
-	list_for_each_entry(cur, &net->nfnl_acct_list, head) {
+	list_for_each_entry(cur, &nfnl_acct_net->nfnl_acct_list, head) {
 		if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX) != 0)
 			continue;
 
@@ -402,10 +418,11 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ACCT);
 
 struct nf_acct *nfnl_acct_find_get(struct net *net, const char *acct_name)
 {
+	struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net);
 	struct nf_acct *cur, *acct = NULL;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(cur, &net->nfnl_acct_list, head) {
+	list_for_each_entry_rcu(cur, &nfnl_acct_net->nfnl_acct_list, head) {
 		if (strncmp(cur->name, acct_name, NFACCT_NAME_MAX)!= 0)
 			continue;
 
@@ -488,16 +505,17 @@ EXPORT_SYMBOL_GPL(nfnl_acct_overquota);
 
 static int __net_init nfnl_acct_net_init(struct net *net)
 {
-	INIT_LIST_HEAD(&net->nfnl_acct_list);
+	INIT_LIST_HEAD(&nfnl_acct_pernet(net)->nfnl_acct_list);
 
 	return 0;
 }
 
 static void __net_exit nfnl_acct_net_exit(struct net *net)
 {
+	struct nfnl_acct_net *nfnl_acct_net = nfnl_acct_pernet(net);
 	struct nf_acct *cur, *tmp;
 
-	list_for_each_entry_safe(cur, tmp, &net->nfnl_acct_list, head) {
+	list_for_each_entry_safe(cur, tmp, &nfnl_acct_net->nfnl_acct_list, head) {
 		list_del_rcu(&cur->head);
 
 		if (refcount_dec_and_test(&cur->refcnt))
@@ -508,6 +526,8 @@ static void __net_exit nfnl_acct_net_exit(struct net *net)
 static struct pernet_operations nfnl_acct_ops = {
         .init   = nfnl_acct_net_init,
         .exit   = nfnl_acct_net_exit,
+        .id     = &nfnl_acct_net_id,
+        .size   = sizeof(struct nfnl_acct_net),
 };
 
 static int __init nfnl_acct_init(void)
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index 5b0d0a77379c..0f94fce1d3ed 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -146,7 +146,7 @@ nfnl_cthelper_expect_policy(struct nf_conntrack_expect_policy *expect_policy,
 	    !tb[NFCTH_POLICY_EXPECT_TIMEOUT])
 		return -EINVAL;
 
-	nla_strlcpy(expect_policy->name,
+	nla_strscpy(expect_policy->name,
 		    tb[NFCTH_POLICY_NAME], NF_CT_HELPER_NAME_LEN);
 	expect_policy->max_expected =
 		ntohl(nla_get_be32(tb[NFCTH_POLICY_EXPECT_MAX]));
@@ -233,7 +233,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[],
 	if (ret < 0)
 		goto err1;
 
-	nla_strlcpy(helper->name,
+	nla_strscpy(helper->name,
 		    tb[NFCTH_NAME], NF_CT_HELPER_NAME_LEN);
 	size = ntohl(nla_get_be32(tb[NFCTH_PRIV_DATA_LEN]));
 	if (size > sizeof_field(struct nf_conn_help, data)) {
diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c
index bc37d6c59db4..bbd773d74377 100644
--- a/net/netfilter/nft_bitwise.c
+++ b/net/netfilter/nft_bitwise.c
@@ -163,11 +163,6 @@ static int nft_bitwise_init(const struct nft_ctx *ctx,
 	u32 len;
 	int err;
 
-	if (!tb[NFTA_BITWISE_SREG] ||
-	    !tb[NFTA_BITWISE_DREG] ||
-	    !tb[NFTA_BITWISE_LEN])
-		return -EINVAL;
-
 	err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len);
 	if (err < 0)
 		return err;
@@ -292,9 +287,143 @@ static const struct nft_expr_ops nft_bitwise_ops = {
 	.offload	= nft_bitwise_offload,
 };
 
+static int
+nft_bitwise_extract_u32_data(const struct nlattr * const tb, u32 *out)
+{
+	struct nft_data_desc desc;
+	struct nft_data data;
+	int err = 0;
+
+	err = nft_data_init(NULL, &data, sizeof(data), &desc, tb);
+	if (err < 0)
+		return err;
+
+	if (desc.type != NFT_DATA_VALUE || desc.len != sizeof(u32)) {
+		err = -EINVAL;
+		goto err;
+	}
+	*out = data.data[0];
+err:
+	nft_data_release(&data, desc.type);
+	return err;
+}
+
+static int nft_bitwise_fast_init(const struct nft_ctx *ctx,
+				 const struct nft_expr *expr,
+				 const struct nlattr * const tb[])
+{
+	struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr);
+	int err;
+
+	priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]);
+	err = nft_validate_register_load(priv->sreg, sizeof(u32));
+	if (err < 0)
+		return err;
+
+	priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]);
+	err = nft_validate_register_store(ctx, priv->dreg, NULL,
+					  NFT_DATA_VALUE, sizeof(u32));
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_BITWISE_DATA])
+		return -EINVAL;
+
+	if (!tb[NFTA_BITWISE_MASK] ||
+	    !tb[NFTA_BITWISE_XOR])
+		return -EINVAL;
+
+	err = nft_bitwise_extract_u32_data(tb[NFTA_BITWISE_MASK], &priv->mask);
+	if (err < 0)
+		return err;
+
+	err = nft_bitwise_extract_u32_data(tb[NFTA_BITWISE_XOR], &priv->xor);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int
+nft_bitwise_fast_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_data data;
+
+	if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg))
+		return -1;
+	if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg))
+		return -1;
+	if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(sizeof(u32))))
+		return -1;
+	if (nla_put_be32(skb, NFTA_BITWISE_OP, htonl(NFT_BITWISE_BOOL)))
+		return -1;
+
+	data.data[0] = priv->mask;
+	if (nft_data_dump(skb, NFTA_BITWISE_MASK, &data,
+			  NFT_DATA_VALUE, sizeof(u32)) < 0)
+		return -1;
+
+	data.data[0] = priv->xor;
+	if (nft_data_dump(skb, NFTA_BITWISE_XOR, &data,
+			  NFT_DATA_VALUE, sizeof(u32)) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int nft_bitwise_fast_offload(struct nft_offload_ctx *ctx,
+				    struct nft_flow_rule *flow,
+				    const struct nft_expr *expr)
+{
+	const struct nft_bitwise_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+
+	if (priv->xor || priv->sreg != priv->dreg || reg->len != sizeof(u32))
+		return -EOPNOTSUPP;
+
+	reg->mask.data[0] = priv->mask;
+	return 0;
+}
+
+const struct nft_expr_ops nft_bitwise_fast_ops = {
+	.type		= &nft_bitwise_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_bitwise_fast_expr)),
+	.eval		= NULL, /* inlined */
+	.init		= nft_bitwise_fast_init,
+	.dump		= nft_bitwise_fast_dump,
+	.offload	= nft_bitwise_fast_offload,
+};
+
+static const struct nft_expr_ops *
+nft_bitwise_select_ops(const struct nft_ctx *ctx,
+		       const struct nlattr * const tb[])
+{
+	int err;
+	u32 len;
+
+	if (!tb[NFTA_BITWISE_LEN] ||
+	    !tb[NFTA_BITWISE_SREG] ||
+	    !tb[NFTA_BITWISE_DREG])
+		return ERR_PTR(-EINVAL);
+
+	err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	if (len != sizeof(u32))
+		return &nft_bitwise_ops;
+
+	if (tb[NFTA_BITWISE_OP] &&
+	    ntohl(nla_get_be32(tb[NFTA_BITWISE_OP])) != NFT_BITWISE_BOOL)
+		return &nft_bitwise_ops;
+
+	return &nft_bitwise_fast_ops;
+}
+
 struct nft_expr_type nft_bitwise_type __read_mostly = {
 	.name		= "bitwise",
-	.ops		= &nft_bitwise_ops,
+	.select_ops	= nft_bitwise_select_ops,
 	.policy		= nft_bitwise_policy,
 	.maxattr	= NFTA_BITWISE_MAX,
 	.owner		= THIS_MODULE,
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index c78d01bc02e9..ff8528ad3dc6 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -161,16 +161,49 @@ static unsigned int nft_do_chain_inet(void *priv, struct sk_buff *skb,
 	return nft_do_chain(&pkt, priv);
 }
 
+static unsigned int nft_do_chain_inet_ingress(void *priv, struct sk_buff *skb,
+					      const struct nf_hook_state *state)
+{
+	struct nf_hook_state ingress_state = *state;
+	struct nft_pktinfo pkt;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		/* Original hook is NFPROTO_NETDEV and NF_NETDEV_INGRESS. */
+		ingress_state.pf = NFPROTO_IPV4;
+		ingress_state.hook = NF_INET_INGRESS;
+		nft_set_pktinfo(&pkt, skb, &ingress_state);
+
+		if (nft_set_pktinfo_ipv4_ingress(&pkt, skb) < 0)
+			return NF_DROP;
+		break;
+	case htons(ETH_P_IPV6):
+		ingress_state.pf = NFPROTO_IPV6;
+		ingress_state.hook = NF_INET_INGRESS;
+		nft_set_pktinfo(&pkt, skb, &ingress_state);
+
+		if (nft_set_pktinfo_ipv6_ingress(&pkt, skb) < 0)
+			return NF_DROP;
+		break;
+	default:
+		return NF_ACCEPT;
+	}
+
+	return nft_do_chain(&pkt, priv);
+}
+
 static const struct nft_chain_type nft_chain_filter_inet = {
 	.name		= "filter",
 	.type		= NFT_CHAIN_T_DEFAULT,
 	.family		= NFPROTO_INET,
-	.hook_mask	= (1 << NF_INET_LOCAL_IN) |
+	.hook_mask	= (1 << NF_INET_INGRESS) |
+			  (1 << NF_INET_LOCAL_IN) |
 			  (1 << NF_INET_LOCAL_OUT) |
 			  (1 << NF_INET_FORWARD) |
 			  (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_POST_ROUTING),
 	.hooks		= {
+		[NF_INET_INGRESS]	= nft_do_chain_inet_ingress,
 		[NF_INET_LOCAL_IN]	= nft_do_chain_inet,
 		[NF_INET_LOCAL_OUT]	= nft_do_chain_inet,
 		[NF_INET_FORWARD]	= nft_do_chain_inet,
diff --git a/net/netfilter/nft_chain_route.c b/net/netfilter/nft_chain_route.c
index 8826bbe71136..edd02cda57fc 100644
--- a/net/netfilter/nft_chain_route.c
+++ b/net/netfilter/nft_chain_route.c
@@ -42,7 +42,7 @@ static unsigned int nf_route_table_hook4(void *priv,
 		    iph->daddr != daddr ||
 		    skb->mark != mark ||
 		    iph->tos != tos) {
-			err = ip_route_me_harder(state->net, skb, RTN_UNSPEC);
+			err = ip_route_me_harder(state->net, state->sk, skb, RTN_UNSPEC);
 			if (err < 0)
 				ret = NF_DROP_ERR(err);
 		}
@@ -92,7 +92,7 @@ static unsigned int nf_route_table_hook6(void *priv,
 	     skb->mark != mark ||
 	     ipv6_hdr(skb)->hop_limit != hop_limit ||
 	     flowlabel != *((u32 *)ipv6_hdr(skb)))) {
-		err = nf_ip6_route_me_harder(state->net, skb);
+		err = nf_ip6_route_me_harder(state->net, state->sk, skb);
 		if (err < 0)
 			ret = NF_DROP_ERR(err);
 	}
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 16f4d84599ac..00e563a72d3d 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -123,11 +123,11 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx,
 	u8 *mask = (u8 *)&flow->match.mask;
 	u8 *key = (u8 *)&flow->match.key;
 
-	if (priv->op != NFT_CMP_EQ || reg->len != priv->len)
+	if (priv->op != NFT_CMP_EQ || priv->len > reg->len)
 		return -EOPNOTSUPP;
 
-	memcpy(key + reg->offset, &priv->data, priv->len);
-	memcpy(mask + reg->offset, &reg->mask, priv->len);
+	memcpy(key + reg->offset, &priv->data, reg->len);
+	memcpy(mask + reg->offset, &reg->mask, reg->len);
 
 	flow->match.dissector.used_keys |= BIT(reg->key);
 	flow->match.dissector.offset[reg->key] = reg->base_offset;
@@ -137,7 +137,7 @@ static int __nft_cmp_offload(struct nft_offload_ctx *ctx,
 	    nft_reg_load16(priv->data.data) != ARPHRD_ETHER)
 		return -EOPNOTSUPP;
 
-	nft_offload_update_dependency(ctx, &priv->data, priv->len);
+	nft_offload_update_dependency(ctx, &priv->data, reg->len);
 
 	return 0;
 }
@@ -167,7 +167,6 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 	struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
 	struct nft_data_desc desc;
 	struct nft_data data;
-	u32 mask;
 	int err;
 
 	err = nft_data_init(NULL, &data, sizeof(data), &desc,
@@ -181,10 +180,11 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 		return err;
 
 	desc.len *= BITS_PER_BYTE;
-	mask = nft_cmp_fast_mask(desc.len);
 
-	priv->data = data.data[0] & mask;
+	priv->mask = nft_cmp_fast_mask(desc.len);
+	priv->data = data.data[0] & priv->mask;
 	priv->len  = desc.len;
+	priv->inv  = ntohl(nla_get_be32(tb[NFTA_CMP_OP])) != NFT_CMP_EQ;
 	return 0;
 }
 
@@ -201,7 +201,7 @@ static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx,
 		},
 		.sreg	= priv->sreg,
 		.len	= priv->len / BITS_PER_BYTE,
-		.op	= NFT_CMP_EQ,
+		.op	= priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ,
 	};
 
 	return __nft_cmp_offload(ctx, flow, &cmp);
@@ -210,11 +210,12 @@ static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx,
 static int nft_cmp_fast_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
+	enum nft_cmp_ops op = priv->inv ? NFT_CMP_NEQ : NFT_CMP_EQ;
 	struct nft_data data;
 
 	if (nft_dump_register(skb, NFTA_CMP_SREG, priv->sreg))
 		goto nla_put_failure;
-	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(NFT_CMP_EQ)))
+	if (nla_put_be32(skb, NFTA_CMP_OP, htonl(op)))
 		goto nla_put_failure;
 
 	data.data[0] = priv->data;
@@ -272,7 +273,7 @@ nft_cmp_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 		goto err1;
 	}
 
-	if (desc.len <= sizeof(u32) && op == NFT_CMP_EQ)
+	if (desc.len <= sizeof(u32) && (op == NFT_CMP_EQ || op == NFT_CMP_NEQ))
 		return &nft_cmp_fast_ops;
 
 	return &nft_cmp_ops;
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 322bd674963e..8bcd49f14797 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -177,8 +177,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr,
 	}
 #endif
 	case NFT_CT_ID:
-		if (!nf_ct_is_confirmed(ct))
-			goto err;
 		*dest = nf_ct_get_id(ct);
 		return;
 	default:
@@ -990,7 +988,7 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
 	if (!priv->l4proto)
 		return -ENOENT;
 
-	nla_strlcpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
+	nla_strscpy(name, tb[NFTA_CT_HELPER_NAME], sizeof(name));
 
 	if (tb[NFTA_CT_HELPER_L3PROTO])
 		family = ntohs(nla_get_be16(tb[NFTA_CT_HELPER_L3PROTO]));
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 64ca13a1885b..d164ef9e6843 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -19,11 +19,31 @@ struct nft_dynset {
 	enum nft_registers		sreg_key:8;
 	enum nft_registers		sreg_data:8;
 	bool				invert;
+	bool				expr;
+	u8				num_exprs;
 	u64				timeout;
-	struct nft_expr			*expr;
+	struct nft_expr			*expr_array[NFT_SET_EXPR_MAX];
 	struct nft_set_binding		binding;
 };
 
+static int nft_dynset_expr_setup(const struct nft_dynset *priv,
+				 const struct nft_set_ext *ext)
+{
+	struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext);
+	struct nft_expr *expr;
+	int i;
+
+	for (i = 0; i < priv->num_exprs; i++) {
+		expr = nft_setelem_expr_at(elem_expr, elem_expr->size);
+		if (nft_expr_clone(expr, priv->expr_array[i]) < 0)
+			return -1;
+
+		elem_expr->size += priv->expr_array[i]->ops->size;
+	}
+
+	return 0;
+}
+
 static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr,
 			    struct nft_regs *regs)
 {
@@ -44,8 +64,7 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr,
 		goto err1;
 
 	ext = nft_set_elem_ext(set, elem);
-	if (priv->expr != NULL &&
-	    nft_expr_clone(nft_set_ext_expr(ext), priv->expr) < 0)
+	if (priv->num_exprs && nft_dynset_expr_setup(priv, ext) < 0)
 		goto err2;
 
 	return elem;
@@ -90,6 +109,41 @@ void nft_dynset_eval(const struct nft_expr *expr,
 		regs->verdict.code = NFT_BREAK;
 }
 
+static void nft_dynset_ext_add_expr(struct nft_dynset *priv)
+{
+	u8 size = 0;
+	int i;
+
+	for (i = 0; i < priv->num_exprs; i++)
+		size += priv->expr_array[i]->ops->size;
+
+	nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_EXPRESSIONS,
+			       sizeof(struct nft_set_elem_expr) + size);
+}
+
+static struct nft_expr *
+nft_dynset_expr_alloc(const struct nft_ctx *ctx, const struct nft_set *set,
+		      const struct nlattr *attr, int pos)
+{
+	struct nft_expr *expr;
+	int err;
+
+	expr = nft_set_elem_expr_alloc(ctx, set, attr);
+	if (IS_ERR(expr))
+		return expr;
+
+	if (set->exprs[pos] && set->exprs[pos]->ops != expr->ops) {
+		err = -EOPNOTSUPP;
+		goto err_dynset_expr;
+	}
+
+	return expr;
+
+err_dynset_expr:
+	nft_expr_destroy(ctx, expr);
+	return ERR_PTR(err);
+}
+
 static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = {
 	[NFTA_DYNSET_SET_NAME]	= { .type = NLA_STRING,
 				    .len = NFT_SET_MAXNAMELEN - 1 },
@@ -100,6 +154,7 @@ static const struct nla_policy nft_dynset_policy[NFTA_DYNSET_MAX + 1] = {
 	[NFTA_DYNSET_TIMEOUT]	= { .type = NLA_U64 },
 	[NFTA_DYNSET_EXPR]	= { .type = NLA_NESTED },
 	[NFTA_DYNSET_FLAGS]	= { .type = NLA_U32 },
+	[NFTA_DYNSET_EXPRESSIONS] = { .type = NLA_NESTED },
 };
 
 static int nft_dynset_init(const struct nft_ctx *ctx,
@@ -110,7 +165,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	u8 genmask = nft_genmask_next(ctx->net);
 	struct nft_set *set;
 	u64 timeout;
-	int err;
+	int err, i;
 
 	lockdep_assert_held(&ctx->net->nft.commit_mutex);
 
@@ -121,11 +176,12 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 
 	if (tb[NFTA_DYNSET_FLAGS]) {
 		u32 flags = ntohl(nla_get_be32(tb[NFTA_DYNSET_FLAGS]));
-
-		if (flags & ~NFT_DYNSET_F_INV)
-			return -EINVAL;
+		if (flags & ~(NFT_DYNSET_F_INV | NFT_DYNSET_F_EXPR))
+			return -EOPNOTSUPP;
 		if (flags & NFT_DYNSET_F_INV)
 			priv->invert = true;
+		if (flags & NFT_DYNSET_F_EXPR)
+			priv->expr = true;
 	}
 
 	set = nft_set_lookup_global(ctx->net, ctx->table,
@@ -156,9 +212,11 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	timeout = 0;
 	if (tb[NFTA_DYNSET_TIMEOUT] != NULL) {
 		if (!(set->flags & NFT_SET_TIMEOUT))
-			return -EINVAL;
-		timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64(
-						tb[NFTA_DYNSET_TIMEOUT])));
+			return -EOPNOTSUPP;
+
+		err = nf_msecs_to_jiffies64(tb[NFTA_DYNSET_TIMEOUT], &timeout);
+		if (err)
+			return err;
 	}
 
 	priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]);
@@ -168,7 +226,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 
 	if (tb[NFTA_DYNSET_SREG_DATA] != NULL) {
 		if (!(set->flags & NFT_SET_MAP))
-			return -EINVAL;
+			return -EOPNOTSUPP;
 		if (set->dtype == NFT_DATA_VERDICT)
 			return -EOPNOTSUPP;
 
@@ -179,31 +237,85 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	} else if (set->flags & NFT_SET_MAP)
 		return -EINVAL;
 
-	if (tb[NFTA_DYNSET_EXPR] != NULL) {
-		if (!(set->flags & NFT_SET_EVAL))
-			return -EINVAL;
+	if ((tb[NFTA_DYNSET_EXPR] || tb[NFTA_DYNSET_EXPRESSIONS]) &&
+	    !(set->flags & NFT_SET_EVAL))
+		return -EINVAL;
+
+	if (tb[NFTA_DYNSET_EXPR]) {
+		struct nft_expr *dynset_expr;
+
+		dynset_expr = nft_dynset_expr_alloc(ctx, set,
+						    tb[NFTA_DYNSET_EXPR], 0);
+		if (IS_ERR(dynset_expr))
+			return PTR_ERR(dynset_expr);
+
+		priv->num_exprs++;
+		priv->expr_array[0] = dynset_expr;
+
+		if (set->num_exprs > 1 ||
+		    (set->num_exprs == 1 &&
+		     dynset_expr->ops != set->exprs[0]->ops)) {
+			err = -EOPNOTSUPP;
+			goto err_expr_free;
+		}
+	} else if (tb[NFTA_DYNSET_EXPRESSIONS]) {
+		struct nft_expr *dynset_expr;
+		struct nlattr *tmp;
+		int left;
 
-		priv->expr = nft_set_elem_expr_alloc(ctx, set,
-						     tb[NFTA_DYNSET_EXPR]);
-		if (IS_ERR(priv->expr))
-			return PTR_ERR(priv->expr);
+		if (!priv->expr)
+			return -EINVAL;
 
-		if (set->expr && set->expr->ops != priv->expr->ops) {
+		i = 0;
+		nla_for_each_nested(tmp, tb[NFTA_DYNSET_EXPRESSIONS], left) {
+			if (i == NFT_SET_EXPR_MAX) {
+				err = -E2BIG;
+				goto err_expr_free;
+			}
+			if (nla_type(tmp) != NFTA_LIST_ELEM) {
+				err = -EINVAL;
+				goto err_expr_free;
+			}
+			dynset_expr = nft_dynset_expr_alloc(ctx, set, tmp, i);
+			if (IS_ERR(dynset_expr)) {
+				err = PTR_ERR(dynset_expr);
+				goto err_expr_free;
+			}
+			priv->expr_array[i] = dynset_expr;
+			priv->num_exprs++;
+
+			if (set->num_exprs &&
+			    dynset_expr->ops != set->exprs[i]->ops) {
+				err = -EOPNOTSUPP;
+				goto err_expr_free;
+			}
+			i++;
+		}
+		if (set->num_exprs && set->num_exprs != i) {
 			err = -EOPNOTSUPP;
 			goto err_expr_free;
 		}
+	} else if (set->num_exprs > 0) {
+		err = nft_set_elem_expr_clone(ctx, set, priv->expr_array);
+		if (err < 0)
+			return err;
+
+		priv->num_exprs = set->num_exprs;
 	}
 
 	nft_set_ext_prepare(&priv->tmpl);
 	nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_KEY, set->klen);
 	if (set->flags & NFT_SET_MAP)
 		nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_DATA, set->dlen);
-	if (priv->expr != NULL)
-		nft_set_ext_add_length(&priv->tmpl, NFT_SET_EXT_EXPR,
-				       priv->expr->ops->size);
+
+	if (priv->num_exprs)
+		nft_dynset_ext_add_expr(priv);
+
 	if (set->flags & NFT_SET_TIMEOUT) {
-		if (timeout || set->timeout)
+		if (timeout || set->timeout) {
+			nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT);
 			nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_EXPIRATION);
+		}
 	}
 
 	priv->timeout = timeout;
@@ -219,8 +331,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	return 0;
 
 err_expr_free:
-	if (priv->expr != NULL)
-		nft_expr_destroy(ctx, priv->expr);
+	for (i = 0; i < priv->num_exprs; i++)
+		nft_expr_destroy(ctx, priv->expr_array[i]);
 	return err;
 }
 
@@ -245,9 +357,10 @@ static void nft_dynset_destroy(const struct nft_ctx *ctx,
 			       const struct nft_expr *expr)
 {
 	struct nft_dynset *priv = nft_expr_priv(expr);
+	int i;
 
-	if (priv->expr != NULL)
-		nft_expr_destroy(ctx, priv->expr);
+	for (i = 0; i < priv->num_exprs; i++)
+		nft_expr_destroy(ctx, priv->expr_array[i]);
 
 	nf_tables_destroy_set(ctx, priv->set);
 }
@@ -256,6 +369,7 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_dynset *priv = nft_expr_priv(expr);
 	u32 flags = priv->invert ? NFT_DYNSET_F_INV : 0;
+	int i;
 
 	if (nft_dump_register(skb, NFTA_DYNSET_SREG_KEY, priv->sreg_key))
 		goto nla_put_failure;
@@ -267,11 +381,29 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr)
 	if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name))
 		goto nla_put_failure;
 	if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT,
-			 cpu_to_be64(jiffies_to_msecs(priv->timeout)),
+			 nf_jiffies64_to_msecs(priv->timeout),
 			 NFTA_DYNSET_PAD))
 		goto nla_put_failure;
-	if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr))
-		goto nla_put_failure;
+	if (priv->set->num_exprs == 0) {
+		if (priv->num_exprs == 1) {
+			if (nft_expr_dump(skb, NFTA_DYNSET_EXPR,
+					  priv->expr_array[0]))
+				goto nla_put_failure;
+		} else if (priv->num_exprs > 1) {
+			struct nlattr *nest;
+
+			nest = nla_nest_start_noflag(skb, NFTA_DYNSET_EXPRESSIONS);
+			if (!nest)
+				goto nla_put_failure;
+
+			for (i = 0; i < priv->num_exprs; i++) {
+				if (nft_expr_dump(skb, NFTA_LIST_ELEM,
+						  priv->expr_array[i]))
+					goto nla_put_failure;
+			}
+			nla_nest_end(skb, nest);
+		}
+	}
 	if (nla_put_be32(skb, NFTA_DYNSET_FLAGS, htonl(flags)))
 		goto nla_put_failure;
 	return 0;
diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c
index 3087e23297db..b77985986b24 100644
--- a/net/netfilter/nft_fwd_netdev.c
+++ b/net/netfilter/nft_fwd_netdev.c
@@ -138,6 +138,7 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
 		return;
 
 	skb->dev = dev;
+	skb->tstamp = 0;
 	neigh_xmit(neigh_table, dev, addr, skb);
 out:
 	regs->verdict.code = verdict;
diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
index 57899454a530..a06a46b039c5 100644
--- a/net/netfilter/nft_log.c
+++ b/net/netfilter/nft_log.c
@@ -152,7 +152,7 @@ static int nft_log_init(const struct nft_ctx *ctx,
 		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
 		if (priv->prefix == NULL)
 			return -ENOMEM;
-		nla_strlcpy(priv->prefix, nla, nla_len(nla) + 1);
+		nla_strscpy(priv->prefix, nla, nla_len(nla) + 1);
 	} else {
 		priv->prefix = (char *)nft_log_null_prefix;
 	}
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index b37bd02448d8..bf4b3ad5314c 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -724,22 +724,22 @@ static int nft_meta_get_offload(struct nft_offload_ctx *ctx,
 
 	switch (priv->key) {
 	case NFT_META_PROTOCOL:
-		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto,
-				  sizeof(__u16), reg);
+		NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto,
+					sizeof(__u16), reg);
 		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK);
 		break;
 	case NFT_META_L4PROTO:
-		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
-				  sizeof(__u8), reg);
+		NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
+					sizeof(__u8), reg);
 		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT);
 		break;
 	case NFT_META_IIF:
-		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta,
-				  ingress_ifindex, sizeof(__u32), reg);
+		NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta,
+					ingress_ifindex, sizeof(__u32), reg);
 		break;
 	case NFT_META_IIFTYPE:
-		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_META, meta,
-				  ingress_iftype, sizeof(__u16), reg);
+		NFT_OFFLOAD_MATCH_EXACT(FLOW_DISSECTOR_KEY_META, meta,
+					ingress_iftype, sizeof(__u16), reg);
 		break;
 	default:
 		return -EOPNOTSUPP;
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 7a2e59638499..47d4e0e21651 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -22,6 +22,7 @@
 #include <linux/icmpv6.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <net/sctp/checksum.h>
 
 static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off,
 					 struct vlan_ethhdr *veth)
@@ -164,6 +165,34 @@ nla_put_failure:
 	return -1;
 }
 
+static bool nft_payload_offload_mask(struct nft_offload_reg *reg,
+				     u32 priv_len, u32 field_len)
+{
+	unsigned int remainder, delta, k;
+	struct nft_data mask = {};
+	__be32 remainder_mask;
+
+	if (priv_len == field_len) {
+		memset(&reg->mask, 0xff, priv_len);
+		return true;
+	} else if (priv_len > field_len) {
+		return false;
+	}
+
+	memset(&mask, 0xff, field_len);
+	remainder = priv_len % sizeof(u32);
+	if (remainder) {
+		k = priv_len / sizeof(u32);
+		delta = field_len - priv_len;
+		remainder_mask = htonl(~((1 << (delta * BITS_PER_BYTE)) - 1));
+		mask.data[k] = (__force u32)remainder_mask;
+	}
+
+	memcpy(&reg->mask, &mask, field_len);
+
+	return true;
+}
+
 static int nft_payload_offload_ll(struct nft_offload_ctx *ctx,
 				  struct nft_flow_rule *flow,
 				  const struct nft_payload *priv)
@@ -172,21 +201,21 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct ethhdr, h_source):
-		if (priv->len != ETH_ALEN)
+		if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs,
 				  src, ETH_ALEN, reg);
 		break;
 	case offsetof(struct ethhdr, h_dest):
-		if (priv->len != ETH_ALEN)
+		if (!nft_payload_offload_mask(reg, priv->len, ETH_ALEN))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs,
 				  dst, ETH_ALEN, reg);
 		break;
 	case offsetof(struct ethhdr, h_proto):
-		if (priv->len != sizeof(__be16))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic,
@@ -194,14 +223,14 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx,
 		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK);
 		break;
 	case offsetof(struct vlan_ethhdr, h_vlan_TCI):
-		if (priv->len != sizeof(__be16))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan,
 				  vlan_tci, sizeof(__be16), reg);
 		break;
 	case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto):
-		if (priv->len != sizeof(__be16))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_VLAN, vlan,
@@ -209,7 +238,7 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx,
 		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK);
 		break;
 	case offsetof(struct vlan_ethhdr, h_vlan_TCI) + sizeof(struct vlan_hdr):
-		if (priv->len != sizeof(__be16))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan,
@@ -217,7 +246,7 @@ static int nft_payload_offload_ll(struct nft_offload_ctx *ctx,
 		break;
 	case offsetof(struct vlan_ethhdr, h_vlan_encapsulated_proto) +
 							sizeof(struct vlan_hdr):
-		if (priv->len != sizeof(__be16))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_CVLAN, vlan,
@@ -238,21 +267,25 @@ static int nft_payload_offload_ip(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct iphdr, saddr):
-		if (priv->len != sizeof(struct in_addr))
+		if (!nft_payload_offload_mask(reg, priv->len,
+					      sizeof(struct in_addr)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src,
 				  sizeof(struct in_addr), reg);
+		nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
 		break;
 	case offsetof(struct iphdr, daddr):
-		if (priv->len != sizeof(struct in_addr))
+		if (!nft_payload_offload_mask(reg, priv->len,
+					      sizeof(struct in_addr)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst,
 				  sizeof(struct in_addr), reg);
+		nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV4_ADDRS);
 		break;
 	case offsetof(struct iphdr, protocol):
-		if (priv->len != sizeof(__u8))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
@@ -274,21 +307,25 @@ static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct ipv6hdr, saddr):
-		if (priv->len != sizeof(struct in6_addr))
+		if (!nft_payload_offload_mask(reg, priv->len,
+					      sizeof(struct in6_addr)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src,
 				  sizeof(struct in6_addr), reg);
+		nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
 		break;
 	case offsetof(struct ipv6hdr, daddr):
-		if (priv->len != sizeof(struct in6_addr))
+		if (!nft_payload_offload_mask(reg, priv->len,
+					      sizeof(struct in6_addr)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst,
 				  sizeof(struct in6_addr), reg);
+		nft_flow_rule_set_addr_type(flow, FLOW_DISSECTOR_KEY_IPV6_ADDRS);
 		break;
 	case offsetof(struct ipv6hdr, nexthdr):
-		if (priv->len != sizeof(__u8))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__u8)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
@@ -330,14 +367,14 @@ static int nft_payload_offload_tcp(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct tcphdr, source):
-		if (priv->len != sizeof(__be16))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src,
 				  sizeof(__be16), reg);
 		break;
 	case offsetof(struct tcphdr, dest):
-		if (priv->len != sizeof(__be16))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst,
@@ -358,14 +395,14 @@ static int nft_payload_offload_udp(struct nft_offload_ctx *ctx,
 
 	switch (priv->offset) {
 	case offsetof(struct udphdr, source):
-		if (priv->len != sizeof(__be16))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src,
 				  sizeof(__be16), reg);
 		break;
 	case offsetof(struct udphdr, dest):
-		if (priv->len != sizeof(__be16))
+		if (!nft_payload_offload_mask(reg, priv->len, sizeof(__be16)))
 			return -EOPNOTSUPP;
 
 		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst,
@@ -484,6 +521,19 @@ static int nft_payload_l4csum_offset(const struct nft_pktinfo *pkt,
 	return 0;
 }
 
+static int nft_payload_csum_sctp(struct sk_buff *skb, int offset)
+{
+	struct sctphdr *sh;
+
+	if (skb_ensure_writable(skb, offset + sizeof(*sh)))
+		return -1;
+
+	sh = (struct sctphdr *)(skb->data + offset);
+	sh->checksum = sctp_compute_cksum(skb, offset);
+	skb->ip_summed = CHECKSUM_UNNECESSARY;
+	return 0;
+}
+
 static int nft_payload_l4csum_update(const struct nft_pktinfo *pkt,
 				     struct sk_buff *skb,
 				     __wsum fsum, __wsum tsum)
@@ -587,6 +637,13 @@ static void nft_payload_set_eval(const struct nft_expr *expr,
 	    skb_store_bits(skb, offset, src, priv->len) < 0)
 		goto err;
 
+	if (priv->csum_type == NFT_PAYLOAD_CSUM_SCTP &&
+	    pkt->tprot == IPPROTO_SCTP &&
+	    skb->ip_summed != CHECKSUM_PARTIAL) {
+		if (nft_payload_csum_sctp(skb, pkt->xt.thoff))
+			goto err;
+	}
+
 	return;
 err:
 	regs->verdict.code = NFT_BREAK;
@@ -623,6 +680,13 @@ static int nft_payload_set_init(const struct nft_ctx *ctx,
 	case NFT_PAYLOAD_CSUM_NONE:
 	case NFT_PAYLOAD_CSUM_INET:
 		break;
+	case NFT_PAYLOAD_CSUM_SCTP:
+		if (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER)
+			return -EINVAL;
+
+		if (priv->csum_offset != offsetof(struct sctphdr, checksum))
+			return -EINVAL;
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/net/netfilter/nft_reject.c b/net/netfilter/nft_reject.c
index 61fb7e8afbf0..927ff8459bd9 100644
--- a/net/netfilter/nft_reject.c
+++ b/net/netfilter/nft_reject.c
@@ -40,6 +40,7 @@ int nft_reject_init(const struct nft_ctx *ctx,
 		    const struct nlattr * const tb[])
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
+	int icmp_code;
 
 	if (tb[NFTA_REJECT_TYPE] == NULL)
 		return -EINVAL;
@@ -47,9 +48,17 @@ int nft_reject_init(const struct nft_ctx *ctx,
 	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
 	switch (priv->type) {
 	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
 		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
 			return -EINVAL;
-		priv->icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+
+		icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
+		if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
+		    icmp_code > NFT_REJECT_ICMPX_MAX)
+			return -EINVAL;
+
+		priv->icmp_code = icmp_code;
+		break;
 	case NFT_REJECT_TCP_RST:
 		break;
 	default:
@@ -69,6 +78,7 @@ int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
 
 	switch (priv->type) {
 	case NFT_REJECT_ICMP_UNREACH:
+	case NFT_REJECT_ICMPX_UNREACH:
 		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
 			goto nla_put_failure;
 		break;
diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c
index cf8f2646e93c..95090186ee90 100644
--- a/net/netfilter/nft_reject_inet.c
+++ b/net/netfilter/nft_reject_inet.c
@@ -28,7 +28,8 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
 					nft_hook(pkt));
 			break;
 		case NFT_REJECT_TCP_RST:
-			nf_send_reset(nft_net(pkt), pkt->skb, nft_hook(pkt));
+			nf_send_reset(nft_net(pkt), pkt->xt.state->sk,
+				      pkt->skb, nft_hook(pkt));
 			break;
 		case NFT_REJECT_ICMPX_UNREACH:
 			nf_send_unreach(pkt->skb,
@@ -44,7 +45,8 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
 					 priv->icmp_code, nft_hook(pkt));
 			break;
 		case NFT_REJECT_TCP_RST:
-			nf_send_reset6(nft_net(pkt), pkt->skb, nft_hook(pkt));
+			nf_send_reset6(nft_net(pkt), pkt->xt.state->sk,
+				       pkt->skb, nft_hook(pkt));
 			break;
 		case NFT_REJECT_ICMPX_UNREACH:
 			nf_send_unreach6(nft_net(pkt), pkt->skb,
@@ -58,60 +60,16 @@ static void nft_reject_inet_eval(const struct nft_expr *expr,
 	regs->verdict.code = NF_DROP;
 }
 
-static int nft_reject_inet_init(const struct nft_ctx *ctx,
-				const struct nft_expr *expr,
-				const struct nlattr * const tb[])
+static int nft_reject_inet_validate(const struct nft_ctx *ctx,
+				    const struct nft_expr *expr,
+				    const struct nft_data **data)
 {
-	struct nft_reject *priv = nft_expr_priv(expr);
-	int icmp_code;
-
-	if (tb[NFTA_REJECT_TYPE] == NULL)
-		return -EINVAL;
-
-	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
-	switch (priv->type) {
-	case NFT_REJECT_ICMP_UNREACH:
-	case NFT_REJECT_ICMPX_UNREACH:
-		if (tb[NFTA_REJECT_ICMP_CODE] == NULL)
-			return -EINVAL;
-
-		icmp_code = nla_get_u8(tb[NFTA_REJECT_ICMP_CODE]);
-		if (priv->type == NFT_REJECT_ICMPX_UNREACH &&
-		    icmp_code > NFT_REJECT_ICMPX_MAX)
-			return -EINVAL;
-
-		priv->icmp_code = icmp_code;
-		break;
-	case NFT_REJECT_TCP_RST:
-		break;
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static int nft_reject_inet_dump(struct sk_buff *skb,
-				const struct nft_expr *expr)
-{
-	const struct nft_reject *priv = nft_expr_priv(expr);
-
-	if (nla_put_be32(skb, NFTA_REJECT_TYPE, htonl(priv->type)))
-		goto nla_put_failure;
-
-	switch (priv->type) {
-	case NFT_REJECT_ICMP_UNREACH:
-	case NFT_REJECT_ICMPX_UNREACH:
-		if (nla_put_u8(skb, NFTA_REJECT_ICMP_CODE, priv->icmp_code))
-			goto nla_put_failure;
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-
-nla_put_failure:
-	return -1;
+	return nft_chain_validate_hooks(ctx->chain,
+					(1 << NF_INET_LOCAL_IN) |
+					(1 << NF_INET_FORWARD) |
+					(1 << NF_INET_LOCAL_OUT) |
+					(1 << NF_INET_PRE_ROUTING) |
+					(1 << NF_INET_INGRESS));
 }
 
 static struct nft_expr_type nft_reject_inet_type;
@@ -119,9 +77,9 @@ static const struct nft_expr_ops nft_reject_inet_ops = {
 	.type		= &nft_reject_inet_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
 	.eval		= nft_reject_inet_eval,
-	.init		= nft_reject_inet_init,
-	.dump		= nft_reject_inet_dump,
-	.validate	= nft_reject_validate,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+	.validate	= nft_reject_inet_validate,
 };
 
 static struct nft_expr_type nft_reject_inet_type __read_mostly = {
diff --git a/net/netfilter/nft_reject_netdev.c b/net/netfilter/nft_reject_netdev.c
new file mode 100644
index 000000000000..d89f68754f42
--- /dev/null
+++ b/net/netfilter/nft_reject_netdev.c
@@ -0,0 +1,189 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020 Laura Garcia Liebana <nevola@gmail.com>
+ * Copyright (c) 2020 Jose M. Guisado <guigom@riseup.net>
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
+
+static void nft_reject_queue_xmit(struct sk_buff *nskb, struct sk_buff *oldskb)
+{
+	dev_hard_header(nskb, nskb->dev, ntohs(oldskb->protocol),
+			eth_hdr(oldskb)->h_source, eth_hdr(oldskb)->h_dest,
+			nskb->len);
+	dev_queue_xmit(nskb);
+}
+
+static void nft_reject_netdev_send_v4_tcp_reset(struct net *net,
+						struct sk_buff *oldskb,
+						const struct net_device *dev,
+						int hook)
+{
+	struct sk_buff *nskb;
+
+	nskb = nf_reject_skb_v4_tcp_reset(net, oldskb, dev, hook);
+	if (!nskb)
+		return;
+
+	nft_reject_queue_xmit(nskb, oldskb);
+}
+
+static void nft_reject_netdev_send_v4_unreach(struct net *net,
+					      struct sk_buff *oldskb,
+					      const struct net_device *dev,
+					      int hook, u8 code)
+{
+	struct sk_buff *nskb;
+
+	nskb = nf_reject_skb_v4_unreach(net, oldskb, dev, hook, code);
+	if (!nskb)
+		return;
+
+	nft_reject_queue_xmit(nskb, oldskb);
+}
+
+static void nft_reject_netdev_send_v6_tcp_reset(struct net *net,
+						struct sk_buff *oldskb,
+						const struct net_device *dev,
+						int hook)
+{
+	struct sk_buff *nskb;
+
+	nskb = nf_reject_skb_v6_tcp_reset(net, oldskb, dev, hook);
+	if (!nskb)
+		return;
+
+	nft_reject_queue_xmit(nskb, oldskb);
+}
+
+
+static void nft_reject_netdev_send_v6_unreach(struct net *net,
+					      struct sk_buff *oldskb,
+					      const struct net_device *dev,
+					      int hook, u8 code)
+{
+	struct sk_buff *nskb;
+
+	nskb = nf_reject_skb_v6_unreach(net, oldskb, dev, hook, code);
+	if (!nskb)
+		return;
+
+	nft_reject_queue_xmit(nskb, oldskb);
+}
+
+static void nft_reject_netdev_eval(const struct nft_expr *expr,
+				   struct nft_regs *regs,
+				   const struct nft_pktinfo *pkt)
+{
+	struct ethhdr *eth = eth_hdr(pkt->skb);
+	struct nft_reject *priv = nft_expr_priv(expr);
+	const unsigned char *dest = eth->h_dest;
+
+	if (is_broadcast_ether_addr(dest) ||
+	    is_multicast_ether_addr(dest))
+		goto out;
+
+	switch (eth->h_proto) {
+	case htons(ETH_P_IP):
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nft_reject_netdev_send_v4_unreach(nft_net(pkt), pkt->skb,
+							  nft_in(pkt),
+							  nft_hook(pkt),
+							  priv->icmp_code);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nft_reject_netdev_send_v4_tcp_reset(nft_net(pkt), pkt->skb,
+							    nft_in(pkt),
+							    nft_hook(pkt));
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nft_reject_netdev_send_v4_unreach(nft_net(pkt), pkt->skb,
+							  nft_in(pkt),
+							  nft_hook(pkt),
+							  nft_reject_icmp_code(priv->icmp_code));
+			break;
+		}
+		break;
+	case htons(ETH_P_IPV6):
+		switch (priv->type) {
+		case NFT_REJECT_ICMP_UNREACH:
+			nft_reject_netdev_send_v6_unreach(nft_net(pkt), pkt->skb,
+							  nft_in(pkt),
+							  nft_hook(pkt),
+							  priv->icmp_code);
+			break;
+		case NFT_REJECT_TCP_RST:
+			nft_reject_netdev_send_v6_tcp_reset(nft_net(pkt), pkt->skb,
+							    nft_in(pkt),
+							    nft_hook(pkt));
+			break;
+		case NFT_REJECT_ICMPX_UNREACH:
+			nft_reject_netdev_send_v6_unreach(nft_net(pkt), pkt->skb,
+							  nft_in(pkt),
+							  nft_hook(pkt),
+							  nft_reject_icmpv6_code(priv->icmp_code));
+			break;
+		}
+		break;
+	default:
+		/* No explicit way to reject this protocol, drop it. */
+		break;
+	}
+out:
+	regs->verdict.code = NF_DROP;
+}
+
+static int nft_reject_netdev_validate(const struct nft_ctx *ctx,
+				      const struct nft_expr *expr,
+				      const struct nft_data **data)
+{
+	return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS));
+}
+
+static struct nft_expr_type nft_reject_netdev_type;
+static const struct nft_expr_ops nft_reject_netdev_ops = {
+	.type		= &nft_reject_netdev_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.eval		= nft_reject_netdev_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+	.validate	= nft_reject_netdev_validate,
+};
+
+static struct nft_expr_type nft_reject_netdev_type __read_mostly = {
+	.family		= NFPROTO_NETDEV,
+	.name		= "reject",
+	.ops		= &nft_reject_netdev_ops,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_reject_netdev_module_init(void)
+{
+	return nft_register_expr(&nft_reject_netdev_type);
+}
+
+static void __exit nft_reject_netdev_module_exit(void)
+{
+	nft_unregister_expr(&nft_reject_netdev_type);
+}
+
+module_init(nft_reject_netdev_module_init);
+module_exit(nft_reject_netdev_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Laura Garcia Liebana <nevola@gmail.com>");
+MODULE_AUTHOR("Jose M. Guisado <guigom@riseup.net>");
+MODULE_DESCRIPTION("Reject packets from netdev via nftables");
+MODULE_ALIAS_NFT_AF_EXPR(5, "reject");
diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 4d3f147e8d8d..bf618b7ec1ae 100644
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -293,6 +293,22 @@ cont:
 	rhashtable_walk_exit(&hti);
 }
 
+static bool nft_rhash_expr_needs_gc_run(const struct nft_set *set,
+					struct nft_set_ext *ext)
+{
+	struct nft_set_elem_expr *elem_expr = nft_set_ext_expr(ext);
+	struct nft_expr *expr;
+	u32 size;
+
+	nft_setelem_expr_foreach(expr, elem_expr, size) {
+		if (expr->ops->gc &&
+		    expr->ops->gc(read_pnet(&set->net), expr))
+			return true;
+	}
+
+	return false;
+}
+
 static void nft_rhash_gc(struct work_struct *work)
 {
 	struct nft_set *set;
@@ -314,16 +330,13 @@ static void nft_rhash_gc(struct work_struct *work)
 			continue;
 		}
 
-		if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPR)) {
-			struct nft_expr *expr = nft_set_ext_expr(&he->ext);
+		if (nft_set_ext_exists(&he->ext, NFT_SET_EXT_EXPRESSIONS) &&
+		    nft_rhash_expr_needs_gc_run(set, &he->ext))
+			goto needs_gc_run;
 
-			if (expr->ops->gc &&
-			    expr->ops->gc(read_pnet(&set->net), expr))
-				goto gc;
-		}
 		if (!nft_set_elem_expired(&he->ext))
 			continue;
-gc:
+needs_gc_run:
 		if (nft_set_elem_mark_busy(&he->ext))
 			continue;
 
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 637ce3e8c575..a28aca5124ce 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -14,6 +14,25 @@ struct nft_socket {
 	};
 };
 
+static void nft_socket_wildcard(const struct nft_pktinfo *pkt,
+				struct nft_regs *regs, struct sock *sk,
+				u32 *dest)
+{
+	switch (nft_pf(pkt)) {
+	case NFPROTO_IPV4:
+		nft_reg_store8(dest, inet_sk(sk)->inet_rcv_saddr == 0);
+		break;
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
+	case NFPROTO_IPV6:
+		nft_reg_store8(dest, ipv6_addr_any(&sk->sk_v6_rcv_saddr));
+		break;
+#endif
+	default:
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+}
+
 static void nft_socket_eval(const struct nft_expr *expr,
 			    struct nft_regs *regs,
 			    const struct nft_pktinfo *pkt)
@@ -59,6 +78,13 @@ static void nft_socket_eval(const struct nft_expr *expr,
 			return;
 		}
 		break;
+	case NFT_SOCKET_WILDCARD:
+		if (!sk_fullsock(sk)) {
+			regs->verdict.code = NFT_BREAK;
+			return;
+		}
+		nft_socket_wildcard(pkt, regs, sk, dest);
+		break;
 	default:
 		WARN_ON(1);
 		regs->verdict.code = NFT_BREAK;
@@ -97,6 +123,7 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 	priv->key = ntohl(nla_get_u32(tb[NFTA_SOCKET_KEY]));
 	switch(priv->key) {
 	case NFT_SOCKET_TRANSPARENT:
+	case NFT_SOCKET_WILDCARD:
 		len = sizeof(u8);
 		break;
 	case NFT_SOCKET_MARK:
diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c
index cedf47ab3c6f..2182d361e273 100644
--- a/net/netfilter/utils.c
+++ b/net/netfilter/utils.c
@@ -191,8 +191,8 @@ static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry
 		      skb->mark == rt_info->mark &&
 		      iph->daddr == rt_info->daddr &&
 		      iph->saddr == rt_info->saddr))
-			return ip_route_me_harder(entry->state.net, skb,
-						  RTN_UNSPEC);
+			return ip_route_me_harder(entry->state.net, entry->state.sk,
+						  skb, RTN_UNSPEC);
 	}
 #endif
 	return 0;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index af22dbe85e2c..acce622582e3 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1349,6 +1349,14 @@ struct xt_counters *xt_counters_alloc(unsigned int counters)
 }
 EXPORT_SYMBOL(xt_counters_alloc);
 
+struct xt_table_info
+*xt_table_get_private_protected(const struct xt_table *table)
+{
+	return rcu_dereference_protected(table->private,
+					 mutex_is_locked(&xt[table->af].mutex));
+}
+EXPORT_SYMBOL(xt_table_get_private_protected);
+
 struct xt_table_info *
 xt_replace_table(struct xt_table *table,
 	      unsigned int num_counters,
@@ -1356,7 +1364,6 @@ xt_replace_table(struct xt_table *table,
 	      int *error)
 {
 	struct xt_table_info *private;
-	unsigned int cpu;
 	int ret;
 
 	ret = xt_jumpstack_alloc(newinfo);
@@ -1366,47 +1373,20 @@ xt_replace_table(struct xt_table *table,
 	}
 
 	/* Do the substitution. */
-	local_bh_disable();
-	private = table->private;
+	private = xt_table_get_private_protected(table);
 
 	/* Check inside lock: is the old number correct? */
 	if (num_counters != private->number) {
 		pr_debug("num_counters != table->private->number (%u/%u)\n",
 			 num_counters, private->number);
-		local_bh_enable();
 		*error = -EAGAIN;
 		return NULL;
 	}
 
 	newinfo->initial_entries = private->initial_entries;
-	/*
-	 * Ensure contents of newinfo are visible before assigning to
-	 * private.
-	 */
-	smp_wmb();
-	table->private = newinfo;
-
-	/* make sure all cpus see new ->private value */
-	smp_wmb();
 
-	/*
-	 * Even though table entries have now been swapped, other CPU's
-	 * may still be using the old entries...
-	 */
-	local_bh_enable();
-
-	/* ... so wait for even xt_recseq on all cpus */
-	for_each_possible_cpu(cpu) {
-		seqcount_t *s = &per_cpu(xt_recseq, cpu);
-		u32 seq = raw_read_seqcount(s);
-
-		if (seq & 1) {
-			do {
-				cond_resched();
-				cpu_relax();
-			} while (seq == raw_read_seqcount(s));
-		}
-	}
+	rcu_assign_pointer(table->private, newinfo);
+	synchronize_rcu();
 
 	audit_log_nfcfg(table->name, table->af, private->number,
 			!private->number ? AUDIT_XT_OP_REGISTER :
@@ -1442,12 +1422,12 @@ struct xt_table *xt_register_table(struct net *net,
 	}
 
 	/* Simplifies replace_table code. */
-	table->private = bootstrap;
+	rcu_assign_pointer(table->private, bootstrap);
 
 	if (!xt_replace_table(table, 0, newinfo, &ret))
 		goto unlock;
 
-	private = table->private;
+	private = xt_table_get_private_protected(table);
 	pr_debug("table->private->number = %u\n", private->number);
 
 	/* save number of initial entries */
@@ -1470,7 +1450,8 @@ void *xt_unregister_table(struct xt_table *table)
 	struct xt_table_info *private;
 
 	mutex_lock(&xt[table->af].mutex);
-	private = table->private;
+	private = xt_table_get_private_protected(table);
+	RCU_INIT_POINTER(table->private, NULL);
 	list_del(&table->list);
 	mutex_unlock(&xt[table->af].mutex);
 	audit_log_nfcfg(table->name, table->af, private->number,
diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c
index 713fb38541df..8928ec56c388 100644
--- a/net/netfilter/xt_HMARK.c
+++ b/net/netfilter/xt_HMARK.c
@@ -276,7 +276,7 @@ hmark_pkt_set_htuple_ipv4(const struct sk_buff *skb, struct hmark_tuple *t,
 		return 0;
 
 	/* follow-up fragments don't contain ports, skip all fragments */
-	if (ip->frag_off & htons(IP_MF | IP_OFFSET))
+	if (ip_is_fragment(ip))
 		return 0;
 
 	hmark_set_tuple_ports(skb, (ip->ihl * 4) + nhoff, t, info);
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index 37253d399c6b..0d5c422f8745 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -115,6 +115,9 @@ static int xt_rateest_tg_checkentry(const struct xt_tgchk_param *par)
 	} cfg;
 	int ret;
 
+	if (strnlen(info->name, sizeof(est->name)) >= sizeof(est->name))
+		return -ENAMETOOLONG;
+
 	net_get_random_once(&jhash_rnd, sizeof(jhash_rnd));
 
 	mutex_lock(&xn->hash_lock);
diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c
index a97c2259bbc8..7c6bf1c16813 100644
--- a/net/netfilter/xt_nfacct.c
+++ b/net/netfilter/xt_nfacct.c
@@ -27,7 +27,7 @@ static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par)
 
 	overquota = nfnl_acct_overquota(xt_net(par), info->nfacct);
 
-	return overquota == NFACCT_UNDERQUOTA ? false : true;
+	return overquota != NFACCT_UNDERQUOTA;
 }
 
 static int
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 606411869698..0446307516cd 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -152,7 +152,8 @@ static void recent_entry_remove(struct recent_table *t, struct recent_entry *e)
 /*
  * Drop entries with timestamps older then 'time'.
  */
-static void recent_entry_reap(struct recent_table *t, unsigned long time)
+static void recent_entry_reap(struct recent_table *t, unsigned long time,
+			      struct recent_entry *working, bool update)
 {
 	struct recent_entry *e;
 
@@ -162,6 +163,12 @@ static void recent_entry_reap(struct recent_table *t, unsigned long time)
 	e = list_entry(t->lru_list.next, struct recent_entry, lru_list);
 
 	/*
+	 * Do not reap the entry which are going to be updated.
+	 */
+	if (e == working && update)
+		return;
+
+	/*
 	 * The last time stamp is the most recent.
 	 */
 	if (time_after(time, e->stamps[e->index-1]))
@@ -303,7 +310,8 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par)
 
 		/* info->seconds must be non-zero */
 		if (info->check_set & XT_RECENT_REAP)
-			recent_entry_reap(t, time);
+			recent_entry_reap(t, time, e,
+				info->check_set & XT_RECENT_UPDATE && ret);
 	}
 
 	if (info->check_set & XT_RECENT_SET ||
diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c
index 249da67d50a2..f28c8947c730 100644
--- a/net/netlabel/netlabel_calipso.c
+++ b/net/netlabel/netlabel_calipso.c
@@ -304,7 +304,7 @@ static int netlbl_calipso_remove(struct sk_buff *skb, struct genl_info *info)
 /* NetLabel Generic NETLINK Command Definitions
  */
 
-static const struct genl_ops netlbl_calipso_ops[] = {
+static const struct genl_small_ops netlbl_calipso_ops[] = {
 	{
 	.cmd = NLBL_CALIPSO_C_ADD,
 	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -342,8 +342,8 @@ static struct genl_family netlbl_calipso_gnl_family __ro_after_init = {
 	.maxattr = NLBL_CALIPSO_A_MAX,
 	.policy = calipso_genl_policy,
 	.module = THIS_MODULE,
-	.ops = netlbl_calipso_ops,
-	.n_ops = ARRAY_SIZE(netlbl_calipso_ops),
+	.small_ops = netlbl_calipso_ops,
+	.n_small_ops = ARRAY_SIZE(netlbl_calipso_ops),
 };
 
 /* NetLabel Generic NETLINK Protocol Functions
@@ -366,6 +366,7 @@ static const struct netlbl_calipso_ops *calipso_ops;
 
 /**
  * netlbl_calipso_ops_register - Register the CALIPSO operations
+ * @ops: ops to register
  *
  * Description:
  * Register the CALIPSO packet engine operations.
@@ -426,7 +427,7 @@ void calipso_doi_free(struct calipso_doi *doi_def)
 /**
  * calipso_doi_remove - Remove an existing DOI from the CALIPSO protocol engine
  * @doi: the DOI value
- * @audit_secid: the LSM secid to use in the audit message
+ * @audit_info: NetLabel audit information
  *
  * Description:
  * Removes a DOI definition from the CALIPSO engine.  The NetLabel routines will
@@ -595,7 +596,7 @@ int calipso_req_setattr(struct request_sock *req,
 
 /**
  * calipso_req_delattr - Delete the CALIPSO option from a request socket
- * @reg: the request socket
+ * @req: the request socket
  *
  * Description:
  * Removes the CALIPSO option from a request socket, if present.
diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c
index 0f16080b87cb..726dda95934c 100644
--- a/net/netlabel/netlabel_cipso_v4.c
+++ b/net/netlabel/netlabel_cipso_v4.c
@@ -724,7 +724,7 @@ static int netlbl_cipsov4_remove(struct sk_buff *skb, struct genl_info *info)
  * NetLabel Generic NETLINK Command Definitions
  */
 
-static const struct genl_ops netlbl_cipsov4_ops[] = {
+static const struct genl_small_ops netlbl_cipsov4_ops[] = {
 	{
 	.cmd = NLBL_CIPSOV4_C_ADD,
 	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -762,8 +762,8 @@ static struct genl_family netlbl_cipsov4_gnl_family __ro_after_init = {
 	.maxattr = NLBL_CIPSOV4_A_MAX,
 	.policy = netlbl_cipsov4_genl_policy,
 	.module = THIS_MODULE,
-	.ops = netlbl_cipsov4_ops,
-	.n_ops = ARRAY_SIZE(netlbl_cipsov4_ops),
+	.small_ops = netlbl_cipsov4_ops,
+	.n_small_ops = ARRAY_SIZE(netlbl_cipsov4_ops),
 };
 
 /*
diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c
index f73a8382c275..dc8c39f51f7d 100644
--- a/net/netlabel/netlabel_domainhash.c
+++ b/net/netlabel/netlabel_domainhash.c
@@ -612,9 +612,8 @@ int netlbl_domhsh_remove_entry(struct netlbl_dom_map *entry,
 	audit_buf = netlbl_audit_start_common(AUDIT_MAC_MAP_DEL, audit_info);
 	if (audit_buf != NULL) {
 		audit_log_format(audit_buf,
-				 " nlbl_domain=%s res=%u",
-				 entry->domain ? entry->domain : "(default)",
-				 ret_val == 0 ? 1 : 0);
+				 " nlbl_domain=%s res=1",
+				 entry->domain ? entry->domain : "(default)");
 		audit_log_end(audit_buf);
 	}
 
diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c
index e7a25fbfaf8b..df1b41ed73fd 100644
--- a/net/netlabel/netlabel_mgmt.c
+++ b/net/netlabel/netlabel_mgmt.c
@@ -95,7 +95,7 @@ static int netlbl_mgmt_add_common(struct genl_info *info,
 			ret_val = -ENOMEM;
 			goto add_free_entry;
 		}
-		nla_strlcpy(entry->domain,
+		nla_strscpy(entry->domain,
 			    info->attrs[NLBL_MGMT_A_DOMAIN], tmp_size);
 	}
 
@@ -757,7 +757,7 @@ version_failure:
  * NetLabel Generic NETLINK Command Definitions
  */
 
-static const struct genl_ops netlbl_mgmt_genl_ops[] = {
+static const struct genl_small_ops netlbl_mgmt_genl_ops[] = {
 	{
 	.cmd = NLBL_MGMT_C_ADD,
 	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -823,8 +823,8 @@ static struct genl_family netlbl_mgmt_gnl_family __ro_after_init = {
 	.maxattr = NLBL_MGMT_A_MAX,
 	.policy = netlbl_mgmt_genl_policy,
 	.module = THIS_MODULE,
-	.ops = netlbl_mgmt_genl_ops,
-	.n_ops = ARRAY_SIZE(netlbl_mgmt_genl_ops),
+	.small_ops = netlbl_mgmt_genl_ops,
+	.n_small_ops = ARRAY_SIZE(netlbl_mgmt_genl_ops),
 };
 
 /*
diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c
index 77bb1bb22c3b..ccb491642811 100644
--- a/net/netlabel/netlabel_unlabeled.c
+++ b/net/netlabel/netlabel_unlabeled.c
@@ -1166,12 +1166,13 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb,
 	struct netlbl_unlhsh_walk_arg cb_arg;
 	u32 skip_bkt = cb->args[0];
 	u32 skip_chain = cb->args[1];
-	u32 iter_bkt;
-	u32 iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0;
+	u32 skip_addr4 = cb->args[2];
+	u32 iter_bkt, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0;
 	struct netlbl_unlhsh_iface *iface;
 	struct list_head *iter_list;
 	struct netlbl_af4list *addr4;
 #if IS_ENABLED(CONFIG_IPV6)
+	u32 skip_addr6 = cb->args[3];
 	struct netlbl_af6list *addr6;
 #endif
 
@@ -1182,7 +1183,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb,
 	rcu_read_lock();
 	for (iter_bkt = skip_bkt;
 	     iter_bkt < rcu_dereference(netlbl_unlhsh)->size;
-	     iter_bkt++, iter_chain = 0, iter_addr4 = 0, iter_addr6 = 0) {
+	     iter_bkt++) {
 		iter_list = &rcu_dereference(netlbl_unlhsh)->tbl[iter_bkt];
 		list_for_each_entry_rcu(iface, iter_list, list) {
 			if (!iface->valid ||
@@ -1190,7 +1191,7 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb,
 				continue;
 			netlbl_af4list_foreach_rcu(addr4,
 						   &iface->addr4_list) {
-				if (iter_addr4++ < cb->args[2])
+				if (iter_addr4++ < skip_addr4)
 					continue;
 				if (netlbl_unlabel_staticlist_gen(
 					      NLBL_UNLABEL_C_STATICLIST,
@@ -1203,10 +1204,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb,
 					goto unlabel_staticlist_return;
 				}
 			}
+			iter_addr4 = 0;
+			skip_addr4 = 0;
 #if IS_ENABLED(CONFIG_IPV6)
 			netlbl_af6list_foreach_rcu(addr6,
 						   &iface->addr6_list) {
-				if (iter_addr6++ < cb->args[3])
+				if (iter_addr6++ < skip_addr6)
 					continue;
 				if (netlbl_unlabel_staticlist_gen(
 					      NLBL_UNLABEL_C_STATICLIST,
@@ -1219,8 +1222,12 @@ static int netlbl_unlabel_staticlist(struct sk_buff *skb,
 					goto unlabel_staticlist_return;
 				}
 			}
+			iter_addr6 = 0;
+			skip_addr6 = 0;
 #endif /* IPv6 */
 		}
+		iter_chain = 0;
+		skip_chain = 0;
 	}
 
 unlabel_staticlist_return:
@@ -1301,7 +1308,7 @@ unlabel_staticlistdef_return:
  * NetLabel Generic NETLINK Command Definitions
  */
 
-static const struct genl_ops netlbl_unlabel_genl_ops[] = {
+static const struct genl_small_ops netlbl_unlabel_genl_ops[] = {
 	{
 	.cmd = NLBL_UNLABEL_C_STATICADD,
 	.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -1367,8 +1374,8 @@ static struct genl_family netlbl_unlabel_gnl_family __ro_after_init = {
 	.maxattr = NLBL_UNLABEL_A_MAX,
 	.policy = netlbl_unlabel_genl_policy,
 	.module = THIS_MODULE,
-	.ops = netlbl_unlabel_genl_ops,
-	.n_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops),
+	.small_ops = netlbl_unlabel_genl_ops,
+	.n_small_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops),
 };
 
 /*
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index d2d1448274f5..daca50d6bb12 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -848,7 +848,7 @@ retry:
  *
  * Test to see if the opener of the socket we received the message
  * from had when the netlink socket was created and the sender of the
- * message has has the capability @cap in the user namespace @user_ns.
+ * message has the capability @cap in the user namespace @user_ns.
  */
 bool __netlink_ns_capable(const struct netlink_skb_parms *nsp,
 			struct user_namespace *user_ns, int cap)
@@ -867,7 +867,7 @@ EXPORT_SYMBOL(__netlink_ns_capable);
  *
  * Test to see if the opener of the socket we received the message
  * from had when the netlink socket was created and the sender of the
- * message has has the capability @cap in the user namespace @user_ns.
+ * message has the capability @cap in the user namespace @user_ns.
  */
 bool netlink_ns_capable(const struct sk_buff *skb,
 			struct user_namespace *user_ns, int cap)
@@ -883,7 +883,7 @@ EXPORT_SYMBOL(netlink_ns_capable);
  *
  * Test to see if the opener of the socket we received the message
  * from had when the netlink socket was created and the sender of the
- * message has has the capability @cap in all user namespaces.
+ * message has the capability @cap in all user namespaces.
  */
 bool netlink_capable(const struct sk_buff *skb, int cap)
 {
@@ -898,7 +898,7 @@ EXPORT_SYMBOL(netlink_capable);
  *
  * Test to see if the opener of the socket we received the message
  * from had when the netlink socket was created and the sender of the
- * message has has the capability @cap over the network namespace of
+ * message has the capability @cap over the network namespace of
  * the socket we received the message from.
  */
 bool netlink_net_capable(const struct sk_buff *skb, int cap)
@@ -1853,7 +1853,7 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	struct scm_cookie scm;
 	u32 netlink_skb_flags = 0;
 
-	if (msg->msg_flags&MSG_OOB)
+	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
 	err = scm_send(sock, msg, &scm, true);
@@ -1916,7 +1916,7 @@ static int netlink_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		refcount_inc(&skb->users);
 		netlink_broadcast(sk, skb, dst_portid, dst_group, GFP_KERNEL);
 	}
-	err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags&MSG_DONTWAIT);
+	err = netlink_unicast(sk, skb, dst_portid, msg->msg_flags & MSG_DONTWAIT);
 
 out:
 	scm_destroy(&scm);
@@ -1929,12 +1929,12 @@ static int netlink_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	struct scm_cookie scm;
 	struct sock *sk = sock->sk;
 	struct netlink_sock *nlk = nlk_sk(sk);
-	int noblock = flags&MSG_DONTWAIT;
+	int noblock = flags & MSG_DONTWAIT;
 	size_t copied;
 	struct sk_buff *skb, *data_skb;
 	int err, ret;
 
-	if (flags&MSG_OOB)
+	if (flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
 	copied = 0;
@@ -2186,13 +2186,35 @@ EXPORT_SYMBOL(__nlmsg_put);
  * It would be better to create kernel thread.
  */
 
+static int netlink_dump_done(struct netlink_sock *nlk, struct sk_buff *skb,
+			     struct netlink_callback *cb,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlmsghdr *nlh;
+
+	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE, sizeof(nlk->dump_done_errno),
+			       NLM_F_MULTI | cb->answer_flags);
+	if (WARN_ON(!nlh))
+		return -ENOBUFS;
+
+	nl_dump_check_consistent(cb, nlh);
+	memcpy(nlmsg_data(nlh), &nlk->dump_done_errno, sizeof(nlk->dump_done_errno));
+
+	if (extack->_msg && nlk->flags & NETLINK_F_EXT_ACK) {
+		nlh->nlmsg_flags |= NLM_F_ACK_TLVS;
+		if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack->_msg))
+			nlmsg_end(skb, nlh);
+	}
+
+	return 0;
+}
+
 static int netlink_dump(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ext_ack extack = {};
 	struct netlink_callback *cb;
 	struct sk_buff *skb = NULL;
-	struct nlmsghdr *nlh;
 	struct module *module;
 	int err = -ENOBUFS;
 	int alloc_min_size;
@@ -2258,22 +2280,19 @@ static int netlink_dump(struct sock *sk)
 		return 0;
 	}
 
-	nlh = nlmsg_put_answer(skb, cb, NLMSG_DONE,
-			       sizeof(nlk->dump_done_errno),
-			       NLM_F_MULTI | cb->answer_flags);
-	if (WARN_ON(!nlh))
+	if (netlink_dump_done(nlk, skb, cb, &extack))
 		goto errout_skb;
 
-	nl_dump_check_consistent(cb, nlh);
-
-	memcpy(nlmsg_data(nlh), &nlk->dump_done_errno,
-	       sizeof(nlk->dump_done_errno));
-
-	if (extack._msg && nlk->flags & NETLINK_F_EXT_ACK) {
-		nlh->nlmsg_flags |= NLM_F_ACK_TLVS;
-		if (!nla_put_string(skb, NLMSGERR_ATTR_MSG, extack._msg))
-			nlmsg_end(skb, nlh);
+#ifdef CONFIG_COMPAT_NETLINK_MESSAGES
+	/* frag_list skb's data is used for compat tasks
+	 * and the regular skb's data for normal (non-compat) tasks.
+	 * See netlink_recvmsg().
+	 */
+	if (unlikely(skb_shinfo(skb)->frag_list)) {
+		if (netlink_dump_done(nlk, skb_shinfo(skb)->frag_list, cb, &extack))
+			goto errout_skb;
 	}
+#endif
 
 	if (sk_filter(sk, skb))
 		kfree_skb(skb);
@@ -2401,6 +2420,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 		tlvlen += nla_total_size(sizeof(u32));
 	if (nlk_has_extack && extack && extack->cookie_len)
 		tlvlen += nla_total_size(extack->cookie_len);
+	if (err && nlk_has_extack && extack && extack->policy)
+		tlvlen += netlink_policy_dump_attr_size_estimate(extack->policy);
 
 	if (tlvlen)
 		flags |= NLM_F_ACK_TLVS;
@@ -2433,6 +2454,9 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err,
 		if (extack->cookie_len)
 			WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE,
 					extack->cookie_len, extack->cookie));
+		if (extack->policy)
+			netlink_policy_dump_write_attr(skb, extack->policy,
+						       NLMSGERR_ATTR_POLICY);
 	}
 
 	nlmsg_end(skb, rep);
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index c4b4d3376227..c992424e4d63 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -107,16 +107,83 @@ static const struct genl_family *genl_family_find_byname(char *name)
 	return NULL;
 }
 
-static const struct genl_ops *genl_get_cmd(u8 cmd,
-					   const struct genl_family *family)
+static int genl_get_cmd_cnt(const struct genl_family *family)
+{
+	return family->n_ops + family->n_small_ops;
+}
+
+static void genl_op_from_full(const struct genl_family *family,
+			      unsigned int i, struct genl_ops *op)
+{
+	*op = family->ops[i];
+
+	if (!op->maxattr)
+		op->maxattr = family->maxattr;
+	if (!op->policy)
+		op->policy = family->policy;
+}
+
+static int genl_get_cmd_full(u32 cmd, const struct genl_family *family,
+			     struct genl_ops *op)
 {
 	int i;
 
 	for (i = 0; i < family->n_ops; i++)
-		if (family->ops[i].cmd == cmd)
-			return &family->ops[i];
+		if (family->ops[i].cmd == cmd) {
+			genl_op_from_full(family, i, op);
+			return 0;
+		}
 
-	return NULL;
+	return -ENOENT;
+}
+
+static void genl_op_from_small(const struct genl_family *family,
+			       unsigned int i, struct genl_ops *op)
+{
+	memset(op, 0, sizeof(*op));
+	op->doit	= family->small_ops[i].doit;
+	op->dumpit	= family->small_ops[i].dumpit;
+	op->cmd		= family->small_ops[i].cmd;
+	op->internal_flags = family->small_ops[i].internal_flags;
+	op->flags	= family->small_ops[i].flags;
+	op->validate	= family->small_ops[i].validate;
+
+	op->maxattr = family->maxattr;
+	op->policy = family->policy;
+}
+
+static int genl_get_cmd_small(u32 cmd, const struct genl_family *family,
+			      struct genl_ops *op)
+{
+	int i;
+
+	for (i = 0; i < family->n_small_ops; i++)
+		if (family->small_ops[i].cmd == cmd) {
+			genl_op_from_small(family, i, op);
+			return 0;
+		}
+
+	return -ENOENT;
+}
+
+static int genl_get_cmd(u32 cmd, const struct genl_family *family,
+			struct genl_ops *op)
+{
+	if (!genl_get_cmd_full(cmd, family, op))
+		return 0;
+	return genl_get_cmd_small(cmd, family, op);
+}
+
+static void genl_get_cmd_by_index(unsigned int i,
+				  const struct genl_family *family,
+				  struct genl_ops *op)
+{
+	if (i < family->n_ops)
+		genl_op_from_full(family, i, op);
+	else if (i < family->n_ops + family->n_small_ops)
+		genl_op_from_small(family, i - family->n_ops, op);
+	else
+		WARN_ON_ONCE(1);
 }
 
 static int genl_allocate_reserve_groups(int n_groups, int *first_id)
@@ -222,7 +289,7 @@ static int genl_validate_assign_mc_groups(struct genl_family *family)
 
 	family->mcgrp_offset = first_id;
 
-	/* if still initializing, can't and don't need to to realloc bitmaps */
+	/* if still initializing, can't and don't need to realloc bitmaps */
 	if (!init_net.genl_sock)
 		return 0;
 
@@ -286,22 +353,25 @@ static void genl_unregister_mc_groups(const struct genl_family *family)
 
 static int genl_validate_ops(const struct genl_family *family)
 {
-	const struct genl_ops *ops = family->ops;
-	unsigned int n_ops = family->n_ops;
 	int i, j;
 
-	if (WARN_ON(n_ops && !ops))
+	if (WARN_ON(family->n_ops && !family->ops) ||
+	    WARN_ON(family->n_small_ops && !family->small_ops))
 		return -EINVAL;
 
-	if (!n_ops)
-		return 0;
+	for (i = 0; i < genl_get_cmd_cnt(family); i++) {
+		struct genl_ops op;
 
-	for (i = 0; i < n_ops; i++) {
-		if (ops[i].dumpit == NULL && ops[i].doit == NULL)
+		genl_get_cmd_by_index(i, family, &op);
+		if (op.dumpit == NULL && op.doit == NULL)
 			return -EINVAL;
-		for (j = i + 1; j < n_ops; j++)
-			if (ops[i].cmd == ops[j].cmd)
+		for (j = i + 1; j < genl_get_cmd_cnt(family); j++) {
+			struct genl_ops op2;
+
+			genl_get_cmd_by_index(j, family, &op2);
+			if (op.cmd == op2.cmd)
 				return -EINVAL;
+		}
 	}
 
 	return 0;
@@ -467,16 +537,16 @@ genl_family_rcv_msg_attrs_parse(const struct genl_family *family,
 	struct nlattr **attrbuf;
 	int err;
 
-	if (!family->maxattr)
+	if (!ops->maxattr)
 		return NULL;
 
-	attrbuf = kmalloc_array(family->maxattr + 1,
+	attrbuf = kmalloc_array(ops->maxattr + 1,
 				sizeof(struct nlattr *), GFP_KERNEL);
 	if (!attrbuf)
 		return ERR_PTR(-ENOMEM);
 
-	err = __nlmsg_parse(nlh, hdrlen, attrbuf, family->maxattr,
-			    family->policy, validate, extack);
+	err = __nlmsg_parse(nlh, hdrlen, attrbuf, ops->maxattr, ops->policy,
+			    validate, extack);
 	if (err) {
 		kfree(attrbuf);
 		return ERR_PTR(err);
@@ -524,7 +594,7 @@ no_attrs:
 		return -ENOMEM;
 	}
 	info->family = ctx->family;
-	info->ops = ops;
+	info->op = *ops;
 	info->attrs = attrs;
 
 	cb->data = info;
@@ -546,7 +616,7 @@ no_attrs:
 
 static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	const struct genl_ops *ops = genl_dumpit_info(cb)->ops;
+	const struct genl_ops *ops = &genl_dumpit_info(cb)->op;
 	int rc;
 
 	genl_lock();
@@ -558,7 +628,7 @@ static int genl_lock_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 static int genl_lock_done(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct genl_ops *ops = info->ops;
+	const struct genl_ops *ops = &info->op;
 	int rc = 0;
 
 	if (ops->done) {
@@ -574,7 +644,7 @@ static int genl_lock_done(struct netlink_callback *cb)
 static int genl_parallel_done(struct netlink_callback *cb)
 {
 	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
-	const struct genl_ops *ops = info->ops;
+	const struct genl_ops *ops = &info->op;
 	int rc = 0;
 
 	if (ops->done)
@@ -682,9 +752,9 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 			       struct nlmsghdr *nlh,
 			       struct netlink_ext_ack *extack)
 {
-	const struct genl_ops *ops;
 	struct net *net = sock_net(skb->sk);
 	struct genlmsghdr *hdr = nlmsg_data(nlh);
+	struct genl_ops op;
 	int hdrlen;
 
 	/* this family doesn't exist in this netns */
@@ -695,24 +765,23 @@ static int genl_family_rcv_msg(const struct genl_family *family,
 	if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen))
 		return -EINVAL;
 
-	ops = genl_get_cmd(hdr->cmd, family);
-	if (ops == NULL)
+	if (genl_get_cmd(hdr->cmd, family, &op))
 		return -EOPNOTSUPP;
 
-	if ((ops->flags & GENL_ADMIN_PERM) &&
+	if ((op.flags & GENL_ADMIN_PERM) &&
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	if ((ops->flags & GENL_UNS_ADMIN_PERM) &&
+	if ((op.flags & GENL_UNS_ADMIN_PERM) &&
 	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 	if ((nlh->nlmsg_flags & NLM_F_DUMP) == NLM_F_DUMP)
 		return genl_family_rcv_msg_dumpit(family, skb, nlh, extack,
-						  ops, hdrlen, net);
+						  &op, hdrlen, net);
 	else
 		return genl_family_rcv_msg_doit(family, skb, nlh, extack,
-						ops, hdrlen, net);
+						&op, hdrlen, net);
 }
 
 static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -765,7 +834,7 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 	    nla_put_u32(skb, CTRL_ATTR_MAXATTR, family->maxattr))
 		goto nla_put_failure;
 
-	if (family->n_ops) {
+	if (genl_get_cmd_cnt(family)) {
 		struct nlattr *nla_ops;
 		int i;
 
@@ -773,23 +842,25 @@ static int ctrl_fill_info(const struct genl_family *family, u32 portid, u32 seq,
 		if (nla_ops == NULL)
 			goto nla_put_failure;
 
-		for (i = 0; i < family->n_ops; i++) {
+		for (i = 0; i < genl_get_cmd_cnt(family); i++) {
 			struct nlattr *nest;
-			const struct genl_ops *ops = &family->ops[i];
-			u32 op_flags = ops->flags;
+			struct genl_ops op;
+			u32 op_flags;
 
-			if (ops->dumpit)
+			genl_get_cmd_by_index(i, family, &op);
+			op_flags = op.flags;
+			if (op.dumpit)
 				op_flags |= GENL_CMD_CAP_DUMP;
-			if (ops->doit)
+			if (op.doit)
 				op_flags |= GENL_CMD_CAP_DO;
-			if (family->policy)
+			if (op.policy)
 				op_flags |= GENL_CMD_CAP_HASPOL;
 
 			nest = nla_nest_start_noflag(skb, i + 1);
 			if (nest == NULL)
 				goto nla_put_failure;
 
-			if (nla_put_u32(skb, CTRL_ATTR_OP_ID, ops->cmd) ||
+			if (nla_put_u32(skb, CTRL_ATTR_OP_ID, op.cmd) ||
 			    nla_put_u32(skb, CTRL_ATTR_OP_FLAGS, op_flags))
 				goto nla_put_failure;
 
@@ -945,7 +1016,7 @@ ctrl_build_mcgrp_msg(const struct genl_family *family,
 	return skb;
 }
 
-static const struct nla_policy ctrl_policy[CTRL_ATTR_MAX+1] = {
+static const struct nla_policy ctrl_policy_family[] = {
 	[CTRL_ATTR_FAMILY_ID]	= { .type = NLA_U16 },
 	[CTRL_ATTR_FAMILY_NAME]	= { .type = NLA_NUL_STRING,
 				    .len = GENL_NAMSIZ - 1 },
@@ -1039,83 +1110,218 @@ static int genl_ctrl_event(int event, const struct genl_family *family,
 	return 0;
 }
 
-static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
-{
+struct ctrl_dump_policy_ctx {
+	struct netlink_policy_dump_state *state;
 	const struct genl_family *rt;
-	unsigned int fam_id = cb->args[0];
-	int err;
+	unsigned int opidx;
+	u32 op;
+	u16 fam_id;
+	u8 policies:1,
+	   single_op:1;
+};
 
-	if (!fam_id) {
-		struct nlattr *tb[CTRL_ATTR_MAX + 1];
+static const struct nla_policy ctrl_policy_policy[] = {
+	[CTRL_ATTR_FAMILY_ID]	= { .type = NLA_U16 },
+	[CTRL_ATTR_FAMILY_NAME]	= { .type = NLA_NUL_STRING,
+				    .len = GENL_NAMSIZ - 1 },
+	[CTRL_ATTR_OP]		= { .type = NLA_U32 },
+};
 
-		err = genlmsg_parse(cb->nlh, &genl_ctrl, tb,
-				    genl_ctrl.maxattr,
-				    genl_ctrl.policy, cb->extack);
-		if (err)
-			return err;
+static int ctrl_dumppolicy_start(struct netlink_callback *cb)
+{
+	const struct genl_dumpit_info *info = genl_dumpit_info(cb);
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	struct nlattr **tb = info->attrs;
+	const struct genl_family *rt;
+	struct genl_ops op;
+	int err, i;
 
-		if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME])
-			return -EINVAL;
+	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
 
-		if (tb[CTRL_ATTR_FAMILY_ID]) {
-			fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]);
-		} else {
-			rt = genl_family_find_byname(
-				nla_data(tb[CTRL_ATTR_FAMILY_NAME]));
-			if (!rt)
-				return -ENOENT;
-			fam_id = rt->id;
-		}
+	if (!tb[CTRL_ATTR_FAMILY_ID] && !tb[CTRL_ATTR_FAMILY_NAME])
+		return -EINVAL;
+
+	if (tb[CTRL_ATTR_FAMILY_ID]) {
+		ctx->fam_id = nla_get_u16(tb[CTRL_ATTR_FAMILY_ID]);
+	} else {
+		rt = genl_family_find_byname(
+			nla_data(tb[CTRL_ATTR_FAMILY_NAME]));
+		if (!rt)
+			return -ENOENT;
+		ctx->fam_id = rt->id;
 	}
 
-	rt = genl_family_find_byid(fam_id);
+	rt = genl_family_find_byid(ctx->fam_id);
 	if (!rt)
 		return -ENOENT;
 
-	if (!rt->policy)
+	ctx->rt = rt;
+
+	if (tb[CTRL_ATTR_OP]) {
+		ctx->single_op = true;
+		ctx->op = nla_get_u32(tb[CTRL_ATTR_OP]);
+
+		err = genl_get_cmd(ctx->op, rt, &op);
+		if (err) {
+			NL_SET_BAD_ATTR(cb->extack, tb[CTRL_ATTR_OP]);
+			return err;
+		}
+
+		if (!op.policy)
+			return -ENODATA;
+
+		return netlink_policy_dump_add_policy(&ctx->state, op.policy,
+						      op.maxattr);
+	}
+
+	for (i = 0; i < genl_get_cmd_cnt(rt); i++) {
+		genl_get_cmd_by_index(i, rt, &op);
+
+		if (op.policy) {
+			err = netlink_policy_dump_add_policy(&ctx->state,
+							     op.policy,
+							     op.maxattr);
+			if (err)
+				return err;
+		}
+	}
+
+	if (!ctx->state)
 		return -ENODATA;
+	return 0;
+}
 
-	err = netlink_policy_dump_start(rt->policy, rt->maxattr, &cb->args[1]);
-	if (err)
-		return err;
+static void *ctrl_dumppolicy_prep(struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	void *hdr;
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+			  cb->nlh->nlmsg_seq, &genl_ctrl,
+			  NLM_F_MULTI, CTRL_CMD_GETPOLICY);
+	if (!hdr)
+		return NULL;
+
+	if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, ctx->fam_id))
+		return NULL;
+
+	return hdr;
+}
+
+static int ctrl_dumppolicy_put_op(struct sk_buff *skb,
+				  struct netlink_callback *cb,
+			          struct genl_ops *op)
+{
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	struct nlattr *nest_pol, *nest_op;
+	void *hdr;
+	int idx;
+
+	/* skip if we have nothing to show */
+	if (!op->policy)
+		return 0;
+	if (!op->doit &&
+	    (!op->dumpit || op->validate & GENL_DONT_VALIDATE_DUMP))
+		return 0;
+
+	hdr = ctrl_dumppolicy_prep(skb, cb);
+	if (!hdr)
+		return -ENOBUFS;
+
+	nest_pol = nla_nest_start(skb, CTRL_ATTR_OP_POLICY);
+	if (!nest_pol)
+		goto err;
+
+	nest_op = nla_nest_start(skb, op->cmd);
+	if (!nest_op)
+		goto err;
+
+	/* for now both do/dump are always the same */
+	idx = netlink_policy_dump_get_policy_idx(ctx->state,
+						 op->policy,
+						 op->maxattr);
+
+	if (op->doit && nla_put_u32(skb, CTRL_ATTR_POLICY_DO, idx))
+		goto err;
+
+	if (op->dumpit && !(op->validate & GENL_DONT_VALIDATE_DUMP) &&
+	    nla_put_u32(skb, CTRL_ATTR_POLICY_DUMP, idx))
+		goto err;
+
+	nla_nest_end(skb, nest_op);
+	nla_nest_end(skb, nest_pol);
+	genlmsg_end(skb, hdr);
 
-	while (netlink_policy_dump_loop(cb->args[1])) {
-		void *hdr;
+	return 0;
+err:
+	genlmsg_cancel(skb, hdr);
+	return -ENOBUFS;
+}
+
+static int ctrl_dumppolicy(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+	void *hdr;
+
+	if (!ctx->policies) {
+		while (ctx->opidx < genl_get_cmd_cnt(ctx->rt)) {
+			struct genl_ops op;
+
+			if (ctx->single_op) {
+				int err;
+
+				err = genl_get_cmd(ctx->op, ctx->rt, &op);
+				if (WARN_ON(err))
+					return skb->len;
+
+				/* break out of the loop after this one */
+				ctx->opidx = genl_get_cmd_cnt(ctx->rt);
+			} else {
+				genl_get_cmd_by_index(ctx->opidx, ctx->rt, &op);
+			}
+
+			if (ctrl_dumppolicy_put_op(skb, cb, &op))
+				return skb->len;
+
+			ctx->opidx++;
+		}
+
+		/* completed with the per-op policy index list */
+		ctx->policies = true;
+	}
+
+	while (netlink_policy_dump_loop(ctx->state)) {
 		struct nlattr *nest;
 
-		hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid,
-				  cb->nlh->nlmsg_seq, &genl_ctrl,
-				  NLM_F_MULTI, CTRL_CMD_GETPOLICY);
+		hdr = ctrl_dumppolicy_prep(skb, cb);
 		if (!hdr)
 			goto nla_put_failure;
 
-		if (nla_put_u16(skb, CTRL_ATTR_FAMILY_ID, rt->id))
-			goto nla_put_failure;
-
 		nest = nla_nest_start(skb, CTRL_ATTR_POLICY);
 		if (!nest)
 			goto nla_put_failure;
 
-		if (netlink_policy_dump_write(skb, cb->args[1]))
+		if (netlink_policy_dump_write(skb, ctx->state))
 			goto nla_put_failure;
 
 		nla_nest_end(skb, nest);
 
 		genlmsg_end(skb, hdr);
-		continue;
-
-nla_put_failure:
-		genlmsg_cancel(skb, hdr);
-		break;
 	}
 
-	cb->args[0] = fam_id;
+	return skb->len;
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
 	return skb->len;
 }
 
 static int ctrl_dumppolicy_done(struct netlink_callback *cb)
 {
-	netlink_policy_dump_free(cb->args[1]);
+	struct ctrl_dump_policy_ctx *ctx = (void *)cb->ctx;
+
+	netlink_policy_dump_free(ctx->state);
 	return 0;
 }
 
@@ -1123,11 +1329,16 @@ static const struct genl_ops genl_ctrl_ops[] = {
 	{
 		.cmd		= CTRL_CMD_GETFAMILY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.policy		= ctrl_policy_family,
+		.maxattr	= ARRAY_SIZE(ctrl_policy_family) - 1,
 		.doit		= ctrl_getfamily,
 		.dumpit		= ctrl_dumpfamily,
 	},
 	{
 		.cmd		= CTRL_CMD_GETPOLICY,
+		.policy		= ctrl_policy_policy,
+		.maxattr	= ARRAY_SIZE(ctrl_policy_policy) - 1,
+		.start		= ctrl_dumppolicy_start,
 		.dumpit		= ctrl_dumppolicy,
 		.done		= ctrl_dumppolicy_done,
 	},
@@ -1146,8 +1357,6 @@ static struct genl_family genl_ctrl __ro_after_init = {
 	.id = GENL_ID_CTRL,
 	.name = "nlctrl",
 	.version = 0x2,
-	.maxattr = CTRL_ATTR_MAX,
-	.policy = ctrl_policy,
 	.netnsok = true,
 };
 
diff --git a/net/netlink/policy.c b/net/netlink/policy.c
index 0176b59ce530..8d7c900e27f4 100644
--- a/net/netlink/policy.c
+++ b/net/netlink/policy.c
@@ -14,7 +14,7 @@
 
 #define INITIAL_POLICIES_ALLOC	10
 
-struct nl_policy_dump {
+struct netlink_policy_dump_state {
 	unsigned int policy_idx;
 	unsigned int attr_idx;
 	unsigned int n_alloc;
@@ -24,18 +24,19 @@ struct nl_policy_dump {
 	} policies[];
 };
 
-static int add_policy(struct nl_policy_dump **statep,
+static int add_policy(struct netlink_policy_dump_state **statep,
 		      const struct nla_policy *policy,
 		      unsigned int maxtype)
 {
-	struct nl_policy_dump *state = *statep;
+	struct netlink_policy_dump_state *state = *statep;
 	unsigned int n_alloc, i;
 
 	if (!policy || !maxtype)
 		return 0;
 
 	for (i = 0; i < state->n_alloc; i++) {
-		if (state->policies[i].policy == policy)
+		if (state->policies[i].policy == policy &&
+		    state->policies[i].maxtype == maxtype)
 			return 0;
 
 		if (!state->policies[i].policy) {
@@ -62,42 +63,85 @@ static int add_policy(struct nl_policy_dump **statep,
 	return 0;
 }
 
-static unsigned int get_policy_idx(struct nl_policy_dump *state,
-				   const struct nla_policy *policy)
+/**
+ * netlink_policy_dump_get_policy_idx - retrieve policy index
+ * @state: the policy dump state
+ * @policy: the policy to find
+ * @maxtype: the policy's maxattr
+ *
+ * Returns: the index of the given policy in the dump state
+ *
+ * Call this to find a policy index when you've added multiple and e.g.
+ * need to tell userspace which command has which policy (by index).
+ *
+ * Note: this will WARN and return 0 if the policy isn't found, which
+ *	 means it wasn't added in the first place, which would be an
+ *	 internal consistency bug.
+ */
+int netlink_policy_dump_get_policy_idx(struct netlink_policy_dump_state *state,
+				       const struct nla_policy *policy,
+				       unsigned int maxtype)
 {
 	unsigned int i;
 
+	if (WARN_ON(!policy || !maxtype))
+                return 0;
+
 	for (i = 0; i < state->n_alloc; i++) {
-		if (state->policies[i].policy == policy)
+		if (state->policies[i].policy == policy &&
+		    state->policies[i].maxtype == maxtype)
 			return i;
 	}
 
-	WARN_ON_ONCE(1);
-	return -1;
+	WARN_ON(1);
+	return 0;
+}
+
+static struct netlink_policy_dump_state *alloc_state(void)
+{
+	struct netlink_policy_dump_state *state;
+
+	state = kzalloc(struct_size(state, policies, INITIAL_POLICIES_ALLOC),
+			GFP_KERNEL);
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+	state->n_alloc = INITIAL_POLICIES_ALLOC;
+
+	return state;
 }
 
-int netlink_policy_dump_start(const struct nla_policy *policy,
-			      unsigned int maxtype,
-                              unsigned long *_state)
+/**
+ * netlink_policy_dump_add_policy - add a policy to the dump
+ * @pstate: state to add to, may be reallocated, must be %NULL the first time
+ * @policy: the new policy to add to the dump
+ * @maxtype: the new policy's max attr type
+ *
+ * Returns: 0 on success, a negative error code otherwise.
+ *
+ * Call this to allocate a policy dump state, and to add policies to it. This
+ * should be called from the dump start() callback.
+ *
+ * Note: on failures, any previously allocated state is freed.
+ */
+int netlink_policy_dump_add_policy(struct netlink_policy_dump_state **pstate,
+				   const struct nla_policy *policy,
+				   unsigned int maxtype)
 {
-	struct nl_policy_dump *state;
+	struct netlink_policy_dump_state *state = *pstate;
 	unsigned int policy_idx;
 	int err;
 
-	if (*_state)
-		return 0;
+	if (!state) {
+		state = alloc_state();
+		if (IS_ERR(state))
+			return PTR_ERR(state);
+	}
 
 	/*
 	 * walk the policies and nested ones first, and build
 	 * a linear list of them.
 	 */
 
-	state = kzalloc(struct_size(state, policies, INITIAL_POLICIES_ALLOC),
-			GFP_KERNEL);
-	if (!state)
-		return -ENOMEM;
-	state->n_alloc = INITIAL_POLICIES_ALLOC;
-
 	err = add_policy(&state, policy, maxtype);
 	if (err)
 		return err;
@@ -128,62 +172,103 @@ int netlink_policy_dump_start(const struct nla_policy *policy,
 		}
 	}
 
-	*_state = (unsigned long)state;
-
+	*pstate = state;
 	return 0;
 }
 
-static bool netlink_policy_dump_finished(struct nl_policy_dump *state)
+static bool
+netlink_policy_dump_finished(struct netlink_policy_dump_state *state)
 {
 	return state->policy_idx >= state->n_alloc ||
 	       !state->policies[state->policy_idx].policy;
 }
 
-bool netlink_policy_dump_loop(unsigned long _state)
+/**
+ * netlink_policy_dump_loop - dumping loop indicator
+ * @state: the policy dump state
+ *
+ * Returns: %true if the dump continues, %false otherwise
+ *
+ * Note: this frees the dump state when finishing
+ */
+bool netlink_policy_dump_loop(struct netlink_policy_dump_state *state)
 {
-	struct nl_policy_dump *state = (void *)_state;
-
 	return !netlink_policy_dump_finished(state);
 }
 
-int netlink_policy_dump_write(struct sk_buff *skb, unsigned long _state)
+int netlink_policy_dump_attr_size_estimate(const struct nla_policy *pt)
 {
-	struct nl_policy_dump *state = (void *)_state;
-	const struct nla_policy *pt;
-	struct nlattr *policy, *attr;
-	enum netlink_attribute_type type;
-	bool again;
+	/* nested + type */
+	int common = 2 * nla_attr_size(sizeof(u32));
 
-send_attribute:
-	again = false;
+	switch (pt->type) {
+	case NLA_UNSPEC:
+	case NLA_REJECT:
+		/* these actually don't need any space */
+		return 0;
+	case NLA_NESTED:
+	case NLA_NESTED_ARRAY:
+		/* common, policy idx, policy maxattr */
+		return common + 2 * nla_attr_size(sizeof(u32));
+	case NLA_U8:
+	case NLA_U16:
+	case NLA_U32:
+	case NLA_U64:
+	case NLA_MSECS:
+	case NLA_S8:
+	case NLA_S16:
+	case NLA_S32:
+	case NLA_S64:
+		/* maximum is common, u64 min/max with padding */
+		return common +
+		       2 * (nla_attr_size(0) + nla_attr_size(sizeof(u64)));
+	case NLA_BITFIELD32:
+		return common + nla_attr_size(sizeof(u32));
+	case NLA_STRING:
+	case NLA_NUL_STRING:
+	case NLA_BINARY:
+		/* maximum is common, u32 min-length/max-length */
+		return common + 2 * nla_attr_size(sizeof(u32));
+	case NLA_FLAG:
+		return common;
+	}
 
-	pt = &state->policies[state->policy_idx].policy[state->attr_idx];
+	/* this should then cause a warning later */
+	return 0;
+}
 
-	policy = nla_nest_start(skb, state->policy_idx);
-	if (!policy)
-		return -ENOBUFS;
+static int
+__netlink_policy_dump_write_attr(struct netlink_policy_dump_state *state,
+				 struct sk_buff *skb,
+				 const struct nla_policy *pt,
+				 int nestattr)
+{
+	int estimate = netlink_policy_dump_attr_size_estimate(pt);
+	enum netlink_attribute_type type;
+	struct nlattr *attr;
 
-	attr = nla_nest_start(skb, state->attr_idx);
+	attr = nla_nest_start(skb, nestattr);
 	if (!attr)
-		goto nla_put_failure;
+		return -ENOBUFS;
 
 	switch (pt->type) {
 	default:
 	case NLA_UNSPEC:
 	case NLA_REJECT:
 		/* skip - use NLA_MIN_LEN to advertise such */
-		nla_nest_cancel(skb, policy);
-		again = true;
-		goto next;
+		nla_nest_cancel(skb, attr);
+		return -ENODATA;
 	case NLA_NESTED:
 		type = NL_ATTR_TYPE_NESTED;
 		fallthrough;
 	case NLA_NESTED_ARRAY:
 		if (pt->type == NLA_NESTED_ARRAY)
 			type = NL_ATTR_TYPE_NESTED_ARRAY;
-		if (pt->nested_policy && pt->len &&
+		if (state && pt->nested_policy && pt->len &&
 		    (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_IDX,
-				 get_policy_idx(state, pt->nested_policy)) ||
+				 netlink_policy_dump_get_policy_idx(state,
+								    pt->nested_policy,
+								    pt->len)) ||
 		     nla_put_u32(skb, NL_POLICY_TYPE_ATTR_POLICY_MAXTYPE,
 				 pt->len)))
 			goto nla_put_failure;
@@ -204,6 +289,14 @@ send_attribute:
 		else
 			type = NL_ATTR_TYPE_U64;
 
+		if (pt->validation_type == NLA_VALIDATE_MASK) {
+			if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MASK,
+					      pt->mask,
+					      NL_POLICY_TYPE_ATTR_PAD))
+				goto nla_put_failure;
+			break;
+		}
+
 		nla_get_range_unsigned(pt, &range);
 
 		if (nla_put_u64_64bit(skb, NL_POLICY_TYPE_ATTR_MIN_VALUE_U,
@@ -243,12 +336,6 @@ send_attribute:
 				pt->bitfield32_valid))
 			goto nla_put_failure;
 		break;
-	case NLA_EXACT_LEN:
-		type = NL_ATTR_TYPE_BINARY;
-		if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len) ||
-		    nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH, pt->len))
-			goto nla_put_failure;
-		break;
 	case NLA_STRING:
 	case NLA_NUL_STRING:
 	case NLA_BINARY:
@@ -258,14 +345,27 @@ send_attribute:
 			type = NL_ATTR_TYPE_NUL_STRING;
 		else
 			type = NL_ATTR_TYPE_BINARY;
-		if (pt->len && nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH,
-					   pt->len))
-			goto nla_put_failure;
-		break;
-	case NLA_MIN_LEN:
-		type = NL_ATTR_TYPE_BINARY;
-		if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH, pt->len))
+
+		if (pt->validation_type == NLA_VALIDATE_RANGE ||
+		    pt->validation_type == NLA_VALIDATE_RANGE_WARN_TOO_LONG) {
+			struct netlink_range_validation range;
+
+			nla_get_range_unsigned(pt, &range);
+
+			if (range.min &&
+			    nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MIN_LENGTH,
+					range.min))
+				goto nla_put_failure;
+
+			if (range.max < U16_MAX &&
+			    nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH,
+					range.max))
+				goto nla_put_failure;
+		} else if (pt->len &&
+			   nla_put_u32(skb, NL_POLICY_TYPE_ATTR_MAX_LENGTH,
+				       pt->len)) {
 			goto nla_put_failure;
+		}
 		break;
 	case NLA_FLAG:
 		type = NL_ATTR_TYPE_FLAG;
@@ -275,8 +375,66 @@ send_attribute:
 	if (nla_put_u32(skb, NL_POLICY_TYPE_ATTR_TYPE, type))
 		goto nla_put_failure;
 
-	/* finish and move state to next attribute */
 	nla_nest_end(skb, attr);
+	WARN_ON(attr->nla_len > estimate);
+
+	return 0;
+nla_put_failure:
+	nla_nest_cancel(skb, attr);
+	return -ENOBUFS;
+}
+
+/**
+ * netlink_policy_dump_write_attr - write a given attribute policy
+ * @skb: the message skb to write to
+ * @pt: the attribute's policy
+ * @nestattr: the nested attribute ID to use
+ *
+ * Returns: 0 on success, an error code otherwise; -%ENODATA is
+ *	    special, indicating that there's no policy data and
+ *	    the attribute is generally rejected.
+ */
+int netlink_policy_dump_write_attr(struct sk_buff *skb,
+				   const struct nla_policy *pt,
+				   int nestattr)
+{
+	return __netlink_policy_dump_write_attr(NULL, skb, pt, nestattr);
+}
+
+/**
+ * netlink_policy_dump_write - write current policy dump attributes
+ * @skb: the message skb to write to
+ * @state: the policy dump state
+ *
+ * Returns: 0 on success, an error code otherwise
+ */
+int netlink_policy_dump_write(struct sk_buff *skb,
+			      struct netlink_policy_dump_state *state)
+{
+	const struct nla_policy *pt;
+	struct nlattr *policy;
+	bool again;
+	int err;
+
+send_attribute:
+	again = false;
+
+	pt = &state->policies[state->policy_idx].policy[state->attr_idx];
+
+	policy = nla_nest_start(skb, state->policy_idx);
+	if (!policy)
+		return -ENOBUFS;
+
+	err = __netlink_policy_dump_write_attr(state, skb, pt, state->attr_idx);
+	if (err == -ENODATA) {
+		nla_nest_cancel(skb, policy);
+		again = true;
+		goto next;
+	} else if (err) {
+		goto nla_put_failure;
+	}
+
+	/* finish and move state to next attribute */
 	nla_nest_end(skb, policy);
 
 next:
@@ -299,9 +457,13 @@ nla_put_failure:
 	return -ENOBUFS;
 }
 
-void netlink_policy_dump_free(unsigned long _state)
+/**
+ * netlink_policy_dump_free - free policy dump state
+ * @state: the policy dump state to free
+ *
+ * Call this from the done() method to ensure dump state is freed.
+ */
+void netlink_policy_dump_free(struct netlink_policy_dump_state *state)
 {
-	struct nl_policy_dump *state = (void *)_state;
-
 	kfree(state);
 }
diff --git a/net/nfc/Kconfig b/net/nfc/Kconfig
index 9b27599870e3..96b91674dd37 100644
--- a/net/nfc/Kconfig
+++ b/net/nfc/Kconfig
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only
 #
-# NFC sybsystem configuration
+# NFC subsystem configuration
 #
 
 menuconfig NFC
diff --git a/net/nfc/core.c b/net/nfc/core.c
index eb377f87bcae..573c80c6ff7a 100644
--- a/net/nfc/core.c
+++ b/net/nfc/core.c
@@ -189,7 +189,8 @@ static const struct rfkill_ops nfc_rfkill_ops = {
  * nfc_start_poll - start polling for nfc targets
  *
  * @dev: The nfc device that must start polling
- * @protocols: bitset of nfc protocols that must be used for polling
+ * @im_protocols: bitset of nfc initiator protocols to be used for polling
+ * @tm_protocols: bitset of nfc transport protocols to be used for polling
  *
  * The device remains polling for targets until a target is found or
  * the nfc_stop_poll function is called.
@@ -436,6 +437,7 @@ error:
  *
  * @dev: The nfc device that found the target
  * @target_idx: index of the target that must be deactivated
+ * @mode: idle or sleep?
  */
 int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx, u8 mode)
 {
@@ -703,7 +705,11 @@ EXPORT_SYMBOL(nfc_tm_deactivated);
 /**
  * nfc_alloc_send_skb - allocate a skb for data exchange responses
  *
+ * @dev: device sending the response
+ * @sk: socket sending the response
+ * @flags: MSG_DONTWAIT flag
  * @size: size to allocate
+ * @err: pointer to memory to store the error code
  */
 struct sk_buff *nfc_alloc_send_skb(struct nfc_dev *dev, struct sock *sk,
 				   unsigned int flags, unsigned int size,
@@ -1039,6 +1045,8 @@ struct nfc_dev *nfc_get_device(unsigned int idx)
  *
  * @ops: device operations
  * @supported_protocols: NFC protocols supported by the device
+ * @tx_headroom: reserved space at beginning of skb
+ * @tx_tailroom: reserved space at end of skb
  */
 struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops,
 				    u32 supported_protocols,
diff --git a/net/nfc/digital_core.c b/net/nfc/digital_core.c
index e3599ed4a7a8..da7e2112771f 100644
--- a/net/nfc/digital_core.c
+++ b/net/nfc/digital_core.c
@@ -458,6 +458,9 @@ static void digital_add_poll_tech(struct nfc_digital_dev *ddev, u8 rf_tech,
 
 /**
  * start_poll operation
+ * @nfc_dev: device to be polled
+ * @im_protocols: bitset of nfc initiator protocols to be used for polling
+ * @tm_protocols: bitset of nfc transport protocols to be used for polling
  *
  * For every supported protocol, the corresponding polling function is added
  * to the table of polling technologies (ddev->poll_techs[]) using
diff --git a/net/nfc/digital_dep.c b/net/nfc/digital_dep.c
index 304b1a9bb18a..5971fb6f51cc 100644
--- a/net/nfc/digital_dep.c
+++ b/net/nfc/digital_dep.c
@@ -38,9 +38,6 @@
 
 #define DIGITAL_GB_BIT	0x02
 
-#define DIGITAL_NFC_DEP_REQ_RES_HEADROOM	2 /* SoD: [SB (NFC-A)] + LEN */
-#define DIGITAL_NFC_DEP_REQ_RES_TAILROOM	2 /* EoD: 2-byte CRC */
-
 #define DIGITAL_NFC_DEP_PFB_TYPE(pfb) ((pfb) & 0xE0)
 
 #define DIGITAL_NFC_DEP_PFB_TIMEOUT_BIT 0x10
diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c
index 741da8f81c2b..02a1f13f0798 100644
--- a/net/nfc/nci/core.c
+++ b/net/nfc/nci/core.c
@@ -165,7 +165,12 @@ static void nci_reset_req(struct nci_dev *ndev, unsigned long opt)
 
 static void nci_init_req(struct nci_dev *ndev, unsigned long opt)
 {
-	nci_send_cmd(ndev, NCI_OP_CORE_INIT_CMD, 0, NULL);
+	u8 plen = 0;
+
+	if (opt)
+		plen = sizeof(struct nci_core_init_v2_cmd);
+
+	nci_send_cmd(ndev, NCI_OP_CORE_INIT_CMD, plen, (void *)opt);
 }
 
 static void nci_init_complete_req(struct nci_dev *ndev, unsigned long opt)
@@ -497,7 +502,16 @@ static int nci_open_device(struct nci_dev *ndev)
 	}
 
 	if (!rc) {
-		rc = __nci_request(ndev, nci_init_req, 0,
+		struct nci_core_init_v2_cmd nci_init_v2_cmd = {
+			.feature1 = NCI_FEATURE_DISABLE,
+			.feature2 = NCI_FEATURE_DISABLE
+		};
+		unsigned long opt = 0;
+
+		if (ndev->nci_ver & NCI_VER_2_MASK)
+			opt = (unsigned long)&nci_init_v2_cmd;
+
+		rc = __nci_request(ndev, nci_init_req, opt,
 				   msecs_to_jiffies(NCI_INIT_TIMEOUT));
 	}
 
@@ -1112,6 +1126,8 @@ static struct nfc_ops nci_nfc_ops = {
  *
  * @ops: device operations
  * @supported_protocols: NFC protocols supported by the device
+ * @tx_headroom: Reserved space at beginning of skb
+ * @tx_tailroom: Reserved space at end of skb
  */
 struct nci_dev *nci_allocate_device(struct nci_ops *ops,
 				    __u32 supported_protocols,
diff --git a/net/nfc/nci/hci.c b/net/nfc/nci/hci.c
index c18e76d6d8ba..6b275a387a92 100644
--- a/net/nfc/nci/hci.c
+++ b/net/nfc/nci/hci.c
@@ -363,16 +363,13 @@ exit:
 }
 
 static void nci_hci_resp_received(struct nci_dev *ndev, u8 pipe,
-				  u8 result, struct sk_buff *skb)
+				  struct sk_buff *skb)
 {
 	struct nci_conn_info    *conn_info;
-	u8 status = result;
 
 	conn_info = ndev->hci_dev->conn_info;
-	if (!conn_info) {
-		status = NCI_STATUS_REJECTED;
+	if (!conn_info)
 		goto exit;
-	}
 
 	conn_info->rx_skb = skb;
 
@@ -388,7 +385,7 @@ static void nci_hci_hcp_message_rx(struct nci_dev *ndev, u8 pipe,
 {
 	switch (type) {
 	case NCI_HCI_HCP_RESPONSE:
-		nci_hci_resp_received(ndev, pipe, instruction, skb);
+		nci_hci_resp_received(ndev, pipe, skb);
 		break;
 	case NCI_HCI_HCP_COMMAND:
 		nci_hci_cmd_received(ndev, pipe, instruction, skb);
diff --git a/net/nfc/nci/ntf.c b/net/nfc/nci/ntf.c
index 33e1170817f0..98af04c86b2c 100644
--- a/net/nfc/nci/ntf.c
+++ b/net/nfc/nci/ntf.c
@@ -27,6 +27,23 @@
 
 /* Handle NCI Notification packets */
 
+static void nci_core_reset_ntf_packet(struct nci_dev *ndev,
+				      struct sk_buff *skb)
+{
+	/* Handle NCI 2.x core reset notification */
+	struct nci_core_reset_ntf *ntf = (void *)skb->data;
+
+	ndev->nci_ver = ntf->nci_ver;
+	pr_debug("nci_ver 0x%x, config_status 0x%x\n",
+		 ntf->nci_ver, ntf->config_status);
+
+	ndev->manufact_id = ntf->manufact_id;
+	ndev->manufact_specific_info =
+		__le32_to_cpu(ntf->manufact_specific_info);
+
+	nci_req_complete(ndev, NCI_STATUS_OK);
+}
+
 static void nci_core_conn_credits_ntf_packet(struct nci_dev *ndev,
 					     struct sk_buff *skb)
 {
@@ -756,6 +773,10 @@ void nci_ntf_packet(struct nci_dev *ndev, struct sk_buff *skb)
 	}
 
 	switch (ntf_opcode) {
+	case NCI_OP_CORE_RESET_NTF:
+		nci_core_reset_ntf_packet(ndev, skb);
+		break;
+
 	case NCI_OP_CORE_CONN_CREDITS_NTF:
 		nci_core_conn_credits_ntf_packet(ndev, skb);
 		break;
diff --git a/net/nfc/nci/rsp.c b/net/nfc/nci/rsp.c
index a48297b79f34..e9605922a322 100644
--- a/net/nfc/nci/rsp.c
+++ b/net/nfc/nci/rsp.c
@@ -31,16 +31,19 @@ static void nci_core_reset_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 
 	pr_debug("status 0x%x\n", rsp->status);
 
-	if (rsp->status == NCI_STATUS_OK) {
-		ndev->nci_ver = rsp->nci_ver;
-		pr_debug("nci_ver 0x%x, config_status 0x%x\n",
-			 rsp->nci_ver, rsp->config_status);
-	}
+	/* Handle NCI 1.x ver */
+	if (skb->len != 1) {
+		if (rsp->status == NCI_STATUS_OK) {
+			ndev->nci_ver = rsp->nci_ver;
+			pr_debug("nci_ver 0x%x, config_status 0x%x\n",
+				 rsp->nci_ver, rsp->config_status);
+		}
 
-	nci_req_complete(ndev, rsp->status);
+		nci_req_complete(ndev, rsp->status);
+	}
 }
 
-static void nci_core_init_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
+static u8 nci_core_init_rsp_packet_v1(struct nci_dev *ndev, struct sk_buff *skb)
 {
 	struct nci_core_init_rsp_1 *rsp_1 = (void *) skb->data;
 	struct nci_core_init_rsp_2 *rsp_2;
@@ -48,16 +51,14 @@ static void nci_core_init_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 	pr_debug("status 0x%x\n", rsp_1->status);
 
 	if (rsp_1->status != NCI_STATUS_OK)
-		goto exit;
+		return rsp_1->status;
 
 	ndev->nfcc_features = __le32_to_cpu(rsp_1->nfcc_features);
 	ndev->num_supported_rf_interfaces = rsp_1->num_supported_rf_interfaces;
 
-	if (ndev->num_supported_rf_interfaces >
-	    NCI_MAX_SUPPORTED_RF_INTERFACES) {
-		ndev->num_supported_rf_interfaces =
-			NCI_MAX_SUPPORTED_RF_INTERFACES;
-	}
+	ndev->num_supported_rf_interfaces =
+		min((int)ndev->num_supported_rf_interfaces,
+		    NCI_MAX_SUPPORTED_RF_INTERFACES);
 
 	memcpy(ndev->supported_rf_interfaces,
 	       rsp_1->supported_rf_interfaces,
@@ -77,6 +78,58 @@ static void nci_core_init_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 	ndev->manufact_specific_info =
 		__le32_to_cpu(rsp_2->manufact_specific_info);
 
+	return NCI_STATUS_OK;
+}
+
+static u8 nci_core_init_rsp_packet_v2(struct nci_dev *ndev, struct sk_buff *skb)
+{
+	struct nci_core_init_rsp_nci_ver2 *rsp = (void *)skb->data;
+	u8 *supported_rf_interface = rsp->supported_rf_interfaces;
+	u8 rf_interface_idx = 0;
+	u8 rf_extension_cnt = 0;
+
+	pr_debug("status %x\n", rsp->status);
+
+	if (rsp->status != NCI_STATUS_OK)
+		return rsp->status;
+
+	ndev->nfcc_features = __le32_to_cpu(rsp->nfcc_features);
+	ndev->num_supported_rf_interfaces = rsp->num_supported_rf_interfaces;
+
+	ndev->num_supported_rf_interfaces =
+		min((int)ndev->num_supported_rf_interfaces,
+		    NCI_MAX_SUPPORTED_RF_INTERFACES);
+
+	while (rf_interface_idx < ndev->num_supported_rf_interfaces) {
+		ndev->supported_rf_interfaces[rf_interface_idx++] = *supported_rf_interface++;
+
+		/* skip rf extension parameters */
+		rf_extension_cnt = *supported_rf_interface++;
+		supported_rf_interface += rf_extension_cnt;
+	}
+
+	ndev->max_logical_connections = rsp->max_logical_connections;
+	ndev->max_routing_table_size =
+			__le16_to_cpu(rsp->max_routing_table_size);
+	ndev->max_ctrl_pkt_payload_len =
+			rsp->max_ctrl_pkt_payload_len;
+	ndev->max_size_for_large_params = NCI_MAX_LARGE_PARAMS_NCI_v2;
+
+	return NCI_STATUS_OK;
+}
+
+static void nci_core_init_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
+{
+	u8 status = 0;
+
+	if (!(ndev->nci_ver & NCI_VER_2_MASK))
+		status = nci_core_init_rsp_packet_v1(ndev, skb);
+	else
+		status = nci_core_init_rsp_packet_v2(ndev, skb);
+
+	if (status != NCI_STATUS_OK)
+		goto exit;
+
 	pr_debug("nfcc_features 0x%x\n",
 		 ndev->nfcc_features);
 	pr_debug("num_supported_rf_interfaces %d\n",
@@ -103,7 +156,7 @@ static void nci_core_init_rsp_packet(struct nci_dev *ndev, struct sk_buff *skb)
 		 ndev->manufact_specific_info);
 
 exit:
-	nci_req_complete(ndev, rsp_1->status);
+	nci_req_complete(ndev, status);
 }
 
 static void nci_core_set_config_rsp_packet(struct nci_dev *ndev,
diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c
index e894254c17d4..e161ef2d4720 100644
--- a/net/nfc/netlink.c
+++ b/net/nfc/netlink.c
@@ -852,6 +852,7 @@ static int nfc_genl_stop_poll(struct sk_buff *skb, struct genl_info *info)
 
 	if (!dev->polling) {
 		device_unlock(&dev->dev);
+		nfc_put_device(dev);
 		return -EINVAL;
 	}
 
@@ -1217,7 +1218,7 @@ static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info)
 	u32 idx;
 	char firmware_name[NFC_FIRMWARE_NAME_MAXSIZE + 1];
 
-	if (!info->attrs[NFC_ATTR_DEVICE_INDEX])
+	if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || !info->attrs[NFC_ATTR_FIRMWARE_NAME])
 		return -EINVAL;
 
 	idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]);
@@ -1226,7 +1227,7 @@ static int nfc_genl_fw_download(struct sk_buff *skb, struct genl_info *info)
 	if (!dev)
 		return -ENODEV;
 
-	nla_strlcpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME],
+	nla_strscpy(firmware_name, info->attrs[NFC_ATTR_FIRMWARE_NAME],
 		    sizeof(firmware_name));
 
 	rc = nfc_fw_download(dev, firmware_name);
diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c
index 955c195ae14b..9c7eb8455ba8 100644
--- a/net/nfc/rawsock.c
+++ b/net/nfc/rawsock.c
@@ -105,7 +105,7 @@ static int rawsock_connect(struct socket *sock, struct sockaddr *_addr,
 	if (addr->target_idx > dev->target_next_idx - 1 ||
 	    addr->target_idx < dev->target_next_idx - dev->n_targets) {
 		rc = -EINVAL;
-		goto error;
+		goto put_dev;
 	}
 
 	rc = nfc_activate_target(dev, addr->target_idx, addr->nfc_protocol);
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 2611657f40ca..e8902a7e60f2 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -9,7 +9,6 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/openvswitch.h>
-#include <linux/netfilter_ipv6.h>
 #include <linux/sctp.h>
 #include <linux/tcp.h>
 #include <linux/udp.h>
@@ -200,6 +199,9 @@ static int set_mpls(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	__be32 lse;
 	int err;
 
+	if (!pskb_may_pull(skb, skb_network_offset(skb) + MPLS_HLEN))
+		return -ENOMEM;
+
 	stack = mpls_hdr(skb);
 	lse = OVS_MASKED(stack->label_stack_entry, *mpls_lse, *mask);
 	err = skb_mpls_update_lse(skb, lse);
@@ -278,9 +280,11 @@ static int set_eth_addr(struct sk_buff *skb, struct sw_flow_key *flow_key,
  */
 static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 {
-	skb_pull_rcsum(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
+	int err;
+
+	err = skb_eth_pop(skb);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_NONE;
@@ -291,22 +295,12 @@ static int pop_eth(struct sk_buff *skb, struct sw_flow_key *key)
 static int push_eth(struct sk_buff *skb, struct sw_flow_key *key,
 		    const struct ovs_action_push_eth *ethh)
 {
-	struct ethhdr *hdr;
-
-	/* Add the new Ethernet header */
-	if (skb_cow_head(skb, ETH_HLEN) < 0)
-		return -ENOMEM;
-
-	skb_push(skb, ETH_HLEN);
-	skb_reset_mac_header(skb);
-	skb_reset_mac_len(skb);
-
-	hdr = eth_hdr(skb);
-	ether_addr_copy(hdr->h_source, ethh->addresses.eth_src);
-	ether_addr_copy(hdr->h_dest, ethh->addresses.eth_dst);
-	hdr->h_proto = skb->protocol;
+	int err;
 
-	skb_postpush_rcsum(skb, hdr, ETH_HLEN);
+	err = skb_eth_push(skb, ethh->addresses.eth_dst,
+			   ethh->addresses.eth_src);
+	if (err)
+		return err;
 
 	/* safe right before invalidate_flow_key */
 	key->mac_proto = MAC_PROTO_ETHERNET;
@@ -742,7 +736,8 @@ static int set_sctp(struct sk_buff *skb, struct sw_flow_key *flow_key,
 	return 0;
 }
 
-static int ovs_vport_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int ovs_vport_output(struct net *net, struct sock *sk,
+			    struct sk_buff *skb)
 {
 	struct ovs_frag_data *data = this_cpu_ptr(&ovs_frag_data_storage);
 	struct vport *vport = data->vport;
@@ -848,13 +843,9 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 		ip_do_fragment(net, skb->sk, skb, ovs_vport_output);
 		refdst_drop(orig_dst);
 	} else if (key->eth.type == htons(ETH_P_IPV6)) {
-		const struct nf_ipv6_ops *v6ops = nf_get_ipv6_ops();
 		unsigned long orig_dst;
 		struct rt6_info ovs_rt;
 
-		if (!v6ops)
-			goto err;
-
 		prepare_frag(vport, skb, orig_network_offset,
 			     ovs_key_mac_proto(key));
 		memset(&ovs_rt, 0, sizeof(ovs_rt));
@@ -866,7 +857,7 @@ static void ovs_fragment(struct net *net, struct vport *vport,
 		skb_dst_set_noref(skb, &ovs_rt.dst);
 		IP6CB(skb)->frag_max_size = mru;
 
-		v6ops->fragment(net, skb->sk, skb, ovs_vport_output);
+		ipv6_stub->ipv6_fragment(net, skb->sk, skb, ovs_vport_output);
 		refdst_drop(orig_dst);
 	} else {
 		WARN_ONCE(1, "Failed fragment ->%s: eth=%04x, MRU=%d, MTU=%d.",
@@ -925,7 +916,7 @@ static int output_userspace(struct datapath *dp, struct sk_buff *skb,
 	upcall.mru = OVS_CB(skb)->mru;
 
 	for (a = nla_data(attr), rem = nla_len(attr); rem > 0;
-		 a = nla_next(a, &rem)) {
+	     a = nla_next(a, &rem)) {
 		switch (nla_type(a)) {
 		case OVS_USERSPACE_ATTR_USERDATA:
 			upcall.userdata = a;
@@ -968,17 +959,13 @@ static int dec_ttl_exception_handler(struct datapath *dp, struct sk_buff *skb,
 				     struct sw_flow_key *key,
 				     const struct nlattr *attr, bool last)
 {
-	/* The first action is always 'OVS_DEC_TTL_ATTR_ARG'. */
-	struct nlattr *dec_ttl_arg = nla_data(attr);
-	int rem = nla_len(attr);
+	/* The first attribute is always 'OVS_DEC_TTL_ATTR_ACTION'. */
+	struct nlattr *actions = nla_data(attr);
 
-	if (nla_len(dec_ttl_arg)) {
-		struct nlattr *actions = nla_next(dec_ttl_arg, &rem);
+	if (nla_len(actions))
+		return clone_execute(dp, skb, key, 0, nla_data(actions),
+				     nla_len(actions), last, false);
 
-		if (actions)
-			return clone_execute(dp, skb, key, 0, actions, rem,
-					     last, false);
-	}
 	consume_skb(skb);
 	return 0;
 }
@@ -1222,7 +1209,7 @@ static int execute_dec_ttl(struct sk_buff *skb, struct sw_flow_key *key)
 			return -EHOSTUNREACH;
 
 		key->ip.ttl = --nh->hop_limit;
-	} else {
+	} else if (skb->protocol == htons(ETH_P_IP)) {
 		struct iphdr *nh;
 		u8 old_ttl;
 
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 12d42ab0193b..5eddfe7bd391 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1037,6 +1037,14 @@ static int __ovs_ct_lookup(struct net *net, struct sw_flow_key *key,
 		    ovs_ct_helper(skb, info->family) != NF_ACCEPT) {
 			return -EINVAL;
 		}
+
+		if (nf_ct_protonum(ct) == IPPROTO_TCP &&
+		    nf_ct_is_confirmed(ct) && nf_conntrack_tcp_established(ct)) {
+			/* Be liberal for tcp packets so that out-of-window
+			 * packets are not marked invalid.
+			 */
+			nf_ct_set_tcp_be_liberal(ct);
+		}
 	}
 
 	return 0;
@@ -1905,8 +1913,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net)
 					 lockdep_ovsl_is_held())
 			kfree_rcu(ct_limit, rcu);
 	}
-	kfree(ovs_net->ct_limit_info->limits);
-	kfree(ovs_net->ct_limit_info);
+	kfree(info->limits);
+	kfree(info);
 }
 
 static struct sk_buff *
@@ -2025,15 +2033,11 @@ static int ovs_ct_limit_get_default_limit(struct ovs_ct_limit_info *info,
 					  struct sk_buff *reply)
 {
 	struct ovs_zone_limit zone_limit;
-	int err;
 
 	zone_limit.zone_id = OVS_ZONE_LIMIT_DEFAULT_ZONE;
 	zone_limit.limit = info->default_limit;
-	err = nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit);
-	if (err)
-		return err;
 
-	return 0;
+	return nla_put_nohdr(reply, sizeof(zone_limit), &zone_limit);
 }
 
 static int __ovs_ct_limit_get_zone_limit(struct net *net,
@@ -2235,7 +2239,7 @@ exit_err:
 	return err;
 }
 
-static struct genl_ops ct_limit_genl_ops[] = {
+static const struct genl_small_ops ct_limit_genl_ops[] = {
 	{ .cmd = OVS_CT_LIMIT_CMD_SET,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN
@@ -2267,8 +2271,8 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = {
 	.policy = ct_limit_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = ct_limit_genl_ops,
-	.n_ops = ARRAY_SIZE(ct_limit_genl_ops),
+	.small_ops = ct_limit_genl_ops,
+	.n_small_ops = ARRAY_SIZE(ct_limit_genl_ops),
 	.mcgrps = &ovs_ct_limit_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 6e47ef7ef036..9d6ef6cb9b26 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -182,7 +182,7 @@ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no)
 
 	head = vport_hash_bucket(dp, port_no);
 	hlist_for_each_entry_rcu(vport, head, dp_hash_node,
-				lockdep_ovsl_is_held()) {
+				 lockdep_ovsl_is_held()) {
 		if (vport->port_no == port_no)
 			return vport;
 	}
@@ -254,7 +254,7 @@ void ovs_dp_process_packet(struct sk_buff *skb, struct sw_flow_key *key)
 	error = ovs_execute_actions(dp, skb, sf_acts, key);
 	if (unlikely(error))
 		net_dbg_ratelimited("ovs: action execution error on datapath %s: %d\n",
-							ovs_dp_name(dp), error);
+				    ovs_dp_name(dp), error);
 
 	stats_counter = &stats->n_hit;
 
@@ -302,7 +302,7 @@ err:
 static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb,
 			     const struct sw_flow_key *key,
 			     const struct dp_upcall_info *upcall_info,
-				 uint32_t cutlen)
+			     uint32_t cutlen)
 {
 	unsigned int gso_type = skb_shinfo(skb)->gso_type;
 	struct sw_flow_key later_key;
@@ -652,7 +652,7 @@ static const struct nla_policy packet_policy[OVS_PACKET_ATTR_MAX + 1] = {
 	[OVS_PACKET_ATTR_HASH] = { .type = NLA_U64 },
 };
 
-static const struct genl_ops dp_packet_genl_ops[] = {
+static const struct genl_small_ops dp_packet_genl_ops[] = {
 	{ .cmd = OVS_PACKET_CMD_EXECUTE,
 	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -668,8 +668,8 @@ static struct genl_family dp_packet_genl_family __ro_after_init = {
 	.policy = packet_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_packet_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_packet_genl_ops),
+	.small_ops = dp_packet_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_packet_genl_ops),
 	.module = THIS_MODULE,
 };
 
@@ -1080,11 +1080,12 @@ error:
 }
 
 /* Factor out action copy to avoid "Wframe-larger-than=1024" warning. */
-static noinline_for_stack struct sw_flow_actions *get_flow_actions(struct net *net,
-						const struct nlattr *a,
-						const struct sw_flow_key *key,
-						const struct sw_flow_mask *mask,
-						bool log)
+static noinline_for_stack
+struct sw_flow_actions *get_flow_actions(struct net *net,
+					 const struct nlattr *a,
+					 const struct sw_flow_key *key,
+					 const struct sw_flow_mask *mask,
+					 bool log)
 {
 	struct sw_flow_actions *acts;
 	struct sw_flow_key masked_key;
@@ -1383,7 +1384,8 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info)
 
 			ovs_notify(&dp_flow_genl_family, reply, info);
 		} else {
-			netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply));
+			netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0,
+					PTR_ERR(reply));
 		}
 	}
 
@@ -1451,7 +1453,7 @@ static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = {
 	[OVS_FLOW_ATTR_UFID_FLAGS] = { .type = NLA_U32 },
 };
 
-static const struct genl_ops dp_flow_genl_ops[] = {
+static const struct genl_small_ops dp_flow_genl_ops[] = {
 	{ .cmd = OVS_FLOW_CMD_NEW,
 	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -1483,8 +1485,8 @@ static struct genl_family dp_flow_genl_family __ro_after_init = {
 	.policy = flow_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_flow_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_flow_genl_ops),
+	.small_ops = dp_flow_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_flow_genl_ops),
 	.mcgrps = &ovs_dp_flow_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
@@ -1513,7 +1515,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb,
 	int err;
 
 	ovs_header = genlmsg_put(skb, portid, seq, &dp_datapath_genl_family,
-				   flags, cmd);
+				 flags, cmd);
 	if (!ovs_header)
 		goto error;
 
@@ -1572,11 +1574,13 @@ static struct datapath *lookup_datapath(struct net *net,
 	return dp ? dp : ERR_PTR(-ENODEV);
 }
 
-static void ovs_dp_reset_user_features(struct sk_buff *skb, struct genl_info *info)
+static void ovs_dp_reset_user_features(struct sk_buff *skb,
+				       struct genl_info *info)
 {
 	struct datapath *dp;
 
-	dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs);
+	dp = lookup_datapath(sock_net(skb->sk), info->userhdr,
+			     info->attrs);
 	if (IS_ERR(dp))
 		return;
 
@@ -1699,13 +1703,13 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	parms.port_no = OVSP_LOCAL;
 	parms.upcall_portids = a[OVS_DP_ATTR_UPCALL_PID];
 
-	err = ovs_dp_change(dp, a);
-	if (err)
-		goto err_destroy_meters;
-
 	/* So far only local changes have been made, now need the lock. */
 	ovs_lock();
 
+	err = ovs_dp_change(dp, a);
+	if (err)
+		goto err_unlock_and_destroy_meters;
+
 	vport = new_vport(&parms);
 	if (IS_ERR(vport)) {
 		err = PTR_ERR(vport);
@@ -1721,8 +1725,7 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 				ovs_dp_reset_user_features(skb, info);
 		}
 
-		ovs_unlock();
-		goto err_destroy_meters;
+		goto err_unlock_and_destroy_meters;
 	}
 
 	err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid,
@@ -1737,7 +1740,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info)
 	ovs_notify(&dp_datapath_genl_family, reply, info);
 	return 0;
 
-err_destroy_meters:
+err_unlock_and_destroy_meters:
+	ovs_unlock();
 	ovs_meters_exit(dp);
 err_destroy_ports:
 	kfree(dp->ports);
@@ -1914,7 +1918,7 @@ static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = {
 		PCPU_MIN_UNIT_SIZE / sizeof(struct mask_cache_entry)),
 };
 
-static const struct genl_ops dp_datapath_genl_ops[] = {
+static const struct genl_small_ops dp_datapath_genl_ops[] = {
 	{ .cmd = OVS_DP_CMD_NEW,
 	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -1946,8 +1950,8 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = {
 	.policy = datapath_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_datapath_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_datapath_genl_ops),
+	.small_ops = dp_datapath_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_datapath_genl_ops),
 	.mcgrps = &ovs_dp_datapath_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
@@ -2075,7 +2079,7 @@ static unsigned int ovs_get_max_headroom(struct datapath *dp)
 
 	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
 		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node,
-					lockdep_ovsl_is_held()) {
+					 lockdep_ovsl_is_held()) {
 			dev = vport->dev;
 			dev_headroom = netdev_get_fwd_headroom(dev);
 			if (dev_headroom > max_headroom)
@@ -2093,10 +2097,11 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom)
 	int i;
 
 	dp->max_headroom = new_headroom;
-	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++)
+	for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) {
 		hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node,
-					lockdep_ovsl_is_held())
+					 lockdep_ovsl_is_held())
 			netdev_set_rx_headroom(vport->dev, new_headroom);
+	}
 }
 
 static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info)
@@ -2396,7 +2401,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = {
 	[OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 },
 };
 
-static const struct genl_ops dp_vport_genl_ops[] = {
+static const struct genl_small_ops dp_vport_genl_ops[] = {
 	{ .cmd = OVS_VPORT_CMD_NEW,
 	  .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 	  .flags = GENL_UNS_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */
@@ -2428,8 +2433,8 @@ struct genl_family dp_vport_genl_family __ro_after_init = {
 	.policy = vport_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_vport_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_vport_genl_ops),
+	.small_ops = dp_vport_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_vport_genl_ops),
 	.mcgrps = &ovs_dp_vport_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
@@ -2476,13 +2481,19 @@ error:
 static int __net_init ovs_init_net(struct net *net)
 {
 	struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
+	int err;
 
 	INIT_LIST_HEAD(&ovs_net->dps);
 	INIT_WORK(&ovs_net->dp_notify_work, ovs_dp_notify_wq);
 	INIT_DELAYED_WORK(&ovs_net->masks_rebalance, ovs_dp_masks_rebalance);
+
+	err = ovs_ct_init(net);
+	if (err)
+		return err;
+
 	schedule_delayed_work(&ovs_net->masks_rebalance,
 			      msecs_to_jiffies(DP_MASKS_REBALANCE_INTERVAL));
-	return ovs_ct_init(net);
+	return 0;
 }
 
 static void __net_exit list_vports_from_net(struct net *net, struct net *dnet,
@@ -2551,7 +2562,8 @@ static int __init dp_init(void)
 {
 	int err;
 
-	BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_field(struct sk_buff, cb));
+	BUILD_BUG_ON(sizeof(struct ovs_skb_cb) >
+		     sizeof_field(struct sk_buff, cb));
 
 	pr_info("Open vSwitch switching datapath\n");
 
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index b03d142ec82e..c7f34d6a9934 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -294,6 +294,10 @@ static bool icmp6hdr_ok(struct sk_buff *skb)
 
 /**
  * Parse vlan tag from vlan header.
+ * @skb: skb containing frame to parse
+ * @key_vh: pointer to parsed vlan tag
+ * @untag_vlan: should the vlan header be removed from the frame
+ *
  * Returns ERROR on memory error.
  * Returns 0 if it encounters a non-vlan or incomplete packet.
  * Returns 1 after successfully parsing vlan tag.
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 9d3e50c4d29f..4c5c2331e764 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2503,28 +2503,42 @@ static int validate_and_copy_dec_ttl(struct net *net,
 				     __be16 eth_type, __be16 vlan_tci,
 				     u32 mpls_label_count, bool log)
 {
-	int start, err;
-	u32 nested = true;
+	const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1];
+	int start, action_start, err, rem;
+	const struct nlattr *a, *actions;
+
+	memset(attrs, 0, sizeof(attrs));
+	nla_for_each_nested(a, attr, rem) {
+		int type = nla_type(a);
 
-	if (!nla_len(attr))
-		return ovs_nla_add_action(sfa, OVS_ACTION_ATTR_DEC_TTL,
-					  NULL, 0, log);
+		/* Ignore unknown attributes to be future proof. */
+		if (type > OVS_DEC_TTL_ATTR_MAX)
+			continue;
+
+		if (!type || attrs[type])
+			return -EINVAL;
+
+		attrs[type] = a;
+	}
+
+	actions = attrs[OVS_DEC_TTL_ATTR_ACTION];
+	if (rem || !actions || (nla_len(actions) && nla_len(actions) < NLA_HDRLEN))
+		return -EINVAL;
 
 	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_DEC_TTL, log);
 	if (start < 0)
 		return start;
 
-	err = ovs_nla_add_action(sfa, OVS_DEC_TTL_ATTR_ACTION, &nested,
-				 sizeof(nested), log);
+	action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log);
+	if (action_start < 0)
+		return action_start;
 
-	if (err)
-		return err;
-
-	err = __ovs_nla_copy_actions(net, attr, key, sfa, eth_type,
+	err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type,
 				     vlan_tci, mpls_label_count, log);
 	if (err)
 		return err;
 
+	add_nested_action_end(*sfa, action_start);
 	add_nested_action_end(*sfa, start);
 	return 0;
 }
@@ -3487,20 +3501,42 @@ out:
 static int dec_ttl_action_to_attr(const struct nlattr *attr,
 				  struct sk_buff *skb)
 {
-	int err = 0, rem = nla_len(attr);
-	struct nlattr *start;
+	struct nlattr *start, *action_start;
+	const struct nlattr *a;
+	int err = 0, rem;
 
 	start = nla_nest_start_noflag(skb, OVS_ACTION_ATTR_DEC_TTL);
-
 	if (!start)
 		return -EMSGSIZE;
 
-	err = ovs_nla_put_actions(nla_data(attr), rem, skb);
-	if (err)
-		nla_nest_cancel(skb, start);
-	else
-		nla_nest_end(skb, start);
+	nla_for_each_attr(a, nla_data(attr), nla_len(attr), rem) {
+		switch (nla_type(a)) {
+		case OVS_DEC_TTL_ATTR_ACTION:
+
+			action_start = nla_nest_start_noflag(skb, OVS_DEC_TTL_ATTR_ACTION);
+			if (!action_start) {
+				err = -EMSGSIZE;
+				goto out;
+			}
+
+			err = ovs_nla_put_actions(nla_data(a), nla_len(a), skb);
+			if (err)
+				goto out;
+
+			nla_nest_end(skb, action_start);
+			break;
 
+		default:
+			/* Ignore all other option to be future compatible */
+			break;
+		}
+	}
+
+	nla_nest_end(skb, start);
+	return 0;
+
+out:
+	nla_nest_cancel(skb, start);
 	return err;
 }
 
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index e2235849a57e..c89c8da99f1a 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -111,12 +111,16 @@ static void flow_free(struct sw_flow *flow)
 	if (ovs_identifier_is_key(&flow->id))
 		kfree(flow->id.unmasked_key);
 	if (flow->sf_acts)
-		ovs_nla_free_flow_actions((struct sw_flow_actions __force *)flow->sf_acts);
+		ovs_nla_free_flow_actions((struct sw_flow_actions __force *)
+					  flow->sf_acts);
 	/* We open code this to make sure cpu 0 is always considered */
-	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask))
+	for (cpu = 0; cpu < nr_cpu_ids;
+	     cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
 		if (flow->stats[cpu])
 			kmem_cache_free(flow_stats_cache,
 					(struct sw_flow_stats __force *)flow->stats[cpu]);
+	}
+
 	kmem_cache_free(flow_cache, flow);
 }
 
@@ -164,7 +168,6 @@ static struct table_instance *table_instance_alloc(int new_size)
 
 	ti->n_buckets = new_size;
 	ti->node_ver = 0;
-	ti->keep_flows = false;
 	get_random_bytes(&ti->hash_seed, sizeof(u32));
 
 	return ti;
@@ -172,7 +175,7 @@ static struct table_instance *table_instance_alloc(int new_size)
 
 static void __mask_array_destroy(struct mask_array *ma)
 {
-	free_percpu(ma->masks_usage_cntr);
+	free_percpu(ma->masks_usage_stats);
 	kfree(ma);
 }
 
@@ -192,19 +195,19 @@ static void tbl_mask_array_reset_counters(struct mask_array *ma)
 	 * zero based counter we store the value at reset, and subtract it
 	 * later when processing.
 	 */
-	for (i = 0; i < ma->max; i++)  {
+	for (i = 0; i < ma->max; i++) {
 		ma->masks_usage_zero_cntr[i] = 0;
 
 		for_each_possible_cpu(cpu) {
-			u64 *usage_counters = per_cpu_ptr(ma->masks_usage_cntr,
-							  cpu);
+			struct mask_array_stats *stats;
 			unsigned int start;
 			u64 counter;
 
+			stats = per_cpu_ptr(ma->masks_usage_stats, cpu);
 			do {
-				start = u64_stats_fetch_begin_irq(&ma->syncp);
-				counter = usage_counters[i];
-			} while (u64_stats_fetch_retry_irq(&ma->syncp, start));
+				start = u64_stats_fetch_begin_irq(&stats->syncp);
+				counter = stats->usage_cntrs[i];
+			} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
 
 			ma->masks_usage_zero_cntr[i] += counter;
 		}
@@ -227,9 +230,10 @@ static struct mask_array *tbl_mask_array_alloc(int size)
 					     sizeof(struct sw_flow_mask *) *
 					     size);
 
-	new->masks_usage_cntr = __alloc_percpu(sizeof(u64) * size,
-					       __alignof__(u64));
-	if (!new->masks_usage_cntr) {
+	new->masks_usage_stats = __alloc_percpu(sizeof(struct mask_array_stats) +
+						sizeof(u64) * size,
+						__alignof__(u64));
+	if (!new->masks_usage_stats) {
 		kfree(new);
 		return NULL;
 	}
@@ -273,7 +277,7 @@ static int tbl_mask_array_add_mask(struct flow_table *tbl,
 
 	if (ma_count >= ma->max) {
 		err = tbl_mask_array_realloc(tbl, ma->max +
-					      MASK_ARRAY_SIZE_MIN);
+						  MASK_ARRAY_SIZE_MIN);
 		if (err)
 			return err;
 
@@ -288,7 +292,7 @@ static int tbl_mask_array_add_mask(struct flow_table *tbl,
 	BUG_ON(ovsl_dereference(ma->masks[ma_count]));
 
 	rcu_assign_pointer(ma->masks[ma_count], new);
-	WRITE_ONCE(ma->count, ma_count +1);
+	WRITE_ONCE(ma->count, ma_count + 1);
 
 	return 0;
 }
@@ -309,10 +313,10 @@ static void tbl_mask_array_del_mask(struct flow_table *tbl,
 	return;
 
 found:
-	WRITE_ONCE(ma->count, ma_count -1);
+	WRITE_ONCE(ma->count, ma_count - 1);
 
-	rcu_assign_pointer(ma->masks[i], ma->masks[ma_count -1]);
-	RCU_INIT_POINTER(ma->masks[ma_count -1], NULL);
+	rcu_assign_pointer(ma->masks[i], ma->masks[ma_count - 1]);
+	RCU_INIT_POINTER(ma->masks[ma_count - 1], NULL);
 
 	kfree_rcu(mask, rcu);
 
@@ -386,7 +390,7 @@ static struct mask_cache *tbl_mask_cache_alloc(u32 size)
 }
 int ovs_flow_tbl_masks_cache_resize(struct flow_table *table, u32 size)
 {
-	struct mask_cache *mc = rcu_dereference(table->mask_cache);
+	struct mask_cache *mc = rcu_dereference_ovsl(table->mask_cache);
 	struct mask_cache *new;
 
 	if (size == mc->cache_size)
@@ -448,26 +452,23 @@ free_mask_cache:
 
 static void flow_tbl_destroy_rcu_cb(struct rcu_head *rcu)
 {
-	struct table_instance *ti = container_of(rcu, struct table_instance, rcu);
+	struct table_instance *ti;
 
+	ti = container_of(rcu, struct table_instance, rcu);
 	__table_instance_destroy(ti);
 }
 
 static void table_instance_flow_free(struct flow_table *table,
-				  struct table_instance *ti,
-				  struct table_instance *ufid_ti,
-				  struct sw_flow *flow,
-				  bool count)
+				     struct table_instance *ti,
+				     struct table_instance *ufid_ti,
+				     struct sw_flow *flow)
 {
 	hlist_del_rcu(&flow->flow_table.node[ti->node_ver]);
-	if (count)
-		table->count--;
+	table->count--;
 
 	if (ovs_identifier_is_ufid(&flow->id)) {
 		hlist_del_rcu(&flow->ufid_table.node[ufid_ti->node_ver]);
-
-		if (count)
-			table->ufid_count--;
+		table->ufid_count--;
 	}
 
 	flow_mask_remove(table, flow->mask);
@@ -480,22 +481,25 @@ void table_instance_flow_flush(struct flow_table *table,
 {
 	int i;
 
-	if (ti->keep_flows)
-		return;
-
 	for (i = 0; i < ti->n_buckets; i++) {
-		struct sw_flow *flow;
 		struct hlist_head *head = &ti->buckets[i];
 		struct hlist_node *n;
+		struct sw_flow *flow;
 
 		hlist_for_each_entry_safe(flow, n, head,
 					  flow_table.node[ti->node_ver]) {
 
 			table_instance_flow_free(table, ti, ufid_ti,
-						 flow, false);
+						 flow);
 			ovs_flow_free(flow, true);
 		}
 	}
+
+	if (WARN_ON(table->count != 0 ||
+		    table->ufid_count != 0)) {
+		table->count = 0;
+		table->ufid_count = 0;
+	}
 }
 
 static void table_instance_destroy(struct table_instance *ti,
@@ -596,8 +600,6 @@ static void flow_table_copy_flows(struct table_instance *old,
 						 lockdep_ovsl_is_held())
 				table_instance_insert(new, flow);
 	}
-
-	old->keep_flows = true;
 }
 
 static struct table_instance *table_instance_rehash(struct table_instance *ti,
@@ -632,8 +634,6 @@ int ovs_flow_tbl_flush(struct flow_table *flow_table)
 	rcu_assign_pointer(flow_table->ti, new_ti);
 	rcu_assign_pointer(flow_table->ufid_ti, new_ufid_ti);
 	flow_table->last_rehash = jiffies;
-	flow_table->count = 0;
-	flow_table->ufid_count = 0;
 
 	table_instance_flow_flush(flow_table, old_ti, old_ufid_ti);
 	table_instance_destroy(old_ti, old_ufid_ti);
@@ -661,7 +661,7 @@ static int flow_key_start(const struct sw_flow_key *key)
 		return 0;
 	else
 		return rounddown(offsetof(struct sw_flow_key, phy),
-					  sizeof(long));
+				 sizeof(long));
 }
 
 static bool cmp_key(const struct sw_flow_key *key1,
@@ -673,7 +673,7 @@ static bool cmp_key(const struct sw_flow_key *key1,
 	long diffs = 0;
 	int i;
 
-	for (i = key_start; i < key_end;  i += sizeof(long))
+	for (i = key_start; i < key_end; i += sizeof(long))
 		diffs |= *cp1++ ^ *cp2++;
 
 	return diffs == 0;
@@ -713,7 +713,7 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 	(*n_mask_hit)++;
 
 	hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver],
-				lockdep_ovsl_is_held()) {
+				 lockdep_ovsl_is_held()) {
 		if (flow->mask == mask && flow->flow_table.hash == hash &&
 		    flow_cmp_masked_key(flow, &masked_key, &mask->range))
 			return flow;
@@ -723,6 +723,8 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti,
 
 /* Flow lookup does full lookup on flow table. It starts with
  * mask from index passed in *index.
+ * This function MUST be called with BH disabled due to the use
+ * of CPU specific variables.
  */
 static struct sw_flow *flow_lookup(struct flow_table *tbl,
 				   struct table_instance *ti,
@@ -732,7 +734,7 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl,
 				   u32 *n_cache_hit,
 				   u32 *index)
 {
-	u64 *usage_counters = this_cpu_ptr(ma->masks_usage_cntr);
+	struct mask_array_stats *stats = this_cpu_ptr(ma->masks_usage_stats);
 	struct sw_flow *flow;
 	struct sw_flow_mask *mask;
 	int i;
@@ -742,9 +744,9 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl,
 		if (mask) {
 			flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
 			if (flow) {
-				u64_stats_update_begin(&ma->syncp);
-				usage_counters[*index]++;
-				u64_stats_update_end(&ma->syncp);
+				u64_stats_update_begin(&stats->syncp);
+				stats->usage_cntrs[*index]++;
+				u64_stats_update_end(&stats->syncp);
 				(*n_cache_hit)++;
 				return flow;
 			}
@@ -763,9 +765,9 @@ static struct sw_flow *flow_lookup(struct flow_table *tbl,
 		flow = masked_flow_lookup(ti, key, mask, n_mask_hit);
 		if (flow) { /* Found */
 			*index = i;
-			u64_stats_update_begin(&ma->syncp);
-			usage_counters[*index]++;
-			u64_stats_update_end(&ma->syncp);
+			u64_stats_update_begin(&stats->syncp);
+			stats->usage_cntrs[*index]++;
+			u64_stats_update_end(&stats->syncp);
 			return flow;
 		}
 	}
@@ -851,9 +853,17 @@ struct sw_flow *ovs_flow_tbl_lookup(struct flow_table *tbl,
 	struct mask_array *ma = rcu_dereference_ovsl(tbl->mask_array);
 	u32 __always_unused n_mask_hit;
 	u32 __always_unused n_cache_hit;
+	struct sw_flow *flow;
 	u32 index = 0;
 
-	return flow_lookup(tbl, ti, ma, key, &n_mask_hit, &n_cache_hit, &index);
+	/* This function gets called trough the netlink interface and therefore
+	 * is preemptible. However, flow_lookup() function needs to be called
+	 * with BH disabled due to CPU specific variables.
+	 */
+	local_bh_disable();
+	flow = flow_lookup(tbl, ti, ma, key, &n_mask_hit, &n_cache_hit, &index);
+	local_bh_enable();
+	return flow;
 }
 
 struct sw_flow *ovs_flow_tbl_lookup_exact(struct flow_table *tbl,
@@ -897,7 +907,8 @@ static bool ovs_flow_cmp_ufid(const struct sw_flow *flow,
 	return !memcmp(flow->id.ufid, sfid->ufid, sfid->ufid_len);
 }
 
-bool ovs_flow_cmp(const struct sw_flow *flow, const struct sw_flow_match *match)
+bool ovs_flow_cmp(const struct sw_flow *flow,
+		  const struct sw_flow_match *match)
 {
 	if (ovs_identifier_is_ufid(&flow->id))
 		return flow_cmp_masked_key(flow, match->key, &match->range);
@@ -916,7 +927,7 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl,
 	hash = ufid_hash(ufid);
 	head = find_bucket(ti, hash);
 	hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver],
-				lockdep_ovsl_is_held()) {
+				 lockdep_ovsl_is_held()) {
 		if (flow->ufid_table.hash == hash &&
 		    ovs_flow_cmp_ufid(flow, ufid))
 			return flow;
@@ -950,7 +961,7 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow)
 	struct table_instance *ufid_ti = ovsl_dereference(table->ufid_ti);
 
 	BUG_ON(table->count == 0);
-	table_instance_flow_free(table, ti, ufid_ti, flow, true);
+	table_instance_flow_free(table, ti, ufid_ti, flow);
 }
 
 static struct sw_flow_mask *mask_alloc(void)
@@ -1107,9 +1118,8 @@ void ovs_flow_masks_rebalance(struct flow_table *table)
 	if (!masks_and_count)
 		return;
 
-	for (i = 0; i < ma->max; i++)  {
+	for (i = 0; i < ma->max; i++) {
 		struct sw_flow_mask *mask;
-		unsigned int start;
 		int cpu;
 
 		mask = rcu_dereference_ovsl(ma->masks[i]);
@@ -1120,14 +1130,16 @@ void ovs_flow_masks_rebalance(struct flow_table *table)
 		masks_and_count[i].counter = 0;
 
 		for_each_possible_cpu(cpu) {
-			u64 *usage_counters = per_cpu_ptr(ma->masks_usage_cntr,
-							  cpu);
+			struct mask_array_stats *stats;
+			unsigned int start;
 			u64 counter;
 
+			stats = per_cpu_ptr(ma->masks_usage_stats, cpu);
 			do {
-				start = u64_stats_fetch_begin_irq(&ma->syncp);
-				counter = usage_counters[i];
-			} while (u64_stats_fetch_retry_irq(&ma->syncp, start));
+				start = u64_stats_fetch_begin_irq(&stats->syncp);
+				counter = stats->usage_cntrs[i];
+			} while (u64_stats_fetch_retry_irq(&stats->syncp,
+							   start));
 
 			masks_and_count[i].counter += counter;
 		}
diff --git a/net/openvswitch/flow_table.h b/net/openvswitch/flow_table.h
index 6e7d4ac59353..9e659db78c05 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -38,12 +38,16 @@ struct mask_count {
 	u64 counter;
 };
 
+struct mask_array_stats {
+	struct u64_stats_sync syncp;
+	u64 usage_cntrs[];
+};
+
 struct mask_array {
 	struct rcu_head rcu;
 	int count, max;
-	u64 __percpu *masks_usage_cntr;
+	struct mask_array_stats __percpu *masks_usage_stats;
 	u64 *masks_usage_zero_cntr;
-	struct u64_stats_sync syncp;
 	struct sw_flow_mask __rcu *masks[];
 };
 
@@ -53,7 +57,6 @@ struct table_instance {
 	struct rcu_head rcu;
 	int node_ver;
 	u32 hash_seed;
-	bool keep_flows;
 };
 
 struct flow_table {
diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 3d3d8e094546..15424d26e85d 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c
@@ -423,7 +423,7 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 
 	meter = dp_meter_create(a);
-	if (IS_ERR_OR_NULL(meter))
+	if (IS_ERR(meter))
 		return PTR_ERR(meter);
 
 	reply = ovs_meter_cmd_reply_start(info, OVS_METER_CMD_SET,
@@ -672,7 +672,7 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
 	return false;
 }
 
-static struct genl_ops dp_meter_genl_ops[] = {
+static const struct genl_small_ops dp_meter_genl_ops[] = {
 	{ .cmd = OVS_METER_CMD_FEATURES,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.flags = 0,		  /* OK for unprivileged users. */
@@ -711,8 +711,8 @@ struct genl_family dp_meter_genl_family __ro_after_init = {
 	.policy = meter_policy,
 	.netnsok = true,
 	.parallel_ops = true,
-	.ops = dp_meter_genl_ops,
-	.n_ops = ARRAY_SIZE(dp_meter_genl_ops),
+	.small_ops = dp_meter_genl_ops,
+	.n_small_ops = ARRAY_SIZE(dp_meter_genl_ops),
 	.mcgrps = &ovs_meter_multicast_group,
 	.n_mcgrps = 1,
 	.module = THIS_MODULE,
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 58a7b8312c28..5b2ee9c1c00b 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -35,21 +35,18 @@ internal_dev_xmit(struct sk_buff *skb, struct net_device *netdev)
 {
 	int len, err;
 
+	/* store len value because skb can be freed inside ovs_vport_receive() */
 	len = skb->len;
+
 	rcu_read_lock();
 	err = ovs_vport_receive(internal_dev_priv(netdev)->vport, skb, NULL);
 	rcu_read_unlock();
 
-	if (likely(!err)) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(netdev->tstats);
-
-		u64_stats_update_begin(&tstats->syncp);
-		tstats->tx_bytes += len;
-		tstats->tx_packets++;
-		u64_stats_update_end(&tstats->syncp);
-	} else {
+	if (likely(!err))
+		dev_sw_netstats_tx_add(netdev, 1, len);
+	else
 		netdev->stats.tx_errors++;
-	}
+
 	return NETDEV_TX_OK;
 }
 
@@ -83,42 +80,12 @@ static void internal_dev_destructor(struct net_device *dev)
 	ovs_vport_free(vport);
 }
 
-static void
-internal_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
-{
-	int i;
-
-	memset(stats, 0, sizeof(*stats));
-	stats->rx_errors  = dev->stats.rx_errors;
-	stats->tx_errors  = dev->stats.tx_errors;
-	stats->tx_dropped = dev->stats.tx_dropped;
-	stats->rx_dropped = dev->stats.rx_dropped;
-
-	for_each_possible_cpu(i) {
-		const struct pcpu_sw_netstats *percpu_stats;
-		struct pcpu_sw_netstats local_stats;
-		unsigned int start;
-
-		percpu_stats = per_cpu_ptr(dev->tstats, i);
-
-		do {
-			start = u64_stats_fetch_begin_irq(&percpu_stats->syncp);
-			local_stats = *percpu_stats;
-		} while (u64_stats_fetch_retry_irq(&percpu_stats->syncp, start));
-
-		stats->rx_bytes         += local_stats.rx_bytes;
-		stats->rx_packets       += local_stats.rx_packets;
-		stats->tx_bytes         += local_stats.tx_bytes;
-		stats->tx_packets       += local_stats.tx_packets;
-	}
-}
-
 static const struct net_device_ops internal_dev_netdev_ops = {
 	.ndo_open = internal_dev_open,
 	.ndo_stop = internal_dev_stop,
 	.ndo_start_xmit = internal_dev_xmit,
 	.ndo_set_mac_address = eth_mac_addr,
-	.ndo_get_stats64 = internal_get_stats,
+	.ndo_get_stats64 = dev_get_tstats64,
 };
 
 static struct rtnl_link_ops internal_dev_link_ops __read_mostly = {
@@ -225,7 +192,6 @@ static void internal_dev_destroy(struct vport *vport)
 static netdev_tx_t internal_dev_recv(struct sk_buff *skb)
 {
 	struct net_device *netdev = skb->dev;
-	struct pcpu_sw_netstats *stats;
 
 	if (unlikely(!(netdev->flags & IFF_UP))) {
 		kfree_skb(skb);
@@ -240,12 +206,7 @@ static netdev_tx_t internal_dev_recv(struct sk_buff *skb)
 	skb->pkt_type = PACKET_HOST;
 	skb->protocol = eth_type_trans(skb, netdev);
 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
-
-	stats = this_cpu_ptr(netdev->tstats);
-	u64_stats_update_begin(&stats->syncp);
-	stats->rx_packets++;
-	stats->rx_bytes += skb->len;
-	u64_stats_update_end(&stats->syncp);
+	dev_sw_netstats_rx_add(netdev, skb->len);
 
 	netif_rx(skb);
 	return NETDEV_TX_OK;
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 0d44c5c013fa..4ed7e52c7012 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -98,7 +98,7 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name)
 	struct vport *vport;
 
 	hlist_for_each_entry_rcu(vport, bucket, hash_node,
-				lockdep_ovsl_is_held())
+				 lockdep_ovsl_is_held())
 		if (!strcmp(name, ovs_vport_name(vport)) &&
 		    net_eq(ovs_dp_get_net(vport->dp), net))
 			return vport;
@@ -111,14 +111,16 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name)
  *
  * @priv_size: Size of private data area to allocate.
  * @ops: vport device ops
+ * @parms: information about new vport.
  *
  * Allocate and initialize a new vport defined by @ops.  The vport will contain
  * a private data area of size @priv_size that can be accessed using
- * vport_priv().  vports that are no longer needed should be released with
+ * vport_priv().  Some parameters of the vport will be initialized from @parms.
+ * @vports that are no longer needed should be released with
  * vport_free().
  */
 struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
-			  const struct vport_parms *parms)
+			      const struct vport_parms *parms)
 {
 	struct vport *vport;
 	size_t alloc_size;
@@ -397,7 +399,8 @@ int ovs_vport_get_upcall_portids(const struct vport *vport,
  *
  * Returns the portid of the target socket.  Must be called with rcu_read_lock.
  */
-u32 ovs_vport_find_upcall_portid(const struct vport *vport, struct sk_buff *skb)
+u32 ovs_vport_find_upcall_portid(const struct vport *vport,
+				 struct sk_buff *skb)
 {
 	struct vport_portids *ids;
 	u32 ids_index;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 2b33e977a905..6bbc7a448593 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -46,6 +46,7 @@
  *					Copyright (C) 2011, <lokec@ccs.neu.edu>
  */
 
+#include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/capability.h>
@@ -93,52 +94,56 @@
 
 /*
    Assumptions:
-   - if device has no dev->hard_header routine, it adds and removes ll header
-     inside itself. In this case ll header is invisible outside of device,
-     but higher levels still should reserve dev->hard_header_len.
-     Some devices are enough clever to reallocate skb, when header
-     will not fit to reserved space (tunnel), another ones are silly
-     (PPP).
+   - If the device has no dev->header_ops->create, there is no LL header
+     visible above the device. In this case, its hard_header_len should be 0.
+     The device may prepend its own header internally. In this case, its
+     needed_headroom should be set to the space needed for it to add its
+     internal header.
+     For example, a WiFi driver pretending to be an Ethernet driver should
+     set its hard_header_len to be the Ethernet header length, and set its
+     needed_headroom to be (the real WiFi header length - the fake Ethernet
+     header length).
    - packet socket receives packets with pulled ll header,
      so that SOCK_RAW should push it back.
 
 On receive:
 -----------
 
-Incoming, dev->hard_header!=NULL
+Incoming, dev_has_header(dev) == true
    mac_header -> ll header
    data       -> data
 
-Outgoing, dev->hard_header!=NULL
+Outgoing, dev_has_header(dev) == true
    mac_header -> ll header
    data       -> ll header
 
-Incoming, dev->hard_header==NULL
-   mac_header -> UNKNOWN position. It is very likely, that it points to ll
-		 header.  PPP makes it, that is wrong, because introduce
-		 assymetry between rx and tx paths.
+Incoming, dev_has_header(dev) == false
+   mac_header -> data
+     However drivers often make it point to the ll header.
+     This is incorrect because the ll header should be invisible to us.
    data       -> data
 
-Outgoing, dev->hard_header==NULL
-   mac_header -> data. ll header is still not built!
+Outgoing, dev_has_header(dev) == false
+   mac_header -> data. ll header is invisible to us.
    data       -> data
 
 Resume
-  If dev->hard_header==NULL we are unlikely to restore sensible ll header.
+  If dev_has_header(dev) == false we are unable to restore the ll header,
+    because it is invisible to us.
 
 
 On transmit:
 ------------
 
-dev->hard_header != NULL
+dev->header_ops != NULL
    mac_header -> ll header
    data       -> ll header
 
-dev->hard_header == NULL (ll header is added by device, we cannot control it)
+dev->header_ops == NULL (ll header is invisible to us)
    mac_header -> data
    data       -> data
 
-   We should set nh.raw on output to correct posistion,
+   We should set network_header on output to the correct position,
    packet classifier depends on it.
  */
 
@@ -177,7 +182,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 #define BLOCK_LEN(x)		((x)->hdr.bh1.blk_len)
 #define BLOCK_SNUM(x)		((x)->hdr.bh1.seq_num)
 #define BLOCK_O2PRIV(x)	((x)->offset_to_priv)
-#define BLOCK_PRIV(x)		((void *)((char *)(x) + BLOCK_O2PRIV(x)))
 
 struct packet_sock;
 static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
@@ -1633,13 +1637,15 @@ static bool fanout_find_new_id(struct sock *sk, u16 *new_id)
 	return false;
 }
 
-static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
+static int fanout_add(struct sock *sk, struct fanout_args *args)
 {
 	struct packet_rollover *rollover = NULL;
 	struct packet_sock *po = pkt_sk(sk);
+	u16 type_flags = args->type_flags;
 	struct packet_fanout *f, *match;
 	u8 type = type_flags & 0xff;
 	u8 flags = type_flags >> 8;
+	u16 id = args->id;
 	int err;
 
 	switch (type) {
@@ -1697,11 +1703,21 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		}
 	}
 	err = -EINVAL;
-	if (match && match->flags != flags)
-		goto out;
-	if (!match) {
+	if (match) {
+		if (match->flags != flags)
+			goto out;
+		if (args->max_num_members &&
+		    args->max_num_members != match->max_num_members)
+			goto out;
+	} else {
+		if (args->max_num_members > PACKET_FANOUT_MAX)
+			goto out;
+		if (!args->max_num_members)
+			/* legacy PACKET_FANOUT_MAX */
+			args->max_num_members = 256;
 		err = -ENOMEM;
-		match = kzalloc(sizeof(*match), GFP_KERNEL);
+		match = kvzalloc(struct_size(match, arr, args->max_num_members),
+				 GFP_KERNEL);
 		if (!match)
 			goto out;
 		write_pnet(&match->net, sock_net(sk));
@@ -1717,6 +1733,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 		match->prot_hook.func = packet_rcv_fanout;
 		match->prot_hook.af_packet_priv = match;
 		match->prot_hook.id_match = match_fanout_group;
+		match->max_num_members = args->max_num_members;
 		list_add(&match->list, &fanout_list);
 	}
 	err = -EINVAL;
@@ -1727,7 +1744,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 	    match->prot_hook.type == po->prot_hook.type &&
 	    match->prot_hook.dev == po->prot_hook.dev) {
 		err = -ENOSPC;
-		if (refcount_read(&match->sk_ref) < PACKET_FANOUT_MAX) {
+		if (refcount_read(&match->sk_ref) < match->max_num_members) {
 			__dev_remove_pack(&po->prot_hook);
 			po->fanout = match;
 			po->rollover = rollover;
@@ -1741,7 +1758,7 @@ static int fanout_add(struct sock *sk, u16 id, u16 type_flags)
 
 	if (err && !refcount_read(&match->sk_ref)) {
 		list_del(&match->list);
-		kfree(match);
+		kvfree(match);
 	}
 
 out:
@@ -2066,7 +2083,7 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	skb->dev = dev;
 
-	if (dev->header_ops) {
+	if (dev_has_header(dev)) {
 		/* The device has an explicit notion of ll header,
 		 * exported to higher levels.
 		 *
@@ -2195,7 +2212,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
 	if (!net_eq(dev_net(dev), sock_net(sk)))
 		goto drop;
 
-	if (dev->header_ops) {
+	if (dev_has_header(dev)) {
 		if (sk->sk_type != SOCK_DGRAM)
 			skb_push(skb, skb->data - skb_mac_header(skb));
 		else if (skb->pkt_type == PACKET_OUTGOING) {
@@ -3072,7 +3089,7 @@ static int packet_release(struct socket *sock)
 	kfree(po->rollover);
 	if (f) {
 		fanout_release_data(f);
-		kfree(f);
+		kvfree(f);
 	}
 	/*
 	 *	Now the socket is dead. No more input will appear.
@@ -3863,14 +3880,14 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval,
 	}
 	case PACKET_FANOUT:
 	{
-		int val;
+		struct fanout_args args = { 0 };
 
-		if (optlen != sizeof(val))
+		if (optlen != sizeof(int) && optlen != sizeof(args))
 			return -EINVAL;
-		if (copy_from_sockptr(&val, optval, sizeof(val)))
+		if (copy_from_sockptr(&args, optval, optlen))
 			return -EFAULT;
 
-		return fanout_add(sk, val & 0xffff, val >> 16);
+		return fanout_add(sk, &args);
 	}
 	case PACKET_FANOUT_DATA:
 	{
@@ -4578,7 +4595,9 @@ static void packet_seq_stop(struct seq_file *seq, void *v)
 static int packet_seq_show(struct seq_file *seq, void *v)
 {
 	if (v == SEQ_START_TOKEN)
-		seq_puts(seq, "sk       RefCnt Type Proto  Iface R Rmem   User   Inode\n");
+		seq_printf(seq,
+			   "%*sRefCnt Type Proto  Iface R Rmem   User   Inode\n",
+			   IS_ENABLED(CONFIG_64BIT) ? -17 : -9, "sk");
 	else {
 		struct sock *s = sk_entry(v);
 		const struct packet_sock *po = pkt_sk(s);
@@ -4612,9 +4631,11 @@ static int __net_init packet_net_init(struct net *net)
 	mutex_init(&net->packet.sklist_lock);
 	INIT_HLIST_HEAD(&net->packet.sklist);
 
+#ifdef CONFIG_PROC_FS
 	if (!proc_create_net("packet", 0, net->proc_net, &packet_seq_ops,
 			sizeof(struct seq_net_private)))
 		return -ENOMEM;
+#endif /* CONFIG_PROC_FS */
 
 	return 0;
 }
diff --git a/net/packet/internal.h b/net/packet/internal.h
index fd41ecb7f605..baafc3f3fa25 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -77,11 +77,12 @@ struct packet_ring_buffer {
 };
 
 extern struct mutex fanout_mutex;
-#define PACKET_FANOUT_MAX	256
+#define PACKET_FANOUT_MAX	(1 << 16)
 
 struct packet_fanout {
 	possible_net_t		net;
 	unsigned int		num_members;
+	u32			max_num_members;
 	u16			id;
 	u8			type;
 	u8			flags;
@@ -90,10 +91,10 @@ struct packet_fanout {
 		struct bpf_prog __rcu	*bpf_prog;
 	};
 	struct list_head	list;
-	struct sock		*arr[PACKET_FANOUT_MAX];
 	spinlock_t		lock;
 	refcount_t		sk_ref;
 	struct packet_type	prot_hook ____cacheline_aligned_in_smp;
+	struct sock		*arr[];
 };
 
 struct packet_rollover {
diff --git a/net/psample/psample.c b/net/psample/psample.c
index a042261a45c5..33e238c965bd 100644
--- a/net/psample/psample.c
+++ b/net/psample/psample.c
@@ -96,7 +96,7 @@ static int psample_nl_cmd_get_group_dumpit(struct sk_buff *msg,
 	return msg->len;
 }
 
-static const struct genl_ops psample_nl_ops[] = {
+static const struct genl_small_ops psample_nl_ops[] = {
 	{
 		.cmd = PSAMPLE_CMD_GET_GROUP,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -112,8 +112,8 @@ static struct genl_family psample_nl_family __ro_after_init = {
 	.netnsok	= true,
 	.module		= THIS_MODULE,
 	.mcgrps		= psample_nl_mcgrps,
-	.ops		= psample_nl_ops,
-	.n_ops		= ARRAY_SIZE(psample_nl_ops),
+	.small_ops	= psample_nl_ops,
+	.n_small_ops	= ARRAY_SIZE(psample_nl_ops),
 	.n_mcgrps	= ARRAY_SIZE(psample_nl_mcgrps),
 };
 
diff --git a/net/qrtr/mhi.c b/net/qrtr/mhi.c
index ff0c41467fc1..2bf2b1943e61 100644
--- a/net/qrtr/mhi.c
+++ b/net/qrtr/mhi.c
@@ -76,6 +76,11 @@ static int qcom_mhi_qrtr_probe(struct mhi_device *mhi_dev,
 	struct qrtr_mhi_dev *qdev;
 	int rc;
 
+	/* start channels */
+	rc = mhi_prepare_for_transfer(mhi_dev);
+	if (rc)
+		return rc;
+
 	qdev = devm_kzalloc(&mhi_dev->dev, sizeof(*qdev), GFP_KERNEL);
 	if (!qdev)
 		return -ENOMEM;
@@ -99,6 +104,7 @@ static void qcom_mhi_qrtr_remove(struct mhi_device *mhi_dev)
 	struct qrtr_mhi_dev *qdev = dev_get_drvdata(&mhi_dev->dev);
 
 	qrtr_endpoint_unregister(&qdev->ep);
+	mhi_unprepare_from_transfer(mhi_dev);
 	dev_set_drvdata(&mhi_dev->dev, NULL);
 }
 
diff --git a/net/qrtr/ns.c b/net/qrtr/ns.c
index b8559c882431..8d00dfe8139e 100644
--- a/net/qrtr/ns.c
+++ b/net/qrtr/ns.c
@@ -517,10 +517,6 @@ static int ctrl_cmd_new_server(struct sockaddr_qrtr *from,
 		port = from->sq_port;
 	}
 
-	/* Don't accept spoofed messages */
-	if (from->sq_node != node_id)
-		return -EINVAL;
-
 	srv = server_add(service, instance, node_id, port);
 	if (!srv)
 		return -EINVAL;
@@ -559,10 +555,6 @@ static int ctrl_cmd_del_server(struct sockaddr_qrtr *from,
 		port = from->sq_port;
 	}
 
-	/* Don't accept spoofed messages */
-	if (from->sq_node != node_id)
-		return -EINVAL;
-
 	/* Local servers may only unregister themselves */
 	if (from->sq_node == qrtr_ns.local_node && from->sq_port != port)
 		return -EINVAL;
@@ -763,7 +755,7 @@ static void qrtr_ns_data_ready(struct sock *sk)
 	queue_work(qrtr_ns.workqueue, &qrtr_ns.work);
 }
 
-void qrtr_ns_init(void)
+int qrtr_ns_init(void)
 {
 	struct sockaddr_qrtr sq;
 	int ret;
@@ -774,7 +766,7 @@ void qrtr_ns_init(void)
 	ret = sock_create_kern(&init_net, AF_QIPCRTR, SOCK_DGRAM,
 			       PF_QIPCRTR, &qrtr_ns.sock);
 	if (ret < 0)
-		return;
+		return ret;
 
 	ret = kernel_getsockname(qrtr_ns.sock, (struct sockaddr *)&sq);
 	if (ret < 0) {
@@ -805,12 +797,13 @@ void qrtr_ns_init(void)
 	if (ret < 0)
 		goto err_wq;
 
-	return;
+	return 0;
 
 err_wq:
 	destroy_workqueue(qrtr_ns.workqueue);
 err_sock:
 	sock_release(qrtr_ns.sock);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(qrtr_ns_init);
 
diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c
index 957aa9263ba4..b34358282f37 100644
--- a/net/qrtr/qrtr.c
+++ b/net/qrtr/qrtr.c
@@ -171,8 +171,13 @@ static void __qrtr_node_release(struct kref *kref)
 	void __rcu **slot;
 
 	spin_lock_irqsave(&qrtr_nodes_lock, flags);
-	if (node->nid != QRTR_EP_NID_AUTO)
-		radix_tree_delete(&qrtr_nodes, node->nid);
+	/* If the node is a bridge for other nodes, there are possibly
+	 * multiple entries pointing to our released node, delete them all.
+	 */
+	radix_tree_for_each_slot(slot, &qrtr_nodes, &iter, 0) {
+		if (*slot == node)
+			radix_tree_iter_delete(&qrtr_nodes, &iter, slot);
+	}
 	spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
 
 	list_del(&node->item);
@@ -347,7 +352,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb,
 	hdr->src_port_id = cpu_to_le32(from->sq_port);
 	if (to->sq_port == QRTR_PORT_CTRL) {
 		hdr->dst_node_id = cpu_to_le32(node->nid);
-		hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST);
+		hdr->dst_port_id = cpu_to_le32(QRTR_PORT_CTRL);
 	} else {
 		hdr->dst_node_id = cpu_to_le32(to->sq_node);
 		hdr->dst_port_id = cpu_to_le32(to->sq_port);
@@ -401,12 +406,13 @@ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid)
 {
 	unsigned long flags;
 
-	if (node->nid != QRTR_EP_NID_AUTO || nid == QRTR_EP_NID_AUTO)
+	if (nid == QRTR_EP_NID_AUTO)
 		return;
 
 	spin_lock_irqsave(&qrtr_nodes_lock, flags);
 	radix_tree_insert(&qrtr_nodes, nid, node);
-	node->nid = nid;
+	if (node->nid == QRTR_EP_NID_AUTO)
+		node->nid = nid;
 	spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
 }
 
@@ -494,6 +500,13 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len)
 
 	qrtr_node_assign(node, cb->src_node);
 
+	if (cb->type == QRTR_TYPE_NEW_SERVER) {
+		/* Remote node endpoint can bridge other distant nodes */
+		const struct qrtr_ctrl_pkt *pkt = data + hdrlen;
+
+		qrtr_node_assign(node, le32_to_cpu(pkt->server.node));
+	}
+
 	if (cb->type == QRTR_TYPE_RESUME_TX) {
 		qrtr_tx_resume(node, skb);
 	} else {
@@ -519,18 +532,20 @@ EXPORT_SYMBOL_GPL(qrtr_endpoint_post);
 /**
  * qrtr_alloc_ctrl_packet() - allocate control packet skb
  * @pkt: reference to qrtr_ctrl_pkt pointer
+ * @flags: the type of memory to allocate
  *
  * Returns newly allocated sk_buff, or NULL on failure
  *
  * This function allocates a sk_buff large enough to carry a qrtr_ctrl_pkt and
  * on success returns a reference to the control packet in @pkt.
  */
-static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt)
+static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt,
+					      gfp_t flags)
 {
 	const int pkt_len = sizeof(struct qrtr_ctrl_pkt);
 	struct sk_buff *skb;
 
-	skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, GFP_KERNEL);
+	skb = alloc_skb(QRTR_HDR_MAX_SIZE + pkt_len, flags);
 	if (!skb)
 		return NULL;
 
@@ -592,6 +607,7 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
 	struct qrtr_ctrl_pkt *pkt;
 	struct qrtr_tx_flow *flow;
 	struct sk_buff *skb;
+	unsigned long flags;
 	void __rcu **slot;
 
 	mutex_lock(&node->ep_lock);
@@ -599,11 +615,18 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep)
 	mutex_unlock(&node->ep_lock);
 
 	/* Notify the local controller about the event */
-	skb = qrtr_alloc_ctrl_packet(&pkt);
-	if (skb) {
-		pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE);
-		qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst);
+	spin_lock_irqsave(&qrtr_nodes_lock, flags);
+	radix_tree_for_each_slot(slot, &qrtr_nodes, &iter, 0) {
+		if (*slot != node)
+			continue;
+		src.sq_node = iter.index;
+		skb = qrtr_alloc_ctrl_packet(&pkt, GFP_ATOMIC);
+		if (skb) {
+			pkt->cmd = cpu_to_le32(QRTR_TYPE_BYE);
+			qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst);
+		}
 	}
+	spin_unlock_irqrestore(&qrtr_nodes_lock, flags);
 
 	/* Wake up any transmitters waiting for resume-tx from the node */
 	mutex_lock(&node->qrtr_tx_lock);
@@ -656,7 +679,7 @@ static void qrtr_port_remove(struct qrtr_sock *ipc)
 	to.sq_node = QRTR_NODE_BCAST;
 	to.sq_port = QRTR_PORT_CTRL;
 
-	skb = qrtr_alloc_ctrl_packet(&pkt);
+	skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL);
 	if (skb) {
 		pkt->cmd = cpu_to_le32(QRTR_TYPE_DEL_CLIENT);
 		pkt->client.node = cpu_to_le32(ipc->us.sq_node);
@@ -982,7 +1005,7 @@ static int qrtr_send_resume_tx(struct qrtr_cb *cb)
 	if (!node)
 		return -EINVAL;
 
-	skb = qrtr_alloc_ctrl_packet(&pkt);
+	skb = qrtr_alloc_ctrl_packet(&pkt, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
@@ -1264,13 +1287,19 @@ static int __init qrtr_proto_init(void)
 		return rc;
 
 	rc = sock_register(&qrtr_family);
-	if (rc) {
-		proto_unregister(&qrtr_proto);
-		return rc;
-	}
+	if (rc)
+		goto err_proto;
 
-	qrtr_ns_init();
+	rc = qrtr_ns_init();
+	if (rc)
+		goto err_sock;
 
+	return 0;
+
+err_sock:
+	sock_unregister(qrtr_family.family);
+err_proto:
+	proto_unregister(&qrtr_proto);
 	return rc;
 }
 postcore_initcall(qrtr_proto_init);
diff --git a/net/qrtr/qrtr.h b/net/qrtr/qrtr.h
index dc2b67f17927..3f2d28696062 100644
--- a/net/qrtr/qrtr.h
+++ b/net/qrtr/qrtr.h
@@ -29,7 +29,7 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep);
 
 int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len);
 
-void qrtr_ns_init(void);
+int qrtr_ns_init(void);
 
 void qrtr_ns_remove(void);
 
diff --git a/net/qrtr/tun.c b/net/qrtr/tun.c
index 15ce9b642b25..b238c40a9984 100644
--- a/net/qrtr/tun.c
+++ b/net/qrtr/tun.c
@@ -80,6 +80,12 @@ static ssize_t qrtr_tun_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	ssize_t ret;
 	void *kbuf;
 
+	if (!len)
+		return -EINVAL;
+
+	if (len > KMALLOC_MAX_SIZE)
+		return -ENOMEM;
+
 	kbuf = kzalloc(len, GFP_KERNEL);
 	if (!kbuf)
 		return -ENOMEM;
diff --git a/net/rds/cong.c b/net/rds/cong.c
index ccdff09a79c8..8b689ebbd5b5 100644
--- a/net/rds/cong.c
+++ b/net/rds/cong.c
@@ -236,7 +236,7 @@ void rds_cong_queue_updates(struct rds_cong_map *map)
 			 *    tcp_setsockopt and/or tcp_sendmsg will deadlock
 			 *    when it tries to get the sock_lock())
 			 * 2. Interrupts are masked so that we can mark the
-			 *    the port congested from both send and recv paths.
+			 *    port congested from both send and recv paths.
 			 *    (See comment around declaration of rdc_cong_lock).
 			 *    An attempt to get the sock_lock() here will
 			 *    therefore trigger warnings.
diff --git a/net/rds/ib.c b/net/rds/ib.c
index deecbdcdae84..24c9a9005a6f 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -30,7 +30,6 @@
  * SOFTWARE.
  *
  */
-#include <linux/dmapool.h>
 #include <linux/kernel.h>
 #include <linux/in.h>
 #include <linux/if.h>
@@ -108,7 +107,6 @@ static void rds_ib_dev_free(struct work_struct *work)
 		rds_ib_destroy_mr_pool(rds_ibdev->mr_1m_pool);
 	if (rds_ibdev->pd)
 		ib_dealloc_pd(rds_ibdev->pd);
-	dma_pool_destroy(rds_ibdev->rid_hdrs_pool);
 
 	list_for_each_entry_safe(i_ipaddr, i_next, &rds_ibdev->ipaddr_list, list) {
 		list_del(&i_ipaddr->list);
@@ -191,14 +189,6 @@ static int rds_ib_add_one(struct ib_device *device)
 		rds_ibdev->pd = NULL;
 		goto put_dev;
 	}
-	rds_ibdev->rid_hdrs_pool = dma_pool_create(device->name,
-						   device->dma_device,
-						   sizeof(struct rds_header),
-						   L1_CACHE_BYTES, 0);
-	if (!rds_ibdev->rid_hdrs_pool) {
-		ret = -ENOMEM;
-		goto put_dev;
-	}
 
 	rds_ibdev->mr_1m_pool =
 		rds_ib_create_mr_pool(rds_ibdev, RDS_IB_MR_1M_POOL);
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 8dfff43cf07f..2ba71102b1f1 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -246,7 +246,6 @@ struct rds_ib_device {
 	struct list_head	conn_list;
 	struct ib_device	*dev;
 	struct ib_pd		*pd;
-	struct dma_pool		*rid_hdrs_pool; /* RDS headers DMA pool */
 	u8			odp_capable:1;
 
 	unsigned int		max_mrs;
@@ -264,13 +263,6 @@ struct rds_ib_device {
 	int			*vector_load;
 };
 
-static inline int ibdev_to_node(struct ib_device *ibdev)
-{
-	struct device *parent;
-
-	parent = ibdev->dev.parent;
-	return parent ? dev_to_node(parent) : NUMA_NO_NODE;
-}
 #define rdsibdev_to_node(rdsibdev) ibdev_to_node(rdsibdev->dev)
 
 /* bits for i_ack_flags */
@@ -387,11 +379,6 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6);
 void rds_ib_cm_connect_complete(struct rds_connection *conn,
 				struct rdma_cm_event *event);
-struct rds_header **rds_dma_hdrs_alloc(struct ib_device *ibdev,
-				       struct dma_pool *pool,
-				       dma_addr_t **dma_addrs, u32 num_hdrs);
-void rds_dma_hdrs_free(struct dma_pool *pool, struct rds_header **hdrs,
-		       dma_addr_t *dma_addrs, u32 num_hdrs);
 
 #define rds_ib_conn_error(conn, fmt...) \
 	__rds_ib_conn_error(conn, KERN_WARNING "RDS/IB: " fmt)
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index c3319ff3ee11..f5cbe963cd8f 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -30,7 +30,6 @@
  * SOFTWARE.
  *
  */
-#include <linux/dmapool.h>
 #include <linux/kernel.h>
 #include <linux/in.h>
 #include <linux/slab.h>
@@ -441,42 +440,87 @@ static inline void ibdev_put_vector(struct rds_ib_device *rds_ibdev, int index)
 	rds_ibdev->vector_load[index]--;
 }
 
+static void rds_dma_hdr_free(struct ib_device *dev, struct rds_header *hdr,
+		dma_addr_t dma_addr, enum dma_data_direction dir)
+{
+	ib_dma_unmap_single(dev, dma_addr, sizeof(*hdr), dir);
+	kfree(hdr);
+}
+
+static struct rds_header *rds_dma_hdr_alloc(struct ib_device *dev,
+		dma_addr_t *dma_addr, enum dma_data_direction dir)
+{
+	struct rds_header *hdr;
+
+	hdr = kzalloc_node(sizeof(*hdr), GFP_KERNEL, ibdev_to_node(dev));
+	if (!hdr)
+		return NULL;
+
+	*dma_addr = ib_dma_map_single(dev, hdr, sizeof(*hdr),
+				      DMA_BIDIRECTIONAL);
+	if (ib_dma_mapping_error(dev, *dma_addr)) {
+		kfree(hdr);
+		return NULL;
+	}
+
+	return hdr;
+}
+
+/* Free the DMA memory used to store struct rds_header.
+ *
+ * @dev: the RDS IB device
+ * @hdrs: pointer to the array storing DMA memory pointers
+ * @dma_addrs: pointer to the array storing DMA addresses
+ * @num_hdars: number of headers to free.
+ */
+static void rds_dma_hdrs_free(struct rds_ib_device *dev,
+		struct rds_header **hdrs, dma_addr_t *dma_addrs, u32 num_hdrs,
+		enum dma_data_direction dir)
+{
+	u32 i;
+
+	for (i = 0; i < num_hdrs; i++)
+		rds_dma_hdr_free(dev->dev, hdrs[i], dma_addrs[i], dir);
+	kvfree(hdrs);
+	kvfree(dma_addrs);
+}
+
+
 /* Allocate DMA coherent memory to be used to store struct rds_header for
  * sending/receiving packets.  The pointers to the DMA memory and the
  * associated DMA addresses are stored in two arrays.
  *
- * @ibdev: the IB device
- * @pool: the DMA memory pool
+ * @dev: the RDS IB device
  * @dma_addrs: pointer to the array for storing DMA addresses
  * @num_hdrs: number of headers to allocate
  *
  * It returns the pointer to the array storing the DMA memory pointers.  On
  * error, NULL pointer is returned.
  */
-struct rds_header **rds_dma_hdrs_alloc(struct ib_device *ibdev,
-				       struct dma_pool *pool,
-				       dma_addr_t **dma_addrs, u32 num_hdrs)
+static struct rds_header **rds_dma_hdrs_alloc(struct rds_ib_device *dev,
+		dma_addr_t **dma_addrs, u32 num_hdrs,
+		enum dma_data_direction dir)
 {
 	struct rds_header **hdrs;
 	dma_addr_t *hdr_daddrs;
 	u32 i;
 
 	hdrs = kvmalloc_node(sizeof(*hdrs) * num_hdrs, GFP_KERNEL,
-			     ibdev_to_node(ibdev));
+			     ibdev_to_node(dev->dev));
 	if (!hdrs)
 		return NULL;
 
 	hdr_daddrs = kvmalloc_node(sizeof(*hdr_daddrs) * num_hdrs, GFP_KERNEL,
-				   ibdev_to_node(ibdev));
+				   ibdev_to_node(dev->dev));
 	if (!hdr_daddrs) {
 		kvfree(hdrs);
 		return NULL;
 	}
 
 	for (i = 0; i < num_hdrs; i++) {
-		hdrs[i] = dma_pool_zalloc(pool, GFP_KERNEL, &hdr_daddrs[i]);
+		hdrs[i] = rds_dma_hdr_alloc(dev->dev, &hdr_daddrs[i], dir);
 		if (!hdrs[i]) {
-			rds_dma_hdrs_free(pool, hdrs, hdr_daddrs, i);
+			rds_dma_hdrs_free(dev, hdrs, hdr_daddrs, i, dir);
 			return NULL;
 		}
 	}
@@ -485,24 +529,6 @@ struct rds_header **rds_dma_hdrs_alloc(struct ib_device *ibdev,
 	return hdrs;
 }
 
-/* Free the DMA memory used to store struct rds_header.
- *
- * @pool: the DMA memory pool
- * @hdrs: pointer to the array storing DMA memory pointers
- * @dma_addrs: pointer to the array storing DMA addresses
- * @num_hdars: number of headers to free.
- */
-void rds_dma_hdrs_free(struct dma_pool *pool, struct rds_header **hdrs,
-		       dma_addr_t *dma_addrs, u32 num_hdrs)
-{
-	u32 i;
-
-	for (i = 0; i < num_hdrs; i++)
-		dma_pool_free(pool, hdrs[i], dma_addrs[i]);
-	kvfree(hdrs);
-	kvfree(dma_addrs);
-}
-
 /*
  * This needs to be very careful to not leave IS_ERR pointers around for
  * cleanup to trip over.
@@ -516,7 +542,6 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 	struct rds_ib_device *rds_ibdev;
 	unsigned long max_wrs;
 	int ret, fr_queue_space;
-	struct dma_pool *pool;
 
 	/*
 	 * It's normal to see a null device if an incoming connection races
@@ -612,25 +637,26 @@ static int rds_ib_setup_qp(struct rds_connection *conn)
 		goto recv_cq_out;
 	}
 
-	pool = rds_ibdev->rid_hdrs_pool;
-	ic->i_send_hdrs = rds_dma_hdrs_alloc(dev, pool, &ic->i_send_hdrs_dma,
-					     ic->i_send_ring.w_nr);
+	ic->i_send_hdrs = rds_dma_hdrs_alloc(rds_ibdev, &ic->i_send_hdrs_dma,
+					     ic->i_send_ring.w_nr,
+					     DMA_TO_DEVICE);
 	if (!ic->i_send_hdrs) {
 		ret = -ENOMEM;
 		rdsdebug("DMA send hdrs alloc failed\n");
 		goto qp_out;
 	}
 
-	ic->i_recv_hdrs = rds_dma_hdrs_alloc(dev, pool, &ic->i_recv_hdrs_dma,
-					     ic->i_recv_ring.w_nr);
+	ic->i_recv_hdrs = rds_dma_hdrs_alloc(rds_ibdev, &ic->i_recv_hdrs_dma,
+					     ic->i_recv_ring.w_nr,
+					     DMA_FROM_DEVICE);
 	if (!ic->i_recv_hdrs) {
 		ret = -ENOMEM;
 		rdsdebug("DMA recv hdrs alloc failed\n");
 		goto send_hdrs_dma_out;
 	}
 
-	ic->i_ack = dma_pool_zalloc(pool, GFP_KERNEL,
-				    &ic->i_ack_dma);
+	ic->i_ack = rds_dma_hdr_alloc(rds_ibdev->dev, &ic->i_ack_dma,
+				      DMA_TO_DEVICE);
 	if (!ic->i_ack) {
 		ret = -ENOMEM;
 		rdsdebug("DMA ack header alloc failed\n");
@@ -666,18 +692,19 @@ sends_out:
 	vfree(ic->i_sends);
 
 ack_dma_out:
-	dma_pool_free(pool, ic->i_ack, ic->i_ack_dma);
+	rds_dma_hdr_free(rds_ibdev->dev, ic->i_ack, ic->i_ack_dma,
+			 DMA_TO_DEVICE);
 	ic->i_ack = NULL;
 
 recv_hdrs_dma_out:
-	rds_dma_hdrs_free(pool, ic->i_recv_hdrs, ic->i_recv_hdrs_dma,
-			  ic->i_recv_ring.w_nr);
+	rds_dma_hdrs_free(rds_ibdev, ic->i_recv_hdrs, ic->i_recv_hdrs_dma,
+			  ic->i_recv_ring.w_nr, DMA_FROM_DEVICE);
 	ic->i_recv_hdrs = NULL;
 	ic->i_recv_hdrs_dma = NULL;
 
 send_hdrs_dma_out:
-	rds_dma_hdrs_free(pool, ic->i_send_hdrs, ic->i_send_hdrs_dma,
-			  ic->i_send_ring.w_nr);
+	rds_dma_hdrs_free(rds_ibdev, ic->i_send_hdrs, ic->i_send_hdrs_dma,
+			  ic->i_send_ring.w_nr, DMA_TO_DEVICE);
 	ic->i_send_hdrs = NULL;
 	ic->i_send_hdrs_dma = NULL;
 
@@ -711,7 +738,7 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6)
 	 * original size. The only way to tell the difference is by looking at
 	 * the contents, which are initialized to zero.
 	 * If the protocol version fields aren't set, this is a connection attempt
-	 * from an older version. This could could be 3.0 or 2.0 - we can't tell.
+	 * from an older version. This could be 3.0 or 2.0 - we can't tell.
 	 * We really should have changed this for OFED 1.3 :-(
 	 */
 
@@ -956,9 +983,10 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6)
 	rds_ib_cm_fill_conn_param(conn, &conn_param, &dp,
 				  conn->c_proposed_version,
 				  UINT_MAX, UINT_MAX, isv6);
-	ret = rdma_connect(cm_id, &conn_param);
+	ret = rdma_connect_locked(cm_id, &conn_param);
 	if (ret)
-		rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret);
+		rds_ib_conn_error(conn, "rdma_connect_locked failed (%d)\n",
+				  ret);
 
 out:
 	/* Beware - returning non-zero tells the rdma_cm to destroy
@@ -1109,29 +1137,30 @@ void rds_ib_conn_path_shutdown(struct rds_conn_path *cp)
 		}
 
 		if (ic->rds_ibdev) {
-			struct dma_pool *pool;
-
-			pool = ic->rds_ibdev->rid_hdrs_pool;
-
 			/* then free the resources that ib callbacks use */
 			if (ic->i_send_hdrs) {
-				rds_dma_hdrs_free(pool, ic->i_send_hdrs,
+				rds_dma_hdrs_free(ic->rds_ibdev,
+						  ic->i_send_hdrs,
 						  ic->i_send_hdrs_dma,
-						  ic->i_send_ring.w_nr);
+						  ic->i_send_ring.w_nr,
+						  DMA_TO_DEVICE);
 				ic->i_send_hdrs = NULL;
 				ic->i_send_hdrs_dma = NULL;
 			}
 
 			if (ic->i_recv_hdrs) {
-				rds_dma_hdrs_free(pool, ic->i_recv_hdrs,
+				rds_dma_hdrs_free(ic->rds_ibdev,
+						  ic->i_recv_hdrs,
 						  ic->i_recv_hdrs_dma,
-						  ic->i_recv_ring.w_nr);
+						  ic->i_recv_ring.w_nr,
+						  DMA_FROM_DEVICE);
 				ic->i_recv_hdrs = NULL;
 				ic->i_recv_hdrs_dma = NULL;
 			}
 
 			if (ic->i_ack) {
-				dma_pool_free(pool, ic->i_ack, ic->i_ack_dma);
+				rds_dma_hdr_free(ic->rds_ibdev->dev, ic->i_ack,
+						 ic->i_ack_dma, DMA_TO_DEVICE);
 				ic->i_ack = NULL;
 			}
 		} else {
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 694d411dc72f..6fdedd9dbbc2 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -310,8 +310,8 @@ static int rds_ib_recv_refill_one(struct rds_connection *conn,
 	struct rds_ib_connection *ic = conn->c_transport_data;
 	struct ib_sge *sge;
 	int ret = -ENOMEM;
-	gfp_t slab_mask = GFP_NOWAIT;
-	gfp_t page_mask = GFP_NOWAIT;
+	gfp_t slab_mask = gfp;
+	gfp_t page_mask = gfp;
 
 	if (gfp & __GFP_DIRECT_RECLAIM) {
 		slab_mask = GFP_KERNEL;
@@ -662,10 +662,16 @@ static void rds_ib_send_ack(struct rds_ib_connection *ic, unsigned int adv_credi
 	seq = rds_ib_get_ack(ic);
 
 	rdsdebug("send_ack: ic %p ack %llu\n", ic, (unsigned long long) seq);
+
+	ib_dma_sync_single_for_cpu(ic->rds_ibdev->dev, ic->i_ack_dma,
+				   sizeof(*hdr), DMA_TO_DEVICE);
 	rds_message_populate_header(hdr, 0, 0, 0);
 	hdr->h_ack = cpu_to_be64(seq);
 	hdr->h_credit = adv_credits;
 	rds_message_make_checksum(hdr);
+	ib_dma_sync_single_for_device(ic->rds_ibdev->dev, ic->i_ack_dma,
+				      sizeof(*hdr), DMA_TO_DEVICE);
+
 	ic->i_ack_queued = jiffies;
 
 	ret = ib_post_send(ic->i_cm_id->qp, &ic->i_ack_wr, NULL);
@@ -845,6 +851,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 	struct rds_ib_connection *ic = conn->c_transport_data;
 	struct rds_ib_incoming *ibinc = ic->i_ibinc;
 	struct rds_header *ihdr, *hdr;
+	dma_addr_t dma_addr = ic->i_recv_hdrs_dma[recv - ic->i_recvs];
 
 	/* XXX shut down the connection if port 0,0 are seen? */
 
@@ -863,6 +870,8 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 
 	ihdr = ic->i_recv_hdrs[recv - ic->i_recvs];
 
+	ib_dma_sync_single_for_cpu(ic->rds_ibdev->dev, dma_addr,
+				   sizeof(*ihdr), DMA_FROM_DEVICE);
 	/* Validate the checksum. */
 	if (!rds_message_verify_checksum(ihdr)) {
 		rds_ib_conn_error(conn, "incoming message "
@@ -870,7 +879,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 		       "forcing a reconnect\n",
 		       &conn->c_faddr);
 		rds_stats_inc(s_recv_drop_bad_checksum);
-		return;
+		goto done;
 	}
 
 	/* Process the ACK sequence which comes with every packet */
@@ -899,7 +908,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 		 */
 		rds_ib_frag_free(ic, recv->r_frag);
 		recv->r_frag = NULL;
-		return;
+		goto done;
 	}
 
 	/*
@@ -933,7 +942,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 		    hdr->h_dport != ihdr->h_dport) {
 			rds_ib_conn_error(conn,
 				"fragment header mismatch; forcing reconnect\n");
-			return;
+			goto done;
 		}
 	}
 
@@ -965,6 +974,9 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 
 		rds_inc_put(&ibinc->ii_inc);
 	}
+done:
+	ib_dma_sync_single_for_device(ic->rds_ibdev->dev, dma_addr,
+				      sizeof(*ihdr), DMA_FROM_DEVICE);
 }
 
 void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic,
@@ -1020,7 +1032,7 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic,
 		rds_ib_stats_inc(s_ib_rx_ring_empty);
 
 	if (rds_ib_ring_low(&ic->i_recv_ring)) {
-		rds_ib_recv_refill(conn, 0, GFP_NOWAIT);
+		rds_ib_recv_refill(conn, 0, GFP_NOWAIT | __GFP_NOWARN);
 		rds_ib_stats_inc(s_ib_rx_refill_from_cq);
 	}
 }
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index dfe778220657..92b4a8689aae 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -638,6 +638,10 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
 		send->s_sge[0].length = sizeof(struct rds_header);
 		send->s_sge[0].lkey = ic->i_pd->local_dma_lkey;
 
+		ib_dma_sync_single_for_cpu(ic->rds_ibdev->dev,
+					   ic->i_send_hdrs_dma[pos],
+					   sizeof(struct rds_header),
+					   DMA_TO_DEVICE);
 		memcpy(ic->i_send_hdrs[pos], &rm->m_inc.i_hdr,
 		       sizeof(struct rds_header));
 
@@ -688,6 +692,10 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
 			adv_credits = 0;
 			rds_ib_stats_inc(s_ib_tx_credit_updates);
 		}
+		ib_dma_sync_single_for_device(ic->rds_ibdev->dev,
+					      ic->i_send_hdrs_dma[pos],
+					      sizeof(struct rds_header),
+					      DMA_TO_DEVICE);
 
 		if (prev)
 			prev->s_wr.next = &send->s_wr;
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index ccdd304eae0a..6f1a50d50d06 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -269,7 +269,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 		goto out;
 	} else {
 		nents = ret;
-		sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL);
+		sg = kmalloc_array(nents, sizeof(*sg), GFP_KERNEL);
 		if (!sg) {
 			ret = -ENOMEM;
 			goto out;
@@ -565,6 +565,9 @@ int rds_rdma_extra_size(struct rds_rdma_args *args,
 	if (args->nr_local == 0)
 		return -EINVAL;
 
+	if (args->nr_local > UIO_MAXIOV)
+		return -EMSGSIZE;
+
 	iov->iov = kcalloc(args->nr_local,
 			   sizeof(struct rds_iovec),
 			   GFP_KERNEL);
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index 971c73c7d34c..68d6ef9e59fc 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -40,6 +40,7 @@ struct rfkill {
 	enum rfkill_type	type;
 
 	unsigned long		state;
+	unsigned long		hard_block_reasons;
 
 	u32			idx;
 
@@ -265,6 +266,7 @@ static void rfkill_fill_event(struct rfkill_event *ev, struct rfkill *rfkill,
 	ev->hard = !!(rfkill->state & RFKILL_BLOCK_HW);
 	ev->soft = !!(rfkill->state & (RFKILL_BLOCK_SW |
 					RFKILL_BLOCK_SW_PREV));
+	ev->hard_block_reasons = rfkill->hard_block_reasons;
 	spin_unlock_irqrestore(&rfkill->lock, flags);
 }
 
@@ -522,19 +524,29 @@ bool rfkill_get_global_sw_state(const enum rfkill_type type)
 }
 #endif
 
-bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked)
+bool rfkill_set_hw_state_reason(struct rfkill *rfkill,
+				bool blocked, unsigned long reason)
 {
 	unsigned long flags;
 	bool ret, prev;
 
 	BUG_ON(!rfkill);
 
+	if (WARN(reason &
+	    ~(RFKILL_HARD_BLOCK_SIGNAL | RFKILL_HARD_BLOCK_NOT_OWNER),
+	    "hw_state reason not supported: 0x%lx", reason))
+		return blocked;
+
 	spin_lock_irqsave(&rfkill->lock, flags);
-	prev = !!(rfkill->state & RFKILL_BLOCK_HW);
-	if (blocked)
+	prev = !!(rfkill->hard_block_reasons & reason);
+	if (blocked) {
 		rfkill->state |= RFKILL_BLOCK_HW;
-	else
-		rfkill->state &= ~RFKILL_BLOCK_HW;
+		rfkill->hard_block_reasons |= reason;
+	} else {
+		rfkill->hard_block_reasons &= ~reason;
+		if (!rfkill->hard_block_reasons)
+			rfkill->state &= ~RFKILL_BLOCK_HW;
+	}
 	ret = !!(rfkill->state & RFKILL_BLOCK_ANY);
 	spin_unlock_irqrestore(&rfkill->lock, flags);
 
@@ -546,7 +558,7 @@ bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked)
 
 	return ret;
 }
-EXPORT_SYMBOL(rfkill_set_hw_state);
+EXPORT_SYMBOL(rfkill_set_hw_state_reason);
 
 static void __rfkill_set_sw_state(struct rfkill *rfkill, bool blocked)
 {
@@ -744,6 +756,16 @@ static ssize_t soft_store(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RW(soft);
 
+static ssize_t hard_block_reasons_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct rfkill *rfkill = to_rfkill(dev);
+
+	return sprintf(buf, "0x%lx\n", rfkill->hard_block_reasons);
+}
+static DEVICE_ATTR_RO(hard_block_reasons);
+
 static u8 user_state_from_blocked(unsigned long state)
 {
 	if (state & RFKILL_BLOCK_HW)
@@ -796,6 +818,7 @@ static struct attribute *rfkill_dev_attrs[] = {
 	&dev_attr_state.attr,
 	&dev_attr_soft.attr,
 	&dev_attr_hard.attr,
+	&dev_attr_hard_block_reasons.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(rfkill_dev);
@@ -811,6 +834,7 @@ static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env)
 {
 	struct rfkill *rfkill = to_rfkill(dev);
 	unsigned long flags;
+	unsigned long reasons;
 	u32 state;
 	int error;
 
@@ -823,10 +847,13 @@ static int rfkill_dev_uevent(struct device *dev, struct kobj_uevent_env *env)
 		return error;
 	spin_lock_irqsave(&rfkill->lock, flags);
 	state = rfkill->state;
+	reasons = rfkill->hard_block_reasons;
 	spin_unlock_irqrestore(&rfkill->lock, flags);
 	error = add_uevent_var(env, "RFKILL_STATE=%d",
 			       user_state_from_blocked(state));
-	return error;
+	if (error)
+		return error;
+	return add_uevent_var(env, "RFKILL_HW_BLOCK_REASON=0x%lx", reasons);
 }
 
 void rfkill_pause_polling(struct rfkill *rfkill)
@@ -876,6 +903,9 @@ static int rfkill_resume(struct device *dev)
 
 	rfkill->suspended = false;
 
+	if (!rfkill->registered)
+		return 0;
+
 	if (!rfkill->persistent) {
 		cur = !!(rfkill->state & RFKILL_BLOCK_SW);
 		rfkill_set_block(rfkill, cur);
diff --git a/net/rose/rose_loopback.c b/net/rose/rose_loopback.c
index 7b094275ea8b..11c45c8c6c16 100644
--- a/net/rose/rose_loopback.c
+++ b/net/rose/rose_loopback.c
@@ -96,10 +96,19 @@ static void rose_loopback_timer(struct timer_list *unused)
 		}
 
 		if (frametype == ROSE_CALL_REQUEST) {
-			if ((dev = rose_dev_get(dest)) != NULL) {
-				if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0)
-					kfree_skb(skb);
-			} else {
+			if (!rose_loopback_neigh->dev) {
+				kfree_skb(skb);
+				continue;
+			}
+
+			dev = rose_dev_get(dest);
+			if (!dev) {
+				kfree_skb(skb);
+				continue;
+			}
+
+			if (rose_rx_call_request(skb, dev, rose_loopback_neigh, lci_o) == 0) {
+				dev_put(dev);
 				kfree_skb(skb);
 			}
 		} else {
diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile
index ddd0f95713a9..b11281bed2a4 100644
--- a/net/rxrpc/Makefile
+++ b/net/rxrpc/Makefile
@@ -28,6 +28,7 @@ rxrpc-y := \
 	rtt.o \
 	security.o \
 	sendmsg.o \
+	server_key.o \
 	skbuff.o \
 	utils.o
 
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 186c8a889b16..41671af6b33f 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -308,9 +308,10 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock,
 		key = NULL; /* a no-security key */
 
 	memset(&p, 0, sizeof(p));
-	p.user_call_ID = user_call_ID;
-	p.tx_total_len = tx_total_len;
-	p.interruptibility = interruptibility;
+	p.user_call_ID		= user_call_ID;
+	p.tx_total_len		= tx_total_len;
+	p.interruptibility	= interruptibility;
+	p.kernel		= true;
 
 	memset(&cp, 0, sizeof(cp));
 	cp.local		= rx->local;
@@ -989,7 +990,7 @@ static int __init af_rxrpc_init(void)
 		goto error_security;
 	}
 
-	ret = register_pernet_subsys(&rxrpc_net_ops);
+	ret = register_pernet_device(&rxrpc_net_ops);
 	if (ret)
 		goto error_pernet;
 
@@ -1034,7 +1035,7 @@ error_key_type:
 error_sock:
 	proto_unregister(&rxrpc_proto);
 error_proto:
-	unregister_pernet_subsys(&rxrpc_net_ops);
+	unregister_pernet_device(&rxrpc_net_ops);
 error_pernet:
 	rxrpc_exit_security();
 error_security:
@@ -1056,7 +1057,7 @@ static void __exit af_rxrpc_exit(void)
 	unregister_key_type(&key_type_rxrpc);
 	sock_unregister(PF_RXRPC);
 	proto_unregister(&rxrpc_proto);
-	unregister_pernet_subsys(&rxrpc_net_ops);
+	unregister_pernet_device(&rxrpc_net_ops);
 	ASSERTCMP(atomic_read(&rxrpc_n_tx_skbs), ==, 0);
 	ASSERTCMP(atomic_read(&rxrpc_n_rx_skbs), ==, 0);
 
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 97aebb5d19db..7bd6f8a66a3e 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -12,6 +12,7 @@
 #include <net/netns/generic.h>
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
+#include <keys/rxrpc-type.h>
 #include "protocol.h"
 
 #if 0
@@ -34,6 +35,7 @@ struct rxrpc_crypt {
 #define rxrpc_queue_delayed_work(WS,D)	\
 	queue_delayed_work(rxrpc_workqueue, (WS), (D))
 
+struct key_preparsed_payload;
 struct rxrpc_connection;
 
 /*
@@ -76,14 +78,12 @@ struct rxrpc_net {
 	struct work_struct	service_conn_reaper;
 	struct timer_list	service_conn_reap_timer;
 
-	unsigned int		nr_client_conns;
-	unsigned int		nr_active_client_conns;
-	bool			kill_all_client_conns;
 	bool			live;
+
+	bool			kill_all_client_conns;
+	atomic_t		nr_client_conns;
 	spinlock_t		client_conn_cache_lock; /* Lock for ->*_client_conns */
 	spinlock_t		client_conn_discard_lock; /* Prevent multiple discarders */
-	struct list_head	waiting_client_conns;
-	struct list_head	active_client_conns;
 	struct list_head	idle_client_conns;
 	struct work_struct	client_conn_reaper;
 	struct timer_list	client_conn_reap_timer;
@@ -218,17 +218,30 @@ struct rxrpc_security {
 	/* Clean up a security service */
 	void (*exit)(void);
 
+	/* Parse the information from a server key */
+	int (*preparse_server_key)(struct key_preparsed_payload *);
+
+	/* Clean up the preparse buffer after parsing a server key */
+	void (*free_preparse_server_key)(struct key_preparsed_payload *);
+
+	/* Destroy the payload of a server key */
+	void (*destroy_server_key)(struct key *);
+
+	/* Describe a server key */
+	void (*describe_server_key)(const struct key *, struct seq_file *);
+
 	/* initialise a connection's security */
-	int (*init_connection_security)(struct rxrpc_connection *);
+	int (*init_connection_security)(struct rxrpc_connection *,
+					struct rxrpc_key_token *);
 
-	/* prime a connection's packet security */
-	int (*prime_packet_security)(struct rxrpc_connection *);
+	/* Work out how much data we can store in a packet, given an estimate
+	 * of the amount of data remaining.
+	 */
+	int (*how_much_data)(struct rxrpc_call *, size_t,
+			     size_t *, size_t *, size_t *);
 
 	/* impose security on a packet */
-	int (*secure_packet)(struct rxrpc_call *,
-			     struct sk_buff *,
-			     size_t,
-			     void *);
+	int (*secure_packet)(struct rxrpc_call *, struct sk_buff *, size_t);
 
 	/* verify the security on a received packet */
 	int (*verify_packet)(struct rxrpc_call *, struct sk_buff *,
@@ -275,8 +288,8 @@ struct rxrpc_local {
 	struct rw_semaphore	defrag_sem;	/* control re-enablement of IP DF bit */
 	struct sk_buff_head	reject_queue;	/* packets awaiting rejection */
 	struct sk_buff_head	event_queue;	/* endpoint event packets awaiting processing */
-	struct rb_root		client_conns;	/* Client connections by socket params */
-	spinlock_t		client_conns_lock; /* Lock for client_conns */
+	struct rb_root		client_bundles;	/* Client connection bundles by socket params */
+	spinlock_t		client_bundles_lock; /* Lock for client_bundles */
 	spinlock_t		lock;		/* access lock */
 	rwlock_t		services_lock;	/* lock for services list */
 	int			debug_id;	/* debug ID for printks */
@@ -353,10 +366,7 @@ struct rxrpc_conn_parameters {
 enum rxrpc_conn_flag {
 	RXRPC_CONN_HAS_IDR,		/* Has a client conn ID assigned */
 	RXRPC_CONN_IN_SERVICE_CONNS,	/* Conn is in peer->service_conns */
-	RXRPC_CONN_IN_CLIENT_CONNS,	/* Conn is in local->client_conns */
-	RXRPC_CONN_EXPOSED,		/* Conn has extra ref for exposure */
 	RXRPC_CONN_DONT_REUSE,		/* Don't reuse this connection */
-	RXRPC_CONN_COUNTED,		/* Counted by rxrpc_nr_client_conns */
 	RXRPC_CONN_PROBING_FOR_UPGRADE,	/* Probing for service upgrade */
 	RXRPC_CONN_FINAL_ACK_0,		/* Need final ACK for channel 0 */
 	RXRPC_CONN_FINAL_ACK_1,		/* Need final ACK for channel 1 */
@@ -377,19 +387,6 @@ enum rxrpc_conn_event {
 };
 
 /*
- * The connection cache state.
- */
-enum rxrpc_conn_cache_state {
-	RXRPC_CONN_CLIENT_INACTIVE,	/* Conn is not yet listed */
-	RXRPC_CONN_CLIENT_WAITING,	/* Conn is on wait list, waiting for capacity */
-	RXRPC_CONN_CLIENT_ACTIVE,	/* Conn is on active list, doing calls */
-	RXRPC_CONN_CLIENT_UPGRADE,	/* Conn is on active list, probing for upgrade */
-	RXRPC_CONN_CLIENT_CULLED,	/* Conn is culled and delisted, doing calls */
-	RXRPC_CONN_CLIENT_IDLE,		/* Conn is on idle list, doing mostly nothing */
-	RXRPC_CONN__NR_CACHE_STATES
-};
-
-/*
  * The connection protocol state.
  */
 enum rxrpc_conn_proto_state {
@@ -405,6 +402,23 @@ enum rxrpc_conn_proto_state {
 };
 
 /*
+ * RxRPC client connection bundle.
+ */
+struct rxrpc_bundle {
+	struct rxrpc_conn_parameters params;
+	atomic_t		usage;
+	unsigned int		debug_id;
+	bool			try_upgrade;	/* True if the bundle is attempting upgrade */
+	bool			alloc_conn;	/* True if someone's getting a conn */
+	short			alloc_error;	/* Error from last conn allocation */
+	spinlock_t		channel_lock;
+	struct rb_node		local_node;	/* Node in local->client_conns */
+	struct list_head	waiting_calls;	/* Calls waiting for channels */
+	unsigned long		avail_chans;	/* Mask of available channels */
+	struct rxrpc_connection	*conns[4];	/* The connections in the bundle (max 4) */
+};
+
+/*
  * RxRPC connection definition
  * - matched by { local, peer, epoch, conn_id, direction }
  * - each connection can only handle four simultaneous calls
@@ -417,10 +431,7 @@ struct rxrpc_connection {
 	struct rcu_head		rcu;
 	struct list_head	cache_link;
 
-	spinlock_t		channel_lock;
-	unsigned char		active_chans;	/* Mask of active channels */
-#define RXRPC_ACTIVE_CHANS_MASK	((1 << RXRPC_MAXCALLS) - 1)
-	struct list_head	waiting_calls;	/* Calls waiting for channels */
+	unsigned char		act_chans;	/* Mask of active channels */
 	struct rxrpc_channel {
 		unsigned long		final_ack_at;	/* Time at which to issue final ACK */
 		struct rxrpc_call __rcu	*call;		/* Active call */
@@ -437,33 +448,33 @@ struct rxrpc_connection {
 
 	struct timer_list	timer;		/* Conn event timer */
 	struct work_struct	processor;	/* connection event processor */
-	union {
-		struct rb_node	client_node;	/* Node in local->client_conns */
-		struct rb_node	service_node;	/* Node in peer->service_conns */
-	};
+	struct rxrpc_bundle	*bundle;	/* Client connection bundle */
+	struct rb_node		service_node;	/* Node in peer->service_conns */
 	struct list_head	proc_link;	/* link in procfs list */
 	struct list_head	link;		/* link in master connection list */
 	struct sk_buff_head	rx_queue;	/* received conn-level packets */
+
 	const struct rxrpc_security *security;	/* applied security module */
-	struct key		*server_key;	/* security for this service */
-	struct crypto_sync_skcipher *cipher;	/* encryption handle */
-	struct rxrpc_crypt	csum_iv;	/* packet checksum base */
+	union {
+		struct {
+			struct crypto_sync_skcipher *cipher;	/* encryption handle */
+			struct rxrpc_crypt csum_iv;	/* packet checksum base */
+			u32	nonce;		/* response re-use preventer */
+		} rxkad;
+	};
 	unsigned long		flags;
 	unsigned long		events;
 	unsigned long		idle_timestamp;	/* Time at which last became idle */
 	spinlock_t		state_lock;	/* state-change lock */
-	enum rxrpc_conn_cache_state cache_state;
 	enum rxrpc_conn_proto_state state;	/* current state of connection */
 	u32			abort_code;	/* Abort code of connection abort */
 	int			debug_id;	/* debug ID for printks */
 	atomic_t		serial;		/* packet serial number counter */
 	unsigned int		hi_serial;	/* highest serial number received */
-	u32			security_nonce;	/* response re-use preventer */
 	u32			service_id;	/* Service ID, possibly upgraded */
-	u8			size_align;	/* data size alignment (for security) */
-	u8			security_size;	/* security header size */
 	u8			security_ix;	/* security type */
 	u8			out_clientflag;	/* RXRPC_CLIENT_INITIATED if we are client */
+	u8			bundle_shift;	/* Index into bundle->avail_chans */
 	short			error;		/* Local error code */
 };
 
@@ -493,6 +504,8 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_RX_HEARD,		/* The peer responded at least once to this call */
 	RXRPC_CALL_RX_UNDERRUN,		/* Got data underrun */
 	RXRPC_CALL_DISCONNECTED,	/* The call has been disconnected */
+	RXRPC_CALL_KERNEL,		/* The call was made by the kernel */
+	RXRPC_CALL_UPGRADE,		/* Service upgrade was requested for the call */
 };
 
 /*
@@ -576,7 +589,7 @@ struct rxrpc_call {
 	struct work_struct	processor;	/* Event processor */
 	rxrpc_notify_rx_t	notify_rx;	/* kernel service Rx notification function */
 	struct list_head	link;		/* link in master call list */
-	struct list_head	chan_wait_link;	/* Link in conn->waiting_calls */
+	struct list_head	chan_wait_link;	/* Link in conn->bundle->waiting_calls */
 	struct hlist_node	error_link;	/* link in error distribution list */
 	struct list_head	accept_link;	/* Link in rx->acceptq */
 	struct list_head	recvmsg_link;	/* Link in rx->recvmsg_q */
@@ -726,6 +739,7 @@ struct rxrpc_call_params {
 		u32		normal;		/* Max time since last call packet (msec) */
 	} timeouts;
 	u8			nr_timeouts;	/* Number of timeouts specified */
+	bool			kernel;		/* T if kernel is making the call */
 	enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */
 };
 
@@ -812,18 +826,19 @@ static inline bool rxrpc_is_client_call(const struct rxrpc_call *call)
 /*
  * conn_client.c
  */
-extern unsigned int rxrpc_max_client_connections;
 extern unsigned int rxrpc_reap_client_connections;
 extern unsigned long rxrpc_conn_idle_client_expiry;
 extern unsigned long rxrpc_conn_idle_client_fast_expiry;
 extern struct idr rxrpc_client_conn_ids;
 
 void rxrpc_destroy_client_conn_ids(void);
+struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *);
+void rxrpc_put_bundle(struct rxrpc_bundle *);
 int rxrpc_connect_call(struct rxrpc_sock *, struct rxrpc_call *,
 		       struct rxrpc_conn_parameters *, struct sockaddr_rxrpc *,
 		       gfp_t);
 void rxrpc_expose_client_call(struct rxrpc_call *);
-void rxrpc_disconnect_client_call(struct rxrpc_call *);
+void rxrpc_disconnect_client_call(struct rxrpc_bundle *, struct rxrpc_call *);
 void rxrpc_put_client_conn(struct rxrpc_connection *);
 void rxrpc_discard_expired_client_conns(struct work_struct *);
 void rxrpc_destroy_all_client_connections(struct rxrpc_net *);
@@ -833,6 +848,7 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *);
  * conn_event.c
  */
 void rxrpc_process_connection(struct work_struct *);
+void rxrpc_process_delayed_final_acks(struct rxrpc_connection *, bool);
 
 /*
  * conn_object.c
@@ -849,7 +865,7 @@ void rxrpc_disconnect_call(struct rxrpc_call *);
 void rxrpc_kill_connection(struct rxrpc_connection *);
 bool rxrpc_queue_conn(struct rxrpc_connection *);
 void rxrpc_see_connection(struct rxrpc_connection *);
-void rxrpc_get_connection(struct rxrpc_connection *);
+struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *);
 struct rxrpc_connection *rxrpc_get_connection_maybe(struct rxrpc_connection *);
 void rxrpc_put_service_conn(struct rxrpc_connection *);
 void rxrpc_service_connection_reaper(struct work_struct *);
@@ -889,8 +905,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *,
 						     struct sk_buff *);
 struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t);
 void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *,
-				   const struct rxrpc_security *, struct key *,
-				   struct sk_buff *);
+				   const struct rxrpc_security *, struct sk_buff *);
 void rxrpc_unpublish_service_conn(struct rxrpc_connection *);
 
 /*
@@ -907,10 +922,8 @@ extern const struct rxrpc_security rxrpc_no_security;
  * key.c
  */
 extern struct key_type key_type_rxrpc;
-extern struct key_type key_type_rxrpc_s;
 
 int rxrpc_request_key(struct rxrpc_sock *, sockptr_t , int);
-int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int);
 int rxrpc_get_server_data_key(struct rxrpc_connection *, const void *, time64_t,
 			      u32);
 
@@ -1053,11 +1066,13 @@ extern const struct rxrpc_security rxkad;
  * security.c
  */
 int __init rxrpc_init_security(void);
+const struct rxrpc_security *rxrpc_security_lookup(u8);
 void rxrpc_exit_security(void);
 int rxrpc_init_client_conn_security(struct rxrpc_connection *);
-bool rxrpc_look_up_server_security(struct rxrpc_local *, struct rxrpc_sock *,
-				   const struct rxrpc_security **, struct key **,
-				   struct sk_buff *);
+const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *,
+							 struct sk_buff *);
+struct key *rxrpc_look_up_server_security(struct rxrpc_connection *,
+					  struct sk_buff *, u32, u32);
 
 /*
  * sendmsg.c
@@ -1065,6 +1080,13 @@ bool rxrpc_look_up_server_security(struct rxrpc_local *, struct rxrpc_sock *,
 int rxrpc_do_sendmsg(struct rxrpc_sock *, struct msghdr *, size_t);
 
 /*
+ * server_key.c
+ */
+extern struct key_type key_type_rxrpc_s;
+
+int rxrpc_server_keyring(struct rxrpc_sock *, sockptr_t, int);
+
+/*
  * skbuff.c
  */
 void rxrpc_kernel_data_consumed(struct rxrpc_call *, struct sk_buff *);
diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c
index 8df1964db333..1ae90fb97936 100644
--- a/net/rxrpc/call_accept.c
+++ b/net/rxrpc/call_accept.c
@@ -197,6 +197,7 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx)
 	tail = b->peer_backlog_tail;
 	while (CIRC_CNT(head, tail, size) > 0) {
 		struct rxrpc_peer *peer = b->peer_backlog[tail];
+		rxrpc_put_local(peer->local);
 		kfree(peer);
 		tail = (tail + 1) & (size - 1);
 	}
@@ -261,7 +262,6 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
 						    struct rxrpc_peer *peer,
 						    struct rxrpc_connection *conn,
 						    const struct rxrpc_security *sec,
-						    struct key *key,
 						    struct sk_buff *skb)
 {
 	struct rxrpc_backlog *b = rx->backlog;
@@ -309,7 +309,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx,
 		conn->params.local = rxrpc_get_local(local);
 		conn->params.peer = peer;
 		rxrpc_see_connection(conn);
-		rxrpc_new_incoming_connection(rx, conn, sec, key, skb);
+		rxrpc_new_incoming_connection(rx, conn, sec, skb);
 	} else {
 		rxrpc_get_connection(conn);
 	}
@@ -353,7 +353,6 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 	struct rxrpc_connection *conn;
 	struct rxrpc_peer *peer = NULL;
 	struct rxrpc_call *call = NULL;
-	struct key *key = NULL;
 
 	_enter("");
 
@@ -374,11 +373,13 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local,
 	 */
 	conn = rxrpc_find_connection_rcu(local, skb, &peer);
 
-	if (!conn && !rxrpc_look_up_server_security(local, rx, &sec, &key, skb))
-		goto no_call;
+	if (!conn) {
+		sec = rxrpc_get_incoming_security(rx, skb);
+		if (!sec)
+			goto no_call;
+	}
 
-	call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, key, skb);
-	key_put(key);
+	call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, skb);
 	if (!call) {
 		skb->mark = RXRPC_SKB_MARK_REJECT_BUSY;
 		goto no_call;
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index ed49769b459d..4eb91d958a48 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -40,6 +40,11 @@ const char *const rxrpc_call_completions[NR__RXRPC_CALL_COMPLETIONS] = {
 
 struct kmem_cache *rxrpc_call_jar;
 
+static struct semaphore rxrpc_call_limiter =
+	__SEMAPHORE_INITIALIZER(rxrpc_call_limiter, 1000);
+static struct semaphore rxrpc_kernel_call_limiter =
+	__SEMAPHORE_INITIALIZER(rxrpc_kernel_call_limiter, 1000);
+
 static void rxrpc_call_timer_expired(struct timer_list *t)
 {
 	struct rxrpc_call *call = from_timer(call, t, timer);
@@ -209,6 +214,34 @@ static void rxrpc_start_call_timer(struct rxrpc_call *call)
 }
 
 /*
+ * Wait for a call slot to become available.
+ */
+static struct semaphore *rxrpc_get_call_slot(struct rxrpc_call_params *p, gfp_t gfp)
+{
+	struct semaphore *limiter = &rxrpc_call_limiter;
+
+	if (p->kernel)
+		limiter = &rxrpc_kernel_call_limiter;
+	if (p->interruptibility == RXRPC_UNINTERRUPTIBLE) {
+		down(limiter);
+		return limiter;
+	}
+	return down_interruptible(limiter) < 0 ? NULL : limiter;
+}
+
+/*
+ * Release a call slot.
+ */
+static void rxrpc_put_call_slot(struct rxrpc_call *call)
+{
+	struct semaphore *limiter = &rxrpc_call_limiter;
+
+	if (test_bit(RXRPC_CALL_KERNEL, &call->flags))
+		limiter = &rxrpc_kernel_call_limiter;
+	up(limiter);
+}
+
+/*
  * Set up a call for the given parameters.
  * - Called with the socket lock held, which it must release.
  * - If it returns a call, the call's lock will need releasing by the caller.
@@ -224,15 +257,21 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 {
 	struct rxrpc_call *call, *xcall;
 	struct rxrpc_net *rxnet;
+	struct semaphore *limiter;
 	struct rb_node *parent, **pp;
 	const void *here = __builtin_return_address(0);
 	int ret;
 
 	_enter("%p,%lx", rx, p->user_call_ID);
 
+	limiter = rxrpc_get_call_slot(p, gfp);
+	if (!limiter)
+		return ERR_PTR(-ERESTARTSYS);
+
 	call = rxrpc_alloc_client_call(rx, srx, gfp, debug_id);
 	if (IS_ERR(call)) {
 		release_sock(&rx->sk);
+		up(limiter);
 		_leave(" = %ld", PTR_ERR(call));
 		return call;
 	}
@@ -242,6 +281,8 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx,
 	trace_rxrpc_call(call->debug_id, rxrpc_call_new_client,
 			 atomic_read(&call->usage),
 			 here, (const void *)p->user_call_ID);
+	if (p->kernel)
+		__set_bit(RXRPC_CALL_KERNEL, &call->flags);
 
 	/* We need to protect a partially set up call against the user as we
 	 * will be acting outside the socket lock.
@@ -468,6 +509,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 		BUG();
 	spin_unlock_bh(&call->lock);
 
+	rxrpc_put_call_slot(call);
+
 	del_timer_sync(&call->timer);
 
 	/* Make sure we don't get any more notifications */
@@ -505,8 +548,6 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call)
 		rxrpc_disconnect_call(call);
 	if (call->security)
 		call->security->free_call_crypto(call);
-
-	rxrpc_cleanup_ring(call);
 	_leave("");
 }
 
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 159e3eda7914..dbea0bfee48e 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -1,63 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /* Client connection-specific management code.
  *
- * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2016, 2020 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * Client connections need to be cached for a little while after they've made a
  * call so as to handle retransmitted DATA packets in case the server didn't
  * receive the final ACK or terminating ABORT we sent it.
  *
- * Client connections can be in one of a number of cache states:
- *
- *  (1) INACTIVE - The connection is not held in any list and may not have been
- *      exposed to the world.  If it has been previously exposed, it was
- *      discarded from the idle list after expiring.
- *
- *  (2) WAITING - The connection is waiting for the number of client conns to
- *      drop below the maximum capacity.  Calls may be in progress upon it from
- *      when it was active and got culled.
- *
- *	The connection is on the rxrpc_waiting_client_conns list which is kept
- *	in to-be-granted order.  Culled conns with waiters go to the back of
- *	the queue just like new conns.
- *
- *  (3) ACTIVE - The connection has at least one call in progress upon it, it
- *      may freely grant available channels to new calls and calls may be
- *      waiting on it for channels to become available.
- *
- *	The connection is on the rxnet->active_client_conns list which is kept
- *	in activation order for culling purposes.
- *
- *	rxrpc_nr_active_client_conns is held incremented also.
- *
- *  (4) UPGRADE - As for ACTIVE, but only one call may be in progress and is
- *      being used to probe for service upgrade.
- *
- *  (5) CULLED - The connection got summarily culled to try and free up
- *      capacity.  Calls currently in progress on the connection are allowed to
- *      continue, but new calls will have to wait.  There can be no waiters in
- *      this state - the conn would have to go to the WAITING state instead.
- *
- *  (6) IDLE - The connection has no calls in progress upon it and must have
- *      been exposed to the world (ie. the EXPOSED flag must be set).  When it
- *      expires, the EXPOSED flag is cleared and the connection transitions to
- *      the INACTIVE state.
- *
- *	The connection is on the rxnet->idle_client_conns list which is kept in
- *	order of how soon they'll expire.
- *
  * There are flags of relevance to the cache:
  *
- *  (1) EXPOSED - The connection ID got exposed to the world.  If this flag is
- *      set, an extra ref is added to the connection preventing it from being
- *      reaped when it has no calls outstanding.  This flag is cleared and the
- *      ref dropped when a conn is discarded from the idle list.
- *
- *      This allows us to move terminal call state retransmission to the
- *      connection and to discard the call immediately we think it is done
- *      with.  It also give us a chance to reuse the connection.
- *
  *  (2) DONT_REUSE - The connection should be discarded as soon as possible and
  *      should not be reused.  This is set when an exclusive connection is used
  *      or a call ID counter overflows.
@@ -78,7 +30,6 @@
 
 #include "ar-internal.h"
 
-__read_mostly unsigned int rxrpc_max_client_connections = 1000;
 __read_mostly unsigned int rxrpc_reap_client_connections = 900;
 __read_mostly unsigned long rxrpc_conn_idle_client_expiry = 2 * 60 * HZ;
 __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
@@ -89,8 +40,6 @@ __read_mostly unsigned long rxrpc_conn_idle_client_fast_expiry = 2 * HZ;
 DEFINE_IDR(rxrpc_client_conn_ids);
 static DEFINE_SPINLOCK(rxrpc_conn_id_lock);
 
-static void rxrpc_cull_active_client_conns(struct rxrpc_net *);
-
 /*
  * Get a connection ID and epoch for a client connection from the global pool.
  * The connection struct pointer is then recorded in the idr radix tree.  The
@@ -162,13 +111,50 @@ void rxrpc_destroy_client_conn_ids(void)
 }
 
 /*
+ * Allocate a connection bundle.
+ */
+static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp,
+					       gfp_t gfp)
+{
+	struct rxrpc_bundle *bundle;
+
+	bundle = kzalloc(sizeof(*bundle), gfp);
+	if (bundle) {
+		bundle->params = *cp;
+		rxrpc_get_peer(bundle->params.peer);
+		atomic_set(&bundle->usage, 1);
+		spin_lock_init(&bundle->channel_lock);
+		INIT_LIST_HEAD(&bundle->waiting_calls);
+	}
+	return bundle;
+}
+
+struct rxrpc_bundle *rxrpc_get_bundle(struct rxrpc_bundle *bundle)
+{
+	atomic_inc(&bundle->usage);
+	return bundle;
+}
+
+void rxrpc_put_bundle(struct rxrpc_bundle *bundle)
+{
+	unsigned int d = bundle->debug_id;
+	unsigned int u = atomic_dec_return(&bundle->usage);
+
+	_debug("PUT B=%x %u", d, u);
+	if (u == 0) {
+		rxrpc_put_peer(bundle->params.peer);
+		kfree(bundle);
+	}
+}
+
+/*
  * Allocate a client connection.
  */
 static struct rxrpc_connection *
-rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp)
+rxrpc_alloc_client_connection(struct rxrpc_bundle *bundle, gfp_t gfp)
 {
 	struct rxrpc_connection *conn;
-	struct rxrpc_net *rxnet = cp->local->rxnet;
+	struct rxrpc_net *rxnet = bundle->params.local->rxnet;
 	int ret;
 
 	_enter("");
@@ -180,15 +166,11 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp)
 	}
 
 	atomic_set(&conn->usage, 1);
-	if (cp->exclusive)
-		__set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
-	if (cp->upgrade)
-		__set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags);
-
-	conn->params		= *cp;
+	conn->bundle		= bundle;
+	conn->params		= bundle->params;
 	conn->out_clientflag	= RXRPC_CLIENT_INITIATED;
 	conn->state		= RXRPC_CONN_CLIENT;
-	conn->service_id	= cp->service_id;
+	conn->service_id	= conn->params.service_id;
 
 	ret = rxrpc_get_client_connection_id(conn, gfp);
 	if (ret < 0)
@@ -198,29 +180,25 @@ rxrpc_alloc_client_connection(struct rxrpc_conn_parameters *cp, gfp_t gfp)
 	if (ret < 0)
 		goto error_1;
 
-	ret = conn->security->prime_packet_security(conn);
-	if (ret < 0)
-		goto error_2;
-
 	atomic_inc(&rxnet->nr_conns);
 	write_lock(&rxnet->conn_lock);
 	list_add_tail(&conn->proc_link, &rxnet->conn_proc_list);
 	write_unlock(&rxnet->conn_lock);
 
-	/* We steal the caller's peer ref. */
-	cp->peer = NULL;
+	rxrpc_get_bundle(bundle);
+	rxrpc_get_peer(conn->params.peer);
 	rxrpc_get_local(conn->params.local);
 	key_get(conn->params.key);
 
 	trace_rxrpc_conn(conn->debug_id, rxrpc_conn_new_client,
 			 atomic_read(&conn->usage),
 			 __builtin_return_address(0));
+
+	atomic_inc(&rxnet->nr_client_conns);
 	trace_rxrpc_client(conn, -1, rxrpc_client_alloc);
 	_leave(" = %p", conn);
 	return conn;
 
-error_2:
-	conn->security->clear(conn);
 error_1:
 	rxrpc_put_client_connection_id(conn);
 error_0:
@@ -234,13 +212,18 @@ error_0:
  */
 static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn)
 {
-	struct rxrpc_net *rxnet = conn->params.local->rxnet;
+	struct rxrpc_net *rxnet;
 	int id_cursor, id, distance, limit;
 
+	if (!conn)
+		goto dont_reuse;
+
+	rxnet = conn->params.local->rxnet;
 	if (test_bit(RXRPC_CONN_DONT_REUSE, &conn->flags))
 		goto dont_reuse;
 
-	if (conn->proto.epoch != rxnet->epoch)
+	if (conn->state != RXRPC_CONN_CLIENT ||
+	    conn->proto.epoch != rxnet->epoch)
 		goto mark_dont_reuse;
 
 	/* The IDR tree gets very expensive on memory if the connection IDs are
@@ -254,7 +237,7 @@ static bool rxrpc_may_reuse_conn(struct rxrpc_connection *conn)
 	distance = id - id_cursor;
 	if (distance < 0)
 		distance = -distance;
-	limit = max(rxrpc_max_client_connections * 4, 1024U);
+	limit = max_t(unsigned long, atomic_read(&rxnet->nr_conns) * 4, 1024);
 	if (distance > limit)
 		goto mark_dont_reuse;
 
@@ -267,277 +250,247 @@ dont_reuse:
 }
 
 /*
- * Create or find a client connection to use for a call.
- *
- * If we return with a connection, the call will be on its waiting list.  It's
- * left to the caller to assign a channel and wake up the call.
+ * Look up the conn bundle that matches the connection parameters, adding it if
+ * it doesn't yet exist.
  */
-static int rxrpc_get_client_conn(struct rxrpc_sock *rx,
-				 struct rxrpc_call *call,
-				 struct rxrpc_conn_parameters *cp,
-				 struct sockaddr_rxrpc *srx,
-				 gfp_t gfp)
+static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *cp,
+						 gfp_t gfp)
 {
-	struct rxrpc_connection *conn, *candidate = NULL;
+	static atomic_t rxrpc_bundle_id;
+	struct rxrpc_bundle *bundle, *candidate;
 	struct rxrpc_local *local = cp->local;
 	struct rb_node *p, **pp, *parent;
 	long diff;
-	int ret = -ENOMEM;
 
-	_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
+	_enter("{%px,%x,%u,%u}",
+	       cp->peer, key_serial(cp->key), cp->security_level, cp->upgrade);
 
-	cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp);
-	if (!cp->peer)
-		goto error;
+	if (cp->exclusive)
+		return rxrpc_alloc_bundle(cp, gfp);
 
-	call->cong_cwnd = cp->peer->cong_cwnd;
-	if (call->cong_cwnd >= call->cong_ssthresh)
-		call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
-	else
-		call->cong_mode = RXRPC_CALL_SLOW_START;
+	/* First, see if the bundle is already there. */
+	_debug("search 1");
+	spin_lock(&local->client_bundles_lock);
+	p = local->client_bundles.rb_node;
+	while (p) {
+		bundle = rb_entry(p, struct rxrpc_bundle, local_node);
 
-	/* If the connection is not meant to be exclusive, search the available
-	 * connections to see if the connection we want to use already exists.
-	 */
-	if (!cp->exclusive) {
-		_debug("search 1");
-		spin_lock(&local->client_conns_lock);
-		p = local->client_conns.rb_node;
-		while (p) {
-			conn = rb_entry(p, struct rxrpc_connection, client_node);
-
-#define cmp(X) ((long)conn->params.X - (long)cp->X)
-			diff = (cmp(peer) ?:
-				cmp(key) ?:
-				cmp(security_level) ?:
-				cmp(upgrade));
+#define cmp(X) ((long)bundle->params.X - (long)cp->X)
+		diff = (cmp(peer) ?:
+			cmp(key) ?:
+			cmp(security_level) ?:
+			cmp(upgrade));
 #undef cmp
-			if (diff < 0) {
-				p = p->rb_left;
-			} else if (diff > 0) {
-				p = p->rb_right;
-			} else {
-				if (rxrpc_may_reuse_conn(conn) &&
-				    rxrpc_get_connection_maybe(conn))
-					goto found_extant_conn;
-				/* The connection needs replacing.  It's better
-				 * to effect that when we have something to
-				 * replace it with so that we don't have to
-				 * rebalance the tree twice.
-				 */
-				break;
-			}
-		}
-		spin_unlock(&local->client_conns_lock);
+		if (diff < 0)
+			p = p->rb_left;
+		else if (diff > 0)
+			p = p->rb_right;
+		else
+			goto found_bundle;
 	}
+	spin_unlock(&local->client_bundles_lock);
+	_debug("not found");
 
-	/* There wasn't a connection yet or we need an exclusive connection.
-	 * We need to create a candidate and then potentially redo the search
-	 * in case we're racing with another thread also trying to connect on a
-	 * shareable connection.
-	 */
-	_debug("new conn");
-	candidate = rxrpc_alloc_client_connection(cp, gfp);
-	if (IS_ERR(candidate)) {
-		ret = PTR_ERR(candidate);
-		goto error_peer;
-	}
-
-	/* Add the call to the new connection's waiting list in case we're
-	 * going to have to wait for the connection to come live.  It's our
-	 * connection, so we want first dibs on the channel slots.  We would
-	 * normally have to take channel_lock but we do this before anyone else
-	 * can see the connection.
-	 */
-	list_add(&call->chan_wait_link, &candidate->waiting_calls);
-
-	if (cp->exclusive) {
-		call->conn = candidate;
-		call->security = candidate->security;
-		call->security_ix = candidate->security_ix;
-		call->service_id = candidate->service_id;
-		_leave(" = 0 [exclusive %d]", candidate->debug_id);
-		return 0;
-	}
+	/* It wasn't.  We need to add one. */
+	candidate = rxrpc_alloc_bundle(cp, gfp);
+	if (!candidate)
+		return NULL;
 
-	/* Publish the new connection for userspace to find.  We need to redo
-	 * the search before doing this lest we race with someone else adding a
-	 * conflicting instance.
-	 */
 	_debug("search 2");
-	spin_lock(&local->client_conns_lock);
-
-	pp = &local->client_conns.rb_node;
+	spin_lock(&local->client_bundles_lock);
+	pp = &local->client_bundles.rb_node;
 	parent = NULL;
 	while (*pp) {
 		parent = *pp;
-		conn = rb_entry(parent, struct rxrpc_connection, client_node);
+		bundle = rb_entry(parent, struct rxrpc_bundle, local_node);
 
-#define cmp(X) ((long)conn->params.X - (long)candidate->params.X)
+#define cmp(X) ((long)bundle->params.X - (long)cp->X)
 		diff = (cmp(peer) ?:
 			cmp(key) ?:
 			cmp(security_level) ?:
 			cmp(upgrade));
 #undef cmp
-		if (diff < 0) {
+		if (diff < 0)
 			pp = &(*pp)->rb_left;
-		} else if (diff > 0) {
+		else if (diff > 0)
 			pp = &(*pp)->rb_right;
-		} else {
-			if (rxrpc_may_reuse_conn(conn) &&
-			    rxrpc_get_connection_maybe(conn))
-				goto found_extant_conn;
-			/* The old connection is from an outdated epoch. */
-			_debug("replace conn");
-			clear_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags);
-			rb_replace_node(&conn->client_node,
-					&candidate->client_node,
-					&local->client_conns);
-			trace_rxrpc_client(conn, -1, rxrpc_client_replace);
-			goto candidate_published;
-		}
+		else
+			goto found_bundle_free;
 	}
 
-	_debug("new conn");
-	rb_link_node(&candidate->client_node, parent, pp);
-	rb_insert_color(&candidate->client_node, &local->client_conns);
-
-candidate_published:
-	set_bit(RXRPC_CONN_IN_CLIENT_CONNS, &candidate->flags);
-	call->conn = candidate;
-	call->security = candidate->security;
-	call->security_ix = candidate->security_ix;
-	call->service_id = candidate->service_id;
-	spin_unlock(&local->client_conns_lock);
-	_leave(" = 0 [new %d]", candidate->debug_id);
-	return 0;
+	_debug("new bundle");
+	candidate->debug_id = atomic_inc_return(&rxrpc_bundle_id);
+	rb_link_node(&candidate->local_node, parent, pp);
+	rb_insert_color(&candidate->local_node, &local->client_bundles);
+	rxrpc_get_bundle(candidate);
+	spin_unlock(&local->client_bundles_lock);
+	_leave(" = %u [new]", candidate->debug_id);
+	return candidate;
+
+found_bundle_free:
+	kfree(candidate);
+found_bundle:
+	rxrpc_get_bundle(bundle);
+	spin_unlock(&local->client_bundles_lock);
+	_leave(" = %u [found]", bundle->debug_id);
+	return bundle;
+}
 
-	/* We come here if we found a suitable connection already in existence.
-	 * Discard any candidate we may have allocated, and try to get a
-	 * channel on this one.
-	 */
-found_extant_conn:
-	_debug("found conn");
-	spin_unlock(&local->client_conns_lock);
+/*
+ * Create or find a client bundle to use for a call.
+ *
+ * If we return with a connection, the call will be on its waiting list.  It's
+ * left to the caller to assign a channel and wake up the call.
+ */
+static struct rxrpc_bundle *rxrpc_prep_call(struct rxrpc_sock *rx,
+					    struct rxrpc_call *call,
+					    struct rxrpc_conn_parameters *cp,
+					    struct sockaddr_rxrpc *srx,
+					    gfp_t gfp)
+{
+	struct rxrpc_bundle *bundle;
 
-	if (candidate) {
-		trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate);
-		rxrpc_put_connection(candidate);
-		candidate = NULL;
-	}
+	_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
 
-	spin_lock(&conn->channel_lock);
-	call->conn = conn;
-	call->security = conn->security;
-	call->security_ix = conn->security_ix;
-	call->service_id = conn->service_id;
-	list_add_tail(&call->chan_wait_link, &conn->waiting_calls);
-	spin_unlock(&conn->channel_lock);
-	_leave(" = 0 [extant %d]", conn->debug_id);
-	return 0;
+	cp->peer = rxrpc_lookup_peer(rx, cp->local, srx, gfp);
+	if (!cp->peer)
+		goto error;
+
+	call->cong_cwnd = cp->peer->cong_cwnd;
+	if (call->cong_cwnd >= call->cong_ssthresh)
+		call->cong_mode = RXRPC_CALL_CONGEST_AVOIDANCE;
+	else
+		call->cong_mode = RXRPC_CALL_SLOW_START;
+	if (cp->upgrade)
+		__set_bit(RXRPC_CALL_UPGRADE, &call->flags);
+
+	/* Find the client connection bundle. */
+	bundle = rxrpc_look_up_bundle(cp, gfp);
+	if (!bundle)
+		goto error;
+
+	/* Get this call queued.  Someone else may activate it whilst we're
+	 * lining up a new connection, but that's fine.
+	 */
+	spin_lock(&bundle->channel_lock);
+	list_add_tail(&call->chan_wait_link, &bundle->waiting_calls);
+	spin_unlock(&bundle->channel_lock);
+
+	_leave(" = [B=%x]", bundle->debug_id);
+	return bundle;
 
-error_peer:
-	rxrpc_put_peer(cp->peer);
-	cp->peer = NULL;
 error:
-	_leave(" = %d", ret);
-	return ret;
+	_leave(" = -ENOMEM");
+	return ERR_PTR(-ENOMEM);
 }
 
 /*
- * Activate a connection.
+ * Allocate a new connection and add it into a bundle.
  */
-static void rxrpc_activate_conn(struct rxrpc_net *rxnet,
-				struct rxrpc_connection *conn)
+static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp)
+	__releases(bundle->channel_lock)
 {
-	if (test_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) {
-		trace_rxrpc_client(conn, -1, rxrpc_client_to_upgrade);
-		conn->cache_state = RXRPC_CONN_CLIENT_UPGRADE;
-	} else {
-		trace_rxrpc_client(conn, -1, rxrpc_client_to_active);
-		conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE;
-	}
-	rxnet->nr_active_client_conns++;
-	list_move_tail(&conn->cache_link, &rxnet->active_client_conns);
-}
+	struct rxrpc_connection *candidate = NULL, *old = NULL;
+	bool conflict;
+	int i;
 
-/*
- * Attempt to animate a connection for a new call.
- *
- * If it's not exclusive, the connection is in the endpoint tree, and we're in
- * the conn's list of those waiting to grab a channel.  There is, however, a
- * limit on the number of live connections allowed at any one time, so we may
- * have to wait for capacity to become available.
- *
- * Note that a connection on the waiting queue might *also* have active
- * channels if it has been culled to make space and then re-requested by a new
- * call.
- */
-static void rxrpc_animate_client_conn(struct rxrpc_net *rxnet,
-				      struct rxrpc_connection *conn)
-{
-	unsigned int nr_conns;
+	_enter("");
 
-	_enter("%d,%d", conn->debug_id, conn->cache_state);
+	conflict = bundle->alloc_conn;
+	if (!conflict)
+		bundle->alloc_conn = true;
+	spin_unlock(&bundle->channel_lock);
+	if (conflict) {
+		_leave(" [conf]");
+		return;
+	}
 
-	if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE ||
-	    conn->cache_state == RXRPC_CONN_CLIENT_UPGRADE)
-		goto out;
+	candidate = rxrpc_alloc_client_connection(bundle, gfp);
 
-	spin_lock(&rxnet->client_conn_cache_lock);
+	spin_lock(&bundle->channel_lock);
+	bundle->alloc_conn = false;
 
-	nr_conns = rxnet->nr_client_conns;
-	if (!test_and_set_bit(RXRPC_CONN_COUNTED, &conn->flags)) {
-		trace_rxrpc_client(conn, -1, rxrpc_client_count);
-		rxnet->nr_client_conns = nr_conns + 1;
+	if (IS_ERR(candidate)) {
+		bundle->alloc_error = PTR_ERR(candidate);
+		spin_unlock(&bundle->channel_lock);
+		_leave(" [err %ld]", PTR_ERR(candidate));
+		return;
 	}
 
-	switch (conn->cache_state) {
-	case RXRPC_CONN_CLIENT_ACTIVE:
-	case RXRPC_CONN_CLIENT_UPGRADE:
-	case RXRPC_CONN_CLIENT_WAITING:
-		break;
-
-	case RXRPC_CONN_CLIENT_INACTIVE:
-	case RXRPC_CONN_CLIENT_CULLED:
-	case RXRPC_CONN_CLIENT_IDLE:
-		if (nr_conns >= rxrpc_max_client_connections)
-			goto wait_for_capacity;
-		goto activate_conn;
+	bundle->alloc_error = 0;
+
+	for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) {
+		unsigned int shift = i * RXRPC_MAXCALLS;
+		int j;
+
+		old = bundle->conns[i];
+		if (!rxrpc_may_reuse_conn(old)) {
+			if (old)
+				trace_rxrpc_client(old, -1, rxrpc_client_replace);
+			candidate->bundle_shift = shift;
+			bundle->conns[i] = candidate;
+			for (j = 0; j < RXRPC_MAXCALLS; j++)
+				set_bit(shift + j, &bundle->avail_chans);
+			candidate = NULL;
+			break;
+		}
 
-	default:
-		BUG();
+		old = NULL;
 	}
 
-out_unlock:
-	spin_unlock(&rxnet->client_conn_cache_lock);
-out:
-	_leave(" [%d]", conn->cache_state);
-	return;
+	spin_unlock(&bundle->channel_lock);
 
-activate_conn:
-	_debug("activate");
-	rxrpc_activate_conn(rxnet, conn);
-	goto out_unlock;
-
-wait_for_capacity:
-	_debug("wait");
-	trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting);
-	conn->cache_state = RXRPC_CONN_CLIENT_WAITING;
-	list_move_tail(&conn->cache_link, &rxnet->waiting_client_conns);
-	goto out_unlock;
+	if (candidate) {
+		_debug("discard C=%x", candidate->debug_id);
+		trace_rxrpc_client(candidate, -1, rxrpc_client_duplicate);
+		rxrpc_put_connection(candidate);
+	}
+
+	rxrpc_put_connection(old);
+	_leave("");
 }
 
 /*
- * Deactivate a channel.
+ * Add a connection to a bundle if there are no usable connections or we have
+ * connections waiting for extra capacity.
  */
-static void rxrpc_deactivate_one_channel(struct rxrpc_connection *conn,
-					 unsigned int channel)
+static void rxrpc_maybe_add_conn(struct rxrpc_bundle *bundle, gfp_t gfp)
 {
-	struct rxrpc_channel *chan = &conn->channels[channel];
+	struct rxrpc_call *call;
+	int i, usable;
 
-	rcu_assign_pointer(chan->call, NULL);
-	conn->active_chans &= ~(1 << channel);
+	_enter("");
+
+	spin_lock(&bundle->channel_lock);
+
+	/* See if there are any usable connections. */
+	usable = 0;
+	for (i = 0; i < ARRAY_SIZE(bundle->conns); i++)
+		if (rxrpc_may_reuse_conn(bundle->conns[i]))
+			usable++;
+
+	if (!usable && !list_empty(&bundle->waiting_calls)) {
+		call = list_first_entry(&bundle->waiting_calls,
+					struct rxrpc_call, chan_wait_link);
+		if (test_bit(RXRPC_CALL_UPGRADE, &call->flags))
+			bundle->try_upgrade = true;
+	}
+
+	if (!usable)
+		goto alloc_conn;
+
+	if (!bundle->avail_chans &&
+	    !bundle->try_upgrade &&
+	    !list_empty(&bundle->waiting_calls) &&
+	    usable < ARRAY_SIZE(bundle->conns))
+		goto alloc_conn;
+
+	spin_unlock(&bundle->channel_lock);
+	_leave("");
+	return;
+
+alloc_conn:
+	return rxrpc_add_conn_to_bundle(bundle, gfp);
 }
 
 /*
@@ -549,35 +502,42 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
 				       unsigned int channel)
 {
 	struct rxrpc_channel *chan = &conn->channels[channel];
-	struct rxrpc_call *call = list_entry(conn->waiting_calls.next,
+	struct rxrpc_bundle *bundle = conn->bundle;
+	struct rxrpc_call *call = list_entry(bundle->waiting_calls.next,
 					     struct rxrpc_call, chan_wait_link);
 	u32 call_id = chan->call_counter + 1;
 
+	_enter("C=%x,%u", conn->debug_id, channel);
+
 	trace_rxrpc_client(conn, channel, rxrpc_client_chan_activate);
 
 	/* Cancel the final ACK on the previous call if it hasn't been sent yet
 	 * as the DATA packet will implicitly ACK it.
 	 */
 	clear_bit(RXRPC_CONN_FINAL_ACK_0 + channel, &conn->flags);
-
-	write_lock_bh(&call->state_lock);
-	call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
-	write_unlock_bh(&call->state_lock);
+	clear_bit(conn->bundle_shift + channel, &bundle->avail_chans);
 
 	rxrpc_see_call(call);
 	list_del_init(&call->chan_wait_link);
-	conn->active_chans |= 1 << channel;
 	call->peer	= rxrpc_get_peer(conn->params.peer);
+	call->conn	= rxrpc_get_connection(conn);
 	call->cid	= conn->proto.cid | channel;
 	call->call_id	= call_id;
+	call->security	= conn->security;
+	call->security_ix = conn->security_ix;
+	call->service_id = conn->service_id;
 
 	trace_rxrpc_connect_call(call);
 	_net("CONNECT call %08x:%08x as call %d on conn %d",
 	     call->cid, call->call_id, call->debug_id, conn->debug_id);
 
-	/* Paired with the read barrier in rxrpc_wait_for_channel().  This
-	 * orders cid and epoch in the connection wrt to call_id without the
-	 * need to take the channel_lock.
+	write_lock_bh(&call->state_lock);
+	call->state = RXRPC_CALL_CLIENT_SEND_REQUEST;
+	write_unlock_bh(&call->state_lock);
+
+	/* Paired with the read barrier in rxrpc_connect_call().  This orders
+	 * cid and epoch in the connection wrt to call_id without the need to
+	 * take the channel_lock.
 	 *
 	 * We provisionally assign a callNumber at this point, but we don't
 	 * confirm it until the call is about to be exposed.
@@ -586,101 +546,137 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
 	 * at the call ID through a connection channel.
 	 */
 	smp_wmb();
-	chan->call_id	= call_id;
-	chan->call_debug_id = call->debug_id;
+
+	chan->call_id		= call_id;
+	chan->call_debug_id	= call->debug_id;
 	rcu_assign_pointer(chan->call, call);
 	wake_up(&call->waitq);
 }
 
 /*
+ * Remove a connection from the idle list if it's on it.
+ */
+static void rxrpc_unidle_conn(struct rxrpc_bundle *bundle, struct rxrpc_connection *conn)
+{
+	struct rxrpc_net *rxnet = bundle->params.local->rxnet;
+	bool drop_ref;
+
+	if (!list_empty(&conn->cache_link)) {
+		drop_ref = false;
+		spin_lock(&rxnet->client_conn_cache_lock);
+		if (!list_empty(&conn->cache_link)) {
+			list_del_init(&conn->cache_link);
+			drop_ref = true;
+		}
+		spin_unlock(&rxnet->client_conn_cache_lock);
+		if (drop_ref)
+			rxrpc_put_connection(conn);
+	}
+}
+
+/*
  * Assign channels and callNumbers to waiting calls with channel_lock
  * held by caller.
  */
-static void rxrpc_activate_channels_locked(struct rxrpc_connection *conn)
+static void rxrpc_activate_channels_locked(struct rxrpc_bundle *bundle)
 {
-	u8 avail, mask;
-
-	switch (conn->cache_state) {
-	case RXRPC_CONN_CLIENT_ACTIVE:
-		mask = RXRPC_ACTIVE_CHANS_MASK;
-		break;
-	case RXRPC_CONN_CLIENT_UPGRADE:
-		mask = 0x01;
-		break;
-	default:
-		return;
-	}
+	struct rxrpc_connection *conn;
+	unsigned long avail, mask;
+	unsigned int channel, slot;
 
-	while (!list_empty(&conn->waiting_calls) &&
-	       (avail = ~conn->active_chans,
-		avail &= mask,
-		avail != 0))
-		rxrpc_activate_one_channel(conn, __ffs(avail));
+	if (bundle->try_upgrade)
+		mask = 1;
+	else
+		mask = ULONG_MAX;
+
+	while (!list_empty(&bundle->waiting_calls)) {
+		avail = bundle->avail_chans & mask;
+		if (!avail)
+			break;
+		channel = __ffs(avail);
+		clear_bit(channel, &bundle->avail_chans);
+
+		slot = channel / RXRPC_MAXCALLS;
+		conn = bundle->conns[slot];
+		if (!conn)
+			break;
+
+		if (bundle->try_upgrade)
+			set_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags);
+		rxrpc_unidle_conn(bundle, conn);
+
+		channel &= (RXRPC_MAXCALLS - 1);
+		conn->act_chans	|= 1 << channel;
+		rxrpc_activate_one_channel(conn, channel);
+	}
 }
 
 /*
  * Assign channels and callNumbers to waiting calls.
  */
-static void rxrpc_activate_channels(struct rxrpc_connection *conn)
+static void rxrpc_activate_channels(struct rxrpc_bundle *bundle)
 {
-	_enter("%d", conn->debug_id);
+	_enter("B=%x", bundle->debug_id);
 
-	trace_rxrpc_client(conn, -1, rxrpc_client_activate_chans);
+	trace_rxrpc_client(NULL, -1, rxrpc_client_activate_chans);
 
-	if (conn->active_chans == RXRPC_ACTIVE_CHANS_MASK)
+	if (!bundle->avail_chans)
 		return;
 
-	spin_lock(&conn->channel_lock);
-	rxrpc_activate_channels_locked(conn);
-	spin_unlock(&conn->channel_lock);
+	spin_lock(&bundle->channel_lock);
+	rxrpc_activate_channels_locked(bundle);
+	spin_unlock(&bundle->channel_lock);
 	_leave("");
 }
 
 /*
  * Wait for a callNumber and a channel to be granted to a call.
  */
-static int rxrpc_wait_for_channel(struct rxrpc_call *call, gfp_t gfp)
+static int rxrpc_wait_for_channel(struct rxrpc_bundle *bundle,
+				  struct rxrpc_call *call, gfp_t gfp)
 {
+	DECLARE_WAITQUEUE(myself, current);
 	int ret = 0;
 
 	_enter("%d", call->debug_id);
 
-	if (!call->call_id) {
-		DECLARE_WAITQUEUE(myself, current);
+	if (!gfpflags_allow_blocking(gfp)) {
+		rxrpc_maybe_add_conn(bundle, gfp);
+		rxrpc_activate_channels(bundle);
+		ret = bundle->alloc_error ?: -EAGAIN;
+		goto out;
+	}
 
-		if (!gfpflags_allow_blocking(gfp)) {
-			ret = -EAGAIN;
-			goto out;
+	add_wait_queue_exclusive(&call->waitq, &myself);
+	for (;;) {
+		rxrpc_maybe_add_conn(bundle, gfp);
+		rxrpc_activate_channels(bundle);
+		ret = bundle->alloc_error;
+		if (ret < 0)
+			break;
+
+		switch (call->interruptibility) {
+		case RXRPC_INTERRUPTIBLE:
+		case RXRPC_PREINTERRUPTIBLE:
+			set_current_state(TASK_INTERRUPTIBLE);
+			break;
+		case RXRPC_UNINTERRUPTIBLE:
+		default:
+			set_current_state(TASK_UNINTERRUPTIBLE);
+			break;
 		}
-
-		add_wait_queue_exclusive(&call->waitq, &myself);
-		for (;;) {
-			switch (call->interruptibility) {
-			case RXRPC_INTERRUPTIBLE:
-			case RXRPC_PREINTERRUPTIBLE:
-				set_current_state(TASK_INTERRUPTIBLE);
-				break;
-			case RXRPC_UNINTERRUPTIBLE:
-			default:
-				set_current_state(TASK_UNINTERRUPTIBLE);
-				break;
-			}
-			if (call->call_id)
-				break;
-			if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
-			     call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
-			    signal_pending(current)) {
-				ret = -ERESTARTSYS;
-				break;
-			}
-			schedule();
+		if (READ_ONCE(call->state) != RXRPC_CALL_CLIENT_AWAIT_CONN)
+			break;
+		if ((call->interruptibility == RXRPC_INTERRUPTIBLE ||
+		     call->interruptibility == RXRPC_PREINTERRUPTIBLE) &&
+		    signal_pending(current)) {
+			ret = -ERESTARTSYS;
+			break;
 		}
-		remove_wait_queue(&call->waitq, &myself);
-		__set_current_state(TASK_RUNNING);
+		schedule();
 	}
-
-	/* Paired with the write barrier in rxrpc_activate_one_channel(). */
-	smp_rmb();
+	remove_wait_queue(&call->waitq, &myself);
+	__set_current_state(TASK_RUNNING);
 
 out:
 	_leave(" = %d", ret);
@@ -697,52 +693,50 @@ int rxrpc_connect_call(struct rxrpc_sock *rx,
 		       struct sockaddr_rxrpc *srx,
 		       gfp_t gfp)
 {
+	struct rxrpc_bundle *bundle;
 	struct rxrpc_net *rxnet = cp->local->rxnet;
-	int ret;
+	int ret = 0;
 
 	_enter("{%d,%lx},", call->debug_id, call->user_call_ID);
 
 	rxrpc_discard_expired_client_conns(&rxnet->client_conn_reaper);
-	rxrpc_cull_active_client_conns(rxnet);
 
-	ret = rxrpc_get_client_conn(rx, call, cp, srx, gfp);
-	if (ret < 0)
+	bundle = rxrpc_prep_call(rx, call, cp, srx, gfp);
+	if (IS_ERR(bundle)) {
+		ret = PTR_ERR(bundle);
 		goto out;
+	}
 
-	rxrpc_animate_client_conn(rxnet, call->conn);
-	rxrpc_activate_channels(call->conn);
-
-	ret = rxrpc_wait_for_channel(call, gfp);
-	if (ret < 0) {
-		trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed);
-		rxrpc_disconnect_client_call(call);
-		goto out;
+	if (call->state == RXRPC_CALL_CLIENT_AWAIT_CONN) {
+		ret = rxrpc_wait_for_channel(bundle, call, gfp);
+		if (ret < 0)
+			goto wait_failed;
 	}
 
-	spin_lock_bh(&call->conn->params.peer->lock);
-	hlist_add_head_rcu(&call->error_link,
-			   &call->conn->params.peer->error_targets);
-	spin_unlock_bh(&call->conn->params.peer->lock);
+granted_channel:
+	/* Paired with the write barrier in rxrpc_activate_one_channel(). */
+	smp_rmb();
 
+out_put_bundle:
+	rxrpc_put_bundle(bundle);
 out:
 	_leave(" = %d", ret);
 	return ret;
-}
 
-/*
- * Note that a connection is about to be exposed to the world.  Once it is
- * exposed, we maintain an extra ref on it that stops it from being summarily
- * discarded before it's (a) had a chance to deal with retransmission and (b)
- * had a chance at re-use (the per-connection security negotiation is
- * expensive).
- */
-static void rxrpc_expose_client_conn(struct rxrpc_connection *conn,
-				     unsigned int channel)
-{
-	if (!test_and_set_bit(RXRPC_CONN_EXPOSED, &conn->flags)) {
-		trace_rxrpc_client(conn, channel, rxrpc_client_exposed);
-		rxrpc_get_connection(conn);
+wait_failed:
+	spin_lock(&bundle->channel_lock);
+	list_del_init(&call->chan_wait_link);
+	spin_unlock(&bundle->channel_lock);
+
+	if (call->state != RXRPC_CALL_CLIENT_AWAIT_CONN) {
+		ret = 0;
+		goto granted_channel;
 	}
+
+	trace_rxrpc_client(call->conn, ret, rxrpc_client_chan_wait_failed);
+	rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, 0, ret);
+	rxrpc_disconnect_client_call(bundle, call);
+	goto out_put_bundle;
 }
 
 /*
@@ -764,7 +758,7 @@ void rxrpc_expose_client_call(struct rxrpc_call *call)
 		chan->call_counter++;
 		if (chan->call_counter >= INT_MAX)
 			set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
-		rxrpc_expose_client_conn(conn, channel);
+		trace_rxrpc_client(conn, channel, rxrpc_client_exposed);
 	}
 }
 
@@ -773,62 +767,56 @@ void rxrpc_expose_client_call(struct rxrpc_call *call)
  */
 static void rxrpc_set_client_reap_timer(struct rxrpc_net *rxnet)
 {
-	unsigned long now = jiffies;
-	unsigned long reap_at = now + rxrpc_conn_idle_client_expiry;
+	if (!rxnet->kill_all_client_conns) {
+		unsigned long now = jiffies;
+		unsigned long reap_at = now + rxrpc_conn_idle_client_expiry;
 
-	if (rxnet->live)
-		timer_reduce(&rxnet->client_conn_reap_timer, reap_at);
+		if (rxnet->live)
+			timer_reduce(&rxnet->client_conn_reap_timer, reap_at);
+	}
 }
 
 /*
  * Disconnect a client call.
  */
-void rxrpc_disconnect_client_call(struct rxrpc_call *call)
+void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call *call)
 {
-	struct rxrpc_connection *conn = call->conn;
+	struct rxrpc_connection *conn;
 	struct rxrpc_channel *chan = NULL;
-	struct rxrpc_net *rxnet = conn->params.local->rxnet;
-	unsigned int channel = -1;
+	struct rxrpc_net *rxnet = bundle->params.local->rxnet;
+	unsigned int channel;
+	bool may_reuse;
 	u32 cid;
 
-	spin_lock(&conn->channel_lock);
-	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
+	_enter("c=%x", call->debug_id);
 
-	cid = call->cid;
-	if (cid) {
-		channel = cid & RXRPC_CHANNELMASK;
-		chan = &conn->channels[channel];
-	}
-	trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
+	spin_lock(&bundle->channel_lock);
+	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 
 	/* Calls that have never actually been assigned a channel can simply be
-	 * discarded.  If the conn didn't get used either, it will follow
-	 * immediately unless someone else grabs it in the meantime.
+	 * discarded.
 	 */
-	if (!list_empty(&call->chan_wait_link)) {
+	conn = call->conn;
+	if (!conn) {
 		_debug("call is waiting");
 		ASSERTCMP(call->call_id, ==, 0);
 		ASSERT(!test_bit(RXRPC_CALL_EXPOSED, &call->flags));
 		list_del_init(&call->chan_wait_link);
-
-		trace_rxrpc_client(conn, channel, rxrpc_client_chan_unstarted);
-
-		/* We must deactivate or idle the connection if it's now
-		 * waiting for nothing.
-		 */
-		spin_lock(&rxnet->client_conn_cache_lock);
-		if (conn->cache_state == RXRPC_CONN_CLIENT_WAITING &&
-		    list_empty(&conn->waiting_calls) &&
-		    !conn->active_chans)
-			goto idle_connection;
 		goto out;
 	}
 
+	cid = call->cid;
+	channel = cid & RXRPC_CHANNELMASK;
+	chan = &conn->channels[channel];
+	trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect);
+
 	if (rcu_access_pointer(chan->call) != call) {
-		spin_unlock(&conn->channel_lock);
+		spin_unlock(&bundle->channel_lock);
 		BUG();
 	}
 
+	may_reuse = rxrpc_may_reuse_conn(conn);
+
 	/* If a client call was exposed to the world, we save the result for
 	 * retransmission.
 	 *
@@ -841,14 +829,21 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 	if (test_bit(RXRPC_CALL_EXPOSED, &call->flags)) {
 		_debug("exposed %u,%u", call->call_id, call->abort_code);
 		__rxrpc_disconnect_call(conn, call);
+
+		if (test_and_clear_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags)) {
+			trace_rxrpc_client(conn, channel, rxrpc_client_to_active);
+			bundle->try_upgrade = false;
+			if (may_reuse)
+				rxrpc_activate_channels_locked(bundle);
+		}
+
 	}
 
 	/* See if we can pass the channel directly to another call. */
-	if (conn->cache_state == RXRPC_CONN_CLIENT_ACTIVE &&
-	    !list_empty(&conn->waiting_calls)) {
+	if (may_reuse && !list_empty(&bundle->waiting_calls)) {
 		trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass);
 		rxrpc_activate_one_channel(conn, channel);
-		goto out_2;
+		goto out;
 	}
 
 	/* Schedule the final ACK to be transmitted in a short while so that it
@@ -865,128 +860,99 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call)
 		rxrpc_reduce_conn_timer(conn, final_ack_at);
 	}
 
-	/* Things are more complex and we need the cache lock.  We might be
-	 * able to simply idle the conn or it might now be lurking on the wait
-	 * list.  It might even get moved back to the active list whilst we're
-	 * waiting for the lock.
-	 */
-	spin_lock(&rxnet->client_conn_cache_lock);
-
-	switch (conn->cache_state) {
-	case RXRPC_CONN_CLIENT_UPGRADE:
-		/* Deal with termination of a service upgrade probe. */
-		if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) {
-			clear_bit(RXRPC_CONN_PROBING_FOR_UPGRADE, &conn->flags);
-			trace_rxrpc_client(conn, channel, rxrpc_client_to_active);
-			conn->cache_state = RXRPC_CONN_CLIENT_ACTIVE;
-			rxrpc_activate_channels_locked(conn);
-		}
-		fallthrough;
-	case RXRPC_CONN_CLIENT_ACTIVE:
-		if (list_empty(&conn->waiting_calls)) {
-			rxrpc_deactivate_one_channel(conn, channel);
-			if (!conn->active_chans) {
-				rxnet->nr_active_client_conns--;
-				goto idle_connection;
-			}
-			goto out;
-		}
-
-		trace_rxrpc_client(conn, channel, rxrpc_client_chan_pass);
-		rxrpc_activate_one_channel(conn, channel);
-		goto out;
+	/* Deactivate the channel. */
+	rcu_assign_pointer(chan->call, NULL);
+	set_bit(conn->bundle_shift + channel, &conn->bundle->avail_chans);
+	conn->act_chans	&= ~(1 << channel);
 
-	case RXRPC_CONN_CLIENT_CULLED:
-		rxrpc_deactivate_one_channel(conn, channel);
-		ASSERT(list_empty(&conn->waiting_calls));
-		if (!conn->active_chans)
-			goto idle_connection;
-		goto out;
+	/* If no channels remain active, then put the connection on the idle
+	 * list for a short while.  Give it a ref to stop it going away if it
+	 * becomes unbundled.
+	 */
+	if (!conn->act_chans) {
+		trace_rxrpc_client(conn, channel, rxrpc_client_to_idle);
+		conn->idle_timestamp = jiffies;
 
-	case RXRPC_CONN_CLIENT_WAITING:
-		rxrpc_deactivate_one_channel(conn, channel);
-		goto out;
+		rxrpc_get_connection(conn);
+		spin_lock(&rxnet->client_conn_cache_lock);
+		list_move_tail(&conn->cache_link, &rxnet->idle_client_conns);
+		spin_unlock(&rxnet->client_conn_cache_lock);
 
-	default:
-		BUG();
+		rxrpc_set_client_reap_timer(rxnet);
 	}
 
 out:
-	spin_unlock(&rxnet->client_conn_cache_lock);
-out_2:
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&bundle->channel_lock);
 	_leave("");
 	return;
+}
 
-idle_connection:
-	/* As no channels remain active, the connection gets deactivated
-	 * immediately or moved to the idle list for a short while.
-	 */
-	if (test_bit(RXRPC_CONN_EXPOSED, &conn->flags)) {
-		trace_rxrpc_client(conn, channel, rxrpc_client_to_idle);
-		conn->idle_timestamp = jiffies;
-		conn->cache_state = RXRPC_CONN_CLIENT_IDLE;
-		list_move_tail(&conn->cache_link, &rxnet->idle_client_conns);
-		if (rxnet->idle_client_conns.next == &conn->cache_link &&
-		    !rxnet->kill_all_client_conns)
-			rxrpc_set_client_reap_timer(rxnet);
-	} else {
-		trace_rxrpc_client(conn, channel, rxrpc_client_to_inactive);
-		conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE;
-		list_del_init(&conn->cache_link);
+/*
+ * Remove a connection from a bundle.
+ */
+static void rxrpc_unbundle_conn(struct rxrpc_connection *conn)
+{
+	struct rxrpc_bundle *bundle = conn->bundle;
+	struct rxrpc_local *local = bundle->params.local;
+	unsigned int bindex;
+	bool need_drop = false, need_put = false;
+	int i;
+
+	_enter("C=%x", conn->debug_id);
+
+	if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
+		rxrpc_process_delayed_final_acks(conn, true);
+
+	spin_lock(&bundle->channel_lock);
+	bindex = conn->bundle_shift / RXRPC_MAXCALLS;
+	if (bundle->conns[bindex] == conn) {
+		_debug("clear slot %u", bindex);
+		bundle->conns[bindex] = NULL;
+		for (i = 0; i < RXRPC_MAXCALLS; i++)
+			clear_bit(conn->bundle_shift + i, &bundle->avail_chans);
+		need_drop = true;
 	}
-	goto out;
+	spin_unlock(&bundle->channel_lock);
+
+	/* If there are no more connections, remove the bundle */
+	if (!bundle->avail_chans) {
+		_debug("maybe unbundle");
+		spin_lock(&local->client_bundles_lock);
+
+		for (i = 0; i < ARRAY_SIZE(bundle->conns); i++)
+			if (bundle->conns[i])
+				break;
+		if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) {
+			_debug("erase bundle");
+			rb_erase(&bundle->local_node, &local->client_bundles);
+			need_put = true;
+		}
+
+		spin_unlock(&local->client_bundles_lock);
+		if (need_put)
+			rxrpc_put_bundle(bundle);
+	}
+
+	if (need_drop)
+		rxrpc_put_connection(conn);
+	_leave("");
 }
 
 /*
  * Clean up a dead client connection.
  */
-static struct rxrpc_connection *
-rxrpc_put_one_client_conn(struct rxrpc_connection *conn)
+static void rxrpc_kill_client_conn(struct rxrpc_connection *conn)
 {
-	struct rxrpc_connection *next = NULL;
 	struct rxrpc_local *local = conn->params.local;
 	struct rxrpc_net *rxnet = local->rxnet;
-	unsigned int nr_conns;
 
-	trace_rxrpc_client(conn, -1, rxrpc_client_cleanup);
+	_enter("C=%x", conn->debug_id);
 
-	if (test_bit(RXRPC_CONN_IN_CLIENT_CONNS, &conn->flags)) {
-		spin_lock(&local->client_conns_lock);
-		if (test_and_clear_bit(RXRPC_CONN_IN_CLIENT_CONNS,
-				       &conn->flags))
-			rb_erase(&conn->client_node, &local->client_conns);
-		spin_unlock(&local->client_conns_lock);
-	}
+	trace_rxrpc_client(conn, -1, rxrpc_client_cleanup);
+	atomic_dec(&rxnet->nr_client_conns);
 
 	rxrpc_put_client_connection_id(conn);
-
-	ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_INACTIVE);
-
-	if (test_bit(RXRPC_CONN_COUNTED, &conn->flags)) {
-		trace_rxrpc_client(conn, -1, rxrpc_client_uncount);
-		spin_lock(&rxnet->client_conn_cache_lock);
-		nr_conns = --rxnet->nr_client_conns;
-
-		if (nr_conns < rxrpc_max_client_connections &&
-		    !list_empty(&rxnet->waiting_client_conns)) {
-			next = list_entry(rxnet->waiting_client_conns.next,
-					  struct rxrpc_connection, cache_link);
-			rxrpc_get_connection(next);
-			rxrpc_activate_conn(rxnet, next);
-		}
-
-		spin_unlock(&rxnet->client_conn_cache_lock);
-	}
-
 	rxrpc_kill_connection(conn);
-	if (next)
-		rxrpc_activate_channels(next);
-
-	/* We need to get rid of the temporary ref we took upon next, but we
-	 * can't call rxrpc_put_connection() recursively.
-	 */
-	return next;
 }
 
 /*
@@ -998,63 +964,12 @@ void rxrpc_put_client_conn(struct rxrpc_connection *conn)
 	unsigned int debug_id = conn->debug_id;
 	int n;
 
-	do {
-		n = atomic_dec_return(&conn->usage);
-		trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here);
-		if (n > 0)
-			return;
+	n = atomic_dec_return(&conn->usage);
+	trace_rxrpc_conn(debug_id, rxrpc_conn_put_client, n, here);
+	if (n <= 0) {
 		ASSERTCMP(n, >=, 0);
-
-		conn = rxrpc_put_one_client_conn(conn);
-	} while (conn);
-}
-
-/*
- * Kill the longest-active client connections to make room for new ones.
- */
-static void rxrpc_cull_active_client_conns(struct rxrpc_net *rxnet)
-{
-	struct rxrpc_connection *conn;
-	unsigned int nr_conns = rxnet->nr_client_conns;
-	unsigned int nr_active, limit;
-
-	_enter("");
-
-	ASSERTCMP(nr_conns, >=, 0);
-	if (nr_conns < rxrpc_max_client_connections) {
-		_leave(" [ok]");
-		return;
+		rxrpc_kill_client_conn(conn);
 	}
-	limit = rxrpc_reap_client_connections;
-
-	spin_lock(&rxnet->client_conn_cache_lock);
-	nr_active = rxnet->nr_active_client_conns;
-
-	while (nr_active > limit) {
-		ASSERT(!list_empty(&rxnet->active_client_conns));
-		conn = list_entry(rxnet->active_client_conns.next,
-				  struct rxrpc_connection, cache_link);
-		ASSERTIFCMP(conn->cache_state != RXRPC_CONN_CLIENT_ACTIVE,
-			    conn->cache_state, ==, RXRPC_CONN_CLIENT_UPGRADE);
-
-		if (list_empty(&conn->waiting_calls)) {
-			trace_rxrpc_client(conn, -1, rxrpc_client_to_culled);
-			conn->cache_state = RXRPC_CONN_CLIENT_CULLED;
-			list_del_init(&conn->cache_link);
-		} else {
-			trace_rxrpc_client(conn, -1, rxrpc_client_to_waiting);
-			conn->cache_state = RXRPC_CONN_CLIENT_WAITING;
-			list_move_tail(&conn->cache_link,
-				       &rxnet->waiting_client_conns);
-		}
-
-		nr_active--;
-	}
-
-	rxnet->nr_active_client_conns = nr_active;
-	spin_unlock(&rxnet->client_conn_cache_lock);
-	ASSERTCMP(nr_active, >=, 0);
-	_leave(" [culled]");
 }
 
 /*
@@ -1088,7 +1003,7 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work)
 	/* We keep an estimate of what the number of conns ought to be after
 	 * we've discarded some so that we don't overdo the discarding.
 	 */
-	nr_conns = rxnet->nr_client_conns;
+	nr_conns = atomic_read(&rxnet->nr_client_conns);
 
 next:
 	spin_lock(&rxnet->client_conn_cache_lock);
@@ -1098,7 +1013,6 @@ next:
 
 	conn = list_entry(rxnet->idle_client_conns.next,
 			  struct rxrpc_connection, cache_link);
-	ASSERT(test_bit(RXRPC_CONN_EXPOSED, &conn->flags));
 
 	if (!rxnet->kill_all_client_conns) {
 		/* If the number of connections is over the reap limit, we
@@ -1120,18 +1034,13 @@ next:
 	}
 
 	trace_rxrpc_client(conn, -1, rxrpc_client_discard);
-	if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags))
-		BUG();
-	conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE;
 	list_del_init(&conn->cache_link);
 
 	spin_unlock(&rxnet->client_conn_cache_lock);
 
-	/* When we cleared the EXPOSED flag, we took on responsibility for the
-	 * reference that that had on the usage count.  We deal with that here.
-	 * If someone re-sets the flag and re-gets the ref, that's fine.
-	 */
-	rxrpc_put_connection(conn);
+	rxrpc_unbundle_conn(conn);
+	rxrpc_put_connection(conn); /* Drop the ->cache_link ref */
+
 	nr_conns--;
 	goto next;
 
@@ -1145,8 +1054,7 @@ not_yet_expired:
 	 */
 	_debug("not yet");
 	if (!rxnet->kill_all_client_conns)
-		timer_reduce(&rxnet->client_conn_reap_timer,
-			     conn_expires_at);
+		timer_reduce(&rxnet->client_conn_reap_timer, conn_expires_at);
 
 out:
 	spin_unlock(&rxnet->client_conn_cache_lock);
@@ -1181,37 +1089,27 @@ void rxrpc_clean_up_local_conns(struct rxrpc_local *local)
 {
 	struct rxrpc_connection *conn, *tmp;
 	struct rxrpc_net *rxnet = local->rxnet;
-	unsigned int nr_active;
 	LIST_HEAD(graveyard);
 
 	_enter("");
 
 	spin_lock(&rxnet->client_conn_cache_lock);
-	nr_active = rxnet->nr_active_client_conns;
 
 	list_for_each_entry_safe(conn, tmp, &rxnet->idle_client_conns,
 				 cache_link) {
 		if (conn->params.local == local) {
-			ASSERTCMP(conn->cache_state, ==, RXRPC_CONN_CLIENT_IDLE);
-
 			trace_rxrpc_client(conn, -1, rxrpc_client_discard);
-			if (!test_and_clear_bit(RXRPC_CONN_EXPOSED, &conn->flags))
-				BUG();
-			conn->cache_state = RXRPC_CONN_CLIENT_INACTIVE;
 			list_move(&conn->cache_link, &graveyard);
-			nr_active--;
 		}
 	}
 
-	rxnet->nr_active_client_conns = nr_active;
 	spin_unlock(&rxnet->client_conn_cache_lock);
-	ASSERTCMP(nr_active, >=, 0);
 
 	while (!list_empty(&graveyard)) {
 		conn = list_entry(graveyard.next,
 				  struct rxrpc_connection, cache_link);
 		list_del_init(&conn->cache_link);
-
+		rxrpc_unbundle_conn(conn);
 		rxrpc_put_connection(conn);
 	}
 
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 64ace2960ecc..aab069701398 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -157,12 +157,12 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
 
 	_enter("{%d},%x", conn->debug_id, conn->abort_code);
 
-	spin_lock(&conn->channel_lock);
+	spin_lock(&conn->bundle->channel_lock);
 
 	for (i = 0; i < RXRPC_MAXCALLS; i++) {
 		call = rcu_dereference_protected(
 			conn->channels[i].call,
-			lockdep_is_held(&conn->channel_lock));
+			lockdep_is_held(&conn->bundle->channel_lock));
 		if (call) {
 			if (compl == RXRPC_CALL_LOCALLY_ABORTED)
 				trace_rxrpc_abort(call->debug_id,
@@ -179,7 +179,7 @@ static void rxrpc_abort_calls(struct rxrpc_connection *conn,
 		}
 	}
 
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&conn->bundle->channel_lock);
 	_leave("");
 }
 
@@ -210,6 +210,7 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 	conn->error = error;
 	conn->abort_code = abort_code;
 	conn->state = RXRPC_CONN_LOCALLY_ABORTED;
+	set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
 	spin_unlock_bh(&conn->state_lock);
 
 	msg.msg_name	= &conn->params.peer->srx.transport;
@@ -319,6 +320,7 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 		conn->error = -ECONNABORTED;
 		conn->abort_code = abort_code;
 		conn->state = RXRPC_CONN_REMOTELY_ABORTED;
+		set_bit(RXRPC_CONN_DONT_REUSE, &conn->flags);
 		rxrpc_abort_calls(conn, RXRPC_CALL_REMOTELY_ABORTED, sp->hdr.serial);
 		return -ECONNABORTED;
 
@@ -331,15 +333,12 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 		if (ret < 0)
 			return ret;
 
-		ret = conn->security->init_connection_security(conn);
+		ret = conn->security->init_connection_security(
+			conn, conn->params.key->payload.data[0]);
 		if (ret < 0)
 			return ret;
 
-		ret = conn->security->prime_packet_security(conn);
-		if (ret < 0)
-			return ret;
-
-		spin_lock(&conn->channel_lock);
+		spin_lock(&conn->bundle->channel_lock);
 		spin_lock_bh(&conn->state_lock);
 
 		if (conn->state == RXRPC_CONN_SERVICE_CHALLENGING) {
@@ -349,12 +348,12 @@ static int rxrpc_process_event(struct rxrpc_connection *conn,
 				rxrpc_call_is_secure(
 					rcu_dereference_protected(
 						conn->channels[loop].call,
-						lockdep_is_held(&conn->channel_lock)));
+						lockdep_is_held(&conn->bundle->channel_lock)));
 		} else {
 			spin_unlock_bh(&conn->state_lock);
 		}
 
-		spin_unlock(&conn->channel_lock);
+		spin_unlock(&conn->bundle->channel_lock);
 		return 0;
 
 	default:
@@ -375,7 +374,6 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn)
 	_enter("{%d}", conn->debug_id);
 
 	ASSERT(conn->security_ix != 0);
-	ASSERT(conn->server_key);
 
 	if (conn->security->issue_challenge(conn) < 0) {
 		abort_code = RX_CALL_DEAD;
@@ -395,7 +393,7 @@ abort:
 /*
  * Process delayed final ACKs that we haven't subsumed into a subsequent call.
  */
-static void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn)
+void rxrpc_process_delayed_final_acks(struct rxrpc_connection *conn, bool force)
 {
 	unsigned long j = jiffies, next_j;
 	unsigned int channel;
@@ -414,7 +412,7 @@ again:
 		smp_rmb(); /* vs rxrpc_disconnect_client_call */
 		ack_at = READ_ONCE(chan->final_ack_at);
 
-		if (time_before(j, ack_at)) {
+		if (time_before(j, ack_at) && !force) {
 			if (time_before(ack_at, next_j)) {
 				next_j = ack_at;
 				set = true;
@@ -448,7 +446,7 @@ static void rxrpc_do_process_connection(struct rxrpc_connection *conn)
 
 	/* Process delayed ACKs whose time has come. */
 	if (conn->flags & RXRPC_CONN_FINAL_ACK_MASK)
-		rxrpc_process_delayed_final_acks(conn);
+		rxrpc_process_delayed_final_acks(conn, false);
 
 	/* go through the conn-level event packets, releasing the ref on this
 	 * connection that each one has when we've finished with it */
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 8cbe0bf20ed5..b2159dbf5412 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -41,8 +41,6 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
 	conn = kzalloc(sizeof(struct rxrpc_connection), gfp);
 	if (conn) {
 		INIT_LIST_HEAD(&conn->cache_link);
-		spin_lock_init(&conn->channel_lock);
-		INIT_LIST_HEAD(&conn->waiting_calls);
 		timer_setup(&conn->timer, &rxrpc_connection_timer, 0);
 		INIT_WORK(&conn->processor, &rxrpc_process_connection);
 		INIT_LIST_HEAD(&conn->proc_link);
@@ -51,7 +49,6 @@ struct rxrpc_connection *rxrpc_alloc_connection(gfp_t gfp)
 		conn->security = &rxrpc_no_security;
 		spin_lock_init(&conn->state_lock);
 		conn->debug_id = atomic_inc_return(&rxrpc_debug_id);
-		conn->size_align = 4;
 		conn->idle_timestamp = jiffies;
 	}
 
@@ -219,11 +216,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call)
 	}
 
 	if (rxrpc_is_client_call(call))
-		return rxrpc_disconnect_client_call(call);
+		return rxrpc_disconnect_client_call(conn->bundle, call);
 
-	spin_lock(&conn->channel_lock);
+	spin_lock(&conn->bundle->channel_lock);
 	__rxrpc_disconnect_call(conn, call);
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&conn->bundle->channel_lock);
 
 	set_bit(RXRPC_CALL_DISCONNECTED, &call->flags);
 	conn->idle_timestamp = jiffies;
@@ -292,12 +289,13 @@ void rxrpc_see_connection(struct rxrpc_connection *conn)
 /*
  * Get a ref on a connection.
  */
-void rxrpc_get_connection(struct rxrpc_connection *conn)
+struct rxrpc_connection *rxrpc_get_connection(struct rxrpc_connection *conn)
 {
 	const void *here = __builtin_return_address(0);
 	int n = atomic_inc_return(&conn->usage);
 
 	trace_rxrpc_conn(conn->debug_id, rxrpc_conn_got, n, here);
+	return conn;
 }
 
 /*
@@ -364,7 +362,7 @@ static void rxrpc_destroy_connection(struct rcu_head *rcu)
 
 	conn->security->clear(conn);
 	key_put(conn->params.key);
-	key_put(conn->server_key);
+	rxrpc_put_bundle(conn->bundle);
 	rxrpc_put_peer(conn->params.peer);
 
 	if (atomic_dec_and_test(&conn->params.local->rxnet->nr_conns))
diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c
index 21da48e3d2e5..e1966dfc9152 100644
--- a/net/rxrpc/conn_service.c
+++ b/net/rxrpc/conn_service.c
@@ -8,6 +8,12 @@
 #include <linux/slab.h>
 #include "ar-internal.h"
 
+static struct rxrpc_bundle rxrpc_service_dummy_bundle = {
+	.usage		= ATOMIC_INIT(1),
+	.debug_id	= UINT_MAX,
+	.channel_lock	= __SPIN_LOCK_UNLOCKED(&rxrpc_service_dummy_bundle.channel_lock),
+};
+
 /*
  * Find a service connection under RCU conditions.
  *
@@ -127,6 +133,7 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn
 		 */
 		conn->state = RXRPC_CONN_SERVICE_PREALLOC;
 		atomic_set(&conn->usage, 2);
+		conn->bundle = rxrpc_get_bundle(&rxrpc_service_dummy_bundle);
 
 		atomic_inc(&rxnet->nr_conns);
 		write_lock(&rxnet->conn_lock);
@@ -149,7 +156,6 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn
 void rxrpc_new_incoming_connection(struct rxrpc_sock *rx,
 				   struct rxrpc_connection *conn,
 				   const struct rxrpc_security *sec,
-				   struct key *key,
 				   struct sk_buff *skb)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
@@ -163,7 +169,6 @@ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx,
 	conn->security_ix	= sp->hdr.securityIndex;
 	conn->out_clientflag	= 0;
 	conn->security		= sec;
-	conn->server_key	= key_get(key);
 	if (conn->security_ix)
 		conn->state	= RXRPC_CONN_SERVICE_UNSECURED;
 	else
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 667c44aa5a63..dc201363f2c4 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -430,7 +430,7 @@ static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb)
 		return;
 	}
 
-	if (call->state == RXRPC_CALL_SERVER_RECV_REQUEST) {
+	if (state == RXRPC_CALL_SERVER_RECV_REQUEST) {
 		unsigned long timo = READ_ONCE(call->next_req_timo);
 		unsigned long now, expect_req_by;
 
diff --git a/net/rxrpc/insecure.c b/net/rxrpc/insecure.c
index f6c59f5fae9d..9aae99d67833 100644
--- a/net/rxrpc/insecure.c
+++ b/net/rxrpc/insecure.c
@@ -8,20 +8,25 @@
 #include <net/af_rxrpc.h>
 #include "ar-internal.h"
 
-static int none_init_connection_security(struct rxrpc_connection *conn)
+static int none_init_connection_security(struct rxrpc_connection *conn,
+					 struct rxrpc_key_token *token)
 {
 	return 0;
 }
 
-static int none_prime_packet_security(struct rxrpc_connection *conn)
+/*
+ * Work out how much data we can put in an unsecured packet.
+ */
+static int none_how_much_data(struct rxrpc_call *call, size_t remain,
+			       size_t *_buf_size, size_t *_data_size, size_t *_offset)
 {
+	*_buf_size = *_data_size = min_t(size_t, remain, RXRPC_JUMBO_DATALEN);
+	*_offset = 0;
 	return 0;
 }
 
-static int none_secure_packet(struct rxrpc_call *call,
-			      struct sk_buff *skb,
-			      size_t data_size,
-			      void *sechdr)
+static int none_secure_packet(struct rxrpc_call *call, struct sk_buff *skb,
+			      size_t data_size)
 {
 	return 0;
 }
@@ -86,8 +91,8 @@ const struct rxrpc_security rxrpc_no_security = {
 	.init				= none_init,
 	.exit				= none_exit,
 	.init_connection_security	= none_init_connection_security,
-	.prime_packet_security		= none_prime_packet_security,
 	.free_call_crypto		= none_free_call_crypto,
+	.how_much_data			= none_how_much_data,
 	.secure_packet			= none_secure_packet,
 	.verify_packet			= none_verify_packet,
 	.locate_data			= none_locate_data,
diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c
index 2e8bd3b97301..8d2073e0e3da 100644
--- a/net/rxrpc/key.c
+++ b/net/rxrpc/key.c
@@ -5,7 +5,7 @@
  * Written by David Howells (dhowells@redhat.com)
  *
  * RxRPC keys should have a description of describing their purpose:
- *	"afs@CAMBRIDGE.REDHAT.COM>
+ *	"afs@example.com"
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -23,13 +23,9 @@
 #include <keys/user-type.h>
 #include "ar-internal.h"
 
-static int rxrpc_vet_description_s(const char *);
 static int rxrpc_preparse(struct key_preparsed_payload *);
-static int rxrpc_preparse_s(struct key_preparsed_payload *);
 static void rxrpc_free_preparse(struct key_preparsed_payload *);
-static void rxrpc_free_preparse_s(struct key_preparsed_payload *);
 static void rxrpc_destroy(struct key *);
-static void rxrpc_destroy_s(struct key *);
 static void rxrpc_describe(const struct key *, struct seq_file *);
 static long rxrpc_read(const struct key *, char *, size_t);
 
@@ -50,38 +46,6 @@ struct key_type key_type_rxrpc = {
 EXPORT_SYMBOL(key_type_rxrpc);
 
 /*
- * rxrpc server defined keys take "<serviceId>:<securityIndex>" as the
- * description and an 8-byte decryption key as the payload
- */
-struct key_type key_type_rxrpc_s = {
-	.name		= "rxrpc_s",
-	.flags		= KEY_TYPE_NET_DOMAIN,
-	.vet_description = rxrpc_vet_description_s,
-	.preparse	= rxrpc_preparse_s,
-	.free_preparse	= rxrpc_free_preparse_s,
-	.instantiate	= generic_key_instantiate,
-	.destroy	= rxrpc_destroy_s,
-	.describe	= rxrpc_describe,
-};
-
-/*
- * Vet the description for an RxRPC server key
- */
-static int rxrpc_vet_description_s(const char *desc)
-{
-	unsigned long num;
-	char *p;
-
-	num = simple_strtoul(desc, &p, 10);
-	if (*p != ':' || num > 65535)
-		return -EINVAL;
-	num = simple_strtoul(p + 1, &p, 10);
-	if (*p || num < 1 || num > 255)
-		return -EINVAL;
-	return 0;
-}
-
-/*
  * parse an RxKAD type XDR format token
  * - the caller guarantees we have at least 4 words
  */
@@ -165,402 +129,17 @@ static int rxrpc_preparse_xdr_rxkad(struct key_preparsed_payload *prep,
 	return 0;
 }
 
-static void rxrpc_free_krb5_principal(struct krb5_principal *princ)
-{
-	int loop;
-
-	if (princ->name_parts) {
-		for (loop = princ->n_name_parts - 1; loop >= 0; loop--)
-			kfree(princ->name_parts[loop]);
-		kfree(princ->name_parts);
-	}
-	kfree(princ->realm);
-}
-
-static void rxrpc_free_krb5_tagged(struct krb5_tagged_data *td)
-{
-	kfree(td->data);
-}
-
-/*
- * free up an RxK5 token
- */
-static void rxrpc_rxk5_free(struct rxk5_key *rxk5)
-{
-	int loop;
-
-	rxrpc_free_krb5_principal(&rxk5->client);
-	rxrpc_free_krb5_principal(&rxk5->server);
-	rxrpc_free_krb5_tagged(&rxk5->session);
-
-	if (rxk5->addresses) {
-		for (loop = rxk5->n_addresses - 1; loop >= 0; loop--)
-			rxrpc_free_krb5_tagged(&rxk5->addresses[loop]);
-		kfree(rxk5->addresses);
-	}
-	if (rxk5->authdata) {
-		for (loop = rxk5->n_authdata - 1; loop >= 0; loop--)
-			rxrpc_free_krb5_tagged(&rxk5->authdata[loop]);
-		kfree(rxk5->authdata);
-	}
-
-	kfree(rxk5->ticket);
-	kfree(rxk5->ticket2);
-	kfree(rxk5);
-}
-
-/*
- * extract a krb5 principal
- */
-static int rxrpc_krb5_decode_principal(struct krb5_principal *princ,
-				       const __be32 **_xdr,
-				       unsigned int *_toklen)
-{
-	const __be32 *xdr = *_xdr;
-	unsigned int toklen = *_toklen, n_parts, loop, tmp, paddedlen;
-
-	/* there must be at least one name, and at least #names+1 length
-	 * words */
-	if (toklen <= 12)
-		return -EINVAL;
-
-	_enter(",{%x,%x,%x},%u",
-	       ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), toklen);
-
-	n_parts = ntohl(*xdr++);
-	toklen -= 4;
-	if (n_parts <= 0 || n_parts > AFSTOKEN_K5_COMPONENTS_MAX)
-		return -EINVAL;
-	princ->n_name_parts = n_parts;
-
-	if (toklen <= (n_parts + 1) * 4)
-		return -EINVAL;
-
-	princ->name_parts = kcalloc(n_parts, sizeof(char *), GFP_KERNEL);
-	if (!princ->name_parts)
-		return -ENOMEM;
-
-	for (loop = 0; loop < n_parts; loop++) {
-		if (toklen < 4)
-			return -EINVAL;
-		tmp = ntohl(*xdr++);
-		toklen -= 4;
-		if (tmp <= 0 || tmp > AFSTOKEN_STRING_MAX)
-			return -EINVAL;
-		paddedlen = (tmp + 3) & ~3;
-		if (paddedlen > toklen)
-			return -EINVAL;
-		princ->name_parts[loop] = kmalloc(tmp + 1, GFP_KERNEL);
-		if (!princ->name_parts[loop])
-			return -ENOMEM;
-		memcpy(princ->name_parts[loop], xdr, tmp);
-		princ->name_parts[loop][tmp] = 0;
-		toklen -= paddedlen;
-		xdr += paddedlen >> 2;
-	}
-
-	if (toklen < 4)
-		return -EINVAL;
-	tmp = ntohl(*xdr++);
-	toklen -= 4;
-	if (tmp <= 0 || tmp > AFSTOKEN_K5_REALM_MAX)
-		return -EINVAL;
-	paddedlen = (tmp + 3) & ~3;
-	if (paddedlen > toklen)
-		return -EINVAL;
-	princ->realm = kmalloc(tmp + 1, GFP_KERNEL);
-	if (!princ->realm)
-		return -ENOMEM;
-	memcpy(princ->realm, xdr, tmp);
-	princ->realm[tmp] = 0;
-	toklen -= paddedlen;
-	xdr += paddedlen >> 2;
-
-	_debug("%s/...@%s", princ->name_parts[0], princ->realm);
-
-	*_xdr = xdr;
-	*_toklen = toklen;
-	_leave(" = 0 [toklen=%u]", toklen);
-	return 0;
-}
-
-/*
- * extract a piece of krb5 tagged data
- */
-static int rxrpc_krb5_decode_tagged_data(struct krb5_tagged_data *td,
-					 size_t max_data_size,
-					 const __be32 **_xdr,
-					 unsigned int *_toklen)
-{
-	const __be32 *xdr = *_xdr;
-	unsigned int toklen = *_toklen, len, paddedlen;
-
-	/* there must be at least one tag and one length word */
-	if (toklen <= 8)
-		return -EINVAL;
-
-	_enter(",%zu,{%x,%x},%u",
-	       max_data_size, ntohl(xdr[0]), ntohl(xdr[1]), toklen);
-
-	td->tag = ntohl(*xdr++);
-	len = ntohl(*xdr++);
-	toklen -= 8;
-	if (len > max_data_size)
-		return -EINVAL;
-	paddedlen = (len + 3) & ~3;
-	if (paddedlen > toklen)
-		return -EINVAL;
-	td->data_len = len;
-
-	if (len > 0) {
-		td->data = kmemdup(xdr, len, GFP_KERNEL);
-		if (!td->data)
-			return -ENOMEM;
-		toklen -= paddedlen;
-		xdr += paddedlen >> 2;
-	}
-
-	_debug("tag %x len %x", td->tag, td->data_len);
-
-	*_xdr = xdr;
-	*_toklen = toklen;
-	_leave(" = 0 [toklen=%u]", toklen);
-	return 0;
-}
-
-/*
- * extract an array of tagged data
- */
-static int rxrpc_krb5_decode_tagged_array(struct krb5_tagged_data **_td,
-					  u8 *_n_elem,
-					  u8 max_n_elem,
-					  size_t max_elem_size,
-					  const __be32 **_xdr,
-					  unsigned int *_toklen)
-{
-	struct krb5_tagged_data *td;
-	const __be32 *xdr = *_xdr;
-	unsigned int toklen = *_toklen, n_elem, loop;
-	int ret;
-
-	/* there must be at least one count */
-	if (toklen < 4)
-		return -EINVAL;
-
-	_enter(",,%u,%zu,{%x},%u",
-	       max_n_elem, max_elem_size, ntohl(xdr[0]), toklen);
-
-	n_elem = ntohl(*xdr++);
-	toklen -= 4;
-	if (n_elem > max_n_elem)
-		return -EINVAL;
-	*_n_elem = n_elem;
-	if (n_elem > 0) {
-		if (toklen <= (n_elem + 1) * 4)
-			return -EINVAL;
-
-		_debug("n_elem %d", n_elem);
-
-		td = kcalloc(n_elem, sizeof(struct krb5_tagged_data),
-			     GFP_KERNEL);
-		if (!td)
-			return -ENOMEM;
-		*_td = td;
-
-		for (loop = 0; loop < n_elem; loop++) {
-			ret = rxrpc_krb5_decode_tagged_data(&td[loop],
-							    max_elem_size,
-							    &xdr, &toklen);
-			if (ret < 0)
-				return ret;
-		}
-	}
-
-	*_xdr = xdr;
-	*_toklen = toklen;
-	_leave(" = 0 [toklen=%u]", toklen);
-	return 0;
-}
-
-/*
- * extract a krb5 ticket
- */
-static int rxrpc_krb5_decode_ticket(u8 **_ticket, u16 *_tktlen,
-				    const __be32 **_xdr, unsigned int *_toklen)
-{
-	const __be32 *xdr = *_xdr;
-	unsigned int toklen = *_toklen, len, paddedlen;
-
-	/* there must be at least one length word */
-	if (toklen <= 4)
-		return -EINVAL;
-
-	_enter(",{%x},%u", ntohl(xdr[0]), toklen);
-
-	len = ntohl(*xdr++);
-	toklen -= 4;
-	if (len > AFSTOKEN_K5_TIX_MAX)
-		return -EINVAL;
-	paddedlen = (len + 3) & ~3;
-	if (paddedlen > toklen)
-		return -EINVAL;
-	*_tktlen = len;
-
-	_debug("ticket len %u", len);
-
-	if (len > 0) {
-		*_ticket = kmemdup(xdr, len, GFP_KERNEL);
-		if (!*_ticket)
-			return -ENOMEM;
-		toklen -= paddedlen;
-		xdr += paddedlen >> 2;
-	}
-
-	*_xdr = xdr;
-	*_toklen = toklen;
-	_leave(" = 0 [toklen=%u]", toklen);
-	return 0;
-}
-
-/*
- * parse an RxK5 type XDR format token
- * - the caller guarantees we have at least 4 words
- */
-static int rxrpc_preparse_xdr_rxk5(struct key_preparsed_payload *prep,
-				   size_t datalen,
-				   const __be32 *xdr, unsigned int toklen)
-{
-	struct rxrpc_key_token *token, **pptoken;
-	struct rxk5_key *rxk5;
-	const __be32 *end_xdr = xdr + (toklen >> 2);
-	time64_t expiry;
-	int ret;
-
-	_enter(",{%x,%x,%x,%x},%u",
-	       ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]),
-	       toklen);
-
-	/* reserve some payload space for this subkey - the length of the token
-	 * is a reasonable approximation */
-	prep->quotalen = datalen + toklen;
-
-	token = kzalloc(sizeof(*token), GFP_KERNEL);
-	if (!token)
-		return -ENOMEM;
-
-	rxk5 = kzalloc(sizeof(*rxk5), GFP_KERNEL);
-	if (!rxk5) {
-		kfree(token);
-		return -ENOMEM;
-	}
-
-	token->security_index = RXRPC_SECURITY_RXK5;
-	token->k5 = rxk5;
-
-	/* extract the principals */
-	ret = rxrpc_krb5_decode_principal(&rxk5->client, &xdr, &toklen);
-	if (ret < 0)
-		goto error;
-	ret = rxrpc_krb5_decode_principal(&rxk5->server, &xdr, &toklen);
-	if (ret < 0)
-		goto error;
-
-	/* extract the session key and the encoding type (the tag field ->
-	 * ENCTYPE_xxx) */
-	ret = rxrpc_krb5_decode_tagged_data(&rxk5->session, AFSTOKEN_DATA_MAX,
-					    &xdr, &toklen);
-	if (ret < 0)
-		goto error;
-
-	if (toklen < 4 * 8 + 2 * 4)
-		goto inval;
-	rxk5->authtime	= be64_to_cpup((const __be64 *) xdr);
-	xdr += 2;
-	rxk5->starttime	= be64_to_cpup((const __be64 *) xdr);
-	xdr += 2;
-	rxk5->endtime	= be64_to_cpup((const __be64 *) xdr);
-	xdr += 2;
-	rxk5->renew_till = be64_to_cpup((const __be64 *) xdr);
-	xdr += 2;
-	rxk5->is_skey = ntohl(*xdr++);
-	rxk5->flags = ntohl(*xdr++);
-	toklen -= 4 * 8 + 2 * 4;
-
-	_debug("times: a=%llx s=%llx e=%llx rt=%llx",
-	       rxk5->authtime, rxk5->starttime, rxk5->endtime,
-	       rxk5->renew_till);
-	_debug("is_skey=%x flags=%x", rxk5->is_skey, rxk5->flags);
-
-	/* extract the permitted client addresses */
-	ret = rxrpc_krb5_decode_tagged_array(&rxk5->addresses,
-					     &rxk5->n_addresses,
-					     AFSTOKEN_K5_ADDRESSES_MAX,
-					     AFSTOKEN_DATA_MAX,
-					     &xdr, &toklen);
-	if (ret < 0)
-		goto error;
-
-	ASSERTCMP((end_xdr - xdr) << 2, ==, toklen);
-
-	/* extract the tickets */
-	ret = rxrpc_krb5_decode_ticket(&rxk5->ticket, &rxk5->ticket_len,
-				       &xdr, &toklen);
-	if (ret < 0)
-		goto error;
-	ret = rxrpc_krb5_decode_ticket(&rxk5->ticket2, &rxk5->ticket2_len,
-				       &xdr, &toklen);
-	if (ret < 0)
-		goto error;
-
-	ASSERTCMP((end_xdr - xdr) << 2, ==, toklen);
-
-	/* extract the typed auth data */
-	ret = rxrpc_krb5_decode_tagged_array(&rxk5->authdata,
-					     &rxk5->n_authdata,
-					     AFSTOKEN_K5_AUTHDATA_MAX,
-					     AFSTOKEN_BDATALN_MAX,
-					     &xdr, &toklen);
-	if (ret < 0)
-		goto error;
-
-	ASSERTCMP((end_xdr - xdr) << 2, ==, toklen);
-
-	if (toklen != 0)
-		goto inval;
-
-	/* attach the payload */
-	for (pptoken = (struct rxrpc_key_token **)&prep->payload.data[0];
-	     *pptoken;
-	     pptoken = &(*pptoken)->next)
-		continue;
-	*pptoken = token;
-	expiry = rxrpc_u32_to_time64(token->k5->endtime);
-	if (expiry < prep->expiry)
-		prep->expiry = expiry;
-
-	_leave(" = 0");
-	return 0;
-
-inval:
-	ret = -EINVAL;
-error:
-	rxrpc_rxk5_free(rxk5);
-	kfree(token);
-	_leave(" = %d", ret);
-	return ret;
-}
-
 /*
  * attempt to parse the data as the XDR format
  * - the caller guarantees we have more than 7 words
  */
 static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep)
 {
-	const __be32 *xdr = prep->data, *token;
+	const __be32 *xdr = prep->data, *token, *p;
 	const char *cp;
 	unsigned int len, paddedlen, loop, ntoken, toklen, sec_ix;
 	size_t datalen = prep->datalen;
-	int ret;
+	int ret, ret2;
 
 	_enter(",{%x,%x,%x,%x},%zu",
 	       ntohl(xdr[0]), ntohl(xdr[1]), ntohl(xdr[2]), ntohl(xdr[3]),
@@ -610,20 +189,20 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep)
 		goto not_xdr;
 
 	/* check each token wrapper */
-	token = xdr;
+	p = xdr;
 	loop = ntoken;
 	do {
 		if (datalen < 8)
 			goto not_xdr;
-		toklen = ntohl(*xdr++);
-		sec_ix = ntohl(*xdr);
+		toklen = ntohl(*p++);
+		sec_ix = ntohl(*p);
 		datalen -= 4;
 		_debug("token: [%x/%zx] %x", toklen, datalen, sec_ix);
 		paddedlen = (toklen + 3) & ~3;
 		if (toklen < 20 || toklen > datalen || paddedlen > datalen)
 			goto not_xdr;
 		datalen -= paddedlen;
-		xdr += paddedlen >> 2;
+		p += paddedlen >> 2;
 
 	} while (--loop > 0);
 
@@ -634,44 +213,50 @@ static int rxrpc_preparse_xdr(struct key_preparsed_payload *prep)
 	/* okay: we're going to assume it's valid XDR format
 	 * - we ignore the cellname, relying on the key to be correctly named
 	 */
+	ret = -EPROTONOSUPPORT;
 	do {
-		xdr = token;
 		toklen = ntohl(*xdr++);
-		token = xdr + ((toklen + 3) >> 2);
-		sec_ix = ntohl(*xdr++);
+		token = xdr;
+		xdr += (toklen + 3) / 4;
+
+		sec_ix = ntohl(*token++);
 		toklen -= 4;
 
-		_debug("TOKEN type=%u [%p-%p]", sec_ix, xdr, token);
+		_debug("TOKEN type=%x len=%x", sec_ix, toklen);
 
 		switch (sec_ix) {
 		case RXRPC_SECURITY_RXKAD:
-			ret = rxrpc_preparse_xdr_rxkad(prep, datalen, xdr, toklen);
-			if (ret != 0)
-				goto error;
+			ret2 = rxrpc_preparse_xdr_rxkad(prep, datalen, token, toklen);
+			break;
+		default:
+			ret2 = -EPROTONOSUPPORT;
 			break;
+		}
 
-		case RXRPC_SECURITY_RXK5:
-			ret = rxrpc_preparse_xdr_rxk5(prep, datalen, xdr, toklen);
+		switch (ret2) {
+		case 0:
+			ret = 0;
+			break;
+		case -EPROTONOSUPPORT:
+			break;
+		case -ENOPKG:
 			if (ret != 0)
-				goto error;
+				ret = -ENOPKG;
 			break;
-
 		default:
-			ret = -EPROTONOSUPPORT;
+			ret = ret2;
 			goto error;
 		}
 
 	} while (--ntoken > 0);
 
-	_leave(" = 0");
-	return 0;
+error:
+	_leave(" = %d", ret);
+	return ret;
 
 not_xdr:
 	_leave(" = -EPROTO");
 	return -EPROTO;
-error:
-	_leave(" = %d", ret);
-	return ret;
 }
 
 /*
@@ -805,10 +390,6 @@ static void rxrpc_free_token_list(struct rxrpc_key_token *token)
 		case RXRPC_SECURITY_RXKAD:
 			kfree(token->kad);
 			break;
-		case RXRPC_SECURITY_RXK5:
-			if (token->k5)
-				rxrpc_rxk5_free(token->k5);
-			break;
 		default:
 			pr_err("Unknown token type %x on rxrpc key\n",
 			       token->security_index);
@@ -828,45 +409,6 @@ static void rxrpc_free_preparse(struct key_preparsed_payload *prep)
 }
 
 /*
- * Preparse a server secret key.
- *
- * The data should be the 8-byte secret key.
- */
-static int rxrpc_preparse_s(struct key_preparsed_payload *prep)
-{
-	struct crypto_skcipher *ci;
-
-	_enter("%zu", prep->datalen);
-
-	if (prep->datalen != 8)
-		return -EINVAL;
-
-	memcpy(&prep->payload.data[2], prep->data, 8);
-
-	ci = crypto_alloc_skcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(ci)) {
-		_leave(" = %ld", PTR_ERR(ci));
-		return PTR_ERR(ci);
-	}
-
-	if (crypto_skcipher_setkey(ci, prep->data, 8) < 0)
-		BUG();
-
-	prep->payload.data[0] = ci;
-	_leave(" = 0");
-	return 0;
-}
-
-/*
- * Clean up preparse data.
- */
-static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep)
-{
-	if (prep->payload.data[0])
-		crypto_free_skcipher(prep->payload.data[0]);
-}
-
-/*
  * dispose of the data dangling from the corpse of a rxrpc key
  */
 static void rxrpc_destroy(struct key *key)
@@ -875,22 +417,29 @@ static void rxrpc_destroy(struct key *key)
 }
 
 /*
- * dispose of the data dangling from the corpse of a rxrpc key
- */
-static void rxrpc_destroy_s(struct key *key)
-{
-	if (key->payload.data[0]) {
-		crypto_free_skcipher(key->payload.data[0]);
-		key->payload.data[0] = NULL;
-	}
-}
-
-/*
  * describe the rxrpc key
  */
 static void rxrpc_describe(const struct key *key, struct seq_file *m)
 {
+	const struct rxrpc_key_token *token;
+	const char *sep = ": ";
+
 	seq_puts(m, key->description);
+
+	for (token = key->payload.data[0]; token; token = token->next) {
+		seq_puts(m, sep);
+
+		switch (token->security_index) {
+		case RXRPC_SECURITY_RXKAD:
+			seq_puts(m, "ka");
+			break;
+		default: /* we have a ticket we can't encode */
+			seq_printf(m, "%u", token->security_index);
+			break;
+		}
+
+		sep = " ";
+	}
 }
 
 /*
@@ -924,36 +473,6 @@ int rxrpc_request_key(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
 }
 
 /*
- * grab the security keyring for a server socket
- */
-int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
-{
-	struct key *key;
-	char *description;
-
-	_enter("");
-
-	if (optlen <= 0 || optlen > PAGE_SIZE - 1)
-		return -EINVAL;
-
-	description = memdup_sockptr_nul(optval, optlen);
-	if (IS_ERR(description))
-		return PTR_ERR(description);
-
-	key = request_key(&key_type_keyring, description, NULL);
-	if (IS_ERR(key)) {
-		kfree(description);
-		_leave(" = %ld", PTR_ERR(key));
-		return PTR_ERR(key);
-	}
-
-	rx->securities = key;
-	kfree(description);
-	_leave(" = 0 [key %x]", key->serial);
-	return 0;
-}
-
-/*
  * generate a server data key
  */
 int rxrpc_get_server_data_key(struct rxrpc_connection *conn,
@@ -1044,12 +563,10 @@ static long rxrpc_read(const struct key *key,
 		       char *buffer, size_t buflen)
 {
 	const struct rxrpc_key_token *token;
-	const struct krb5_principal *princ;
 	size_t size;
 	__be32 *xdr, *oldxdr;
 	u32 cnlen, toksize, ntoks, tok, zero;
 	u16 toksizes[AFSTOKEN_MAX];
-	int loop;
 
 	_enter("");
 
@@ -1074,42 +591,14 @@ static long rxrpc_read(const struct key *key,
 		case RXRPC_SECURITY_RXKAD:
 			toksize += 8 * 4;	/* viceid, kvno, key*2, begin,
 						 * end, primary, tktlen */
-			toksize += RND(token->kad->ticket_len);
-			break;
-
-		case RXRPC_SECURITY_RXK5:
-			princ = &token->k5->client;
-			toksize += 4 + princ->n_name_parts * 4;
-			for (loop = 0; loop < princ->n_name_parts; loop++)
-				toksize += RND(strlen(princ->name_parts[loop]));
-			toksize += 4 + RND(strlen(princ->realm));
-
-			princ = &token->k5->server;
-			toksize += 4 + princ->n_name_parts * 4;
-			for (loop = 0; loop < princ->n_name_parts; loop++)
-				toksize += RND(strlen(princ->name_parts[loop]));
-			toksize += 4 + RND(strlen(princ->realm));
-
-			toksize += 8 + RND(token->k5->session.data_len);
-
-			toksize += 4 * 8 + 2 * 4;
-
-			toksize += 4 + token->k5->n_addresses * 8;
-			for (loop = 0; loop < token->k5->n_addresses; loop++)
-				toksize += RND(token->k5->addresses[loop].data_len);
-
-			toksize += 4 + RND(token->k5->ticket_len);
-			toksize += 4 + RND(token->k5->ticket2_len);
-
-			toksize += 4 + token->k5->n_authdata * 8;
-			for (loop = 0; loop < token->k5->n_authdata; loop++)
-				toksize += RND(token->k5->authdata[loop].data_len);
+			if (!token->no_leak_key)
+				toksize += RND(token->kad->ticket_len);
 			break;
 
 		default: /* we have a ticket we can't encode */
 			pr_err("Unsupported key token type (%u)\n",
 			       token->security_index);
-			continue;
+			return -ENOPKG;
 		}
 
 		_debug("token[%u]: toksize=%u", ntoks, toksize);
@@ -1178,53 +667,16 @@ static long rxrpc_read(const struct key *key,
 			ENCODE(token->kad->start);
 			ENCODE(token->kad->expiry);
 			ENCODE(token->kad->primary_flag);
-			ENCODE_DATA(token->kad->ticket_len, token->kad->ticket);
-			break;
-
-		case RXRPC_SECURITY_RXK5:
-			princ = &token->k5->client;
-			ENCODE(princ->n_name_parts);
-			for (loop = 0; loop < princ->n_name_parts; loop++)
-				ENCODE_STR(princ->name_parts[loop]);
-			ENCODE_STR(princ->realm);
-
-			princ = &token->k5->server;
-			ENCODE(princ->n_name_parts);
-			for (loop = 0; loop < princ->n_name_parts; loop++)
-				ENCODE_STR(princ->name_parts[loop]);
-			ENCODE_STR(princ->realm);
-
-			ENCODE(token->k5->session.tag);
-			ENCODE_DATA(token->k5->session.data_len,
-				    token->k5->session.data);
-
-			ENCODE64(token->k5->authtime);
-			ENCODE64(token->k5->starttime);
-			ENCODE64(token->k5->endtime);
-			ENCODE64(token->k5->renew_till);
-			ENCODE(token->k5->is_skey);
-			ENCODE(token->k5->flags);
-
-			ENCODE(token->k5->n_addresses);
-			for (loop = 0; loop < token->k5->n_addresses; loop++) {
-				ENCODE(token->k5->addresses[loop].tag);
-				ENCODE_DATA(token->k5->addresses[loop].data_len,
-					    token->k5->addresses[loop].data);
-			}
-
-			ENCODE_DATA(token->k5->ticket_len, token->k5->ticket);
-			ENCODE_DATA(token->k5->ticket2_len, token->k5->ticket2);
-
-			ENCODE(token->k5->n_authdata);
-			for (loop = 0; loop < token->k5->n_authdata; loop++) {
-				ENCODE(token->k5->authdata[loop].tag);
-				ENCODE_DATA(token->k5->authdata[loop].data_len,
-					    token->k5->authdata[loop].data);
-			}
+			if (token->no_leak_key)
+				ENCODE(0);
+			else
+				ENCODE_DATA(token->kad->ticket_len, token->kad->ticket);
 			break;
 
 		default:
-			break;
+			pr_err("Unsupported key token type (%u)\n",
+			       token->security_index);
+			return -ENOPKG;
 		}
 
 		ASSERTCMP((unsigned long)xdr - (unsigned long)oldxdr, ==,
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index ede058f9cc15..8c2881054266 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -86,8 +86,8 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
 		init_rwsem(&local->defrag_sem);
 		skb_queue_head_init(&local->reject_queue);
 		skb_queue_head_init(&local->event_queue);
-		local->client_conns = RB_ROOT;
-		spin_lock_init(&local->client_conns_lock);
+		local->client_bundles = RB_ROOT;
+		spin_lock_init(&local->client_bundles_lock);
 		spin_lock_init(&local->lock);
 		rwlock_init(&local->services_lock);
 		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
diff --git a/net/rxrpc/net_ns.c b/net/rxrpc/net_ns.c
index b312aab80fed..25bbc4cc8b13 100644
--- a/net/rxrpc/net_ns.c
+++ b/net/rxrpc/net_ns.c
@@ -62,13 +62,10 @@ static __net_init int rxrpc_init_net(struct net *net)
 	timer_setup(&rxnet->service_conn_reap_timer,
 		    rxrpc_service_conn_reap_timeout, 0);
 
-	rxnet->nr_client_conns = 0;
-	rxnet->nr_active_client_conns = 0;
+	atomic_set(&rxnet->nr_client_conns, 0);
 	rxnet->kill_all_client_conns = false;
 	spin_lock_init(&rxnet->client_conn_cache_lock);
 	spin_lock_init(&rxnet->client_conn_discard_lock);
-	INIT_LIST_HEAD(&rxnet->waiting_client_conns);
-	INIT_LIST_HEAD(&rxnet->active_client_conns);
 	INIT_LIST_HEAD(&rxnet->idle_client_conns);
 	INIT_WORK(&rxnet->client_conn_reaper,
 		  rxrpc_discard_expired_client_conns);
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 3cfff7922ba8..10f2bf2e9068 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -357,6 +357,12 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 
 	_enter(",{%d}", skb->len);
 
+	if (hlist_unhashed(&call->error_link)) {
+		spin_lock_bh(&call->peer->lock);
+		hlist_add_head_rcu(&call->error_link, &call->peer->error_targets);
+		spin_unlock_bh(&call->peer->lock);
+	}
+
 	/* Each transmission of a Tx packet needs a new serial number */
 	serial = atomic_inc_return(&conn->serial);
 
diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 543afd9bd664..e2f990754f88 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -165,7 +165,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
 			 "Proto Local                                          "
 			 " Remote                                         "
 			 " SvID ConnID   End Use State    Key     "
-			 " Serial   ISerial\n"
+			 " Serial   ISerial  CallId0  CallId1  CallId2  CallId3\n"
 			 );
 		return 0;
 	}
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 2c842851d72e..fef3573fdc8b 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -69,7 +69,7 @@ bool __rxrpc_set_call_completion(struct rxrpc_call *call,
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		call->abort_code = abort_code;
 		call->error = error;
-		call->completion = compl,
+		call->completion = compl;
 		call->state = RXRPC_CALL_COMPLETE;
 		trace_rxrpc_call_complete(call);
 		wake_up(&call->waitq);
diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c
index 1221b0637a7e..4e565eeab426 100644
--- a/net/rxrpc/rtt.c
+++ b/net/rxrpc/rtt.c
@@ -14,7 +14,6 @@
 #define RXRPC_RTO_MAX	((unsigned)(120 * HZ))
 #define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ))	/* RFC6298 2.1 initial RTO value	*/
 #define rxrpc_jiffies32 ((u32)jiffies)		/* As rxrpc_jiffies32 */
-#define rxrpc_min_rtt_wlen 300			/* As sysctl_tcp_min_rtt_wlen */
 
 static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer)
 {
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index e08130e5746b..e2e9e9b0a6d7 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -15,6 +15,7 @@
 #include <linux/scatterlist.h>
 #include <linux/ctype.h>
 #include <linux/slab.h>
+#include <linux/key-type.h>
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include <keys/rxrpc-type.h>
@@ -27,6 +28,7 @@
 #define INST_SZ				40	/* size of principal's instance */
 #define REALM_SZ			40	/* size of principal's auth domain */
 #define SNAME_SZ			40	/* size of service name */
+#define RXKAD_ALIGN			8
 
 struct rxkad_level1_hdr {
 	__be32	data_size;	/* true data size (excluding padding) */
@@ -37,6 +39,9 @@ struct rxkad_level2_hdr {
 	__be32	checksum;	/* decrypted data checksum */
 };
 
+static int rxkad_prime_packet_security(struct rxrpc_connection *conn,
+				       struct crypto_sync_skcipher *ci);
+
 /*
  * this holds a pinned cipher so that keventd doesn't get called by the cipher
  * alloc routine, but since we have it to hand, we use it to decrypt RESPONSE
@@ -47,17 +52,59 @@ static struct skcipher_request *rxkad_ci_req;
 static DEFINE_MUTEX(rxkad_ci_mutex);
 
 /*
+ * Parse the information from a server key
+ *
+ * The data should be the 8-byte secret key.
+ */
+static int rxkad_preparse_server_key(struct key_preparsed_payload *prep)
+{
+	struct crypto_skcipher *ci;
+
+	if (prep->datalen != 8)
+		return -EINVAL;
+
+	memcpy(&prep->payload.data[2], prep->data, 8);
+
+	ci = crypto_alloc_skcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC);
+	if (IS_ERR(ci)) {
+		_leave(" = %ld", PTR_ERR(ci));
+		return PTR_ERR(ci);
+	}
+
+	if (crypto_skcipher_setkey(ci, prep->data, 8) < 0)
+		BUG();
+
+	prep->payload.data[0] = ci;
+	_leave(" = 0");
+	return 0;
+}
+
+static void rxkad_free_preparse_server_key(struct key_preparsed_payload *prep)
+{
+
+	if (prep->payload.data[0])
+		crypto_free_skcipher(prep->payload.data[0]);
+}
+
+static void rxkad_destroy_server_key(struct key *key)
+{
+	if (key->payload.data[0]) {
+		crypto_free_skcipher(key->payload.data[0]);
+		key->payload.data[0] = NULL;
+	}
+}
+
+/*
  * initialise connection security
  */
-static int rxkad_init_connection_security(struct rxrpc_connection *conn)
+static int rxkad_init_connection_security(struct rxrpc_connection *conn,
+					  struct rxrpc_key_token *token)
 {
 	struct crypto_sync_skcipher *ci;
-	struct rxrpc_key_token *token;
 	int ret;
 
 	_enter("{%d},{%x}", conn->debug_id, key_serial(conn->params.key));
 
-	token = conn->params.key->payload.data[0];
 	conn->security_ix = token->security_index;
 
 	ci = crypto_alloc_sync_skcipher("pcbc(fcrypt)", 0, 0);
@@ -73,32 +120,68 @@ static int rxkad_init_connection_security(struct rxrpc_connection *conn)
 
 	switch (conn->params.security_level) {
 	case RXRPC_SECURITY_PLAIN:
-		break;
 	case RXRPC_SECURITY_AUTH:
-		conn->size_align = 8;
-		conn->security_size = sizeof(struct rxkad_level1_hdr);
-		break;
 	case RXRPC_SECURITY_ENCRYPT:
-		conn->size_align = 8;
-		conn->security_size = sizeof(struct rxkad_level2_hdr);
 		break;
 	default:
 		ret = -EKEYREJECTED;
 		goto error;
 	}
 
-	conn->cipher = ci;
-	ret = 0;
+	ret = rxkad_prime_packet_security(conn, ci);
+	if (ret < 0)
+		goto error_ci;
+
+	conn->rxkad.cipher = ci;
+	return 0;
+
+error_ci:
+	crypto_free_sync_skcipher(ci);
 error:
 	_leave(" = %d", ret);
 	return ret;
 }
 
 /*
+ * Work out how much data we can put in a packet.
+ */
+static int rxkad_how_much_data(struct rxrpc_call *call, size_t remain,
+			       size_t *_buf_size, size_t *_data_size, size_t *_offset)
+{
+	size_t shdr, buf_size, chunk;
+
+	switch (call->conn->params.security_level) {
+	default:
+		buf_size = chunk = min_t(size_t, remain, RXRPC_JUMBO_DATALEN);
+		shdr = 0;
+		goto out;
+	case RXRPC_SECURITY_AUTH:
+		shdr = sizeof(struct rxkad_level1_hdr);
+		break;
+	case RXRPC_SECURITY_ENCRYPT:
+		shdr = sizeof(struct rxkad_level2_hdr);
+		break;
+	}
+
+	buf_size = round_down(RXRPC_JUMBO_DATALEN, RXKAD_ALIGN);
+
+	chunk = buf_size - shdr;
+	if (remain < chunk)
+		buf_size = round_up(shdr + remain, RXKAD_ALIGN);
+
+out:
+	*_buf_size = buf_size;
+	*_data_size = chunk;
+	*_offset = shdr;
+	return 0;
+}
+
+/*
  * prime the encryption state with the invariant parts of a connection's
  * description
  */
-static int rxkad_prime_packet_security(struct rxrpc_connection *conn)
+static int rxkad_prime_packet_security(struct rxrpc_connection *conn,
+				       struct crypto_sync_skcipher *ci)
 {
 	struct skcipher_request *req;
 	struct rxrpc_key_token *token;
@@ -116,7 +199,7 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn)
 	if (!tmpbuf)
 		return -ENOMEM;
 
-	req = skcipher_request_alloc(&conn->cipher->base, GFP_NOFS);
+	req = skcipher_request_alloc(&ci->base, GFP_NOFS);
 	if (!req) {
 		kfree(tmpbuf);
 		return -ENOMEM;
@@ -131,13 +214,13 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn)
 	tmpbuf[3] = htonl(conn->security_ix);
 
 	sg_init_one(&sg, tmpbuf, tmpsize);
-	skcipher_request_set_sync_tfm(req, conn->cipher);
+	skcipher_request_set_sync_tfm(req, ci);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, &sg, &sg, tmpsize, iv.x);
 	crypto_skcipher_encrypt(req);
 	skcipher_request_free(req);
 
-	memcpy(&conn->csum_iv, tmpbuf + 2, sizeof(conn->csum_iv));
+	memcpy(&conn->rxkad.csum_iv, tmpbuf + 2, sizeof(conn->rxkad.csum_iv));
 	kfree(tmpbuf);
 	_leave(" = 0");
 	return 0;
@@ -149,7 +232,7 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn)
  */
 static struct skcipher_request *rxkad_get_call_crypto(struct rxrpc_call *call)
 {
-	struct crypto_skcipher *tfm = &call->conn->cipher->base;
+	struct crypto_skcipher *tfm = &call->conn->rxkad.cipher->base;
 	struct skcipher_request	*cipher_req = call->cipher_req;
 
 	if (!cipher_req) {
@@ -176,15 +259,14 @@ static void rxkad_free_call_crypto(struct rxrpc_call *call)
  * partially encrypt a packet (level 1 security)
  */
 static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
-				    struct sk_buff *skb,
-				    u32 data_size,
-				    void *sechdr,
+				    struct sk_buff *skb, u32 data_size,
 				    struct skcipher_request *req)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxkad_level1_hdr hdr;
 	struct rxrpc_crypt iv;
 	struct scatterlist sg;
+	size_t pad;
 	u16 check;
 
 	_enter("");
@@ -193,13 +275,19 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
 	data_size |= (u32)check << 16;
 
 	hdr.data_size = htonl(data_size);
-	memcpy(sechdr, &hdr, sizeof(hdr));
+	memcpy(skb->head, &hdr, sizeof(hdr));
+
+	pad = sizeof(struct rxkad_level1_hdr) + data_size;
+	pad = RXKAD_ALIGN - pad;
+	pad &= RXKAD_ALIGN - 1;
+	if (pad)
+		skb_put_zero(skb, pad);
 
 	/* start the encryption afresh */
 	memset(&iv, 0, sizeof(iv));
 
-	sg_init_one(&sg, sechdr, 8);
-	skcipher_request_set_sync_tfm(req, call->conn->cipher);
+	sg_init_one(&sg, skb->head, 8);
+	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x);
 	crypto_skcipher_encrypt(req);
@@ -215,7 +303,6 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
 static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call,
 				       struct sk_buff *skb,
 				       u32 data_size,
-				       void *sechdr,
 				       struct skcipher_request *req)
 {
 	const struct rxrpc_key_token *token;
@@ -224,6 +311,7 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call,
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[16];
 	unsigned int len;
+	size_t pad;
 	u16 check;
 	int err;
 
@@ -235,14 +323,20 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call,
 
 	rxkhdr.data_size = htonl(data_size | (u32)check << 16);
 	rxkhdr.checksum = 0;
-	memcpy(sechdr, &rxkhdr, sizeof(rxkhdr));
+	memcpy(skb->head, &rxkhdr, sizeof(rxkhdr));
+
+	pad = sizeof(struct rxkad_level2_hdr) + data_size;
+	pad = RXKAD_ALIGN - pad;
+	pad &= RXKAD_ALIGN - 1;
+	if (pad)
+		skb_put_zero(skb, pad);
 
 	/* encrypt from the session key */
 	token = call->conn->params.key->payload.data[0];
 	memcpy(&iv, token->kad->session_key, sizeof(iv));
 
-	sg_init_one(&sg[0], sechdr, sizeof(rxkhdr));
-	skcipher_request_set_sync_tfm(req, call->conn->cipher);
+	sg_init_one(&sg[0], skb->head, sizeof(rxkhdr));
+	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, &sg[0], &sg[0], sizeof(rxkhdr), iv.x);
 	crypto_skcipher_encrypt(req);
@@ -252,11 +346,10 @@ static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call,
 	if (skb_shinfo(skb)->nr_frags > 16)
 		goto out;
 
-	len = data_size + call->conn->size_align - 1;
-	len &= ~(call->conn->size_align - 1);
+	len = round_up(data_size, RXKAD_ALIGN);
 
 	sg_init_table(sg, ARRAY_SIZE(sg));
-	err = skb_to_sgvec(skb, sg, 0, len);
+	err = skb_to_sgvec(skb, sg, 8, len);
 	if (unlikely(err < 0))
 		goto out;
 	skcipher_request_set_crypt(req, sg, sg, len, iv.x);
@@ -275,8 +368,7 @@ out:
  */
 static int rxkad_secure_packet(struct rxrpc_call *call,
 			       struct sk_buff *skb,
-			       size_t data_size,
-			       void *sechdr)
+			       size_t data_size)
 {
 	struct rxrpc_skb_priv *sp;
 	struct skcipher_request	*req;
@@ -291,7 +383,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call,
 	       call->debug_id, key_serial(call->conn->params.key),
 	       sp->hdr.seq, data_size);
 
-	if (!call->conn->cipher)
+	if (!call->conn->rxkad.cipher)
 		return 0;
 
 	ret = key_validate(call->conn->params.key);
@@ -303,7 +395,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call,
 		return -ENOMEM;
 
 	/* continue encrypting from where we left off */
-	memcpy(&iv, call->conn->csum_iv.x, sizeof(iv));
+	memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv));
 
 	/* calculate the security checksum */
 	x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT);
@@ -312,7 +404,7 @@ static int rxkad_secure_packet(struct rxrpc_call *call,
 	call->crypto_buf[1] = htonl(x);
 
 	sg_init_one(&sg, call->crypto_buf, 8);
-	skcipher_request_set_sync_tfm(req, call->conn->cipher);
+	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x);
 	crypto_skcipher_encrypt(req);
@@ -329,12 +421,10 @@ static int rxkad_secure_packet(struct rxrpc_call *call,
 		ret = 0;
 		break;
 	case RXRPC_SECURITY_AUTH:
-		ret = rxkad_secure_packet_auth(call, skb, data_size, sechdr,
-					       req);
+		ret = rxkad_secure_packet_auth(call, skb, data_size, req);
 		break;
 	case RXRPC_SECURITY_ENCRYPT:
-		ret = rxkad_secure_packet_encrypt(call, skb, data_size,
-						  sechdr, req);
+		ret = rxkad_secure_packet_encrypt(call, skb, data_size, req);
 		break;
 	default:
 		ret = -EPERM;
@@ -380,7 +470,7 @@ static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
 	/* start the decryption afresh */
 	memset(&iv, 0, sizeof(iv));
 
-	skcipher_request_set_sync_tfm(req, call->conn->cipher);
+	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, sg, sg, 8, iv.x);
 	crypto_skcipher_decrypt(req);
@@ -472,7 +562,7 @@ static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 	token = call->conn->params.key->payload.data[0];
 	memcpy(&iv, token->kad->session_key, sizeof(iv));
 
-	skcipher_request_set_sync_tfm(req, call->conn->cipher);
+	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, sg, sg, len, iv.x);
 	crypto_skcipher_decrypt(req);
@@ -538,7 +628,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	_enter("{%d{%x}},{#%u}",
 	       call->debug_id, key_serial(call->conn->params.key), seq);
 
-	if (!call->conn->cipher)
+	if (!call->conn->rxkad.cipher)
 		return 0;
 
 	req = rxkad_get_call_crypto(call);
@@ -546,7 +636,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
 		return -ENOMEM;
 
 	/* continue encrypting from where we left off */
-	memcpy(&iv, call->conn->csum_iv.x, sizeof(iv));
+	memcpy(&iv, call->conn->rxkad.csum_iv.x, sizeof(iv));
 
 	/* validate the security checksum */
 	x = (call->cid & RXRPC_CHANNELMASK) << (32 - RXRPC_CIDSHIFT);
@@ -555,7 +645,7 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	call->crypto_buf[1] = htonl(x);
 
 	sg_init_one(&sg, call->crypto_buf, 8);
-	skcipher_request_set_sync_tfm(req, call->conn->cipher);
+	skcipher_request_set_sync_tfm(req, call->conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, &sg, &sg, 8, iv.x);
 	crypto_skcipher_encrypt(req);
@@ -648,16 +738,12 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 	u32 serial;
 	int ret;
 
-	_enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key));
+	_enter("{%d}", conn->debug_id);
 
-	ret = key_validate(conn->server_key);
-	if (ret < 0)
-		return ret;
-
-	get_random_bytes(&conn->security_nonce, sizeof(conn->security_nonce));
+	get_random_bytes(&conn->rxkad.nonce, sizeof(conn->rxkad.nonce));
 
 	challenge.version	= htonl(2);
-	challenge.nonce		= htonl(conn->security_nonce);
+	challenge.nonce		= htonl(conn->rxkad.nonce);
 	challenge.min_level	= htonl(0);
 	challenge.__padding	= 0;
 
@@ -785,7 +871,7 @@ static int rxkad_encrypt_response(struct rxrpc_connection *conn,
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[1];
 
-	req = skcipher_request_alloc(&conn->cipher->base, GFP_NOFS);
+	req = skcipher_request_alloc(&conn->rxkad.cipher->base, GFP_NOFS);
 	if (!req)
 		return -ENOMEM;
 
@@ -794,7 +880,7 @@ static int rxkad_encrypt_response(struct rxrpc_connection *conn,
 
 	sg_init_table(sg, 1);
 	sg_set_buf(sg, &resp->encrypted, sizeof(resp->encrypted));
-	skcipher_request_set_sync_tfm(req, conn->cipher);
+	skcipher_request_set_sync_tfm(req, conn->rxkad.cipher);
 	skcipher_request_set_callback(req, 0, NULL, NULL);
 	skcipher_request_set_crypt(req, sg, sg, sizeof(resp->encrypted), iv.x);
 	crypto_skcipher_encrypt(req);
@@ -892,6 +978,7 @@ other_error:
  * decrypt the kerberos IV ticket in the response
  */
 static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
+				struct key *server_key,
 				struct sk_buff *skb,
 				void *ticket, size_t ticket_len,
 				struct rxrpc_crypt *_session_key,
@@ -911,30 +998,17 @@ static int rxkad_decrypt_ticket(struct rxrpc_connection *conn,
 	u32 abort_code;
 	u8 *p, *q, *name, *end;
 
-	_enter("{%d},{%x}", conn->debug_id, key_serial(conn->server_key));
+	_enter("{%d},{%x}", conn->debug_id, key_serial(server_key));
 
 	*_expiry = 0;
 
-	ret = key_validate(conn->server_key);
-	if (ret < 0) {
-		switch (ret) {
-		case -EKEYEXPIRED:
-			abort_code = RXKADEXPIRED;
-			goto other_error;
-		default:
-			abort_code = RXKADNOAUTH;
-			goto other_error;
-		}
-	}
-
-	ASSERT(conn->server_key->payload.data[0] != NULL);
+	ASSERT(server_key->payload.data[0] != NULL);
 	ASSERTCMP((unsigned long) ticket & 7UL, ==, 0);
 
-	memcpy(&iv, &conn->server_key->payload.data[2], sizeof(iv));
+	memcpy(&iv, &server_key->payload.data[2], sizeof(iv));
 
 	ret = -ENOMEM;
-	req = skcipher_request_alloc(conn->server_key->payload.data[0],
-				     GFP_NOFS);
+	req = skcipher_request_alloc(server_key->payload.data[0], GFP_NOFS);
 	if (!req)
 		goto temporary_error;
 
@@ -1090,6 +1164,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	struct rxkad_response *response;
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
 	struct rxrpc_crypt session_key;
+	struct key *server_key;
 	const char *eproto;
 	time64_t expiry;
 	void *ticket;
@@ -1097,7 +1172,27 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	__be32 csum;
 	int ret, i;
 
-	_enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key));
+	_enter("{%d}", conn->debug_id);
+
+	server_key = rxrpc_look_up_server_security(conn, skb, 0, 0);
+	if (IS_ERR(server_key)) {
+		switch (PTR_ERR(server_key)) {
+		case -ENOKEY:
+			abort_code = RXKADUNKNOWNKEY;
+			break;
+		case -EKEYEXPIRED:
+			abort_code = RXKADEXPIRED;
+			break;
+		default:
+			abort_code = RXKADNOAUTH;
+			break;
+		}
+		trace_rxrpc_abort(0, "SVK",
+				  sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
+				  abort_code, PTR_ERR(server_key));
+		*_abort_code = abort_code;
+		return -EPROTO;
+	}
 
 	ret = -ENOMEM;
 	response = kzalloc(sizeof(struct rxkad_response), GFP_NOFS);
@@ -1109,8 +1204,6 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
 			  response, sizeof(*response)) < 0)
 		goto protocol_error;
-	if (!pskb_pull(skb, sizeof(*response)))
-		BUG();
 
 	version = ntohl(response->version);
 	ticket_len = ntohl(response->ticket_len);
@@ -1141,12 +1234,12 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 
 	eproto = tracepoint_string("rxkad_tkt_short");
 	abort_code = RXKADPACKETSHORT;
-	if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header),
+	if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header) + sizeof(*response),
 			  ticket, ticket_len) < 0)
 		goto protocol_error_free;
 
-	ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key,
-				   &expiry, _abort_code);
+	ret = rxkad_decrypt_ticket(conn, server_key, skb, ticket, ticket_len,
+				   &session_key, &expiry, _abort_code);
 	if (ret < 0)
 		goto temporary_error_free_ticket;
 
@@ -1169,7 +1262,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	if (response->encrypted.checksum != csum)
 		goto protocol_error_free;
 
-	spin_lock(&conn->channel_lock);
+	spin_lock(&conn->bundle->channel_lock);
 	for (i = 0; i < RXRPC_MAXCALLS; i++) {
 		struct rxrpc_call *call;
 		u32 call_id = ntohl(response->encrypted.call_id[i]);
@@ -1186,17 +1279,17 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 		if (call_id > conn->channels[i].call_counter) {
 			call = rcu_dereference_protected(
 				conn->channels[i].call,
-				lockdep_is_held(&conn->channel_lock));
+				lockdep_is_held(&conn->bundle->channel_lock));
 			if (call && call->state < RXRPC_CALL_COMPLETE)
 				goto protocol_error_unlock;
 			conn->channels[i].call_counter = call_id;
 		}
 	}
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&conn->bundle->channel_lock);
 
 	eproto = tracepoint_string("rxkad_rsp_seq");
 	abort_code = RXKADOUTOFSEQUENCE;
-	if (ntohl(response->encrypted.inc_nonce) != conn->security_nonce + 1)
+	if (ntohl(response->encrypted.inc_nonce) != conn->rxkad.nonce + 1)
 		goto protocol_error_free;
 
 	eproto = tracepoint_string("rxkad_rsp_level");
@@ -1219,12 +1312,13 @@ static int rxkad_verify_response(struct rxrpc_connection *conn,
 	return 0;
 
 protocol_error_unlock:
-	spin_unlock(&conn->channel_lock);
+	spin_unlock(&conn->bundle->channel_lock);
 protocol_error_free:
 	kfree(ticket);
 protocol_error:
 	kfree(response);
 	trace_rxrpc_rx_eproto(NULL, sp->hdr.serial, eproto);
+	key_put(server_key);
 	*_abort_code = abort_code;
 	return -EPROTO;
 
@@ -1237,6 +1331,7 @@ temporary_error:
 	 * ENOMEM.  We just want to send the challenge again.  Note that we
 	 * also come out this way if the ticket decryption fails.
 	 */
+	key_put(server_key);
 	return ret;
 }
 
@@ -1247,8 +1342,8 @@ static void rxkad_clear(struct rxrpc_connection *conn)
 {
 	_enter("");
 
-	if (conn->cipher)
-		crypto_free_sync_skcipher(conn->cipher);
+	if (conn->rxkad.cipher)
+		crypto_free_sync_skcipher(conn->rxkad.cipher);
 }
 
 /*
@@ -1296,8 +1391,11 @@ const struct rxrpc_security rxkad = {
 	.no_key_abort			= RXKADUNKNOWNKEY,
 	.init				= rxkad_init,
 	.exit				= rxkad_exit,
+	.preparse_server_key		= rxkad_preparse_server_key,
+	.free_preparse_server_key	= rxkad_free_preparse_server_key,
+	.destroy_server_key		= rxkad_destroy_server_key,
 	.init_connection_security	= rxkad_init_connection_security,
-	.prime_packet_security		= rxkad_prime_packet_security,
+	.how_much_data			= rxkad_how_much_data,
 	.secure_packet			= rxkad_secure_packet,
 	.verify_packet			= rxkad_verify_packet,
 	.free_call_crypto		= rxkad_free_call_crypto,
diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c
index 9b1fb9ed0717..50cb5f1ee0c0 100644
--- a/net/rxrpc/security.c
+++ b/net/rxrpc/security.c
@@ -55,7 +55,7 @@ void rxrpc_exit_security(void)
 /*
  * look up an rxrpc security module
  */
-static const struct rxrpc_security *rxrpc_security_lookup(u8 security_index)
+const struct rxrpc_security *rxrpc_security_lookup(u8 security_index)
 {
 	if (security_index >= ARRAY_SIZE(rxrpc_security_types))
 		return NULL;
@@ -81,16 +81,17 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
 	if (ret < 0)
 		return ret;
 
-	token = key->payload.data[0];
-	if (!token)
-		return -EKEYREJECTED;
+	for (token = key->payload.data[0]; token; token = token->next) {
+		sec = rxrpc_security_lookup(token->security_index);
+		if (sec)
+			goto found;
+	}
+	return -EKEYREJECTED;
 
-	sec = rxrpc_security_lookup(token->security_index);
-	if (!sec)
-		return -EKEYREJECTED;
+found:
 	conn->security = sec;
 
-	ret = conn->security->init_connection_security(conn);
+	ret = conn->security->init_connection_security(conn, token);
 	if (ret < 0) {
 		conn->security = &rxrpc_no_security;
 		return ret;
@@ -101,22 +102,16 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn)
 }
 
 /*
- * Find the security key for a server connection.
+ * Set the ops a server connection.
  */
-bool rxrpc_look_up_server_security(struct rxrpc_local *local, struct rxrpc_sock *rx,
-				   const struct rxrpc_security **_sec,
-				   struct key **_key,
-				   struct sk_buff *skb)
+const struct rxrpc_security *rxrpc_get_incoming_security(struct rxrpc_sock *rx,
+							 struct sk_buff *skb)
 {
 	const struct rxrpc_security *sec;
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-	key_ref_t kref = NULL;
-	char kdesc[5 + 1 + 3 + 1];
 
 	_enter("");
 
-	sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex);
-
 	sec = rxrpc_security_lookup(sp->hdr.securityIndex);
 	if (!sec) {
 		trace_rxrpc_abort(0, "SVS",
@@ -124,35 +119,72 @@ bool rxrpc_look_up_server_security(struct rxrpc_local *local, struct rxrpc_sock
 				  RX_INVALID_OPERATION, EKEYREJECTED);
 		skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
 		skb->priority = RX_INVALID_OPERATION;
-		return false;
+		return NULL;
 	}
 
-	if (sp->hdr.securityIndex == RXRPC_SECURITY_NONE)
-		goto out;
-
-	if (!rx->securities) {
+	if (sp->hdr.securityIndex != RXRPC_SECURITY_NONE &&
+	    !rx->securities) {
 		trace_rxrpc_abort(0, "SVR",
 				  sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
 				  RX_INVALID_OPERATION, EKEYREJECTED);
 		skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
-		skb->priority = RX_INVALID_OPERATION;
-		return false;
+		skb->priority = sec->no_key_abort;
+		return NULL;
 	}
 
+	return sec;
+}
+
+/*
+ * Find the security key for a server connection.
+ */
+struct key *rxrpc_look_up_server_security(struct rxrpc_connection *conn,
+					  struct sk_buff *skb,
+					  u32 kvno, u32 enctype)
+{
+	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
+	struct rxrpc_sock *rx;
+	struct key *key = ERR_PTR(-EKEYREJECTED);
+	key_ref_t kref = NULL;
+	char kdesc[5 + 1 + 3 + 1 + 12 + 1 + 12 + 1];
+	int ret;
+
+	_enter("");
+
+	if (enctype)
+		sprintf(kdesc, "%u:%u:%u:%u",
+			sp->hdr.serviceId, sp->hdr.securityIndex, kvno, enctype);
+	else if (kvno)
+		sprintf(kdesc, "%u:%u:%u",
+			sp->hdr.serviceId, sp->hdr.securityIndex, kvno);
+	else
+		sprintf(kdesc, "%u:%u",
+			sp->hdr.serviceId, sp->hdr.securityIndex);
+
+	rcu_read_lock();
+
+	rx = rcu_dereference(conn->params.local->service);
+	if (!rx)
+		goto out;
+
 	/* look through the service's keyring */
 	kref = keyring_search(make_key_ref(rx->securities, 1UL),
 			      &key_type_rxrpc_s, kdesc, true);
 	if (IS_ERR(kref)) {
-		trace_rxrpc_abort(0, "SVK",
-				  sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq,
-				  sec->no_key_abort, EKEYREJECTED);
-		skb->mark = RXRPC_SKB_MARK_REJECT_ABORT;
-		skb->priority = sec->no_key_abort;
-		return false;
+		key = ERR_CAST(kref);
+		goto out;
+	}
+
+	key = key_ref_to_ptr(kref);
+
+	ret = key_validate(key);
+	if (ret < 0) {
+		key_put(key);
+		key = ERR_PTR(ret);
+		goto out;
 	}
 
 out:
-	*_sec = sec;
-	*_key = key_ref_to_ptr(kref);
-	return true;
+	rcu_read_unlock();
+	return key;
 }
diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c
index d27140c836cc..af8ad6c30b9f 100644
--- a/net/rxrpc/sendmsg.c
+++ b/net/rxrpc/sendmsg.c
@@ -327,7 +327,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 			rxrpc_send_ack_packet(call, false, NULL);
 
 		if (!skb) {
-			size_t size, chunk, max, space;
+			size_t remain, bufsize, chunk, offset;
 
 			_debug("alloc");
 
@@ -342,24 +342,21 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 					goto maybe_error;
 			}
 
-			max = RXRPC_JUMBO_DATALEN;
-			max -= call->conn->security_size;
-			max &= ~(call->conn->size_align - 1UL);
-
-			chunk = max;
-			if (chunk > msg_data_left(msg) && !more)
-				chunk = msg_data_left(msg);
-
-			space = chunk + call->conn->size_align;
-			space &= ~(call->conn->size_align - 1UL);
-
-			size = space + call->conn->security_size;
+			/* Work out the maximum size of a packet.  Assume that
+			 * the security header is going to be in the padded
+			 * region (enc blocksize), but the trailer is not.
+			 */
+			remain = more ? INT_MAX : msg_data_left(msg);
+			ret = call->conn->security->how_much_data(call, remain,
+								  &bufsize, &chunk, &offset);
+			if (ret < 0)
+				goto maybe_error;
 
-			_debug("SIZE: %zu/%zu/%zu", chunk, space, size);
+			_debug("SIZE: %zu/%zu @%zu", chunk, bufsize, offset);
 
 			/* create a buffer that we can retain until it's ACK'd */
 			skb = sock_alloc_send_skb(
-				sk, size, msg->msg_flags & MSG_DONTWAIT, &ret);
+				sk, bufsize, msg->msg_flags & MSG_DONTWAIT, &ret);
 			if (!skb)
 				goto maybe_error;
 
@@ -371,9 +368,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 
 			ASSERTCMP(skb->mark, ==, 0);
 
-			_debug("HS: %u", call->conn->security_size);
-			skb_reserve(skb, call->conn->security_size);
-			skb->len += call->conn->security_size;
+			__skb_put(skb, offset);
 
 			sp->remain = chunk;
 			if (sp->remain > skb_tailroom(skb))
@@ -422,17 +417,6 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 		    (msg_data_left(msg) == 0 && !more)) {
 			struct rxrpc_connection *conn = call->conn;
 			uint32_t seq;
-			size_t pad;
-
-			/* pad out if we're using security */
-			if (conn->security_ix) {
-				pad = conn->security_size + skb->mark;
-				pad = conn->size_align - pad;
-				pad &= conn->size_align - 1;
-				_debug("pad %zu", pad);
-				if (pad)
-					skb_put_zero(skb, pad);
-			}
 
 			seq = call->tx_top + 1;
 
@@ -446,8 +430,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx,
 				 call->tx_winsize)
 				sp->hdr.flags |= RXRPC_MORE_PACKETS;
 
-			ret = call->security->secure_packet(
-				call, skb, skb->mark, skb->head);
+			ret = call->security->secure_packet(call, skb, skb->mark);
 			if (ret < 0)
 				goto out;
 
diff --git a/net/rxrpc/server_key.c b/net/rxrpc/server_key.c
new file mode 100644
index 000000000000..ead3471307ee
--- /dev/null
+++ b/net/rxrpc/server_key.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* RxRPC key management
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * RxRPC keys should have a description of describing their purpose:
+ *	"afs@CAMBRIDGE.REDHAT.COM>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <crypto/skcipher.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/key-type.h>
+#include <linux/ctype.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/af_rxrpc.h>
+#include <keys/rxrpc-type.h>
+#include <keys/user-type.h>
+#include "ar-internal.h"
+
+static int rxrpc_vet_description_s(const char *);
+static int rxrpc_preparse_s(struct key_preparsed_payload *);
+static void rxrpc_free_preparse_s(struct key_preparsed_payload *);
+static void rxrpc_destroy_s(struct key *);
+static void rxrpc_describe_s(const struct key *, struct seq_file *);
+
+/*
+ * rxrpc server keys take "<serviceId>:<securityIndex>[:<sec-specific>]" as the
+ * description and the key material as the payload.
+ */
+struct key_type key_type_rxrpc_s = {
+	.name		= "rxrpc_s",
+	.flags		= KEY_TYPE_NET_DOMAIN,
+	.vet_description = rxrpc_vet_description_s,
+	.preparse	= rxrpc_preparse_s,
+	.free_preparse	= rxrpc_free_preparse_s,
+	.instantiate	= generic_key_instantiate,
+	.destroy	= rxrpc_destroy_s,
+	.describe	= rxrpc_describe_s,
+};
+
+/*
+ * Vet the description for an RxRPC server key.
+ */
+static int rxrpc_vet_description_s(const char *desc)
+{
+	unsigned long service, sec_class;
+	char *p;
+
+	service = simple_strtoul(desc, &p, 10);
+	if (*p != ':' || service > 65535)
+		return -EINVAL;
+	sec_class = simple_strtoul(p + 1, &p, 10);
+	if ((*p && *p != ':') || sec_class < 1 || sec_class > 255)
+		return -EINVAL;
+	return 0;
+}
+
+/*
+ * Preparse a server secret key.
+ */
+static int rxrpc_preparse_s(struct key_preparsed_payload *prep)
+{
+	const struct rxrpc_security *sec;
+	unsigned int service, sec_class;
+	int n;
+
+	_enter("%zu", prep->datalen);
+
+	if (!prep->orig_description)
+		return -EINVAL;
+
+	if (sscanf(prep->orig_description, "%u:%u%n", &service, &sec_class, &n) != 2)
+		return -EINVAL;
+
+	sec = rxrpc_security_lookup(sec_class);
+	if (!sec)
+		return -ENOPKG;
+
+	prep->payload.data[1] = (struct rxrpc_security *)sec;
+
+	return sec->preparse_server_key(prep);
+}
+
+static void rxrpc_free_preparse_s(struct key_preparsed_payload *prep)
+{
+	const struct rxrpc_security *sec = prep->payload.data[1];
+
+	if (sec)
+		sec->free_preparse_server_key(prep);
+}
+
+static void rxrpc_destroy_s(struct key *key)
+{
+	const struct rxrpc_security *sec = key->payload.data[1];
+
+	if (sec)
+		sec->destroy_server_key(key);
+}
+
+static void rxrpc_describe_s(const struct key *key, struct seq_file *m)
+{
+	const struct rxrpc_security *sec = key->payload.data[1];
+
+	seq_puts(m, key->description);
+	if (sec && sec->describe_server_key)
+		sec->describe_server_key(key, m);
+}
+
+/*
+ * grab the security keyring for a server socket
+ */
+int rxrpc_server_keyring(struct rxrpc_sock *rx, sockptr_t optval, int optlen)
+{
+	struct key *key;
+	char *description;
+
+	_enter("");
+
+	if (optlen <= 0 || optlen > PAGE_SIZE - 1)
+		return -EINVAL;
+
+	description = memdup_sockptr_nul(optval, optlen);
+	if (IS_ERR(description))
+		return PTR_ERR(description);
+
+	key = request_key(&key_type_keyring, description, NULL);
+	if (IS_ERR(key)) {
+		kfree(description);
+		_leave(" = %ld", PTR_ERR(key));
+		return PTR_ERR(key);
+	}
+
+	rx->securities = key;
+	kfree(description);
+	_leave(" = 0 [key %x]", key->serial);
+	return 0;
+}
diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index e91acc95ff28..540351d6a5f4 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -74,21 +74,13 @@ static struct ctl_table rxrpc_sysctl_table[] = {
 
 	/* Non-time values */
 	{
-		.procname	= "max_client_conns",
-		.data		= &rxrpc_max_client_connections,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= (void *)&rxrpc_reap_client_connections,
-	},
-	{
 		.procname	= "reap_client_conns",
 		.data		= &rxrpc_reap_client_connections,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= (void *)SYSCTL_ONE,
-		.extra2		= (void *)&rxrpc_max_client_connections,
+		.extra2		= (void *)&n_65535,
 	},
 	{
 		.procname	= "max_backlog",
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a3b37d88800e..1e8ab4749c6c 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -281,7 +281,7 @@ config NET_SCH_CHOKE
 	help
 	  Say Y here if you want to use the CHOKe packet scheduler (CHOose
 	  and Keep for responsive flows, CHOose and Kill for unresponsive
-	  flows). This is a variation of RED which trys to penalize flows
+	  flows). This is a variation of RED which tries to penalize flows
 	  that monopolize the queue.
 
 	  To compile this code as a module, choose M here: the
@@ -813,7 +813,7 @@ config NET_ACT_SAMPLE
 
 config NET_ACT_IPT
 	tristate "IPtables targets"
-	depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES
+	depends on NET_CLS_ACT && NETFILTER && NETFILTER_XTABLES
 	help
 	  Say Y here to be able to invoke iptables targets after successful
 	  classification.
@@ -912,7 +912,7 @@ config NET_ACT_BPF
 
 config NET_ACT_CONNMARK
 	tristate "Netfilter Connection Mark Retriever"
-	depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES
+	depends on NET_CLS_ACT && NETFILTER
 	depends on NF_CONNTRACK && NF_CONNTRACK_MARK
 	help
 	  Say Y here to allow retrieving of conn mark
@@ -924,7 +924,7 @@ config NET_ACT_CONNMARK
 
 config NET_ACT_CTINFO
 	tristate "Netfilter Connection Mark Actions"
-	depends on NET_CLS_ACT && NETFILTER && IP_NF_IPTABLES
+	depends on NET_CLS_ACT && NETFILTER
 	depends on NF_CONNTRACK && NF_CONNTRACK_MARK
 	help
 	  Say Y here to allow transfer of a connmark stored information.
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 66bbf9a98f9e..dd14ef413fda 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -5,6 +5,7 @@
 
 obj-y	:= sch_generic.o sch_mq.o
 
+obj-$(CONFIG_INET)		+= sch_frag.o
 obj-$(CONFIG_NET_SCHED)		+= sch_api.o sch_blackhole.o
 obj-$(CONFIG_NET_CLS)		+= cls_api.o
 obj-$(CONFIG_NET_CLS_ACT)	+= act_api.o
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 798430e1a79f..2e85b636b27b 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -22,6 +22,22 @@
 #include <net/act_api.h>
 #include <net/netlink.h>
 
+#ifdef CONFIG_INET
+DEFINE_STATIC_KEY_FALSE(tcf_frag_xmit_count);
+EXPORT_SYMBOL_GPL(tcf_frag_xmit_count);
+#endif
+
+int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
+{
+#ifdef CONFIG_INET
+	if (static_branch_unlikely(&tcf_frag_xmit_count))
+		return sch_frag_xmit_hook(skb, xmit);
+#endif
+
+	return xmit(skb);
+}
+EXPORT_SYMBOL_GPL(tcf_dev_queue_xmit);
+
 static void tcf_action_goto_chain_exec(const struct tc_action *a,
 				       struct tcf_result *res)
 {
@@ -215,6 +231,36 @@ static size_t tcf_action_fill_size(const struct tc_action *act)
 	return sz;
 }
 
+static int
+tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a, bool from_act)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct tc_cookie *cookie;
+
+	if (nla_put_string(skb, TCA_KIND, a->ops->kind))
+		goto nla_put_failure;
+	if (tcf_action_copy_stats(skb, a, 0))
+		goto nla_put_failure;
+	if (from_act && nla_put_u32(skb, TCA_ACT_INDEX, a->tcfa_index))
+		goto nla_put_failure;
+
+	rcu_read_lock();
+	cookie = rcu_dereference(a->act_cookie);
+	if (cookie) {
+		if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
+			rcu_read_unlock();
+			goto nla_put_failure;
+		}
+	}
+	rcu_read_unlock();
+
+	return 0;
+
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -1;
+}
+
 static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 			   struct netlink_callback *cb)
 {
@@ -248,7 +294,9 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 			index--;
 			goto nla_put_failure;
 		}
-		err = tcf_action_dump_1(skb, p, 0, 0);
+		err = (act_flags & TCA_ACT_FLAG_TERSE_DUMP) ?
+			tcf_action_dump_terse(skb, p, true) :
+			tcf_action_dump_1(skb, p, 0, 0);
 		if (err < 0) {
 			index--;
 			nlmsg_trim(skb, nest);
@@ -256,7 +304,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 		}
 		nla_nest_end(skb, nest);
 		n_i++;
-		if (!(act_flags & TCA_FLAG_LARGE_DUMP_ON) &&
+		if (!(act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON) &&
 		    n_i >= TCA_ACT_MAX_PRIO)
 			goto done;
 	}
@@ -266,7 +314,7 @@ done:
 
 	mutex_unlock(&idrinfo->lock);
 	if (n_i) {
-		if (act_flags & TCA_FLAG_LARGE_DUMP_ON)
+		if (act_flags & TCA_ACT_FLAG_LARGE_DUMP_ON)
 			cb->args[1] = n_i;
 	}
 	return n_i;
@@ -651,7 +699,7 @@ static struct tc_action_ops *tc_lookup_action(struct nlattr *kind)
 	return res;
 }
 
-/*TCA_ACT_MAX_PRIO is 32, there count upto 32 */
+/*TCA_ACT_MAX_PRIO is 32, there count up to 32 */
 #define TCA_ACT_MAX_PRIO_MASK 0x1FF
 int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 		    int nr_actions, struct tcf_result *res)
@@ -752,34 +800,6 @@ tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 	return a->ops->dump(skb, a, bind, ref);
 }
 
-static int
-tcf_action_dump_terse(struct sk_buff *skb, struct tc_action *a)
-{
-	unsigned char *b = skb_tail_pointer(skb);
-	struct tc_cookie *cookie;
-
-	if (nla_put_string(skb, TCA_KIND, a->ops->kind))
-		goto nla_put_failure;
-	if (tcf_action_copy_stats(skb, a, 0))
-		goto nla_put_failure;
-
-	rcu_read_lock();
-	cookie = rcu_dereference(a->act_cookie);
-	if (cookie) {
-		if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
-			rcu_read_unlock();
-			goto nla_put_failure;
-		}
-	}
-	rcu_read_unlock();
-
-	return 0;
-
-nla_put_failure:
-	nlmsg_trim(skb, b);
-	return -1;
-}
-
 int
 tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 {
@@ -787,7 +807,7 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
 
-	if (tcf_action_dump_terse(skb, a))
+	if (tcf_action_dump_terse(skb, a, false))
 		goto nla_put_failure;
 
 	if (a->hw_stats != TCA_ACT_HW_STATS_ANY &&
@@ -832,7 +852,7 @@ int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[],
 		nest = nla_nest_start_noflag(skb, i + 1);
 		if (nest == NULL)
 			goto nla_put_failure;
-		err = terse ? tcf_action_dump_terse(skb, a) :
+		err = terse ? tcf_action_dump_terse(skb, a, false) :
 			tcf_action_dump_1(skb, a, bind, ref);
 		if (err < 0)
 			goto errout;
@@ -935,7 +955,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 			NL_SET_ERR_MSG(extack, "TC action kind must be specified");
 			goto err_out;
 		}
-		if (nla_strlcpy(act_name, kind, IFNAMSIZ) >= IFNAMSIZ) {
+		if (nla_strscpy(act_name, kind, IFNAMSIZ) < 0) {
 			NL_SET_ERR_MSG(extack, "TC action name too long");
 			goto err_out;
 		}
@@ -982,7 +1002,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 #endif
 		NL_SET_ERR_MSG(extack, "Failed to load TC action module");
 		err = -ENOENT;
-		goto err_out;
+		goto err_free;
 	}
 
 	/* backward compatibility for policer */
@@ -1012,11 +1032,12 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 
 err_mod:
 	module_put(a_o->owner);
-err_out:
+err_free:
 	if (cookie) {
 		kfree(cookie->data);
 		kfree(cookie);
 	}
+err_out:
 	return ERR_PTR(err);
 }
 
@@ -1468,7 +1489,8 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 }
 
 static const struct nla_policy tcaa_policy[TCA_ROOT_MAX + 1] = {
-	[TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_FLAG_LARGE_DUMP_ON),
+	[TCA_ROOT_FLAGS] = NLA_POLICY_BITFIELD32(TCA_ACT_FLAG_LARGE_DUMP_ON |
+						 TCA_ACT_FLAG_TERSE_DUMP),
 	[TCA_ROOT_TIME_DELTA]      = { .type = NLA_U32 },
 };
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index a4c7ba35a343..e48e980c3b93 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -65,7 +65,7 @@ static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
 	 * In case a different well-known TC_ACT opcode has been
 	 * returned, it will overwrite the default one.
 	 *
-	 * For everything else that is unkown, TC_ACT_UNSPEC is
+	 * For everything else that is unknown, TC_ACT_UNSPEC is
 	 * returned.
 	 */
 	switch (filter_res) {
diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
index a780afdf570d..83a5c6722a06 100644
--- a/net/sched/act_ct.c
+++ b/net/sched/act_ct.c
@@ -156,11 +156,11 @@ tcf_ct_flow_table_add_action_nat_udp(const struct nf_conntrack_tuple *tuple,
 	__be16 target_dst = target.dst.u.udp.port;
 
 	if (target_src != tuple->src.u.udp.port)
-		tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
+		tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP,
 					 offsetof(struct udphdr, source),
 					 0xFFFF, be16_to_cpu(target_src));
 	if (target_dst != tuple->dst.u.udp.port)
-		tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_TCP,
+		tcf_ct_add_mangle_action(action, FLOW_ACT_MANGLE_HDR_TYPE_UDP,
 					 offsetof(struct udphdr, dest),
 					 0xFFFF, be16_to_cpu(target_dst));
 }
@@ -296,7 +296,8 @@ static int tcf_ct_flow_table_get(struct tcf_ct_params *params)
 		goto err_insert;
 
 	ct_ft->nf_ft.type = &flowtable_ct;
-	ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD;
+	ct_ft->nf_ft.flags |= NF_FLOWTABLE_HW_OFFLOAD |
+			      NF_FLOWTABLE_COUNTER;
 	err = nf_flow_table_init(&ct_ft->nf_ft);
 	if (err)
 		goto err_init;
@@ -540,7 +541,8 @@ static bool tcf_ct_flow_table_lookup(struct tcf_ct_params *p,
 	flow_offload_refresh(nf_ft, flow);
 	nf_conntrack_get(&ct->ct_general);
 	nf_ct_set(skb, ct, ctinfo);
-	nf_ct_acct_update(ct, dir, skb->len);
+	if (nf_ft->flags & NF_FLOWTABLE_COUNTER)
+		nf_ct_acct_update(ct, dir, skb->len);
 
 	return true;
 }
@@ -1039,7 +1041,7 @@ drop:
 
 static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
 	[TCA_CT_ACTION] = { .type = NLA_U16 },
-	[TCA_CT_PARMS] = { .type = NLA_EXACT_LEN, .len = sizeof(struct tc_ct) },
+	[TCA_CT_PARMS] = NLA_POLICY_EXACT_LEN(sizeof(struct tc_ct)),
 	[TCA_CT_ZONE] = { .type = NLA_U16 },
 	[TCA_CT_MARK] = { .type = NLA_U32 },
 	[TCA_CT_MARK_MASK] = { .type = NLA_U32 },
@@ -1049,10 +1051,8 @@ static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = {
 				 .len = 128 / BITS_PER_BYTE },
 	[TCA_CT_NAT_IPV4_MIN] = { .type = NLA_U32 },
 	[TCA_CT_NAT_IPV4_MAX] = { .type = NLA_U32 },
-	[TCA_CT_NAT_IPV6_MIN] = { .type = NLA_EXACT_LEN,
-				  .len = sizeof(struct in6_addr) },
-	[TCA_CT_NAT_IPV6_MAX] = { .type = NLA_EXACT_LEN,
-				   .len = sizeof(struct in6_addr) },
+	[TCA_CT_NAT_IPV6_MIN] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+	[TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
 	[TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 },
 	[TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 },
 };
@@ -1543,6 +1543,8 @@ static int __init ct_init_module(void)
 	if (err)
 		goto err_register;
 
+	static_branch_inc(&tcf_frag_xmit_count);
+
 	return 0;
 
 err_register:
@@ -1554,6 +1556,7 @@ err_tbl_init:
 
 static void __exit ct_cleanup_module(void)
 {
+	static_branch_dec(&tcf_frag_xmit_count);
 	tcf_unregister_action(&act_ct_ops, &ct_net_ops);
 	tcf_ct_flow_tables_uninit();
 	destroy_workqueue(act_ct_wq);
diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c
index 6084300e51ad..b20c8ce59905 100644
--- a/net/sched/act_ctinfo.c
+++ b/net/sched/act_ctinfo.c
@@ -144,9 +144,8 @@ out:
 }
 
 static const struct nla_policy ctinfo_policy[TCA_CTINFO_MAX + 1] = {
-	[TCA_CTINFO_ACT]		  = { .type = NLA_EXACT_LEN,
-					      .len = sizeof(struct
-							    tc_ctinfo) },
+	[TCA_CTINFO_ACT]		  =
+		NLA_POLICY_EXACT_LEN(sizeof(struct tc_ctinfo)),
 	[TCA_CTINFO_ZONE]		  = { .type = NLA_U16 },
 	[TCA_CTINFO_PARMS_DSCP_MASK]	  = { .type = NLA_U32 },
 	[TCA_CTINFO_PARMS_DSCP_STATEMASK] = { .type = NLA_U32 },
diff --git a/net/sched/act_gate.c b/net/sched/act_gate.c
index 7c0771dd77a3..a78cb7965718 100644
--- a/net/sched/act_gate.c
+++ b/net/sched/act_gate.c
@@ -159,8 +159,8 @@ static const struct nla_policy entry_policy[TCA_GATE_ENTRY_MAX + 1] = {
 };
 
 static const struct nla_policy gate_policy[TCA_GATE_MAX + 1] = {
-	[TCA_GATE_PARMS]		= { .len = sizeof(struct tc_gate),
-					    .type = NLA_EXACT_LEN },
+	[TCA_GATE_PARMS]		=
+		NLA_POLICY_EXACT_LEN(sizeof(struct tc_gate)),
 	[TCA_GATE_PRIORITY]		= { .type = NLA_S32 },
 	[TCA_GATE_ENTRY_LIST]		= { .type = NLA_NESTED },
 	[TCA_GATE_BASE_TIME]		= { .type = NLA_U64 },
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 8dc3bec0d325..ac7297f42355 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -166,7 +166,7 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 	if (unlikely(!tname))
 		goto err1;
 	if (tb[TCA_IPT_TABLE] == NULL ||
-	    nla_strlcpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ)
+	    nla_strscpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ)
 		strcpy(tname, "mangle");
 
 	t = kmemdup(td, td->u.target_size, GFP_KERNEL);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index e24b7e2331cd..7153c67f641e 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -205,6 +205,18 @@ release_idr:
 	return err;
 }
 
+static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb)
+{
+	int err;
+
+	if (!want_ingress)
+		err = tcf_dev_queue_xmit(skb, dev_queue_xmit);
+	else
+		err = netif_receive_skb(skb);
+
+	return err;
+}
+
 static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 			  struct tcf_result *res)
 {
@@ -287,18 +299,15 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 		/* let's the caller reinsert the packet, if possible */
 		if (use_reinsert) {
 			res->ingress = want_ingress;
-			if (skb_tc_reinsert(skb, res))
+			err = tcf_mirred_forward(res->ingress, skb);
+			if (err)
 				tcf_action_inc_overlimit_qstats(&m->common);
 			__this_cpu_dec(mirred_rec_level);
 			return TC_ACT_CONSUMED;
 		}
 	}
 
-	if (!want_ingress)
-		err = dev_queue_xmit(skb2);
-	else
-		err = netif_receive_skb(skb2);
-
+	err = tcf_mirred_forward(want_ingress, skb2);
 	if (err) {
 out:
 		tcf_action_inc_overlimit_qstats(&m->common);
diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c
index e298ec3b3c9e..d1486ea496a2 100644
--- a/net/sched/act_mpls.c
+++ b/net/sched/act_mpls.c
@@ -87,7 +87,27 @@ static int tcf_mpls_act(struct sk_buff *skb, const struct tc_action *a,
 				  skb->dev && skb->dev->type == ARPHRD_ETHER))
 			goto drop;
 		break;
+	case TCA_MPLS_ACT_MAC_PUSH:
+		if (skb_vlan_tag_present(skb)) {
+			if (__vlan_insert_inner_tag(skb, skb->vlan_proto,
+						    skb_vlan_tag_get(skb),
+						    ETH_HLEN) < 0)
+				goto drop;
+
+			skb->protocol = skb->vlan_proto;
+			__vlan_hwaccel_clear_tag(skb);
+		}
+
+		new_lse = tcf_mpls_get_lse(NULL, p, mac_len ||
+					   !eth_p_mpls(skb->protocol));
+
+		if (skb_mpls_push(skb, new_lse, p->tcfm_proto, 0, false))
+			goto drop;
+		break;
 	case TCA_MPLS_ACT_MODIFY:
+		if (!pskb_may_pull(skb,
+				   skb_network_offset(skb) + MPLS_HLEN))
+			goto drop;
 		new_lse = tcf_mpls_get_lse(mpls_hdr(skb), p, false);
 		if (skb_mpls_update_lse(skb, new_lse))
 			goto drop;
@@ -188,6 +208,7 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla,
 		}
 		break;
 	case TCA_MPLS_ACT_PUSH:
+	case TCA_MPLS_ACT_MAC_PUSH:
 		if (!tb[TCA_MPLS_LABEL]) {
 			NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push");
 			return -EINVAL;
@@ -408,6 +429,7 @@ static void __exit mpls_cleanup_module(void)
 module_init(mpls_init_module);
 module_exit(mpls_cleanup_module);
 
+MODULE_SOFTDEP("post: mpls_gso");
 MODULE_AUTHOR("Netronome Systems <oss-drivers@netronome.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("MPLS manipulation actions");
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index a4f3d0f0daa9..726cc956d06f 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -52,7 +52,7 @@ static int alloc_defdata(struct tcf_defact *d, const struct nlattr *defdata)
 	d->tcfd_defdata = kzalloc(SIMP_MAX_DATA, GFP_KERNEL);
 	if (unlikely(!d->tcfd_defdata))
 		return -ENOMEM;
-	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	return 0;
 }
 
@@ -71,7 +71,7 @@ static int reset_policy(struct tc_action *a, const struct nlattr *defdata,
 	spin_lock_bh(&d->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(a, p->action, goto_ch);
 	memset(d->tcfd_defdata, 0, SIMP_MAX_DATA);
-	nla_strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
+	nla_strscpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);
 	spin_unlock_bh(&d->tcf_lock);
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index a229751ee8c4..85c0d0d5b9da 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -459,7 +459,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 
 			metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port,
 						      0, flags,
-						      key_id, 0);
+						      key_id, opts_len);
 		} else {
 			NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst");
 			ret = -EINVAL;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 163b0385fd4c..1cac3c6fbb49 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -77,6 +77,16 @@ static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a,
 		/* put updated tci as hwaccel tag */
 		__vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci);
 		break;
+	case TCA_VLAN_ACT_POP_ETH:
+		err = skb_eth_pop(skb);
+		if (err)
+			goto drop;
+		break;
+	case TCA_VLAN_ACT_PUSH_ETH:
+		err = skb_eth_push(skb, p->tcfv_push_dst, p->tcfv_push_src);
+		if (err)
+			goto drop;
+		break;
 	default:
 		BUG();
 	}
@@ -93,10 +103,13 @@ drop:
 }
 
 static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
+	[TCA_VLAN_UNSPEC]		= { .strict_start_type = TCA_VLAN_PUSH_ETH_DST },
 	[TCA_VLAN_PARMS]		= { .len = sizeof(struct tc_vlan) },
 	[TCA_VLAN_PUSH_VLAN_ID]		= { .type = NLA_U16 },
 	[TCA_VLAN_PUSH_VLAN_PROTOCOL]	= { .type = NLA_U16 },
 	[TCA_VLAN_PUSH_VLAN_PRIORITY]	= { .type = NLA_U8 },
+	[TCA_VLAN_PUSH_ETH_DST]		= NLA_POLICY_ETH_ADDR,
+	[TCA_VLAN_PUSH_ETH_SRC]		= NLA_POLICY_ETH_ADDR,
 };
 
 static int tcf_vlan_init(struct net *net, struct nlattr *nla,
@@ -179,6 +192,17 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		if (tb[TCA_VLAN_PUSH_VLAN_PRIORITY])
 			push_prio = nla_get_u8(tb[TCA_VLAN_PUSH_VLAN_PRIORITY]);
 		break;
+	case TCA_VLAN_ACT_POP_ETH:
+		break;
+	case TCA_VLAN_ACT_PUSH_ETH:
+		if (!tb[TCA_VLAN_PUSH_ETH_DST] || !tb[TCA_VLAN_PUSH_ETH_SRC]) {
+			if (exists)
+				tcf_idr_release(*a, bind);
+			else
+				tcf_idr_cleanup(tn, index);
+			return -EINVAL;
+		}
+		break;
 	default:
 		if (exists)
 			tcf_idr_release(*a, bind);
@@ -219,6 +243,13 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	p->tcfv_push_prio = push_prio;
 	p->tcfv_push_proto = push_proto;
 
+	if (action == TCA_VLAN_ACT_PUSH_ETH) {
+		nla_memcpy(&p->tcfv_push_dst, tb[TCA_VLAN_PUSH_ETH_DST],
+			   ETH_ALEN);
+		nla_memcpy(&p->tcfv_push_src, tb[TCA_VLAN_PUSH_ETH_SRC],
+			   ETH_ALEN);
+	}
+
 	spin_lock_bh(&v->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
 	p = rcu_replace_pointer(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
@@ -277,6 +308,15 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 					      p->tcfv_push_prio))))
 		goto nla_put_failure;
 
+	if (p->tcfv_action == TCA_VLAN_ACT_PUSH_ETH) {
+		if (nla_put(skb, TCA_VLAN_PUSH_ETH_DST, ETH_ALEN,
+			    p->tcfv_push_dst))
+			goto nla_put_failure;
+		if (nla_put(skb, TCA_VLAN_PUSH_ETH_SRC, ETH_ALEN,
+			    p->tcfv_push_src))
+			goto nla_put_failure;
+	}
+
 	tcf_tm_dump(&t, &v->tcf_tm);
 	if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
 		goto nla_put_failure;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 41a55c6cbeb8..37b77bd30974 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -223,7 +223,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp)
 static bool tcf_proto_check_kind(struct nlattr *kind, char *name)
 {
 	if (kind)
-		return nla_strlcpy(name, kind, IFNAMSIZ) >= IFNAMSIZ;
+		return nla_strscpy(name, kind, IFNAMSIZ) < 0;
 	memset(name, 0, IFNAMSIZ);
 	return false;
 }
@@ -652,12 +652,12 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb)
 			       block_cb->indr.binder_type,
 			       &block->flow_block, tcf_block_shared(block),
 			       &extack);
+	rtnl_lock();
 	down_write(&block->cb_lock);
 	list_del(&block_cb->driver_list);
 	list_move(&block_cb->list, &bo.cb_list);
-	up_write(&block->cb_lock);
-	rtnl_lock();
 	tcf_block_unbind(block, &bo);
+	up_write(&block->cb_lock);
 	rtnl_unlock();
 }
 
@@ -991,13 +991,12 @@ __tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp)
  */
 
 struct tcf_proto *
-tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp,
-		   bool rtnl_held)
+tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp)
 {
 	struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp);
 
 	if (tp)
-		tcf_proto_put(tp, rtnl_held, NULL);
+		tcf_proto_put(tp, true, NULL);
 
 	return tp_next;
 }
@@ -1924,15 +1923,14 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb,
 static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
 				 struct tcf_block *block, struct Qdisc *q,
 				 u32 parent, struct nlmsghdr *n,
-				 struct tcf_chain *chain, int event,
-				 bool rtnl_held)
+				 struct tcf_chain *chain, int event)
 {
 	struct tcf_proto *tp;
 
-	for (tp = tcf_get_next_proto(chain, NULL, rtnl_held);
-	     tp; tp = tcf_get_next_proto(chain, tp, rtnl_held))
+	for (tp = tcf_get_next_proto(chain, NULL);
+	     tp; tp = tcf_get_next_proto(chain, tp))
 		tfilter_notify(net, oskb, n, tp, block,
-			       q, parent, NULL, event, false, rtnl_held);
+			       q, parent, NULL, event, false, true);
 }
 
 static void tfilter_put(struct tcf_proto *tp, void *fh)
@@ -2262,7 +2260,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 
 	if (prio == 0) {
 		tfilter_notify_chain(net, skb, block, q, parent, n,
-				     chain, RTM_DELTFILTER, rtnl_held);
+				     chain, RTM_DELTFILTER);
 		tcf_chain_flush(chain, rtnl_held);
 		err = 0;
 		goto errout;
@@ -2895,7 +2893,7 @@ replay:
 		break;
 	case RTM_DELCHAIN:
 		tfilter_notify_chain(net, skb, block, q, parent, n,
-				     chain, RTM_DELTFILTER, true);
+				     chain, RTM_DELTFILTER);
 		/* Flush the chain first as the user requested chain removal. */
 		tcf_chain_flush(chain, true);
 		/* In case the chain was successfully deleted, put a reference
@@ -2940,7 +2938,6 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 	struct tcf_chain *chain;
 	long index_start;
 	long index;
-	u32 parent;
 	int err;
 
 	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
@@ -2955,13 +2952,6 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 		block = tcf_block_refcnt_get(net, tcm->tcm_block_index);
 		if (!block)
 			goto out;
-		/* If we work with block index, q is NULL and parent value
-		 * will never be used in the following code. The check
-		 * in tcf_fill_node prevents it. However, compiler does not
-		 * see that far, so set parent to zero to silence the warning
-		 * about parent being uninitialized.
-		 */
-		parent = 0;
 	} else {
 		const struct Qdisc_class_ops *cops;
 		struct net_device *dev;
@@ -2971,13 +2961,11 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 		if (!dev)
 			return skb->len;
 
-		parent = tcm->tcm_parent;
-		if (!parent) {
+		if (!tcm->tcm_parent)
 			q = dev->qdisc;
-			parent = q->handle;
-		} else {
+		else
 			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
-		}
+
 		if (!q)
 			goto out;
 		cops = q->ops->cl_ops;
@@ -3712,7 +3700,7 @@ int tc_setup_flow_action(struct flow_action *flow_action,
 			entry->gate.num_entries = tcf_gate_num_entries(act);
 			err = tcf_gate_get_entries(entry, act);
 			if (err)
-				goto err_out;
+				goto err_out_locked;
 		} else {
 			err = -EOPNOTSUPP;
 			goto err_out_locked;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index fed18fd2c50b..84f932532db7 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1272,6 +1272,10 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 
 		nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
 		msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
+		if (!nla_ok(nla_opt_msk, msk_depth)) {
+			NL_SET_ERR_MSG(extack, "Invalid nested attribute for masks");
+			return -EINVAL;
+		}
 	}
 
 	nla_for_each_attr(nla_opt_key, nla_enc_key,
@@ -1307,9 +1311,6 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 				NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
 				return -EINVAL;
 			}
-
-			if (msk_depth)
-				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
 			break;
 		case TCA_FLOWER_KEY_ENC_OPTS_VXLAN:
 			if (key->enc_opts.dst_opt_type) {
@@ -1340,9 +1341,6 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 				NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
 				return -EINVAL;
 			}
-
-			if (msk_depth)
-				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
 			break;
 		case TCA_FLOWER_KEY_ENC_OPTS_ERSPAN:
 			if (key->enc_opts.dst_opt_type) {
@@ -1373,14 +1371,20 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 				NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
 				return -EINVAL;
 			}
-
-			if (msk_depth)
-				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
 			break;
 		default:
 			NL_SET_ERR_MSG(extack, "Unknown tunnel option type");
 			return -EINVAL;
 		}
+
+		if (!msk_depth)
+			continue;
+
+		if (!nla_ok(nla_opt_msk, msk_depth)) {
+			NL_SET_ERR_MSG(extack, "A mask attribute is invalid");
+			return -EINVAL;
+		}
+		nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
 	}
 
 	return 0;
@@ -2424,8 +2428,8 @@ static int fl_dump_key_mpls_opt_lse(struct sk_buff *skb,
 			return err;
 	}
 	if (lse_mask->mpls_label) {
-		err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL,
-				 lse_key->mpls_label);
+		err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL,
+				  lse_key->mpls_label);
 		if (err)
 			return err;
 	}
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index d36949d9382c..2e288f88ff02 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -238,7 +238,7 @@ static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h)
 		}
 	}
 
-	/* Something went wrong if we are trying to replace a non-existant
+	/* Something went wrong if we are trying to replace a non-existent
 	 * node. Mind as well halt instead of silently failing.
 	 */
 	BUG_ON(1);
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 78bec347b8b6..c4007b9cd16d 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -366,9 +366,13 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 	if (tb[TCA_TCINDEX_MASK])
 		cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]);
 
-	if (tb[TCA_TCINDEX_SHIFT])
+	if (tb[TCA_TCINDEX_SHIFT]) {
 		cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]);
-
+		if (cp->shift > 16) {
+			err = -EINVAL;
+			goto errout;
+		}
+	}
 	if (!cp->hash) {
 		/* Hash not specified, use perfect hash if the upper limit
 		 * of the hashing index is below the threshold.
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 7b69ab1993ba..6e1abe805448 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -79,7 +79,7 @@ struct tc_u_hnode {
 	/* The 'ht' field MUST be the last field in structure to allow for
 	 * more entries allocated at end of structure.
 	 */
-	struct tc_u_knode __rcu	*ht[1];
+	struct tc_u_knode __rcu	*ht[];
 };
 
 struct tc_u_common {
@@ -353,7 +353,7 @@ static int u32_init(struct tcf_proto *tp)
 	void *key = tc_u_common_ptr(tp);
 	struct tc_u_common *tp_c = tc_u_common_find(key);
 
-	root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL);
+	root_ht = kzalloc(struct_size(root_ht, ht, 1), GFP_KERNEL);
 	if (root_ht == NULL)
 		return -ENOBUFS;
 
@@ -364,7 +364,7 @@ static int u32_init(struct tcf_proto *tp)
 	idr_init(&root_ht->handle_idr);
 
 	if (tp_c == NULL) {
-		tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL);
+		tp_c = kzalloc(struct_size(tp_c, hlist->ht, 1), GFP_KERNEL);
 		if (tp_c == NULL) {
 			kfree(root_ht);
 			return -ENOBUFS;
@@ -933,7 +933,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 			NL_SET_ERR_MSG_MOD(extack, "Divisor can only be used on a hash table");
 			return -EINVAL;
 		}
-		ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL);
+		ht = kzalloc(struct_size(ht, ht, divisor + 1), GFP_KERNEL);
 		if (ht == NULL)
 			return -ENOBUFS;
 		if (handle == 0) {
@@ -1171,7 +1171,6 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
-	int err;
 
 	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack);
 	cls_u32.command = add ?
@@ -1194,13 +1193,9 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 			cls_u32.knode.link_handle = ht->handle;
 	}
 
-	err = tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSU32,
-				    &cls_u32, cb_priv, &n->flags,
-				    &n->in_hw_count);
-	if (err)
-		return err;
-
-	return 0;
+	return tc_setup_cb_reoffload(block, tp, add, cb, TC_SETUP_CLSU32,
+				     &cls_u32, cb_priv, &n->flags,
+				     &n->in_hw_count);
 }
 
 static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c
index a4d09b1fb66a..f17b049ea530 100644
--- a/net/sched/em_cmp.c
+++ b/net/sched/em_cmp.c
@@ -41,7 +41,7 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em,
 		break;
 
 	case TCF_EM_ALIGN_U32:
-		/* Worth checking boundries? The branching seems
+		/* Worth checking boundaries? The branching seems
 		 * to get worse. Visit again.
 		 */
 		val = get_unaligned_be32(ptr);
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 2a76a2f5ed88..6fe4e5cc807c 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -412,7 +412,8 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
 {
 	struct qdisc_rate_table *rtab;
 
-	if (tab == NULL || r->rate == 0 || r->cell_log == 0 ||
+	if (tab == NULL || r->rate == 0 ||
+	    r->cell_log == 0 || r->cell_log >= 32 ||
 	    nla_len(tab) != TC_RTAB_SIZE) {
 		NL_SET_ERR_MSG(extack, "Invalid rate table parameters for searching");
 		return NULL;
@@ -1170,7 +1171,7 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 #ifdef CONFIG_MODULES
 	if (ops == NULL && kind != NULL) {
 		char name[IFNAMSIZ];
-		if (nla_strlcpy(name, kind, IFNAMSIZ) < IFNAMSIZ) {
+		if (nla_strscpy(name, kind, IFNAMSIZ) >= 0) {
 			/* We dropped the RTNL semaphore in order to
 			 * perform the module load.  So, even if we
 			 * succeeded in loading the module we have to
@@ -1943,8 +1944,8 @@ static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl,
 	     chain = tcf_get_next_chain(block, chain)) {
 		struct tcf_proto *tp;
 
-		for (tp = tcf_get_next_proto(chain, NULL, true);
-		     tp; tp = tcf_get_next_proto(chain, tp, true)) {
+		for (tp = tcf_get_next_proto(chain, NULL);
+		     tp; tp = tcf_get_next_proto(chain, tp)) {
 			struct tcf_bind_args arg = {};
 
 			arg.w.fn = tcf_node_bind;
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index 1c281cc81f57..007bd2d9f1ff 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -466,10 +466,10 @@ drop: __maybe_unused
  * non-ATM interfaces.
  */
 
-static void sch_atm_dequeue(unsigned long data)
+static void sch_atm_dequeue(struct tasklet_struct *t)
 {
-	struct Qdisc *sch = (struct Qdisc *)data;
-	struct atm_qdisc_data *p = qdisc_priv(sch);
+	struct atm_qdisc_data *p = from_tasklet(p, t, task);
+	struct Qdisc *sch = qdisc_from_priv(p);
 	struct atm_flow_data *flow;
 	struct sk_buff *skb;
 
@@ -563,7 +563,7 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt,
 	if (err)
 		return err;
 
-	tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch);
+	tasklet_setup(&p->task, sch_atm_dequeue);
 	return 0;
 }
 
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index 2eaac2ff380f..459cc240eda9 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -50,6 +50,7 @@
  *	locredit = max_frame_size * (sendslope / port_transmit_rate)
  */
 
+#include <linux/ethtool.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index bd618b00d319..50f680f03a54 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -362,7 +362,7 @@ static int choke_change(struct Qdisc *sch, struct nlattr *opt,
 
 	ctl = nla_data(tb[TCA_CHOKE_PARMS]);
 
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog))
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
 		return -EINVAL;
 
 	if (ctl->limit > CHOKE_MAX_QUEUE)
diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c
index 4dda15588cf4..949163fe68af 100644
--- a/net/sched/sch_fq_pie.c
+++ b/net/sched/sch_fq_pie.c
@@ -401,6 +401,7 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt,
 
 	INIT_LIST_HEAD(&q->new_flows);
 	INIT_LIST_HEAD(&q->old_flows);
+	timer_setup(&q->adapt_timer, fq_pie_timer, 0);
 
 	if (opt) {
 		err = fq_pie_change(sch, opt, extack);
@@ -426,7 +427,6 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt,
 		pie_vars_init(&flow->vars);
 	}
 
-	timer_setup(&q->adapt_timer, fq_pie_timer, 0);
 	mod_timer(&q->adapt_timer, jiffies + HZ / 2);
 
 	return 0;
diff --git a/net/sched/sch_frag.c b/net/sched/sch_frag.c
new file mode 100644
index 000000000000..e1e77d3fb6c0
--- /dev/null
+++ b/net/sched/sch_frag.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/dst.h>
+#include <net/ip.h>
+#include <net/ip6_fib.h>
+
+struct sch_frag_data {
+	unsigned long dst;
+	struct qdisc_skb_cb cb;
+	__be16 inner_protocol;
+	u16 vlan_tci;
+	__be16 vlan_proto;
+	unsigned int l2_len;
+	u8 l2_data[VLAN_ETH_HLEN];
+	int (*xmit)(struct sk_buff *skb);
+};
+
+static DEFINE_PER_CPU(struct sch_frag_data, sch_frag_data_storage);
+
+static int sch_frag_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct sch_frag_data *data = this_cpu_ptr(&sch_frag_data_storage);
+
+	if (skb_cow_head(skb, data->l2_len) < 0) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	__skb_dst_copy(skb, data->dst);
+	*qdisc_skb_cb(skb) = data->cb;
+	skb->inner_protocol = data->inner_protocol;
+	if (data->vlan_tci & VLAN_CFI_MASK)
+		__vlan_hwaccel_put_tag(skb, data->vlan_proto,
+				       data->vlan_tci & ~VLAN_CFI_MASK);
+	else
+		__vlan_hwaccel_clear_tag(skb);
+
+	/* Reconstruct the MAC header.  */
+	skb_push(skb, data->l2_len);
+	memcpy(skb->data, &data->l2_data, data->l2_len);
+	skb_postpush_rcsum(skb, skb->data, data->l2_len);
+	skb_reset_mac_header(skb);
+
+	return data->xmit(skb);
+}
+
+static void sch_frag_prepare_frag(struct sk_buff *skb,
+				  int (*xmit)(struct sk_buff *skb))
+{
+	unsigned int hlen = skb_network_offset(skb);
+	struct sch_frag_data *data;
+
+	data = this_cpu_ptr(&sch_frag_data_storage);
+	data->dst = skb->_skb_refdst;
+	data->cb = *qdisc_skb_cb(skb);
+	data->xmit = xmit;
+	data->inner_protocol = skb->inner_protocol;
+	if (skb_vlan_tag_present(skb))
+		data->vlan_tci = skb_vlan_tag_get(skb) | VLAN_CFI_MASK;
+	else
+		data->vlan_tci = 0;
+	data->vlan_proto = skb->vlan_proto;
+	data->l2_len = hlen;
+	memcpy(&data->l2_data, skb->data, hlen);
+
+	memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
+	skb_pull(skb, hlen);
+}
+
+static unsigned int
+sch_frag_dst_get_mtu(const struct dst_entry *dst)
+{
+	return dst->dev->mtu;
+}
+
+static struct dst_ops sch_frag_dst_ops = {
+	.family = AF_UNSPEC,
+	.mtu = sch_frag_dst_get_mtu,
+};
+
+static int sch_fragment(struct net *net, struct sk_buff *skb,
+			u16 mru, int (*xmit)(struct sk_buff *skb))
+{
+	int ret = -1;
+
+	if (skb_network_offset(skb) > VLAN_ETH_HLEN) {
+		net_warn_ratelimited("L2 header too long to fragment\n");
+		goto err;
+	}
+
+	if (skb_protocol(skb, true) == htons(ETH_P_IP)) {
+		struct dst_entry sch_frag_dst;
+		unsigned long orig_dst;
+
+		sch_frag_prepare_frag(skb, xmit);
+		dst_init(&sch_frag_dst, &sch_frag_dst_ops, NULL, 1,
+			 DST_OBSOLETE_NONE, DST_NOCOUNT);
+		sch_frag_dst.dev = skb->dev;
+
+		orig_dst = skb->_skb_refdst;
+		skb_dst_set_noref(skb, &sch_frag_dst);
+		IPCB(skb)->frag_max_size = mru;
+
+		ret = ip_do_fragment(net, skb->sk, skb, sch_frag_xmit);
+		refdst_drop(orig_dst);
+	} else if (skb_protocol(skb, true) == htons(ETH_P_IPV6)) {
+		unsigned long orig_dst;
+		struct rt6_info sch_frag_rt;
+
+		sch_frag_prepare_frag(skb, xmit);
+		memset(&sch_frag_rt, 0, sizeof(sch_frag_rt));
+		dst_init(&sch_frag_rt.dst, &sch_frag_dst_ops, NULL, 1,
+			 DST_OBSOLETE_NONE, DST_NOCOUNT);
+		sch_frag_rt.dst.dev = skb->dev;
+
+		orig_dst = skb->_skb_refdst;
+		skb_dst_set_noref(skb, &sch_frag_rt.dst);
+		IP6CB(skb)->frag_max_size = mru;
+
+		ret = ipv6_stub->ipv6_fragment(net, skb->sk, skb,
+					       sch_frag_xmit);
+		refdst_drop(orig_dst);
+	} else {
+		net_warn_ratelimited("Fail frag %s: eth=%x, MRU=%d, MTU=%d\n",
+				     netdev_name(skb->dev),
+				     ntohs(skb_protocol(skb, true)), mru,
+				     skb->dev->mtu);
+		goto err;
+	}
+
+	return ret;
+err:
+	kfree_skb(skb);
+	return ret;
+}
+
+int sch_frag_xmit_hook(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb))
+{
+	u16 mru = qdisc_skb_cb(skb)->mru;
+	int err;
+
+	if (mru && skb->len > mru + skb->dev->hard_header_len)
+		err = sch_fragment(dev_net(skb->dev), skb, mru, xmit);
+	else
+		err = xmit(skb);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(sch_frag_xmit_hook);
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 54c417244642..49eae93d1489 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -802,9 +802,8 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 			  const struct Qdisc_ops *ops,
 			  struct netlink_ext_ack *extack)
 {
-	void *p;
 	struct Qdisc *sch;
-	unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
+	unsigned int size = sizeof(*sch) + ops->priv_size;
 	int err = -ENOBUFS;
 	struct net_device *dev;
 
@@ -815,22 +814,10 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	}
 
 	dev = dev_queue->dev;
-	p = kzalloc_node(size, GFP_KERNEL,
-			 netdev_queue_numa_node_read(dev_queue));
+	sch = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue));
 
-	if (!p)
+	if (!sch)
 		goto errout;
-	sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
-	/* if we got non aligned memory, ask more and do alignment ourself */
-	if (sch != p) {
-		kfree(p);
-		p = kzalloc_node(size + QDISC_ALIGNTO - 1, GFP_KERNEL,
-				 netdev_queue_numa_node_read(dev_queue));
-		if (!p)
-			goto errout;
-		sch = (struct Qdisc *) QDISC_ALIGN((unsigned long) p);
-		sch->padded = (char *) sch - (char *) p;
-	}
 	__skb_queue_head_init(&sch->gso_skb);
 	__skb_queue_head_init(&sch->skb_bad_txq);
 	qdisc_skb_head_init(&sch->q);
@@ -873,7 +860,7 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 
 	return sch;
 errout1:
-	kfree(p);
+	kfree(sch);
 errout:
 	return ERR_PTR(err);
 }
@@ -941,7 +928,7 @@ void qdisc_free(struct Qdisc *qdisc)
 		free_percpu(qdisc->cpu_qstats);
 	}
 
-	kfree((char *) qdisc - qdisc->padded);
+	kfree(qdisc);
 }
 
 static void qdisc_free_cb(struct rcu_head *head)
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index 8599c6f31b05..e0bc77533acc 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -480,7 +480,7 @@ static inline int gred_change_vq(struct Qdisc *sch, int dp,
 	struct gred_sched *table = qdisc_priv(sch);
 	struct gred_sched_data *q = table->tab[dp];
 
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog)) {
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log)) {
 		NL_SET_ERR_MSG_MOD(extack, "invalid RED parameters");
 		return -EINVAL;
 	}
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 84f82771cdf5..0c345e43a09a 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -330,7 +330,7 @@ static s64 tabledist(s64 mu, s32 sigma,
 
 	/* default uniform distribution */
 	if (dist == NULL)
-		return ((rnd % (2 * sigma)) + mu) - sigma;
+		return ((rnd % (2 * (u32)sigma)) + mu) - sigma;
 
 	t = dist->table[rnd % dist->size];
 	x = (sigma % NETEM_DIST_SCALE) * t;
@@ -812,6 +812,10 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr)
 		q->slot_config.max_packets = INT_MAX;
 	if (q->slot_config.max_bytes == 0)
 		q->slot_config.max_bytes = INT_MAX;
+
+	/* capping dist_jitter to the range acceptable by tabledist() */
+	q->slot_config.dist_jitter = min_t(__s64, INT_MAX, abs(q->slot_config.dist_jitter));
+
 	q->slot.packets_left = q->slot_config.max_packets;
 	q->slot.bytes_left = q->slot_config.max_bytes;
 	if (q->slot_config.min_delay | q->slot_config.max_delay |
@@ -1037,6 +1041,9 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_NETEM_SLOT])
 		get_slot(q, tb[TCA_NETEM_SLOT]);
 
+	/* capping jitter to the range acceptable by tabledist() */
+	q->jitter = min_t(s64, abs(q->jitter), INT_MAX);
+
 	return ret;
 
 get_table_failure:
diff --git a/net/sched/sch_pie.c b/net/sched/sch_pie.c
index c65077f0c0f3..5a457ff61acd 100644
--- a/net/sched/sch_pie.c
+++ b/net/sched/sch_pie.c
@@ -405,7 +405,7 @@ void pie_calculate_probability(struct pie_params *params, struct pie_vars *vars,
 	/* We restart the measurement cycle if the following conditions are met
 	 * 1. If the delay has been low for 2 consecutive Tupdate periods
 	 * 2. Calculated drop probability is zero
-	 * 3. If average dq_rate_estimator is enabled, we have atleast one
+	 * 3. If average dq_rate_estimator is enabled, we have at least one
 	 *    estimate for the avg_dq_rate ie., is a non-zero value
 	 */
 	if ((vars->qdelay < params->target / 2) &&
diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c
index e89fab6ccb34..b4ae34d7aa96 100644
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -250,7 +250,7 @@ static int __red_change(struct Qdisc *sch, struct nlattr **tb,
 	max_P = tb[TCA_RED_MAX_P] ? nla_get_u32(tb[TCA_RED_MAX_P]) : 0;
 
 	ctl = nla_data(tb[TCA_RED_PARMS]);
-	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog))
+	if (!red_check_params(ctl->qth_min, ctl->qth_max, ctl->Wlog, ctl->Scell_log))
 		return -EINVAL;
 
 	err = red_get_flags(ctl->flags, TC_RED_HISTORIC_FLAGS,
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index bca2be57d9fc..b25e51440623 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -647,7 +647,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt)
 	}
 
 	if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max,
-					ctl_v1->Wlog))
+					ctl_v1->Wlog, ctl_v1->Scell_log))
 		return -EINVAL;
 	if (ctl_v1 && ctl_v1->qth_min) {
 		p = kmalloc(sizeof(*p), GFP_KERNEL);
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index b0ad7687ee2c..6f775275826a 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -6,6 +6,7 @@
  *
  */
 
+#include <linux/ethtool.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
@@ -1596,6 +1597,22 @@ free_sched:
 	return err;
 }
 
+static void taprio_reset(struct Qdisc *sch)
+{
+	struct taprio_sched *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	int i;
+
+	hrtimer_cancel(&q->advance_timer);
+	if (q->qdiscs) {
+		for (i = 0; i < dev->num_tx_queues; i++)
+			if (q->qdiscs[i])
+				qdisc_reset(q->qdiscs[i]);
+	}
+	sch->qstats.backlog = 0;
+	sch->q.qlen = 0;
+}
+
 static void taprio_destroy(struct Qdisc *sch)
 {
 	struct taprio_sched *q = qdisc_priv(sch);
@@ -1606,12 +1623,11 @@ static void taprio_destroy(struct Qdisc *sch)
 	list_del(&q->taprio_list);
 	spin_unlock(&taprio_list_lock);
 
-	hrtimer_cancel(&q->advance_timer);
 
 	taprio_disable_offload(dev, q, NULL);
 
 	if (q->qdiscs) {
-		for (i = 0; i < dev->num_tx_queues && q->qdiscs[i]; i++)
+		for (i = 0; i < dev->num_tx_queues; i++)
 			qdisc_put(q->qdiscs[i]);
 
 		kfree(q->qdiscs);
@@ -1953,6 +1969,7 @@ static struct Qdisc_ops taprio_qdisc_ops __read_mostly = {
 	.init		= taprio_init,
 	.change		= taprio_change,
 	.destroy	= taprio_destroy,
+	.reset		= taprio_reset,
 	.peek		= taprio_peek,
 	.dequeue	= taprio_dequeue,
 	.enqueue	= taprio_enqueue,
diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
index 39d7fa9569f8..5da599ff84a9 100644
--- a/net/sctp/Kconfig
+++ b/net/sctp/Kconfig
@@ -11,6 +11,7 @@ menuconfig IP_SCTP
 	select CRYPTO_HMAC
 	select CRYPTO_SHA1
 	select LIBCRC32C
+	select NET_UDP_TUNNEL
 	help
 	  Stream Control Transmission Protocol
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 8d735461fa19..336df4b36655 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -99,6 +99,8 @@ static struct sctp_association *sctp_association_init(
 	 */
 	asoc->hbinterval = msecs_to_jiffies(sp->hbinterval);
 
+	asoc->encap_port = sp->encap_port;
+
 	/* Initialize path max retrans value. */
 	asoc->pathmaxrxt = sp->pathmaxrxt;
 
@@ -624,6 +626,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	 */
 	peer->hbinterval = asoc->hbinterval;
 
+	peer->encap_port = asoc->encap_port;
+
 	/* Set the path max_retrans.  */
 	peer->pathmaxrxt = asoc->pathmaxrxt;
 
@@ -1351,7 +1355,7 @@ static void sctp_select_active_and_retran_path(struct sctp_association *asoc)
 	}
 
 	/* We did not find anything useful for a possible retransmission
-	 * path; either primary path that we found is the the same as
+	 * path; either primary path that we found is the same as
 	 * the current one, or we didn't generally find an active one.
 	 */
 	if (trans_sec == NULL)
@@ -1537,7 +1541,7 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len)
 
 	/* If we've reached or overflowed our receive buffer, announce
 	 * a 0 rwnd if rwnd would still be positive.  Store the
-	 * the potential pressure overflow so that the window can be restored
+	 * potential pressure overflow so that the window can be restored
 	 * back to original value.
 	 */
 	if (rx_count >= asoc->base.sk->sk_rcvbuf)
diff --git a/net/sctp/auth.c b/net/sctp/auth.c
index 7e59d8a18f3e..6f8319b828b0 100644
--- a/net/sctp/auth.c
+++ b/net/sctp/auth.c
@@ -445,7 +445,7 @@ struct sctp_shared_key *sctp_auth_get_shkey(
 }
 
 /*
- * Initialize all the possible digest transforms that we can use.  Right now
+ * Initialize all the possible digest transforms that we can use.  Right
  * now, the supported digests are SHA1 and SHA256.  We do this here once
  * because of the restrictiong that transforms may only be allocated in
  * user context.  This forces us to pre-allocated all possible transforms
@@ -811,7 +811,7 @@ int sctp_auth_ep_set_hmacs(struct sctp_endpoint *ep,
 }
 
 /* Set a new shared key on either endpoint or association.  If the
- * the key with a same ID already exists, replace the key (remove the
+ * key with a same ID already exists, replace the key (remove the
  * old key and add a new one).
  */
 int sctp_auth_set_key(struct sctp_endpoint *ep,
diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c
index 701c5a4e441d..53e5ed79f63f 100644
--- a/net/sctp/bind_addr.c
+++ b/net/sctp/bind_addr.c
@@ -505,7 +505,7 @@ int sctp_in_scope(struct net *net, const union sctp_addr *addr,
 		return 0;
 	/*
 	 * For INIT and INIT-ACK address list, let L be the level of
-	 * of requested destination address, sender and receiver
+	 * requested destination address, sender and receiver
 	 * SHOULD include all of its addresses with level greater
 	 * than or equal to L.
 	 *
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index ab6a997e222f..fd4f8243cc35 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -179,7 +179,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc,
 				    __func__, asoc, max_data);
 	}
 
-	/* If the the peer requested that we authenticate DATA chunks
+	/* If the peer requested that we authenticate DATA chunks
 	 * we need to account for bundling of the AUTH chunks along with
 	 * DATA.
 	 */
diff --git a/net/sctp/input.c b/net/sctp/input.c
index 55d4fc6f371d..d508f6f3dd08 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -449,7 +449,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk,
 		else {
 			if (!mod_timer(&t->proto_unreach_timer,
 						jiffies + (HZ/20)))
-				sctp_association_hold(asoc);
+				sctp_transport_hold(t);
 		}
 	} else {
 		struct net *net = sock_net(sk);
@@ -458,7 +458,7 @@ void sctp_icmp_proto_unreachable(struct sock *sk,
 			 "encountered!\n", __func__);
 
 		if (del_timer(&t->proto_unreach_timer))
-			sctp_association_put(asoc);
+			sctp_transport_put(t);
 
 		sctp_do_sm(net, SCTP_EVENT_T_OTHER,
 			   SCTP_ST_OTHER(SCTP_EVENT_ICMP_PROTO_UNREACH),
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 8a58f42d6d19..c3e89c776e66 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -55,6 +55,7 @@
 #include <net/inet_common.h>
 #include <net/inet_ecn.h>
 #include <net/sctp/sctp.h>
+#include <net/udp_tunnel.h>
 
 #include <linux/uaccess.h>
 
@@ -191,33 +192,53 @@ out:
 	return ret;
 }
 
-static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
+static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *t)
 {
+	struct dst_entry *dst = dst_clone(t->dst);
+	struct flowi6 *fl6 = &t->fl.u.ip6;
 	struct sock *sk = skb->sk;
 	struct ipv6_pinfo *np = inet6_sk(sk);
-	struct flowi6 *fl6 = &transport->fl.u.ip6;
 	__u8 tclass = np->tclass;
-	int res;
+	__be32 label;
 
 	pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb,
 		 skb->len, &fl6->saddr, &fl6->daddr);
 
-	if (transport->dscp & SCTP_DSCP_SET_MASK)
-		tclass = transport->dscp & SCTP_DSCP_VAL_MASK;
+	if (t->dscp & SCTP_DSCP_SET_MASK)
+		tclass = t->dscp & SCTP_DSCP_VAL_MASK;
 
 	if (INET_ECN_is_capable(tclass))
 		IP6_ECN_flow_xmit(sk, fl6->flowlabel);
 
-	if (!(transport->param_flags & SPP_PMTUD_ENABLE))
+	if (!(t->param_flags & SPP_PMTUD_ENABLE))
 		skb->ignore_df = 1;
 
 	SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
 
-	rcu_read_lock();
-	res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
-		       tclass, sk->sk_priority);
-	rcu_read_unlock();
-	return res;
+	if (!t->encap_port || !sctp_sk(sk)->udp_port) {
+		int res;
+
+		skb_dst_set(skb, dst);
+		rcu_read_lock();
+		res = ip6_xmit(sk, skb, fl6, sk->sk_mark,
+			       rcu_dereference(np->opt),
+			       tclass, sk->sk_priority);
+		rcu_read_unlock();
+		return res;
+	}
+
+	if (skb_is_gso(skb))
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+
+	skb->encapsulation = 1;
+	skb_reset_inner_mac_header(skb);
+	skb_reset_inner_transport_header(skb);
+	skb_set_inner_ipproto(skb, IPPROTO_SCTP);
+	label = ip6_make_flowlabel(sock_net(sk), skb, fl6->flowlabel, true, fl6);
+
+	return udp_tunnel6_xmit_skb(dst, sk, skb, NULL, &fl6->saddr,
+				    &fl6->daddr, tclass, ip6_dst_hoplimit(dst),
+				    label, sctp_sk(sk)->udp_port, t->encap_port, false);
 }
 
 /* Returns the dst cache entry for the given source and destination ip
@@ -1053,6 +1074,7 @@ static struct inet_protosw sctpv6_stream_protosw = {
 
 static int sctp6_rcv(struct sk_buff *skb)
 {
+	SCTP_INPUT_CB(skb)->encap_port = 0;
 	return sctp_rcv(skb) ? -1 : 0;
 }
 
diff --git a/net/sctp/offload.c b/net/sctp/offload.c
index 74847d613835..ce281a9a2875 100644
--- a/net/sctp/offload.c
+++ b/net/sctp/offload.c
@@ -27,7 +27,11 @@ static __le32 sctp_gso_make_checksum(struct sk_buff *skb)
 {
 	skb->ip_summed = CHECKSUM_NONE;
 	skb->csum_not_inet = 0;
-	gso_reset_checksum(skb, ~0);
+	/* csum and csum_start in GSO CB may be needed to do the UDP
+	 * checksum when it's a UDP tunneling packet.
+	 */
+	SKB_GSO_CB(skb)->csum = (__force __wsum)~0;
+	SKB_GSO_CB(skb)->csum_start = skb_headroom(skb) + skb->len;
 	return sctp_compute_cksum(skb, skb_transport_offset(skb));
 }
 
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 1441eaf460bb..6614c9fdc51e 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -508,20 +508,14 @@ merge:
 					sizeof(struct inet6_skb_parm)));
 		skb_shinfo(head)->gso_segs = pkt_count;
 		skb_shinfo(head)->gso_size = GSO_BY_FRAGS;
-		rcu_read_lock();
-		if (skb_dst(head) != tp->dst) {
-			dst_hold(tp->dst);
-			sk_setup_caps(sk, tp->dst);
-		}
-		rcu_read_unlock();
 		goto chksum;
 	}
 
 	if (sctp_checksum_disable)
 		return 1;
 
-	if (!(skb_dst(head)->dev->features & NETIF_F_SCTP_CRC) ||
-	    dst_xfrm(skb_dst(head)) || packet->ipfragok) {
+	if (!(tp->dst->dev->features & NETIF_F_SCTP_CRC) ||
+	    dst_xfrm(tp->dst) || packet->ipfragok || tp->encap_port) {
 		struct sctphdr *sh =
 			(struct sctphdr *)skb_transport_header(head);
 
@@ -548,7 +542,6 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	struct sctp_association *asoc = tp->asoc;
 	struct sctp_chunk *chunk, *tmp;
 	int pkt_count, gso = 0;
-	struct dst_entry *dst;
 	struct sk_buff *head;
 	struct sctphdr *sh;
 	struct sock *sk;
@@ -585,13 +578,18 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	sh->checksum = 0;
 
 	/* drop packet if no dst */
-	dst = dst_clone(tp->dst);
-	if (!dst) {
+	if (!tp->dst) {
 		IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES);
 		kfree_skb(head);
 		goto out;
 	}
-	skb_dst_set(head, dst);
+
+	rcu_read_lock();
+	if (__sk_dst_get(sk) != tp->dst) {
+		dst_hold(tp->dst);
+		sk_setup_caps(sk, tp->dst);
+	}
+	rcu_read_unlock();
 
 	/* pack up chunks */
 	pkt_count = sctp_packet_pack(packet, head, gso, gfp);
diff --git a/net/sctp/proc.c b/net/sctp/proc.c
index f7da88ae20a5..982a87b3e11f 100644
--- a/net/sctp/proc.c
+++ b/net/sctp/proc.c
@@ -215,6 +215,12 @@ static void sctp_transport_seq_stop(struct seq_file *seq, void *v)
 {
 	struct sctp_ht_iter *iter = seq->private;
 
+	if (v && v != SEQ_START_TOKEN) {
+		struct sctp_transport *transport = v;
+
+		sctp_transport_put(transport);
+	}
+
 	sctp_transport_walk_stop(&iter->hti);
 }
 
@@ -222,6 +228,12 @@ static void *sctp_transport_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	struct sctp_ht_iter *iter = seq->private;
 
+	if (v && v != SEQ_START_TOKEN) {
+		struct sctp_transport *transport = v;
+
+		sctp_transport_put(transport);
+	}
+
 	++*pos;
 
 	return sctp_transport_get_next(seq_file_net(seq), &iter->hti);
@@ -277,8 +289,6 @@ static int sctp_assocs_seq_show(struct seq_file *seq, void *v)
 		sk->sk_rcvbuf);
 	seq_printf(seq, "\n");
 
-	sctp_transport_put(transport);
-
 	return 0;
 }
 
@@ -354,8 +364,6 @@ static int sctp_remaddr_seq_show(struct seq_file *seq, void *v)
 		seq_printf(seq, "\n");
 	}
 
-	sctp_transport_put(transport);
-
 	return 0;
 }
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index d19db22262fd..6f2bbfeec3a4 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -44,6 +44,7 @@
 #include <net/addrconf.h>
 #include <net/inet_common.h>
 #include <net/inet_ecn.h>
+#include <net/udp_tunnel.h>
 
 #define MAX_SCTP_PORT_HASH_ENTRIES (64 * 1024)
 
@@ -372,7 +373,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
  * Level 3 - private addresses.
  * Level 4 - global addresses
  * For INIT and INIT-ACK address list, let L be the level of
- * of requested destination address, sender and receiver
+ * requested destination address, sender and receiver
  * SHOULD include all of its addresses with level greater
  * than or equal to L.
  *
@@ -840,6 +841,92 @@ static int sctp_ctl_sock_init(struct net *net)
 	return 0;
 }
 
+static int sctp_udp_rcv(struct sock *sk, struct sk_buff *skb)
+{
+	SCTP_INPUT_CB(skb)->encap_port = udp_hdr(skb)->source;
+
+	skb_set_transport_header(skb, sizeof(struct udphdr));
+	sctp_rcv(skb);
+	return 0;
+}
+
+static int sctp_udp_err_lookup(struct sock *sk, struct sk_buff *skb)
+{
+	struct sctp_association *asoc;
+	struct sctp_transport *t;
+	int family;
+
+	skb->transport_header += sizeof(struct udphdr);
+	family = (ip_hdr(skb)->version == 4) ? AF_INET : AF_INET6;
+	sk = sctp_err_lookup(dev_net(skb->dev), family, skb, sctp_hdr(skb),
+			     &asoc, &t);
+	if (!sk)
+		return -ENOENT;
+
+	sctp_err_finish(sk, t);
+	return 0;
+}
+
+int sctp_udp_sock_start(struct net *net)
+{
+	struct udp_tunnel_sock_cfg tuncfg = {NULL};
+	struct udp_port_cfg udp_conf = {0};
+	struct socket *sock;
+	int err;
+
+	udp_conf.family = AF_INET;
+	udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
+	udp_conf.local_udp_port = htons(net->sctp.udp_port);
+	err = udp_sock_create(net, &udp_conf, &sock);
+	if (err) {
+		pr_err("Failed to create the SCTP UDP tunneling v4 sock\n");
+		return err;
+	}
+
+	tuncfg.encap_type = 1;
+	tuncfg.encap_rcv = sctp_udp_rcv;
+	tuncfg.encap_err_lookup = sctp_udp_err_lookup;
+	setup_udp_tunnel_sock(net, sock, &tuncfg);
+	net->sctp.udp4_sock = sock->sk;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	memset(&udp_conf, 0, sizeof(udp_conf));
+
+	udp_conf.family = AF_INET6;
+	udp_conf.local_ip6 = in6addr_any;
+	udp_conf.local_udp_port = htons(net->sctp.udp_port);
+	udp_conf.use_udp6_rx_checksums = true;
+	udp_conf.ipv6_v6only = true;
+	err = udp_sock_create(net, &udp_conf, &sock);
+	if (err) {
+		pr_err("Failed to create the SCTP UDP tunneling v6 sock\n");
+		udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+		net->sctp.udp4_sock = NULL;
+		return err;
+	}
+
+	tuncfg.encap_type = 1;
+	tuncfg.encap_rcv = sctp_udp_rcv;
+	tuncfg.encap_err_lookup = sctp_udp_err_lookup;
+	setup_udp_tunnel_sock(net, sock, &tuncfg);
+	net->sctp.udp6_sock = sock->sk;
+#endif
+
+	return 0;
+}
+
+void sctp_udp_sock_stop(struct net *net)
+{
+	if (net->sctp.udp4_sock) {
+		udp_tunnel_sock_release(net->sctp.udp4_sock->sk_socket);
+		net->sctp.udp4_sock = NULL;
+	}
+	if (net->sctp.udp6_sock) {
+		udp_tunnel_sock_release(net->sctp.udp6_sock->sk_socket);
+		net->sctp.udp6_sock = NULL;
+	}
+}
+
 /* Register address family specific functions. */
 int sctp_register_af(struct sctp_af *af)
 {
@@ -971,25 +1058,44 @@ static int sctp_inet_supported_addrs(const struct sctp_sock *opt,
 }
 
 /* Wrapper routine that calls the ip transmit routine. */
-static inline int sctp_v4_xmit(struct sk_buff *skb,
-			       struct sctp_transport *transport)
+static inline int sctp_v4_xmit(struct sk_buff *skb, struct sctp_transport *t)
 {
-	struct inet_sock *inet = inet_sk(skb->sk);
+	struct dst_entry *dst = dst_clone(t->dst);
+	struct flowi4 *fl4 = &t->fl.u.ip4;
+	struct sock *sk = skb->sk;
+	struct inet_sock *inet = inet_sk(sk);
 	__u8 dscp = inet->tos;
+	__be16 df = 0;
 
 	pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
-		 skb->len, &transport->fl.u.ip4.saddr,
-		 &transport->fl.u.ip4.daddr);
+		 skb->len, &fl4->saddr, &fl4->daddr);
 
-	if (transport->dscp & SCTP_DSCP_SET_MASK)
-		dscp = transport->dscp & SCTP_DSCP_VAL_MASK;
+	if (t->dscp & SCTP_DSCP_SET_MASK)
+		dscp = t->dscp & SCTP_DSCP_VAL_MASK;
+
+	inet->pmtudisc = t->param_flags & SPP_PMTUD_ENABLE ? IP_PMTUDISC_DO
+							   : IP_PMTUDISC_DONT;
+	SCTP_INC_STATS(sock_net(sk), SCTP_MIB_OUTSCTPPACKS);
 
-	inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
-			 IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
+	if (!t->encap_port || !sctp_sk(sk)->udp_port) {
+		skb_dst_set(skb, dst);
+		return __ip_queue_xmit(sk, skb, &t->fl, dscp);
+	}
 
-	SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS);
+	if (skb_is_gso(skb))
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
 
-	return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp);
+	if (ip_dont_fragment(sk, dst) && !skb->ignore_df)
+		df = htons(IP_DF);
+
+	skb->encapsulation = 1;
+	skb_reset_inner_mac_header(skb);
+	skb_reset_inner_transport_header(skb);
+	skb_set_inner_ipproto(skb, IPPROTO_SCTP);
+	udp_tunnel_xmit_skb((struct rtable *)dst, sk, skb, fl4->saddr,
+			    fl4->daddr, dscp, ip4_dst_hoplimit(dst), df,
+			    sctp_sk(sk)->udp_port, t->encap_port, false, false);
+	return 0;
 }
 
 static struct sctp_af sctp_af_inet;
@@ -1054,9 +1160,15 @@ static struct inet_protosw sctp_stream_protosw = {
 	.flags      = SCTP_PROTOSW_FLAG
 };
 
+static int sctp4_rcv(struct sk_buff *skb)
+{
+	SCTP_INPUT_CB(skb)->encap_port = 0;
+	return sctp_rcv(skb);
+}
+
 /* Register with IP layer.  */
 static const struct net_protocol sctp_protocol = {
-	.handler     = sctp_rcv,
+	.handler     = sctp4_rcv,
 	.err_handler = sctp_v4_err,
 	.no_policy   = 1,
 	.netns_ok    = 1,
@@ -1271,6 +1383,12 @@ static int __net_init sctp_defaults_init(struct net *net)
 	/* Enable ECN by default. */
 	net->sctp.ecn_enable = 1;
 
+	/* Set UDP tunneling listening port to 0 by default */
+	net->sctp.udp_port = 0;
+
+	/* Set remote encap port to 0 by default */
+	net->sctp.encap_port = 0;
+
 	/* Set SCOPE policy to enabled */
 	net->sctp.scope_policy = SCTP_SCOPE_POLICY_ENABLE;
 
@@ -1483,10 +1601,10 @@ static __init int sctp_init(void)
 	num_entries = (1UL << order) * PAGE_SIZE /
 		      sizeof(struct sctp_bind_hashbucket);
 
-	/* And finish by rounding it down to the nearest power of two
-	 * this wastes some memory of course, but its needed because
+	/* And finish by rounding it down to the nearest power of two.
+	 * This wastes some memory of course, but it's needed because
 	 * the hash function operates based on the assumption that
-	 * that the number of entries is a power of two
+	 * the number of entries is a power of two.
 	 */
 	sctp_port_hashsize = rounddown_pow_of_two(num_entries);
 
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index c11c24524652..f77484df097b 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -1142,6 +1142,26 @@ nodata:
 	return retval;
 }
 
+struct sctp_chunk *sctp_make_new_encap_port(const struct sctp_association *asoc,
+					    const struct sctp_chunk *chunk)
+{
+	struct sctp_new_encap_port_hdr nep;
+	struct sctp_chunk *retval;
+
+	retval = sctp_make_abort(asoc, chunk,
+				 sizeof(struct sctp_errhdr) + sizeof(nep));
+	if (!retval)
+		goto nodata;
+
+	sctp_init_cause(retval, SCTP_ERROR_NEW_ENCAP_PORT, sizeof(nep));
+	nep.cur_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
+	nep.new_port = chunk->transport->encap_port;
+	sctp_addto_chunk(retval, sizeof(nep), &nep);
+
+nodata:
+	return retval;
+}
+
 /* Make a HEARTBEAT chunk.  */
 struct sctp_chunk *sctp_make_heartbeat(const struct sctp_association *asoc,
 				       const struct sctp_transport *transport)
@@ -1235,7 +1255,7 @@ nodata:
 
 /* Create an Operation Error chunk of a fixed size, specifically,
  * min(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - overheads.
- * This is a helper function to allocate an error chunk for for those
+ * This is a helper function to allocate an error chunk for those
  * invalid parameter codes in which we may not want to report all the
  * errors, if the incoming chunk is large. If it can't fit in a single
  * packet, we ignore it.
@@ -1780,7 +1800,7 @@ no_hmac:
 	 * for init collision case of lost COOKIE ACK.
 	 * If skb has been timestamped, then use the stamp, otherwise
 	 * use current time.  This introduces a small possibility that
-	 * that a cookie may be considered expired, but his would only slow
+	 * a cookie may be considered expired, but this would only slow
 	 * down the new association establishment instead of every packet.
 	 */
 	if (sock_flag(ep->base.sk, SOCK_TIMESTAMP))
@@ -2319,8 +2339,9 @@ int sctp_process_init(struct sctp_association *asoc, struct sctp_chunk *chunk,
 
 	/* This implementation defaults to making the first transport
 	 * added as the primary transport.  The source address seems to
-	 * be a a better choice than any of the embedded addresses.
+	 * be a better choice than any of the embedded addresses.
 	 */
+	asoc->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
 	if (!sctp_assoc_add_peer(asoc, peer_addr, gfp, SCTP_ACTIVE))
 		goto nomem;
 
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index aa821e71f05e..0948f14ce221 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -419,7 +419,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t)
 		/* Try again later.  */
 		if (!mod_timer(&transport->proto_unreach_timer,
 				jiffies + (HZ/20)))
-			sctp_association_hold(asoc);
+			sctp_transport_hold(transport);
 		goto out_unlock;
 	}
 
@@ -435,7 +435,7 @@ void sctp_generate_proto_unreach_event(struct timer_list *t)
 
 out_unlock:
 	bh_unlock_sock(sk);
-	sctp_association_put(asoc);
+	sctp_transport_put(transport);
 }
 
  /* Handle the timeout of the RE-CONFIG timer. */
@@ -1601,12 +1601,12 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type,
 			break;
 
 		case SCTP_CMD_INIT_FAILED:
-			sctp_cmd_init_failed(commands, asoc, cmd->obj.u32);
+			sctp_cmd_init_failed(commands, asoc, cmd->obj.u16);
 			break;
 
 		case SCTP_CMD_ASSOC_FAILED:
 			sctp_cmd_assoc_failed(commands, asoc, event_type,
-					      subtype, chunk, cmd->obj.u32);
+					      subtype, chunk, cmd->obj.u16);
 			break;
 
 		case SCTP_CMD_INIT_COUNTER_INC:
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index c669f8bd1eab..af2b7041fa4e 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -87,6 +87,13 @@ static enum sctp_disposition sctp_sf_tabort_8_4_8(
 					const union sctp_subtype type,
 					void *arg,
 					struct sctp_cmd_seq *commands);
+static enum sctp_disposition sctp_sf_new_encap_port(
+					struct net *net,
+					const struct sctp_endpoint *ep,
+					const struct sctp_association *asoc,
+					const union sctp_subtype type,
+					void *arg,
+					struct sctp_cmd_seq *commands);
 static struct sctp_sackhdr *sctp_sm_pull_sack(struct sctp_chunk *chunk);
 
 static enum sctp_disposition sctp_stop_t1_and_abort(
@@ -1493,6 +1500,10 @@ static enum sctp_disposition sctp_sf_do_unexpected_init(
 	if (!sctp_chunk_length_valid(chunk, sizeof(struct sctp_init_chunk)))
 		return sctp_sf_violation_chunklen(net, ep, asoc, type, arg,
 						  commands);
+
+	if (SCTP_INPUT_CB(chunk->skb)->encap_port != chunk->transport->encap_port)
+		return sctp_sf_new_encap_port(net, ep, asoc, type, arg, commands);
+
 	/* Grab the INIT header.  */
 	chunk->subh.init_hdr = (struct sctp_inithdr *)chunk->skb->data;
 
@@ -3392,6 +3403,45 @@ static enum sctp_disposition sctp_sf_tabort_8_4_8(
 
 	sctp_packet_append_chunk(packet, abort);
 
+	sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT, SCTP_PACKET(packet));
+
+	SCTP_INC_STATS(net, SCTP_MIB_OUTCTRLCHUNKS);
+
+	sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+	return SCTP_DISPOSITION_CONSUME;
+}
+
+/* Handling of SCTP Packets Containing an INIT Chunk Matching an
+ * Existing Associations when the UDP encap port is incorrect.
+ *
+ * From Section 4 at draft-tuexen-tsvwg-sctp-udp-encaps-cons-03.
+ */
+static enum sctp_disposition sctp_sf_new_encap_port(
+					struct net *net,
+					const struct sctp_endpoint *ep,
+					const struct sctp_association *asoc,
+					const union sctp_subtype type,
+					void *arg,
+					struct sctp_cmd_seq *commands)
+{
+	struct sctp_packet *packet = NULL;
+	struct sctp_chunk *chunk = arg;
+	struct sctp_chunk *abort;
+
+	packet = sctp_ootb_pkt_new(net, asoc, chunk);
+	if (!packet)
+		return SCTP_DISPOSITION_NOMEM;
+
+	abort = sctp_make_new_encap_port(asoc, chunk);
+	if (!abort) {
+		sctp_ootb_pkt_free(packet);
+		return SCTP_DISPOSITION_NOMEM;
+	}
+
+	abort->skb->sk = ep->base.sk;
+
+	sctp_packet_append_chunk(packet, abort);
+
 	sctp_add_cmd_sf(commands, SCTP_CMD_SEND_PKT,
 			SCTP_PACKET(packet));
 
@@ -6268,6 +6318,8 @@ static struct sctp_packet *sctp_ootb_pkt_new(
 	if (!transport)
 		goto nomem;
 
+	transport->encap_port = SCTP_INPUT_CB(chunk->skb)->encap_port;
+
 	/* Cache a route for the transport with the chunk's destination as
 	 * the source address.
 	 */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 53d0a4161df3..a710917c5ac7 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4417,6 +4417,55 @@ out:
 	return retval;
 }
 
+static int sctp_setsockopt_encap_port(struct sock *sk,
+				      struct sctp_udpencaps *encap,
+				      unsigned int optlen)
+{
+	struct sctp_association *asoc;
+	struct sctp_transport *t;
+	__be16 encap_port;
+
+	if (optlen != sizeof(*encap))
+		return -EINVAL;
+
+	/* If an address other than INADDR_ANY is specified, and
+	 * no transport is found, then the request is invalid.
+	 */
+	encap_port = (__force __be16)encap->sue_port;
+	if (!sctp_is_any(sk, (union sctp_addr *)&encap->sue_address)) {
+		t = sctp_addr_id2transport(sk, &encap->sue_address,
+					   encap->sue_assoc_id);
+		if (!t)
+			return -EINVAL;
+
+		t->encap_port = encap_port;
+		return 0;
+	}
+
+	/* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the
+	 * socket is a one to many style socket, and an association
+	 * was not found, then the id was invalid.
+	 */
+	asoc = sctp_id2assoc(sk, encap->sue_assoc_id);
+	if (!asoc && encap->sue_assoc_id != SCTP_FUTURE_ASSOC &&
+	    sctp_style(sk, UDP))
+		return -EINVAL;
+
+	/* If changes are for association, also apply encap_port to
+	 * each transport.
+	 */
+	if (asoc) {
+		list_for_each_entry(t, &asoc->peer.transport_addr_list,
+				    transports)
+			t->encap_port = encap_port;
+
+		return 0;
+	}
+
+	sctp_sk(sk)->encap_port = encap_port;
+	return 0;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4636,6 +4685,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 	case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
 		retval = sctp_setsockopt_pf_expose(sk, kopt, optlen);
 		break;
+	case SCTP_REMOTE_UDP_ENCAPS_PORT:
+		retval = sctp_setsockopt_encap_port(sk, kopt, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -4876,6 +4928,8 @@ static int sctp_init_sock(struct sock *sk)
 	 * be modified via SCTP_PEER_ADDR_PARAMS
 	 */
 	sp->hbinterval  = net->sctp.hb_interval;
+	sp->udp_port    = htons(net->sctp.udp_port);
+	sp->encap_port  = htons(net->sctp.encap_port);
 	sp->pathmaxrxt  = net->sctp.max_retrans_path;
 	sp->pf_retrans  = net->sctp.pf_retrans;
 	sp->ps_retrans  = net->sctp.ps_retrans;
@@ -7790,6 +7844,65 @@ out:
 	return retval;
 }
 
+static int sctp_getsockopt_encap_port(struct sock *sk, int len,
+				      char __user *optval, int __user *optlen)
+{
+	struct sctp_association *asoc;
+	struct sctp_udpencaps encap;
+	struct sctp_transport *t;
+	__be16 encap_port;
+
+	if (len < sizeof(encap))
+		return -EINVAL;
+
+	len = sizeof(encap);
+	if (copy_from_user(&encap, optval, len))
+		return -EFAULT;
+
+	/* If an address other than INADDR_ANY is specified, and
+	 * no transport is found, then the request is invalid.
+	 */
+	if (!sctp_is_any(sk, (union sctp_addr *)&encap.sue_address)) {
+		t = sctp_addr_id2transport(sk, &encap.sue_address,
+					   encap.sue_assoc_id);
+		if (!t) {
+			pr_debug("%s: failed no transport\n", __func__);
+			return -EINVAL;
+		}
+
+		encap_port = t->encap_port;
+		goto out;
+	}
+
+	/* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the
+	 * socket is a one to many style socket, and an association
+	 * was not found, then the id was invalid.
+	 */
+	asoc = sctp_id2assoc(sk, encap.sue_assoc_id);
+	if (!asoc && encap.sue_assoc_id != SCTP_FUTURE_ASSOC &&
+	    sctp_style(sk, UDP)) {
+		pr_debug("%s: failed no association\n", __func__);
+		return -EINVAL;
+	}
+
+	if (asoc) {
+		encap_port = asoc->encap_port;
+		goto out;
+	}
+
+	encap_port = sctp_sk(sk)->encap_port;
+
+out:
+	encap.sue_port = (__force uint16_t)encap_port;
+	if (copy_to_user(optval, &encap, len))
+		return -EFAULT;
+
+	if (put_user(len, optlen))
+		return -EFAULT;
+
+	return 0;
+}
+
 static int sctp_getsockopt(struct sock *sk, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
@@ -8010,6 +8123,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 	case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE:
 		retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen);
 		break;
+	case SCTP_REMOTE_UDP_ENCAPS_PORT:
+		retval = sctp_getsockopt_encap_port(sk, len, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c
index c16c80963e55..e92df779af73 100644
--- a/net/sctp/sysctl.c
+++ b/net/sctp/sysctl.c
@@ -36,6 +36,7 @@ static int rto_alpha_max = 1000;
 static int rto_beta_max = 1000;
 static int pf_expose_max = SCTP_PF_EXPOSE_MAX;
 static int ps_retrans_max = SCTP_PS_RETRANS_MAX;
+static int udp_port_max = 65535;
 
 static unsigned long max_autoclose_min = 0;
 static unsigned long max_autoclose_max =
@@ -48,6 +49,8 @@ static int proc_sctp_do_rto_min(struct ctl_table *ctl, int write,
 				void *buffer, size_t *lenp, loff_t *ppos);
 static int proc_sctp_do_rto_max(struct ctl_table *ctl, int write, void *buffer,
 				size_t *lenp, loff_t *ppos);
+static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write, void *buffer,
+				 size_t *lenp, loff_t *ppos);
 static int proc_sctp_do_alpha_beta(struct ctl_table *ctl, int write,
 				   void *buffer, size_t *lenp, loff_t *ppos);
 static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
@@ -291,6 +294,24 @@ static struct ctl_table sctp_net_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 	{
+		.procname	= "udp_port",
+		.data		= &init_net.sctp.udp_port,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_sctp_do_udp_port,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &udp_port_max,
+	},
+	{
+		.procname	= "encap_port",
+		.data		= &init_net.sctp.encap_port,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &udp_port_max,
+	},
+	{
 		.procname	= "addr_scope_policy",
 		.data		= &init_net.sctp.scope_policy,
 		.maxlen		= sizeof(int),
@@ -477,6 +498,47 @@ static int proc_sctp_do_auth(struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static int proc_sctp_do_udp_port(struct ctl_table *ctl, int write,
+				 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = current->nsproxy->net_ns;
+	unsigned int min = *(unsigned int *)ctl->extra1;
+	unsigned int max = *(unsigned int *)ctl->extra2;
+	struct ctl_table tbl;
+	int ret, new_value;
+
+	memset(&tbl, 0, sizeof(struct ctl_table));
+	tbl.maxlen = sizeof(unsigned int);
+
+	if (write)
+		tbl.data = &new_value;
+	else
+		tbl.data = &net->sctp.udp_port;
+
+	ret = proc_dointvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		struct sock *sk = net->sctp.ctl_sock;
+
+		if (new_value > max || new_value < min)
+			return -EINVAL;
+
+		net->sctp.udp_port = new_value;
+		sctp_udp_sock_stop(net);
+		if (new_value) {
+			ret = sctp_udp_sock_start(net);
+			if (ret)
+				net->sctp.udp_port = 0;
+		}
+
+		/* Update the value in the control socket */
+		lock_sock(sk);
+		sctp_sk(sk)->udp_port = htons(net->sctp.udp_port);
+		release_sock(sk);
+	}
+
+	return ret;
+}
+
 int sctp_sysctl_net_register(struct net *net)
 {
 	struct ctl_table *table;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index 806af58f4375..bf0ac467e757 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -8,7 +8,7 @@
  *
  * This file is part of the SCTP kernel implementation
  *
- * This module provides the abstraction for an SCTP tranport representing
+ * This module provides the abstraction for an SCTP transport representing
  * a remote transport address.  For local transport addresses, we just use
  * union sctp_addr.
  *
@@ -123,7 +123,7 @@ void sctp_transport_free(struct sctp_transport *transport)
 	/* Delete the T3_rtx timer if it's active.
 	 * There is no point in not doing this now and letting
 	 * structure hang around in memory since we know
-	 * the tranport is going away.
+	 * the transport is going away.
 	 */
 	if (del_timer(&transport->T3_rtx_timer))
 		sctp_transport_put(transport);
@@ -133,7 +133,7 @@ void sctp_transport_free(struct sctp_transport *transport)
 
 	/* Delete the ICMP proto unreachable timer if it's active. */
 	if (del_timer(&transport->proto_unreach_timer))
-		sctp_association_put(transport->asoc);
+		sctp_transport_put(transport);
 
 	sctp_transport_put(transport);
 }
diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c
index 1c6c640607c5..407fed46931b 100644
--- a/net/sctp/ulpqueue.c
+++ b/net/sctp/ulpqueue.c
@@ -740,7 +740,7 @@ static void sctp_ulpq_reasm_drain(struct sctp_ulpq *ulpq)
 
 
 /* Helper function to gather skbs that have possibly become
- * ordered by an an incoming chunk.
+ * ordered by an incoming chunk.
  */
 static void sctp_ulpq_retrieve_ordered(struct sctp_ulpq *ulpq,
 					      struct sctp_ulpevent *event)
diff --git a/net/smc/Makefile b/net/smc/Makefile
index cb1254541f37..77e54fe42b1c 100644
--- a/net/smc/Makefile
+++ b/net/smc/Makefile
@@ -2,4 +2,4 @@
 obj-$(CONFIG_SMC)	+= smc.o
 obj-$(CONFIG_SMC_DIAG)	+= smc_diag.o
 smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
-smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o
+smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o smc_netlink.o
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index e7649bbc2b87..47340b3b514f 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -26,6 +26,7 @@
 #include <linux/sched/signal.h>
 #include <linux/if_vlan.h>
 #include <linux/rcupdate_wait.h>
+#include <linux/ctype.h>
 
 #include <net/sock.h>
 #include <net/tcp.h>
@@ -44,6 +45,7 @@
 #include "smc_ib.h"
 #include "smc_ism.h"
 #include "smc_pnet.h"
+#include "smc_netlink.h"
 #include "smc_tx.h"
 #include "smc_rx.h"
 #include "smc_close.h"
@@ -55,6 +57,9 @@ static DEFINE_MUTEX(smc_client_lgr_pending);	/* serialize link group
 						 * creation on client
 						 */
 
+struct workqueue_struct	*smc_hs_wq;	/* wq for handshake work */
+struct workqueue_struct	*smc_close_wq;	/* wq for close work */
+
 static void smc_tcp_listen_work(struct work_struct *);
 static void smc_connect_work(struct work_struct *);
 
@@ -436,26 +441,52 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc)
 static void smcr_conn_save_peer_info(struct smc_sock *smc,
 				     struct smc_clc_msg_accept_confirm *clc)
 {
-	int bufsize = smc_uncompress_bufsize(clc->rmbe_size);
+	int bufsize = smc_uncompress_bufsize(clc->r0.rmbe_size);
 
-	smc->conn.peer_rmbe_idx = clc->rmbe_idx;
-	smc->conn.local_tx_ctrl.token = ntohl(clc->rmbe_alert_token);
+	smc->conn.peer_rmbe_idx = clc->r0.rmbe_idx;
+	smc->conn.local_tx_ctrl.token = ntohl(clc->r0.rmbe_alert_token);
 	smc->conn.peer_rmbe_size = bufsize;
 	atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
 	smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1);
 }
 
+static bool smc_isascii(char *hostname)
+{
+	int i;
+
+	for (i = 0; i < SMC_MAX_HOSTNAME_LEN; i++)
+		if (!isascii(hostname[i]))
+			return false;
+	return true;
+}
+
 static void smcd_conn_save_peer_info(struct smc_sock *smc,
 				     struct smc_clc_msg_accept_confirm *clc)
 {
-	int bufsize = smc_uncompress_bufsize(clc->dmbe_size);
+	int bufsize = smc_uncompress_bufsize(clc->d0.dmbe_size);
 
-	smc->conn.peer_rmbe_idx = clc->dmbe_idx;
-	smc->conn.peer_token = clc->token;
+	smc->conn.peer_rmbe_idx = clc->d0.dmbe_idx;
+	smc->conn.peer_token = clc->d0.token;
 	/* msg header takes up space in the buffer */
 	smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg);
 	atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
 	smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx;
+	if (clc->hdr.version > SMC_V1 &&
+	    (clc->hdr.typev2 & SMC_FIRST_CONTACT_MASK)) {
+		struct smc_clc_msg_accept_confirm_v2 *clc_v2 =
+			(struct smc_clc_msg_accept_confirm_v2 *)clc;
+		struct smc_clc_first_contact_ext *fce =
+			(struct smc_clc_first_contact_ext *)
+				(((u8 *)clc_v2) + sizeof(*clc_v2));
+
+		memcpy(smc->conn.lgr->negotiated_eid, clc_v2->eid,
+		       SMC_MAX_EID_LEN);
+		smc->conn.lgr->peer_os = fce->os_type;
+		smc->conn.lgr->peer_smc_release = fce->release;
+		if (smc_isascii(fce->hostname))
+			memcpy(smc->conn.lgr->peer_hostname, fce->hostname,
+			       SMC_MAX_HOSTNAME_LEN);
+	}
 }
 
 static void smc_conn_save_peer_info(struct smc_sock *smc,
@@ -470,11 +501,11 @@ static void smc_conn_save_peer_info(struct smc_sock *smc,
 static void smc_link_save_peer_info(struct smc_link *link,
 				    struct smc_clc_msg_accept_confirm *clc)
 {
-	link->peer_qpn = ntoh24(clc->qpn);
-	memcpy(link->peer_gid, clc->lcl.gid, SMC_GID_SIZE);
-	memcpy(link->peer_mac, clc->lcl.mac, sizeof(link->peer_mac));
-	link->peer_psn = ntoh24(clc->psn);
-	link->peer_mtu = clc->qp_mtu;
+	link->peer_qpn = ntoh24(clc->r0.qpn);
+	memcpy(link->peer_gid, clc->r0.lcl.gid, SMC_GID_SIZE);
+	memcpy(link->peer_mac, clc->r0.lcl.mac, sizeof(link->peer_mac));
+	link->peer_psn = ntoh24(clc->r0.psn);
+	link->peer_mtu = clc->r0.qp_mtu;
 }
 
 static void smc_switch_to_fallback(struct smc_sock *smc)
@@ -501,7 +532,8 @@ static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
 }
 
 /* decline and fall back during connect */
-static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
+static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code,
+					u8 version)
 {
 	int rc;
 
@@ -511,7 +543,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 		return reason_code;
 	}
 	if (reason_code != SMC_CLC_DECL_PEERDECL) {
-		rc = smc_clc_send_decline(smc, reason_code);
+		rc = smc_clc_send_decline(smc, reason_code, version);
 		if (rc < 0) {
 			if (smc->sk.sk_state == SMC_INIT)
 				sock_put(&smc->sk); /* passive closing */
@@ -521,24 +553,12 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 	return smc_connect_fallback(smc, reason_code);
 }
 
-/* abort connecting */
-static int smc_connect_abort(struct smc_sock *smc, int reason_code,
-			     int local_contact)
+static void smc_conn_abort(struct smc_sock *smc, int local_first)
 {
-	bool is_smcd = smc->conn.lgr->is_smcd;
-
-	if (local_contact == SMC_FIRST_CONTACT)
+	if (local_first)
 		smc_lgr_cleanup_early(&smc->conn);
 	else
 		smc_conn_free(&smc->conn);
-	if (is_smcd)
-		/* there is only one lgr role for SMC-D; use server lock */
-		mutex_unlock(&smc_server_lgr_pending);
-	else
-		mutex_unlock(&smc_client_lgr_pending);
-
-	smc->connect_nonblock = 0;
-	return reason_code;
 }
 
 /* check if there is a rdma device available for this connection. */
@@ -561,47 +581,137 @@ static int smc_find_ism_device(struct smc_sock *smc, struct smc_init_info *ini)
 {
 	/* Find ISM device with same PNETID as connecting interface  */
 	smc_pnet_find_ism_resource(smc->clcsock->sk, ini);
-	if (!ini->ism_dev)
+	if (!ini->ism_dev[0])
 		return SMC_CLC_DECL_NOSMCDDEV;
+	else
+		ini->ism_chid[0] = smc_ism_get_chid(ini->ism_dev[0]);
 	return 0;
 }
 
+/* is chid unique for the ism devices that are already determined? */
+static bool smc_find_ism_v2_is_unique_chid(u16 chid, struct smc_init_info *ini,
+					   int cnt)
+{
+	int i = (!ini->ism_dev[0]) ? 1 : 0;
+
+	for (; i < cnt; i++)
+		if (ini->ism_chid[i] == chid)
+			return false;
+	return true;
+}
+
+/* determine possible V2 ISM devices (either without PNETID or with PNETID plus
+ * PNETID matching net_device)
+ */
+static int smc_find_ism_v2_device_clnt(struct smc_sock *smc,
+				       struct smc_init_info *ini)
+{
+	int rc = SMC_CLC_DECL_NOSMCDDEV;
+	struct smcd_dev *smcd;
+	int i = 1;
+	u16 chid;
+
+	if (smcd_indicated(ini->smc_type_v1))
+		rc = 0;		/* already initialized for V1 */
+	mutex_lock(&smcd_dev_list.mutex);
+	list_for_each_entry(smcd, &smcd_dev_list.list, list) {
+		if (smcd->going_away || smcd == ini->ism_dev[0])
+			continue;
+		chid = smc_ism_get_chid(smcd);
+		if (!smc_find_ism_v2_is_unique_chid(chid, ini, i))
+			continue;
+		if (!smc_pnet_is_pnetid_set(smcd->pnetid) ||
+		    smc_pnet_is_ndev_pnetid(sock_net(&smc->sk), smcd->pnetid)) {
+			ini->ism_dev[i] = smcd;
+			ini->ism_chid[i] = chid;
+			ini->is_smcd = true;
+			rc = 0;
+			i++;
+			if (i > SMC_MAX_ISM_DEVS)
+				break;
+		}
+	}
+	mutex_unlock(&smcd_dev_list.mutex);
+	ini->ism_offered_cnt = i - 1;
+	if (!ini->ism_dev[0] && !ini->ism_dev[1])
+		ini->smcd_version = 0;
+
+	return rc;
+}
+
 /* Check for VLAN ID and register it on ISM device just for CLC handshake */
 static int smc_connect_ism_vlan_setup(struct smc_sock *smc,
 				      struct smc_init_info *ini)
 {
-	if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev, ini->vlan_id))
+	if (ini->vlan_id && smc_ism_get_vlan(ini->ism_dev[0], ini->vlan_id))
 		return SMC_CLC_DECL_ISMVLANERR;
 	return 0;
 }
 
+static int smc_find_proposal_devices(struct smc_sock *smc,
+				     struct smc_init_info *ini)
+{
+	int rc = 0;
+
+	/* check if there is an ism device available */
+	if (ini->smcd_version & SMC_V1) {
+		if (smc_find_ism_device(smc, ini) ||
+		    smc_connect_ism_vlan_setup(smc, ini)) {
+			if (ini->smc_type_v1 == SMC_TYPE_B)
+				ini->smc_type_v1 = SMC_TYPE_R;
+			else
+				ini->smc_type_v1 = SMC_TYPE_N;
+		} /* else ISM V1 is supported for this connection */
+		if (smc_find_rdma_device(smc, ini)) {
+			if (ini->smc_type_v1 == SMC_TYPE_B)
+				ini->smc_type_v1 = SMC_TYPE_D;
+			else
+				ini->smc_type_v1 = SMC_TYPE_N;
+		} /* else RDMA is supported for this connection */
+	}
+	if (smc_ism_is_v2_capable() && smc_find_ism_v2_device_clnt(smc, ini))
+		ini->smc_type_v2 = SMC_TYPE_N;
+
+	/* if neither ISM nor RDMA are supported, fallback */
+	if (!smcr_indicated(ini->smc_type_v1) &&
+	    ini->smc_type_v1 == SMC_TYPE_N && ini->smc_type_v2 == SMC_TYPE_N)
+		rc = SMC_CLC_DECL_NOSMCDEV;
+
+	return rc;
+}
+
 /* cleanup temporary VLAN ID registration used for CLC handshake. If ISM is
  * used, the VLAN ID will be registered again during the connection setup.
  */
-static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
+static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc,
 					struct smc_init_info *ini)
 {
-	if (!is_smcd)
+	if (!smcd_indicated(ini->smc_type_v1))
 		return 0;
-	if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev, ini->vlan_id))
+	if (ini->vlan_id && smc_ism_put_vlan(ini->ism_dev[0], ini->vlan_id))
 		return SMC_CLC_DECL_CNFERR;
 	return 0;
 }
 
+#define SMC_CLC_MAX_ACCEPT_LEN \
+	(sizeof(struct smc_clc_msg_accept_confirm_v2) + \
+	 sizeof(struct smc_clc_first_contact_ext) + \
+	 sizeof(struct smc_clc_msg_trail))
+
 /* CLC handshake during connect */
-static int smc_connect_clc(struct smc_sock *smc, int smc_type,
-			   struct smc_clc_msg_accept_confirm *aclc,
+static int smc_connect_clc(struct smc_sock *smc,
+			   struct smc_clc_msg_accept_confirm_v2 *aclc2,
 			   struct smc_init_info *ini)
 {
 	int rc = 0;
 
 	/* do inband token exchange */
-	rc = smc_clc_send_proposal(smc, smc_type, ini);
+	rc = smc_clc_send_proposal(smc, ini);
 	if (rc)
 		return rc;
 	/* receive SMC Accept CLC message */
-	return smc_clc_wait_msg(smc, aclc, sizeof(*aclc), SMC_CLC_ACCEPT,
-				CLC_WAIT_TIME);
+	return smc_clc_wait_msg(smc, aclc2, SMC_CLC_MAX_ACCEPT_LEN,
+				SMC_CLC_ACCEPT, CLC_WAIT_TIME);
 }
 
 /* setup for RDMA connection of client */
@@ -613,9 +723,9 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	struct smc_link *link;
 
 	ini->is_smcd = false;
-	ini->ib_lcl = &aclc->lcl;
-	ini->ib_clcqpn = ntoh24(aclc->qpn);
-	ini->srv_first_contact = aclc->hdr.flag;
+	ini->ib_lcl = &aclc->r0.lcl;
+	ini->ib_clcqpn = ntoh24(aclc->r0.qpn);
+	ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK;
 
 	mutex_lock(&smc_client_lgr_pending);
 	reason_code = smc_conn_create(smc, ini);
@@ -626,7 +736,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 
 	smc_conn_save_peer_info(smc, aclc);
 
-	if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
+	if (ini->first_contact_local) {
 		link = smc->conn.lnk;
 	} else {
 		/* set link that was assigned by server */
@@ -634,60 +744,66 @@ static int smc_connect_rdma(struct smc_sock *smc,
 		for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
 			struct smc_link *l = &smc->conn.lgr->lnk[i];
 
-			if (l->peer_qpn == ntoh24(aclc->qpn) &&
-			    !memcmp(l->peer_gid, &aclc->lcl.gid, SMC_GID_SIZE) &&
-			    !memcmp(l->peer_mac, &aclc->lcl.mac, sizeof(l->peer_mac))) {
+			if (l->peer_qpn == ntoh24(aclc->r0.qpn) &&
+			    !memcmp(l->peer_gid, &aclc->r0.lcl.gid,
+				    SMC_GID_SIZE) &&
+			    !memcmp(l->peer_mac, &aclc->r0.lcl.mac,
+				    sizeof(l->peer_mac))) {
 				link = l;
 				break;
 			}
 		}
-		if (!link)
-			return smc_connect_abort(smc, SMC_CLC_DECL_NOSRVLINK,
-						 ini->cln_first_contact);
+		if (!link) {
+			reason_code = SMC_CLC_DECL_NOSRVLINK;
+			goto connect_abort;
+		}
 		smc->conn.lnk = link;
 	}
 
 	/* create send buffer and rmb */
-	if (smc_buf_create(smc, false))
-		return smc_connect_abort(smc, SMC_CLC_DECL_MEM,
-					 ini->cln_first_contact);
+	if (smc_buf_create(smc, false)) {
+		reason_code = SMC_CLC_DECL_MEM;
+		goto connect_abort;
+	}
 
-	if (ini->cln_first_contact == SMC_FIRST_CONTACT)
+	if (ini->first_contact_local)
 		smc_link_save_peer_info(link, aclc);
 
-	if (smc_rmb_rtoken_handling(&smc->conn, link, aclc))
-		return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK,
-					 ini->cln_first_contact);
+	if (smc_rmb_rtoken_handling(&smc->conn, link, aclc)) {
+		reason_code = SMC_CLC_DECL_ERR_RTOK;
+		goto connect_abort;
+	}
 
 	smc_close_init(smc);
 	smc_rx_init(smc);
 
-	if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
-		if (smc_ib_ready_link(link))
-			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK,
-						 ini->cln_first_contact);
+	if (ini->first_contact_local) {
+		if (smc_ib_ready_link(link)) {
+			reason_code = SMC_CLC_DECL_ERR_RDYLNK;
+			goto connect_abort;
+		}
 	} else {
-		if (smcr_lgr_reg_rmbs(link, smc->conn.rmb_desc))
-			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
-						 ini->cln_first_contact);
+		if (smcr_lgr_reg_rmbs(link, smc->conn.rmb_desc)) {
+			reason_code = SMC_CLC_DECL_ERR_REGRMB;
+			goto connect_abort;
+		}
 	}
 	smc_rmb_sync_sg_for_device(&smc->conn);
 
-	reason_code = smc_clc_send_confirm(smc);
+	reason_code = smc_clc_send_confirm(smc, ini->first_contact_local,
+					   SMC_V1);
 	if (reason_code)
-		return smc_connect_abort(smc, reason_code,
-					 ini->cln_first_contact);
+		goto connect_abort;
 
 	smc_tx_init(smc);
 
-	if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
+	if (ini->first_contact_local) {
 		/* QP confirmation over RoCE fabric */
 		smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK);
 		reason_code = smcr_clnt_conf_first_link(smc);
 		smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl);
 		if (reason_code)
-			return smc_connect_abort(smc, reason_code,
-						 ini->cln_first_contact);
+			goto connect_abort;
 	}
 	mutex_unlock(&smc_client_lgr_pending);
 
@@ -697,6 +813,31 @@ static int smc_connect_rdma(struct smc_sock *smc,
 		smc->sk.sk_state = SMC_ACTIVE;
 
 	return 0;
+connect_abort:
+	smc_conn_abort(smc, ini->first_contact_local);
+	mutex_unlock(&smc_client_lgr_pending);
+	smc->connect_nonblock = 0;
+
+	return reason_code;
+}
+
+/* The server has chosen one of the proposed ISM devices for the communication.
+ * Determine from the CHID of the received CLC ACCEPT the ISM device chosen.
+ */
+static int
+smc_v2_determine_accepted_chid(struct smc_clc_msg_accept_confirm_v2 *aclc,
+			       struct smc_init_info *ini)
+{
+	int i;
+
+	for (i = 0; i < ini->ism_offered_cnt + 1; i++) {
+		if (ini->ism_chid[i] == ntohs(aclc->chid)) {
+			ini->ism_selected = i;
+			return 0;
+		}
+	}
+
+	return -EPROTO;
 }
 
 /* setup for ISM connection of client */
@@ -707,8 +848,17 @@ static int smc_connect_ism(struct smc_sock *smc,
 	int rc = 0;
 
 	ini->is_smcd = true;
-	ini->ism_gid = aclc->gid;
-	ini->srv_first_contact = aclc->hdr.flag;
+	ini->first_contact_peer = aclc->hdr.typev2 & SMC_FIRST_CONTACT_MASK;
+
+	if (aclc->hdr.version == SMC_V2) {
+		struct smc_clc_msg_accept_confirm_v2 *aclc_v2 =
+			(struct smc_clc_msg_accept_confirm_v2 *)aclc;
+
+		rc = smc_v2_determine_accepted_chid(aclc_v2, ini);
+		if (rc)
+			return rc;
+	}
+	ini->ism_peer_gid[ini->ism_selected] = aclc->d0.gid;
 
 	/* there is only one lgr role for SMC-D; use server lock */
 	mutex_lock(&smc_server_lgr_pending);
@@ -720,20 +870,20 @@ static int smc_connect_ism(struct smc_sock *smc,
 
 	/* Create send and receive buffers */
 	rc = smc_buf_create(smc, true);
-	if (rc)
-		return smc_connect_abort(smc, (rc == -ENOSPC) ?
-					      SMC_CLC_DECL_MAX_DMB :
-					      SMC_CLC_DECL_MEM,
-					 ini->cln_first_contact);
+	if (rc) {
+		rc = (rc == -ENOSPC) ? SMC_CLC_DECL_MAX_DMB : SMC_CLC_DECL_MEM;
+		goto connect_abort;
+	}
 
 	smc_conn_save_peer_info(smc, aclc);
 	smc_close_init(smc);
 	smc_rx_init(smc);
 	smc_tx_init(smc);
 
-	rc = smc_clc_send_confirm(smc);
+	rc = smc_clc_send_confirm(smc, ini->first_contact_local,
+				  aclc->hdr.version);
 	if (rc)
-		return smc_connect_abort(smc, rc, ini->cln_first_contact);
+		goto connect_abort;
 	mutex_unlock(&smc_server_lgr_pending);
 
 	smc_copy_sock_settings_to_clc(smc);
@@ -742,15 +892,40 @@ static int smc_connect_ism(struct smc_sock *smc,
 		smc->sk.sk_state = SMC_ACTIVE;
 
 	return 0;
+connect_abort:
+	smc_conn_abort(smc, ini->first_contact_local);
+	mutex_unlock(&smc_server_lgr_pending);
+	smc->connect_nonblock = 0;
+
+	return rc;
+}
+
+/* check if received accept type and version matches a proposed one */
+static int smc_connect_check_aclc(struct smc_init_info *ini,
+				  struct smc_clc_msg_accept_confirm *aclc)
+{
+	if ((aclc->hdr.typev1 == SMC_TYPE_R &&
+	     !smcr_indicated(ini->smc_type_v1)) ||
+	    (aclc->hdr.typev1 == SMC_TYPE_D &&
+	     ((!smcd_indicated(ini->smc_type_v1) &&
+	       !smcd_indicated(ini->smc_type_v2)) ||
+	      (aclc->hdr.version == SMC_V1 &&
+	       !smcd_indicated(ini->smc_type_v1)) ||
+	      (aclc->hdr.version == SMC_V2 &&
+	       !smcd_indicated(ini->smc_type_v2)))))
+		return SMC_CLC_DECL_MODEUNSUPP;
+
+	return 0;
 }
 
 /* perform steps before actually connecting */
 static int __smc_connect(struct smc_sock *smc)
 {
-	bool ism_supported = false, rdma_supported = false;
-	struct smc_clc_msg_accept_confirm aclc;
-	struct smc_init_info ini = {0};
-	int smc_type;
+	u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1;
+	struct smc_clc_msg_accept_confirm_v2 *aclc2;
+	struct smc_clc_msg_accept_confirm *aclc;
+	struct smc_init_info *ini = NULL;
+	u8 *buf = NULL;
 	int rc = 0;
 
 	if (smc->use_fallback)
@@ -760,58 +935,74 @@ static int __smc_connect(struct smc_sock *smc)
 	if (!tcp_sk(smc->clcsock->sk)->syn_smc)
 		return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC);
 
-	/* IPSec connections opt out of SMC-R optimizations */
+	/* IPSec connections opt out of SMC optimizations */
 	if (using_ipsec(smc))
-		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC);
+		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC,
+						    version);
 
-	/* get vlan id from IP device */
-	if (smc_vlan_by_tcpsk(smc->clcsock, &ini))
-		return smc_connect_decline_fallback(smc,
-						    SMC_CLC_DECL_GETVLANERR);
+	ini = kzalloc(sizeof(*ini), GFP_KERNEL);
+	if (!ini)
+		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_MEM,
+						    version);
 
-	/* check if there is an ism device available */
-	if (!smc_find_ism_device(smc, &ini) &&
-	    !smc_connect_ism_vlan_setup(smc, &ini)) {
-		/* ISM is supported for this connection */
-		ism_supported = true;
-		smc_type = SMC_TYPE_D;
-	}
-
-	/* check if there is a rdma device available */
-	if (!smc_find_rdma_device(smc, &ini)) {
-		/* RDMA is supported for this connection */
-		rdma_supported = true;
-		if (ism_supported)
-			smc_type = SMC_TYPE_B; /* both */
-		else
-			smc_type = SMC_TYPE_R; /* only RDMA */
+	ini->smcd_version = SMC_V1;
+	ini->smcd_version |= smc_ism_is_v2_capable() ? SMC_V2 : 0;
+	ini->smc_type_v1 = SMC_TYPE_B;
+	ini->smc_type_v2 = smc_ism_is_v2_capable() ? SMC_TYPE_D : SMC_TYPE_N;
+
+	/* get vlan id from IP device */
+	if (smc_vlan_by_tcpsk(smc->clcsock, ini)) {
+		ini->smcd_version &= ~SMC_V1;
+		ini->smc_type_v1 = SMC_TYPE_N;
+		if (!ini->smcd_version) {
+			rc = SMC_CLC_DECL_GETVLANERR;
+			goto fallback;
+		}
 	}
 
-	/* if neither ISM nor RDMA are supported, fallback */
-	if (!rdma_supported && !ism_supported)
-		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV);
+	rc = smc_find_proposal_devices(smc, ini);
+	if (rc)
+		goto fallback;
 
-	/* perform CLC handshake */
-	rc = smc_connect_clc(smc, smc_type, &aclc, &ini);
-	if (rc) {
-		smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
-		return smc_connect_decline_fallback(smc, rc);
+	buf = kzalloc(SMC_CLC_MAX_ACCEPT_LEN, GFP_KERNEL);
+	if (!buf) {
+		rc = SMC_CLC_DECL_MEM;
+		goto fallback;
 	}
+	aclc2 = (struct smc_clc_msg_accept_confirm_v2 *)buf;
+	aclc = (struct smc_clc_msg_accept_confirm *)aclc2;
+
+	/* perform CLC handshake */
+	rc = smc_connect_clc(smc, aclc2, ini);
+	if (rc)
+		goto vlan_cleanup;
+
+	/* check if smc modes and versions of CLC proposal and accept match */
+	rc = smc_connect_check_aclc(ini, aclc);
+	version = aclc->hdr.version == SMC_V1 ? SMC_V1 : SMC_V2;
+	ini->smcd_version = version;
+	if (rc)
+		goto vlan_cleanup;
 
 	/* depending on previous steps, connect using rdma or ism */
-	if (rdma_supported && aclc.hdr.path == SMC_TYPE_R)
-		rc = smc_connect_rdma(smc, &aclc, &ini);
-	else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
-		rc = smc_connect_ism(smc, &aclc, &ini);
-	else
-		rc = SMC_CLC_DECL_MODEUNSUPP;
-	if (rc) {
-		smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
-		return smc_connect_decline_fallback(smc, rc);
-	}
+	if (aclc->hdr.typev1 == SMC_TYPE_R)
+		rc = smc_connect_rdma(smc, aclc, ini);
+	else if (aclc->hdr.typev1 == SMC_TYPE_D)
+		rc = smc_connect_ism(smc, aclc, ini);
+	if (rc)
+		goto vlan_cleanup;
 
-	smc_connect_ism_vlan_cleanup(smc, ism_supported, &ini);
+	smc_connect_ism_vlan_cleanup(smc, ini);
+	kfree(buf);
+	kfree(ini);
 	return 0;
+
+vlan_cleanup:
+	smc_connect_ism_vlan_cleanup(smc, ini);
+	kfree(buf);
+fallback:
+	kfree(ini);
+	return smc_connect_decline_fallback(smc, rc, version);
 }
 
 static void smc_connect_work(struct work_struct *work)
@@ -903,7 +1094,7 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr,
 	if (smc->use_fallback)
 		goto out;
 	if (flags & O_NONBLOCK) {
-		if (schedule_work(&smc->connect_work))
+		if (queue_work(smc_hs_wq, &smc->connect_work))
 			smc->connect_nonblock = 1;
 		rc = -EINPROGRESS;
 	} else {
@@ -940,10 +1131,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
 
 	mutex_lock(&lsmc->clcsock_release_lock);
 	if (lsmc->clcsock)
-		rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0);
+		rc = kernel_accept(lsmc->clcsock, &new_clcsock, SOCK_NONBLOCK);
 	mutex_unlock(&lsmc->clcsock_release_lock);
 	lock_sock(lsk);
-	if  (rc < 0)
+	if  (rc < 0 && rc != -EAGAIN)
 		lsk->sk_err = -rc;
 	if (rc < 0 || lsk->sk_state == SMC_CLOSED) {
 		new_sk->sk_prot->unhash(new_sk);
@@ -956,6 +1147,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc)
 		goto out;
 	}
 
+	/* new clcsock has inherited the smc listen-specific sk_data_ready
+	 * function; switch it back to the original sk_data_ready function
+	 */
+	new_clcsock->sk->sk_data_ready = lsmc->clcsk_data_ready;
 	(*new_smc)->clcsock = new_clcsock;
 out:
 	return rc;
@@ -1123,13 +1318,10 @@ static void smc_listen_out_err(struct smc_sock *new_smc)
 
 /* listen worker: decline and fall back if possible */
 static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
-			       int local_contact)
+			       int local_first, u8 version)
 {
 	/* RDMA setup failed, switch back to TCP */
-	if (local_contact == SMC_FIRST_CONTACT)
-		smc_lgr_cleanup_early(&new_smc->conn);
-	else
-		smc_conn_free(&new_smc->conn);
+	smc_conn_abort(new_smc, local_first);
 	if (reason_code < 0) { /* error, no fallback possible */
 		smc_listen_out_err(new_smc);
 		return;
@@ -1137,7 +1329,7 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 	smc_switch_to_fallback(new_smc);
 	new_smc->fallback_rsn = reason_code;
 	if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
-		if (smc_clc_send_decline(new_smc, reason_code) < 0) {
+		if (smc_clc_send_decline(new_smc, reason_code, version) < 0) {
 			smc_listen_out_err(new_smc);
 			return;
 		}
@@ -1145,6 +1337,49 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 	smc_listen_out_connected(new_smc);
 }
 
+/* listen worker: version checking */
+static int smc_listen_v2_check(struct smc_sock *new_smc,
+			       struct smc_clc_msg_proposal *pclc,
+			       struct smc_init_info *ini)
+{
+	struct smc_clc_smcd_v2_extension *pclc_smcd_v2_ext;
+	struct smc_clc_v2_extension *pclc_v2_ext;
+	int rc = SMC_CLC_DECL_PEERNOSMC;
+
+	ini->smc_type_v1 = pclc->hdr.typev1;
+	ini->smc_type_v2 = pclc->hdr.typev2;
+	ini->smcd_version = ini->smc_type_v1 != SMC_TYPE_N ? SMC_V1 : 0;
+	if (pclc->hdr.version > SMC_V1)
+		ini->smcd_version |=
+				ini->smc_type_v2 != SMC_TYPE_N ? SMC_V2 : 0;
+	if (!(ini->smcd_version & SMC_V2)) {
+		rc = SMC_CLC_DECL_PEERNOSMC;
+		goto out;
+	}
+	if (!smc_ism_is_v2_capable()) {
+		ini->smcd_version &= ~SMC_V2;
+		rc = SMC_CLC_DECL_NOISM2SUPP;
+		goto out;
+	}
+	pclc_v2_ext = smc_get_clc_v2_ext(pclc);
+	if (!pclc_v2_ext) {
+		ini->smcd_version &= ~SMC_V2;
+		rc = SMC_CLC_DECL_NOV2EXT;
+		goto out;
+	}
+	pclc_smcd_v2_ext = smc_get_clc_smcd_v2_ext(pclc_v2_ext);
+	if (!pclc_smcd_v2_ext) {
+		ini->smcd_version &= ~SMC_V2;
+		rc = SMC_CLC_DECL_NOV2DEXT;
+	}
+
+out:
+	if (!ini->smcd_version)
+		return rc;
+
+	return 0;
+}
+
 /* listen worker: check prefixes */
 static int smc_listen_prfx_check(struct smc_sock *new_smc,
 				 struct smc_clc_msg_proposal *pclc)
@@ -1152,6 +1387,8 @@ static int smc_listen_prfx_check(struct smc_sock *new_smc,
 	struct smc_clc_msg_proposal_prefix *pclc_prfx;
 	struct socket *newclcsock = new_smc->clcsock;
 
+	if (pclc->hdr.typev1 == SMC_TYPE_N)
+		return 0;
 	pclc_prfx = smc_clc_proposal_get_prefix(pclc);
 	if (smc_clc_prfx_match(newclcsock, pclc_prfx))
 		return SMC_CLC_DECL_DIFFPREFIX;
@@ -1179,36 +1416,18 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc,
 
 /* listen worker: initialize connection and buffers for SMC-D */
 static int smc_listen_ism_init(struct smc_sock *new_smc,
-			       struct smc_clc_msg_proposal *pclc,
 			       struct smc_init_info *ini)
 {
-	struct smc_clc_msg_smcd *pclc_smcd;
 	int rc;
 
-	pclc_smcd = smc_get_clc_msg_smcd(pclc);
-	ini->ism_gid = pclc_smcd->gid;
 	rc = smc_conn_create(new_smc, ini);
 	if (rc)
 		return rc;
 
-	/* Check if peer can be reached via ISM device */
-	if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid,
-			    new_smc->conn.lgr->vlan_id,
-			    new_smc->conn.lgr->smcd)) {
-		if (ini->cln_first_contact == SMC_FIRST_CONTACT)
-			smc_lgr_cleanup_early(&new_smc->conn);
-		else
-			smc_conn_free(&new_smc->conn);
-		return SMC_CLC_DECL_SMCDNOTALK;
-	}
-
 	/* Create send and receive buffers */
 	rc = smc_buf_create(new_smc, true);
 	if (rc) {
-		if (ini->cln_first_contact == SMC_FIRST_CONTACT)
-			smc_lgr_cleanup_early(&new_smc->conn);
-		else
-			smc_conn_free(&new_smc->conn);
+		smc_conn_abort(new_smc, ini->first_contact_local);
 		return (rc == -ENOSPC) ? SMC_CLC_DECL_MAX_DMB :
 					 SMC_CLC_DECL_MEM;
 	}
@@ -1216,12 +1435,150 @@ static int smc_listen_ism_init(struct smc_sock *new_smc,
 	return 0;
 }
 
+static bool smc_is_already_selected(struct smcd_dev *smcd,
+				    struct smc_init_info *ini,
+				    int matches)
+{
+	int i;
+
+	for (i = 0; i < matches; i++)
+		if (smcd == ini->ism_dev[i])
+			return true;
+
+	return false;
+}
+
+/* check for ISM devices matching proposed ISM devices */
+static void smc_check_ism_v2_match(struct smc_init_info *ini,
+				   u16 proposed_chid, u64 proposed_gid,
+				   unsigned int *matches)
+{
+	struct smcd_dev *smcd;
+
+	list_for_each_entry(smcd, &smcd_dev_list.list, list) {
+		if (smcd->going_away)
+			continue;
+		if (smc_is_already_selected(smcd, ini, *matches))
+			continue;
+		if (smc_ism_get_chid(smcd) == proposed_chid &&
+		    !smc_ism_cantalk(proposed_gid, ISM_RESERVED_VLANID, smcd)) {
+			ini->ism_peer_gid[*matches] = proposed_gid;
+			ini->ism_dev[*matches] = smcd;
+			(*matches)++;
+			break;
+		}
+	}
+}
+
+static void smc_find_ism_store_rc(u32 rc, struct smc_init_info *ini)
+{
+	if (!ini->rc)
+		ini->rc = rc;
+}
+
+static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc,
+					struct smc_clc_msg_proposal *pclc,
+					struct smc_init_info *ini)
+{
+	struct smc_clc_smcd_v2_extension *smcd_v2_ext;
+	struct smc_clc_v2_extension *smc_v2_ext;
+	struct smc_clc_msg_smcd *pclc_smcd;
+	unsigned int matches = 0;
+	u8 smcd_version;
+	u8 *eid = NULL;
+	int i, rc;
+
+	if (!(ini->smcd_version & SMC_V2) || !smcd_indicated(ini->smc_type_v2))
+		goto not_found;
+
+	pclc_smcd = smc_get_clc_msg_smcd(pclc);
+	smc_v2_ext = smc_get_clc_v2_ext(pclc);
+	smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext);
+	if (!smcd_v2_ext ||
+	    !smc_v2_ext->hdr.flag.seid) { /* no system EID support for SMCD */
+		smc_find_ism_store_rc(SMC_CLC_DECL_NOSEID, ini);
+		goto not_found;
+	}
+
+	mutex_lock(&smcd_dev_list.mutex);
+	if (pclc_smcd->ism.chid)
+		/* check for ISM device matching proposed native ISM device */
+		smc_check_ism_v2_match(ini, ntohs(pclc_smcd->ism.chid),
+				       ntohll(pclc_smcd->ism.gid), &matches);
+	for (i = 1; i <= smc_v2_ext->hdr.ism_gid_cnt; i++) {
+		/* check for ISM devices matching proposed non-native ISM
+		 * devices
+		 */
+		smc_check_ism_v2_match(ini,
+				       ntohs(smcd_v2_ext->gidchid[i - 1].chid),
+				       ntohll(smcd_v2_ext->gidchid[i - 1].gid),
+				       &matches);
+	}
+	mutex_unlock(&smcd_dev_list.mutex);
+
+	if (ini->ism_dev[0]) {
+		smc_ism_get_system_eid(ini->ism_dev[0], &eid);
+		if (memcmp(eid, smcd_v2_ext->system_eid, SMC_MAX_EID_LEN))
+			goto not_found;
+	} else {
+		goto not_found;
+	}
+
+	/* separate - outside the smcd_dev_list.lock */
+	smcd_version = ini->smcd_version;
+	for (i = 0; i < matches; i++) {
+		ini->smcd_version = SMC_V2;
+		ini->is_smcd = true;
+		ini->ism_selected = i;
+		rc = smc_listen_ism_init(new_smc, ini);
+		if (rc) {
+			smc_find_ism_store_rc(rc, ini);
+			/* try next active ISM device */
+			continue;
+		}
+		return; /* matching and usable V2 ISM device found */
+	}
+	/* no V2 ISM device could be initialized */
+	ini->smcd_version = smcd_version;	/* restore original value */
+
+not_found:
+	ini->smcd_version &= ~SMC_V2;
+	ini->ism_dev[0] = NULL;
+	ini->is_smcd = false;
+}
+
+static void smc_find_ism_v1_device_serv(struct smc_sock *new_smc,
+					struct smc_clc_msg_proposal *pclc,
+					struct smc_init_info *ini)
+{
+	struct smc_clc_msg_smcd *pclc_smcd = smc_get_clc_msg_smcd(pclc);
+	int rc = 0;
+
+	/* check if ISM V1 is available */
+	if (!(ini->smcd_version & SMC_V1) || !smcd_indicated(ini->smc_type_v1))
+		goto not_found;
+	ini->is_smcd = true; /* prepare ISM check */
+	ini->ism_peer_gid[0] = ntohll(pclc_smcd->ism.gid);
+	rc = smc_find_ism_device(new_smc, ini);
+	if (rc)
+		goto not_found;
+	ini->ism_selected = 0;
+	rc = smc_listen_ism_init(new_smc, ini);
+	if (!rc)
+		return;		/* V1 ISM device found */
+
+not_found:
+	smc_find_ism_store_rc(rc, ini);
+	ini->ism_dev[0] = NULL;
+	ini->is_smcd = false;
+}
+
 /* listen worker: register buffers */
-static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
+static int smc_listen_rdma_reg(struct smc_sock *new_smc, bool local_first)
 {
 	struct smc_connection *conn = &new_smc->conn;
 
-	if (local_contact != SMC_FIRST_CONTACT) {
+	if (!local_first) {
 		if (smcr_lgr_reg_rmbs(conn->lnk, conn->rmb_desc))
 			return SMC_CLC_DECL_ERR_REGRMB;
 	}
@@ -1230,52 +1587,107 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
 	return 0;
 }
 
+static int smc_find_rdma_v1_device_serv(struct smc_sock *new_smc,
+					struct smc_clc_msg_proposal *pclc,
+					struct smc_init_info *ini)
+{
+	int rc;
+
+	if (!smcr_indicated(ini->smc_type_v1))
+		return SMC_CLC_DECL_NOSMCDEV;
+
+	/* prepare RDMA check */
+	ini->ib_lcl = &pclc->lcl;
+	rc = smc_find_rdma_device(new_smc, ini);
+	if (rc) {
+		/* no RDMA device found */
+		if (ini->smc_type_v1 == SMC_TYPE_B)
+			/* neither ISM nor RDMA device found */
+			rc = SMC_CLC_DECL_NOSMCDEV;
+		return rc;
+	}
+	rc = smc_listen_rdma_init(new_smc, ini);
+	if (rc)
+		return rc;
+	return smc_listen_rdma_reg(new_smc, ini->first_contact_local);
+}
+
+/* determine the local device matching to proposal */
+static int smc_listen_find_device(struct smc_sock *new_smc,
+				  struct smc_clc_msg_proposal *pclc,
+				  struct smc_init_info *ini)
+{
+	int rc;
+
+	/* check for ISM device matching V2 proposed device */
+	smc_find_ism_v2_device_serv(new_smc, pclc, ini);
+	if (ini->ism_dev[0])
+		return 0;
+
+	if (!(ini->smcd_version & SMC_V1))
+		return ini->rc ?: SMC_CLC_DECL_NOSMCD2DEV;
+
+	/* check for matching IP prefix and subnet length */
+	rc = smc_listen_prfx_check(new_smc, pclc);
+	if (rc)
+		return ini->rc ?: rc;
+
+	/* get vlan id from IP device */
+	if (smc_vlan_by_tcpsk(new_smc->clcsock, ini))
+		return ini->rc ?: SMC_CLC_DECL_GETVLANERR;
+
+	/* check for ISM device matching V1 proposed device */
+	smc_find_ism_v1_device_serv(new_smc, pclc, ini);
+	if (ini->ism_dev[0])
+		return 0;
+
+	if (pclc->hdr.typev1 == SMC_TYPE_D)
+		/* skip RDMA and decline */
+		return ini->rc ?: SMC_CLC_DECL_NOSMCDDEV;
+
+	/* check if RDMA is available */
+	rc = smc_find_rdma_v1_device_serv(new_smc, pclc, ini);
+	smc_find_ism_store_rc(rc, ini);
+
+	return (!rc) ? 0 : ini->rc;
+}
+
 /* listen worker: finish RDMA setup */
 static int smc_listen_rdma_finish(struct smc_sock *new_smc,
 				  struct smc_clc_msg_accept_confirm *cclc,
-				  int local_contact)
+				  bool local_first)
 {
 	struct smc_link *link = new_smc->conn.lnk;
 	int reason_code = 0;
 
-	if (local_contact == SMC_FIRST_CONTACT)
+	if (local_first)
 		smc_link_save_peer_info(link, cclc);
 
-	if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc)) {
-		reason_code = SMC_CLC_DECL_ERR_RTOK;
-		goto decline;
-	}
+	if (smc_rmb_rtoken_handling(&new_smc->conn, link, cclc))
+		return SMC_CLC_DECL_ERR_RTOK;
 
-	if (local_contact == SMC_FIRST_CONTACT) {
-		if (smc_ib_ready_link(link)) {
-			reason_code = SMC_CLC_DECL_ERR_RDYLNK;
-			goto decline;
-		}
+	if (local_first) {
+		if (smc_ib_ready_link(link))
+			return SMC_CLC_DECL_ERR_RDYLNK;
 		/* QP confirmation over RoCE fabric */
 		smc_llc_flow_initiate(link->lgr, SMC_LLC_FLOW_ADD_LINK);
 		reason_code = smcr_serv_conf_first_link(new_smc);
 		smc_llc_flow_stop(link->lgr, &link->lgr->llc_flow_lcl);
-		if (reason_code)
-			goto decline;
 	}
-	return 0;
-
-decline:
-	smc_listen_decline(new_smc, reason_code, local_contact);
 	return reason_code;
 }
 
-/* setup for RDMA connection of server */
+/* setup for connection of server */
 static void smc_listen_work(struct work_struct *work)
 {
 	struct smc_sock *new_smc = container_of(work, struct smc_sock,
 						smc_listen_work);
+	u8 version = smc_ism_is_v2_capable() ? SMC_V2 : SMC_V1;
 	struct socket *newclcsock = new_smc->clcsock;
-	struct smc_clc_msg_accept_confirm cclc;
+	struct smc_clc_msg_accept_confirm *cclc;
+	struct smc_clc_msg_proposal_area *buf;
 	struct smc_clc_msg_proposal *pclc;
-	struct smc_init_info ini = {0};
-	bool ism_supported = false;
-	u8 buf[SMC_CLC_MAX_LEN];
+	struct smc_init_info *ini = NULL;
 	int rc = 0;
 
 	if (new_smc->listen_smc->sk.sk_state != SMC_LISTEN)
@@ -1297,102 +1709,86 @@ static void smc_listen_work(struct work_struct *work)
 	/* do inband token exchange -
 	 * wait for and receive SMC Proposal CLC message
 	 */
-	pclc = (struct smc_clc_msg_proposal *)&buf;
-	rc = smc_clc_wait_msg(new_smc, pclc, SMC_CLC_MAX_LEN,
+	buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+	if (!buf) {
+		rc = SMC_CLC_DECL_MEM;
+		goto out_decl;
+	}
+	pclc = (struct smc_clc_msg_proposal *)buf;
+	rc = smc_clc_wait_msg(new_smc, pclc, sizeof(*buf),
 			      SMC_CLC_PROPOSAL, CLC_WAIT_TIME);
 	if (rc)
 		goto out_decl;
+	version = pclc->hdr.version == SMC_V1 ? SMC_V1 : version;
 
-	/* IPSec connections opt out of SMC-R optimizations */
+	/* IPSec connections opt out of SMC optimizations */
 	if (using_ipsec(new_smc)) {
 		rc = SMC_CLC_DECL_IPSEC;
 		goto out_decl;
 	}
 
-	/* check for matching IP prefix and subnet length */
-	rc = smc_listen_prfx_check(new_smc, pclc);
-	if (rc)
+	ini = kzalloc(sizeof(*ini), GFP_KERNEL);
+	if (!ini) {
+		rc = SMC_CLC_DECL_MEM;
 		goto out_decl;
+	}
 
-	/* get vlan id from IP device */
-	if (smc_vlan_by_tcpsk(new_smc->clcsock, &ini)) {
-		rc = SMC_CLC_DECL_GETVLANERR;
+	/* initial version checking */
+	rc = smc_listen_v2_check(new_smc, pclc, ini);
+	if (rc)
 		goto out_decl;
-	}
 
 	mutex_lock(&smc_server_lgr_pending);
 	smc_close_init(new_smc);
 	smc_rx_init(new_smc);
 	smc_tx_init(new_smc);
 
-	/* check if ISM is available */
-	if (pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) {
-		ini.is_smcd = true; /* prepare ISM check */
-		rc = smc_find_ism_device(new_smc, &ini);
-		if (!rc)
-			rc = smc_listen_ism_init(new_smc, pclc, &ini);
-		if (!rc)
-			ism_supported = true;
-		else if (pclc->hdr.path == SMC_TYPE_D)
-			goto out_unlock; /* skip RDMA and decline */
-	}
-
-	/* check if RDMA is available */
-	if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */
-		/* prepare RDMA check */
-		ini.is_smcd = false;
-		ini.ism_dev = NULL;
-		ini.ib_lcl = &pclc->lcl;
-		rc = smc_find_rdma_device(new_smc, &ini);
-		if (rc) {
-			/* no RDMA device found */
-			if (pclc->hdr.path == SMC_TYPE_B)
-				/* neither ISM nor RDMA device found */
-				rc = SMC_CLC_DECL_NOSMCDEV;
-			goto out_unlock;
-		}
-		rc = smc_listen_rdma_init(new_smc, &ini);
-		if (rc)
-			goto out_unlock;
-		rc = smc_listen_rdma_reg(new_smc, ini.cln_first_contact);
-		if (rc)
-			goto out_unlock;
-	}
+	/* determine ISM or RoCE device used for connection */
+	rc = smc_listen_find_device(new_smc, pclc, ini);
+	if (rc)
+		goto out_unlock;
 
 	/* send SMC Accept CLC message */
-	rc = smc_clc_send_accept(new_smc, ini.cln_first_contact);
+	rc = smc_clc_send_accept(new_smc, ini->first_contact_local,
+				 ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1);
 	if (rc)
 		goto out_unlock;
 
 	/* SMC-D does not need this lock any more */
-	if (ism_supported)
+	if (ini->is_smcd)
 		mutex_unlock(&smc_server_lgr_pending);
 
 	/* receive SMC Confirm CLC message */
-	rc = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc),
+	memset(buf, 0, sizeof(*buf));
+	cclc = (struct smc_clc_msg_accept_confirm *)buf;
+	rc = smc_clc_wait_msg(new_smc, cclc, sizeof(*buf),
 			      SMC_CLC_CONFIRM, CLC_WAIT_TIME);
 	if (rc) {
-		if (!ism_supported)
+		if (!ini->is_smcd)
 			goto out_unlock;
 		goto out_decl;
 	}
 
 	/* finish worker */
-	if (!ism_supported) {
-		rc = smc_listen_rdma_finish(new_smc, &cclc,
-					    ini.cln_first_contact);
-		mutex_unlock(&smc_server_lgr_pending);
+	if (!ini->is_smcd) {
+		rc = smc_listen_rdma_finish(new_smc, cclc,
+					    ini->first_contact_local);
 		if (rc)
-			return;
+			goto out_unlock;
+		mutex_unlock(&smc_server_lgr_pending);
 	}
-	smc_conn_save_peer_info(new_smc, &cclc);
+	smc_conn_save_peer_info(new_smc, cclc);
 	smc_listen_out_connected(new_smc);
-	return;
+	goto out_free;
 
 out_unlock:
 	mutex_unlock(&smc_server_lgr_pending);
 out_decl:
-	smc_listen_decline(new_smc, rc, ini.cln_first_contact);
+	smc_listen_decline(new_smc, rc, ini ? ini->first_contact_local : 0,
+			   version);
+out_free:
+	kfree(ini);
+	kfree(buf);
 }
 
 static void smc_tcp_listen_work(struct work_struct *work)
@@ -1406,7 +1802,7 @@ static void smc_tcp_listen_work(struct work_struct *work)
 	lock_sock(lsk);
 	while (lsk->sk_state == SMC_LISTEN) {
 		rc = smc_clcsock_accept(lsmc, &new_smc);
-		if (rc)
+		if (rc) /* clcsock accept queue empty or error */
 			goto out;
 		if (!new_smc)
 			continue;
@@ -1420,13 +1816,29 @@ static void smc_tcp_listen_work(struct work_struct *work)
 		new_smc->sk.sk_sndbuf = lsmc->sk.sk_sndbuf;
 		new_smc->sk.sk_rcvbuf = lsmc->sk.sk_rcvbuf;
 		sock_hold(&new_smc->sk); /* sock_put in passive closing */
-		if (!schedule_work(&new_smc->smc_listen_work))
+		if (!queue_work(smc_hs_wq, &new_smc->smc_listen_work))
 			sock_put(&new_smc->sk);
 	}
 
 out:
 	release_sock(lsk);
-	sock_put(&lsmc->sk); /* sock_hold in smc_listen */
+	sock_put(&lsmc->sk); /* sock_hold in smc_clcsock_data_ready() */
+}
+
+static void smc_clcsock_data_ready(struct sock *listen_clcsock)
+{
+	struct smc_sock *lsmc;
+
+	lsmc = (struct smc_sock *)
+	       ((uintptr_t)listen_clcsock->sk_user_data & ~SK_USER_DATA_NOCOPY);
+	if (!lsmc)
+		return;
+	lsmc->clcsk_data_ready(listen_clcsock);
+	if (lsmc->sk.sk_state == SMC_LISTEN) {
+		sock_hold(&lsmc->sk); /* sock_put in smc_tcp_listen_work() */
+		if (!queue_work(smc_hs_wq, &lsmc->tcp_listen_work))
+			sock_put(&lsmc->sk);
+	}
 }
 
 static int smc_listen(struct socket *sock, int backlog)
@@ -1455,15 +1867,19 @@ static int smc_listen(struct socket *sock, int backlog)
 	if (!smc->use_fallback)
 		tcp_sk(smc->clcsock->sk)->syn_smc = 1;
 
+	/* save original sk_data_ready function and establish
+	 * smc-specific sk_data_ready function
+	 */
+	smc->clcsk_data_ready = smc->clcsock->sk->sk_data_ready;
+	smc->clcsock->sk->sk_data_ready = smc_clcsock_data_ready;
+	smc->clcsock->sk->sk_user_data =
+		(void *)((uintptr_t)smc | SK_USER_DATA_NOCOPY);
 	rc = kernel_listen(smc->clcsock, backlog);
 	if (rc)
 		goto out;
 	sk->sk_max_ack_backlog = backlog;
 	sk->sk_ack_backlog = 0;
 	sk->sk_state = SMC_LISTEN;
-	sock_hold(sk); /* sock_hold in tcp_listen_worker */
-	if (!schedule_work(&smc->tcp_listen_work))
-		sock_put(sk);
 
 out:
 	release_sock(sk);
@@ -1788,8 +2204,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		    sk->sk_state != SMC_LISTEN &&
 		    sk->sk_state != SMC_CLOSED) {
 			if (val)
-				mod_delayed_work(system_wq, &smc->conn.tx_work,
-						 0);
+				mod_delayed_work(smc->conn.lgr->tx_wq,
+						 &smc->conn.tx_work, 0);
 		}
 		break;
 	case TCP_CORK:
@@ -1797,8 +2213,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		    sk->sk_state != SMC_LISTEN &&
 		    sk->sk_state != SMC_CLOSED) {
 			if (!val)
-				mod_delayed_work(system_wq, &smc->conn.tx_work,
-						 0);
+				mod_delayed_work(smc->conn.lgr->tx_wq,
+						 &smc->conn.tx_work, 0);
 		}
 		break;
 	case TCP_DEFER_ACCEPT:
@@ -2077,14 +2493,30 @@ static int __init smc_init(void)
 	if (rc)
 		return rc;
 
-	rc = smc_pnet_init();
+	smc_ism_init();
+	smc_clc_init();
+
+	rc = smc_nl_init();
 	if (rc)
 		goto out_pernet_subsys;
 
+	rc = smc_pnet_init();
+	if (rc)
+		goto out_nl;
+
+	rc = -ENOMEM;
+	smc_hs_wq = alloc_workqueue("smc_hs_wq", 0, 0);
+	if (!smc_hs_wq)
+		goto out_pnet;
+
+	smc_close_wq = alloc_workqueue("smc_close_wq", 0, 0);
+	if (!smc_close_wq)
+		goto out_alloc_hs_wq;
+
 	rc = smc_core_init();
 	if (rc) {
 		pr_err("%s: smc_core_init fails with %d\n", __func__, rc);
-		goto out_pnet;
+		goto out_alloc_wqs;
 	}
 
 	rc = smc_llc_init();
@@ -2136,8 +2568,14 @@ out_proto:
 	proto_unregister(&smc_proto);
 out_core:
 	smc_core_exit();
+out_alloc_wqs:
+	destroy_workqueue(smc_close_wq);
+out_alloc_hs_wq:
+	destroy_workqueue(smc_hs_wq);
 out_pnet:
 	smc_pnet_exit();
+out_nl:
+	smc_nl_exit();
 out_pernet_subsys:
 	unregister_pernet_subsys(&smc_net_ops);
 
@@ -2150,9 +2588,12 @@ static void __exit smc_exit(void)
 	sock_unregister(PF_SMC);
 	smc_core_exit();
 	smc_ib_unregister_client();
+	destroy_workqueue(smc_close_wq);
+	destroy_workqueue(smc_hs_wq);
 	proto_unregister(&smc_proto6);
 	proto_unregister(&smc_proto);
 	smc_pnet_exit();
+	smc_nl_exit();
 	unregister_pernet_subsys(&smc_net_ops);
 	rcu_barrier();
 }
diff --git a/net/smc/smc.h b/net/smc/smc.h
index 6f1c42da7a4c..d65e15f0c944 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -18,9 +18,20 @@
 
 #include "smc_ib.h"
 
+#define SMC_V1		1		/* SMC version V1 */
+#define SMC_V2		2		/* SMC version V2 */
+#define SMC_RELEASE	0
+
 #define SMCPROTO_SMC		0	/* SMC protocol, IPv4 */
 #define SMCPROTO_SMC6		1	/* SMC protocol, IPv6 */
 
+#define SMC_MAX_ISM_DEVS	8	/* max # of proposed non-native ISM
+					 * devices
+					 */
+
+#define SMC_MAX_HOSTNAME_LEN	32
+#define SMC_MAX_EID_LEN		32
+
 extern struct proto smc_proto;
 extern struct proto smc_proto6;
 
@@ -201,6 +212,8 @@ struct smc_connection {
 struct smc_sock {				/* smc sock container */
 	struct sock		sk;
 	struct socket		*clcsock;	/* internal tcp socket */
+	void			(*clcsk_data_ready)(struct sock *sk);
+						/* original data_ready fct. **/
 	struct smc_connection	conn;		/* smc connection */
 	struct smc_sock		*listen_smc;	/* listen parent */
 	struct work_struct	connect_work;	/* handle non-blocking connect*/
@@ -235,10 +248,16 @@ static inline struct smc_sock *smc_sk(const struct sock *sk)
 	return (struct smc_sock *)sk;
 }
 
+extern struct workqueue_struct	*smc_hs_wq;	/* wq for handshake work */
+extern struct workqueue_struct	*smc_close_wq;	/* wq for close work */
+
 #define SMC_SYSTEMID_LEN		8
 
 extern u8	local_systemid[SMC_SYSTEMID_LEN]; /* unique system identifier */
 
+#define ntohll(x) be64_to_cpu(x)
+#define htonll(x) cpu_to_be64(x)
+
 /* convert an u32 value into network byte order, store it into a 3 byte field */
 static inline void hton24(u8 *net, u32 host)
 {
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index ce468ff62a19..f23f558054a7 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -299,7 +299,7 @@ static void smc_cdc_msg_validate(struct smc_sock *smc, struct smc_cdc_msg *cdc,
 		conn->lnk = link;
 		spin_unlock_bh(&conn->send_lock);
 		sock_hold(&smc->sk); /* sock_put in abort_work */
-		if (!schedule_work(&conn->abort_work))
+		if (!queue_work(smc_close_wq, &conn->abort_work))
 			sock_put(&smc->sk);
 	}
 }
@@ -368,7 +368,7 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 			smc->clcsock->sk->sk_shutdown |= RCV_SHUTDOWN;
 		sock_set_flag(&smc->sk, SOCK_DONE);
 		sock_hold(&smc->sk); /* sock_put in close_work */
-		if (!schedule_work(&conn->close_work))
+		if (!queue_work(smc_close_wq, &conn->close_work))
 			sock_put(&smc->sk);
 	}
 }
@@ -389,9 +389,9 @@ static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc)
  * Context:
  * - tasklet context
  */
-static void smcd_cdc_rx_tsklet(unsigned long data)
+static void smcd_cdc_rx_tsklet(struct tasklet_struct *t)
 {
-	struct smc_connection *conn = (struct smc_connection *)data;
+	struct smc_connection *conn = from_tasklet(conn, t, rx_tsklet);
 	struct smcd_cdc_msg *data_cdc;
 	struct smcd_cdc_msg cdc;
 	struct smc_sock *smc;
@@ -411,7 +411,7 @@ static void smcd_cdc_rx_tsklet(unsigned long data)
  */
 void smcd_cdc_rx_init(struct smc_connection *conn)
 {
-	tasklet_init(&conn->rx_tsklet, smcd_cdc_rx_tsklet, (unsigned long)conn);
+	tasklet_setup(&conn->rx_tsklet, smcd_cdc_rx_tsklet);
 }
 
 /***************************** init, exit, misc ******************************/
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 779f4142a11d..e286dafd6e88 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -14,6 +14,8 @@
 #include <linux/inetdevice.h>
 #include <linux/if_ether.h>
 #include <linux/sched/signal.h>
+#include <linux/utsname.h>
+#include <linux/ctype.h>
 
 #include <net/addrconf.h>
 #include <net/sock.h>
@@ -27,6 +29,7 @@
 
 #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68
 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48
+#define SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 78
 #define SMC_CLC_RECV_BUF_LEN	100
 
 /* eye catcher "SMCR" EBCDIC for CLC messages */
@@ -34,13 +37,88 @@ static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'};
 /* eye catcher "SMCD" EBCDIC for CLC messages */
 static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'};
 
+static u8 smc_hostname[SMC_MAX_HOSTNAME_LEN];
+
+/* check arriving CLC proposal */
+static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc)
+{
+	struct smc_clc_msg_proposal_prefix *pclc_prfx;
+	struct smc_clc_smcd_v2_extension *smcd_v2_ext;
+	struct smc_clc_msg_hdr *hdr = &pclc->hdr;
+	struct smc_clc_v2_extension *v2_ext;
+
+	v2_ext = smc_get_clc_v2_ext(pclc);
+	pclc_prfx = smc_clc_proposal_get_prefix(pclc);
+	if (hdr->version == SMC_V1) {
+		if (hdr->typev1 == SMC_TYPE_N)
+			return false;
+		if (ntohs(hdr->length) !=
+			sizeof(*pclc) + ntohs(pclc->iparea_offset) +
+			sizeof(*pclc_prfx) +
+			pclc_prfx->ipv6_prefixes_cnt *
+				sizeof(struct smc_clc_ipv6_prefix) +
+			sizeof(struct smc_clc_msg_trail))
+			return false;
+	} else {
+		if (ntohs(hdr->length) !=
+			sizeof(*pclc) +
+			sizeof(struct smc_clc_msg_smcd) +
+			(hdr->typev1 != SMC_TYPE_N ?
+				sizeof(*pclc_prfx) +
+				pclc_prfx->ipv6_prefixes_cnt *
+				sizeof(struct smc_clc_ipv6_prefix) : 0) +
+			(hdr->typev2 != SMC_TYPE_N ?
+				sizeof(*v2_ext) +
+				v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN : 0) +
+			(smcd_indicated(hdr->typev2) ?
+				sizeof(*smcd_v2_ext) + v2_ext->hdr.ism_gid_cnt *
+					sizeof(struct smc_clc_smcd_gid_chid) :
+				0) +
+			sizeof(struct smc_clc_msg_trail))
+			return false;
+	}
+	return true;
+}
+
+/* check arriving CLC accept or confirm */
+static bool
+smc_clc_msg_acc_conf_valid(struct smc_clc_msg_accept_confirm_v2 *clc_v2)
+{
+	struct smc_clc_msg_hdr *hdr = &clc_v2->hdr;
+
+	if (hdr->typev1 != SMC_TYPE_R && hdr->typev1 != SMC_TYPE_D)
+		return false;
+	if (hdr->version == SMC_V1) {
+		if ((hdr->typev1 == SMC_TYPE_R &&
+		     ntohs(hdr->length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) ||
+		    (hdr->typev1 == SMC_TYPE_D &&
+		     ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN))
+			return false;
+	} else {
+		if (hdr->typev1 == SMC_TYPE_D &&
+		    ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 &&
+		    (ntohs(hdr->length) != SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 +
+				sizeof(struct smc_clc_first_contact_ext)))
+			return false;
+	}
+	return true;
+}
+
+static void smc_clc_fill_fce(struct smc_clc_first_contact_ext *fce, int *len)
+{
+	memset(fce, 0, sizeof(*fce));
+	fce->os_type = SMC_CLC_OS_LINUX;
+	fce->release = SMC_RELEASE;
+	memcpy(fce->hostname, smc_hostname, sizeof(smc_hostname));
+	(*len) += sizeof(*fce);
+}
+
 /* check if received message has a correct header length and contains valid
  * heading and trailing eyecatchers
  */
 static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl)
 {
-	struct smc_clc_msg_proposal_prefix *pclc_prfx;
-	struct smc_clc_msg_accept_confirm *clc;
+	struct smc_clc_msg_accept_confirm_v2 *clc_v2;
 	struct smc_clc_msg_proposal *pclc;
 	struct smc_clc_msg_decline *dclc;
 	struct smc_clc_msg_trail *trl;
@@ -51,29 +129,19 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm, bool check_trl)
 	switch (clcm->type) {
 	case SMC_CLC_PROPOSAL:
 		pclc = (struct smc_clc_msg_proposal *)clcm;
-		pclc_prfx = smc_clc_proposal_get_prefix(pclc);
-		if (ntohs(pclc->hdr.length) <
-			sizeof(*pclc) + ntohs(pclc->iparea_offset) +
-			sizeof(*pclc_prfx) +
-			pclc_prfx->ipv6_prefixes_cnt *
-				sizeof(struct smc_clc_ipv6_prefix) +
-			sizeof(*trl))
+		if (!smc_clc_msg_prop_valid(pclc))
 			return false;
 		trl = (struct smc_clc_msg_trail *)
 			((u8 *)pclc + ntohs(pclc->hdr.length) - sizeof(*trl));
 		break;
 	case SMC_CLC_ACCEPT:
 	case SMC_CLC_CONFIRM:
-		if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D)
-			return false;
-		clc = (struct smc_clc_msg_accept_confirm *)clcm;
-		if ((clcm->path == SMC_TYPE_R &&
-		     ntohs(clc->hdr.length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) ||
-		    (clcm->path == SMC_TYPE_D &&
-		     ntohs(clc->hdr.length) != SMCD_CLC_ACCEPT_CONFIRM_LEN))
+		clc_v2 = (struct smc_clc_msg_accept_confirm_v2 *)clcm;
+		if (!smc_clc_msg_acc_conf_valid(clc_v2))
 			return false;
 		trl = (struct smc_clc_msg_trail *)
-			((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl));
+			((u8 *)clc_v2 + ntohs(clc_v2->hdr.length) -
+							sizeof(*trl));
 		break;
 	case SMC_CLC_DECLINE:
 		dclc = (struct smc_clc_msg_decline *)clcm;
@@ -153,7 +221,6 @@ static int smc_clc_prfx_set(struct socket *clcsock,
 	struct sockaddr_in *addr;
 	int rc = -ENOENT;
 
-	memset(prop, 0, sizeof(*prop));
 	if (!dst) {
 		rc = -ENOTCONN;
 		goto out;
@@ -320,7 +387,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	}
 	datlen = ntohs(clcm->length);
 	if ((len < sizeof(struct smc_clc_msg_hdr)) ||
-	    (clcm->version < SMC_CLC_V1) ||
+	    (clcm->version < SMC_V1) ||
 	    ((clcm->type != SMC_CLC_DECLINE) &&
 	     (clcm->type != expected_type))) {
 		smc->sk.sk_err = EPROTO;
@@ -328,9 +395,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		goto out;
 	}
 
-	if (clcm->type == SMC_CLC_PROPOSAL && clcm->path == SMC_TYPE_N)
-		reason_code = SMC_CLC_DECL_VERSMISMAT; /* just V2 offered */
-
 	/* receive the complete CLC message */
 	memset(&msg, 0, sizeof(struct msghdr));
 	if (datlen > buflen) {
@@ -366,7 +430,8 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		dclc = (struct smc_clc_msg_decline *)clcm;
 		reason_code = SMC_CLC_DECL_PEERDECL;
 		smc->peer_diagnosis = ntohl(dclc->peer_diagnosis);
-		if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
+		if (((struct smc_clc_msg_decline *)buf)->hdr.typev2 &
+						SMC_FIRST_CONTACT_MASK) {
 			smc->conn.lgr->sync_err = 1;
 			smc_lgr_terminate_sched(smc->conn.lgr);
 		}
@@ -378,7 +443,7 @@ out:
 }
 
 /* send CLC DECLINE message across internal TCP socket */
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version)
 {
 	struct smc_clc_msg_decline dclc;
 	struct msghdr msg;
@@ -389,8 +454,10 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 	memcpy(dclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	dclc.hdr.type = SMC_CLC_DECLINE;
 	dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline));
-	dclc.hdr.version = SMC_CLC_V1;
-	dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0;
+	dclc.hdr.version = version;
+	dclc.os_type = version == SMC_V1 ? 0 : SMC_CLC_OS_LINUX;
+	dclc.hdr.typev2 = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ?
+						SMC_FIRST_CONTACT_MASK : 0;
 	if ((!smc->conn.lgr || !smc->conn.lgr->is_smcd) &&
 	    smc_ib_is_valid_local_systemid())
 		memcpy(dclc.id_for_peer, local_systemid,
@@ -409,142 +476,274 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 }
 
 /* send CLC PROPOSAL message across internal TCP socket */
-int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
-			  struct smc_init_info *ini)
+int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini)
 {
-	struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
-	struct smc_clc_msg_proposal_prefix pclc_prfx;
-	struct smc_clc_msg_smcd pclc_smcd;
-	struct smc_clc_msg_proposal pclc;
-	struct smc_clc_msg_trail trl;
+	struct smc_clc_smcd_v2_extension *smcd_v2_ext;
+	struct smc_clc_msg_proposal_prefix *pclc_prfx;
+	struct smc_clc_msg_proposal *pclc_base;
+	struct smc_clc_smcd_gid_chid *gidchids;
+	struct smc_clc_msg_proposal_area *pclc;
+	struct smc_clc_ipv6_prefix *ipv6_prfx;
+	struct smc_clc_v2_extension *v2_ext;
+	struct smc_clc_msg_smcd *pclc_smcd;
+	struct smc_clc_msg_trail *trl;
 	int len, i, plen, rc;
 	int reason_code = 0;
-	struct kvec vec[5];
+	struct kvec vec[8];
 	struct msghdr msg;
 
+	pclc = kzalloc(sizeof(*pclc), GFP_KERNEL);
+	if (!pclc)
+		return -ENOMEM;
+
+	pclc_base = &pclc->pclc_base;
+	pclc_smcd = &pclc->pclc_smcd;
+	pclc_prfx = &pclc->pclc_prfx;
+	ipv6_prfx = pclc->pclc_prfx_ipv6;
+	v2_ext = &pclc->pclc_v2_ext;
+	smcd_v2_ext = &pclc->pclc_smcd_v2_ext;
+	gidchids = pclc->pclc_gidchids;
+	trl = &pclc->pclc_trl;
+
+	pclc_base->hdr.version = SMC_V2;
+	pclc_base->hdr.typev1 = ini->smc_type_v1;
+	pclc_base->hdr.typev2 = ini->smc_type_v2;
+	plen = sizeof(*pclc_base) + sizeof(*pclc_smcd) + sizeof(*trl);
+
 	/* retrieve ip prefixes for CLC proposal msg */
-	rc = smc_clc_prfx_set(smc->clcsock, &pclc_prfx, ipv6_prfx);
-	if (rc)
-		return SMC_CLC_DECL_CNFERR; /* configuration error */
+	if (ini->smc_type_v1 != SMC_TYPE_N) {
+		rc = smc_clc_prfx_set(smc->clcsock, pclc_prfx, ipv6_prfx);
+		if (rc) {
+			if (ini->smc_type_v2 == SMC_TYPE_N) {
+				kfree(pclc);
+				return SMC_CLC_DECL_CNFERR;
+			}
+			pclc_base->hdr.typev1 = SMC_TYPE_N;
+		} else {
+			pclc_base->iparea_offset = htons(sizeof(*pclc_smcd));
+			plen += sizeof(*pclc_prfx) +
+					pclc_prfx->ipv6_prefixes_cnt *
+					sizeof(ipv6_prfx[0]);
+		}
+	}
 
-	/* send SMC Proposal CLC message */
-	plen = sizeof(pclc) + sizeof(pclc_prfx) +
-	       (pclc_prfx.ipv6_prefixes_cnt * sizeof(ipv6_prfx[0])) +
-	       sizeof(trl);
-	memset(&pclc, 0, sizeof(pclc));
-	memcpy(pclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
-	pclc.hdr.type = SMC_CLC_PROPOSAL;
-	pclc.hdr.version = SMC_CLC_V1;		/* SMC version */
-	pclc.hdr.path = smc_type;
-	if (smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B) {
+	/* build SMC Proposal CLC message */
+	memcpy(pclc_base->hdr.eyecatcher, SMC_EYECATCHER,
+	       sizeof(SMC_EYECATCHER));
+	pclc_base->hdr.type = SMC_CLC_PROPOSAL;
+	if (smcr_indicated(ini->smc_type_v1)) {
 		/* add SMC-R specifics */
-		memcpy(pclc.lcl.id_for_peer, local_systemid,
+		memcpy(pclc_base->lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
-		memcpy(&pclc.lcl.gid, ini->ib_gid, SMC_GID_SIZE);
-		memcpy(&pclc.lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1],
+		memcpy(pclc_base->lcl.gid, ini->ib_gid, SMC_GID_SIZE);
+		memcpy(pclc_base->lcl.mac, &ini->ib_dev->mac[ini->ib_port - 1],
 		       ETH_ALEN);
-		pclc.iparea_offset = htons(0);
 	}
-	if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
+	if (smcd_indicated(ini->smc_type_v1)) {
 		/* add SMC-D specifics */
-		memset(&pclc_smcd, 0, sizeof(pclc_smcd));
-		plen += sizeof(pclc_smcd);
-		pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET);
-		pclc_smcd.gid = ini->ism_dev->local_gid;
+		if (ini->ism_dev[0]) {
+			pclc_smcd->ism.gid = htonll(ini->ism_dev[0]->local_gid);
+			pclc_smcd->ism.chid =
+				htons(smc_ism_get_chid(ini->ism_dev[0]));
+		}
 	}
-	pclc.hdr.length = htons(plen);
+	if (ini->smc_type_v2 == SMC_TYPE_N) {
+		pclc_smcd->v2_ext_offset = 0;
+	} else {
+		u16 v2_ext_offset;
+		u8 *eid = NULL;
+
+		v2_ext_offset = sizeof(*pclc_smcd) -
+			offsetofend(struct smc_clc_msg_smcd, v2_ext_offset);
+		if (ini->smc_type_v1 != SMC_TYPE_N)
+			v2_ext_offset += sizeof(*pclc_prfx) +
+						pclc_prfx->ipv6_prefixes_cnt *
+						sizeof(ipv6_prfx[0]);
+		pclc_smcd->v2_ext_offset = htons(v2_ext_offset);
+		v2_ext->hdr.eid_cnt = 0;
+		v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt;
+		v2_ext->hdr.flag.release = SMC_RELEASE;
+		v2_ext->hdr.flag.seid = 1;
+		v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) -
+				offsetofend(struct smc_clnt_opts_area_hdr,
+					    smcd_v2_ext_offset) +
+				v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN);
+		if (ini->ism_dev[0])
+			smc_ism_get_system_eid(ini->ism_dev[0], &eid);
+		else
+			smc_ism_get_system_eid(ini->ism_dev[1], &eid);
+		if (eid)
+			memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN);
+		plen += sizeof(*v2_ext) + sizeof(*smcd_v2_ext);
+		if (ini->ism_offered_cnt) {
+			for (i = 1; i <= ini->ism_offered_cnt; i++) {
+				gidchids[i - 1].gid =
+					htonll(ini->ism_dev[i]->local_gid);
+				gidchids[i - 1].chid =
+					htons(smc_ism_get_chid(ini->ism_dev[i]));
+			}
+			plen += ini->ism_offered_cnt *
+				sizeof(struct smc_clc_smcd_gid_chid);
+		}
+	}
+	pclc_base->hdr.length = htons(plen);
+	memcpy(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 
-	memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	/* send SMC Proposal CLC message */
 	memset(&msg, 0, sizeof(msg));
 	i = 0;
-	vec[i].iov_base = &pclc;
-	vec[i++].iov_len = sizeof(pclc);
-	if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
-		vec[i].iov_base = &pclc_smcd;
-		vec[i++].iov_len = sizeof(pclc_smcd);
+	vec[i].iov_base = pclc_base;
+	vec[i++].iov_len = sizeof(*pclc_base);
+	vec[i].iov_base = pclc_smcd;
+	vec[i++].iov_len = sizeof(*pclc_smcd);
+	if (ini->smc_type_v1 != SMC_TYPE_N) {
+		vec[i].iov_base = pclc_prfx;
+		vec[i++].iov_len = sizeof(*pclc_prfx);
+		if (pclc_prfx->ipv6_prefixes_cnt > 0) {
+			vec[i].iov_base = ipv6_prfx;
+			vec[i++].iov_len = pclc_prfx->ipv6_prefixes_cnt *
+					   sizeof(ipv6_prfx[0]);
+		}
 	}
-	vec[i].iov_base = &pclc_prfx;
-	vec[i++].iov_len = sizeof(pclc_prfx);
-	if (pclc_prfx.ipv6_prefixes_cnt > 0) {
-		vec[i].iov_base = &ipv6_prfx[0];
-		vec[i++].iov_len = pclc_prfx.ipv6_prefixes_cnt *
-				   sizeof(ipv6_prfx[0]);
+	if (ini->smc_type_v2 != SMC_TYPE_N) {
+		vec[i].iov_base = v2_ext;
+		vec[i++].iov_len = sizeof(*v2_ext);
+		vec[i].iov_base = smcd_v2_ext;
+		vec[i++].iov_len = sizeof(*smcd_v2_ext);
+		if (ini->ism_offered_cnt) {
+			vec[i].iov_base = gidchids;
+			vec[i++].iov_len = ini->ism_offered_cnt *
+					sizeof(struct smc_clc_smcd_gid_chid);
+		}
 	}
-	vec[i].iov_base = &trl;
-	vec[i++].iov_len = sizeof(trl);
+	vec[i].iov_base = trl;
+	vec[i++].iov_len = sizeof(*trl);
 	/* due to the few bytes needed for clc-handshake this cannot block */
 	len = kernel_sendmsg(smc->clcsock, &msg, vec, i, plen);
 	if (len < 0) {
 		smc->sk.sk_err = smc->clcsock->sk->sk_err;
 		reason_code = -smc->sk.sk_err;
-	} else if (len < (int)sizeof(pclc)) {
+	} else if (len < ntohs(pclc_base->hdr.length)) {
 		reason_code = -ENETUNREACH;
 		smc->sk.sk_err = -reason_code;
 	}
 
+	kfree(pclc);
 	return reason_code;
 }
 
-/* send CLC CONFIRM message across internal TCP socket */
-int smc_clc_send_confirm(struct smc_sock *smc)
+/* build and send CLC CONFIRM / ACCEPT message */
+static int smc_clc_send_confirm_accept(struct smc_sock *smc,
+				       struct smc_clc_msg_accept_confirm_v2 *clc_v2,
+				       int first_contact, u8 version)
 {
 	struct smc_connection *conn = &smc->conn;
-	struct smc_clc_msg_accept_confirm cclc;
-	struct smc_link *link;
-	int reason_code = 0;
+	struct smc_clc_msg_accept_confirm *clc;
+	struct smc_clc_first_contact_ext fce;
+	struct smc_clc_msg_trail trl;
+	struct kvec vec[3];
 	struct msghdr msg;
-	struct kvec vec;
-	int len;
+	int i, len;
 
 	/* send SMC Confirm CLC msg */
-	memset(&cclc, 0, sizeof(cclc));
-	cclc.hdr.type = SMC_CLC_CONFIRM;
-	cclc.hdr.version = SMC_CLC_V1;		/* SMC version */
-	if (smc->conn.lgr->is_smcd) {
+	clc = (struct smc_clc_msg_accept_confirm *)clc_v2;
+	clc->hdr.version = version;	/* SMC version */
+	if (first_contact)
+		clc->hdr.typev2 |= SMC_FIRST_CONTACT_MASK;
+	if (conn->lgr->is_smcd) {
 		/* SMC-D specific settings */
-		memcpy(cclc.hdr.eyecatcher, SMCD_EYECATCHER,
+		memcpy(clc->hdr.eyecatcher, SMCD_EYECATCHER,
 		       sizeof(SMCD_EYECATCHER));
-		cclc.hdr.path = SMC_TYPE_D;
-		cclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
-		cclc.gid = conn->lgr->smcd->local_gid;
-		cclc.token = conn->rmb_desc->token;
-		cclc.dmbe_size = conn->rmbe_size_short;
-		cclc.dmbe_idx = 0;
-		memcpy(&cclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
-		memcpy(cclc.smcd_trl.eyecatcher, SMCD_EYECATCHER,
+		clc->hdr.typev1 = SMC_TYPE_D;
+		clc->d0.gid = conn->lgr->smcd->local_gid;
+		clc->d0.token = conn->rmb_desc->token;
+		clc->d0.dmbe_size = conn->rmbe_size_short;
+		clc->d0.dmbe_idx = 0;
+		memcpy(&clc->d0.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
+		if (version == SMC_V1) {
+			clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+		} else {
+			u8 *eid = NULL;
+
+			clc_v2->chid = htons(smc_ism_get_chid(conn->lgr->smcd));
+			smc_ism_get_system_eid(conn->lgr->smcd, &eid);
+			if (eid)
+				memcpy(clc_v2->eid, eid, SMC_MAX_EID_LEN);
+			len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2;
+			if (first_contact)
+				smc_clc_fill_fce(&fce, &len);
+			clc_v2->hdr.length = htons(len);
+		}
+		memcpy(trl.eyecatcher, SMCD_EYECATCHER,
 		       sizeof(SMCD_EYECATCHER));
 	} else {
+		struct smc_link *link = conn->lnk;
+
 		/* SMC-R specific settings */
 		link = conn->lnk;
-		memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER,
+		memcpy(clc->hdr.eyecatcher, SMC_EYECATCHER,
 		       sizeof(SMC_EYECATCHER));
-		cclc.hdr.path = SMC_TYPE_R;
-		cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
-		memcpy(cclc.lcl.id_for_peer, local_systemid,
+		clc->hdr.typev1 = SMC_TYPE_R;
+		clc->hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
+		memcpy(clc->r0.lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
-		memcpy(&cclc.lcl.gid, link->gid, SMC_GID_SIZE);
-		memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
+		memcpy(&clc->r0.lcl.gid, link->gid, SMC_GID_SIZE);
+		memcpy(&clc->r0.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
 		       ETH_ALEN);
-		hton24(cclc.qpn, link->roce_qp->qp_num);
-		cclc.rmb_rkey =
+		hton24(clc->r0.qpn, link->roce_qp->qp_num);
+		clc->r0.rmb_rkey =
 			htonl(conn->rmb_desc->mr_rx[link->link_idx]->rkey);
-		cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
-		cclc.rmbe_alert_token = htonl(conn->alert_token_local);
-		cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
-		cclc.rmbe_size = conn->rmbe_size_short;
-		cclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
+		clc->r0.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
+		clc->r0.rmbe_alert_token = htonl(conn->alert_token_local);
+		switch (clc->hdr.type) {
+		case SMC_CLC_ACCEPT:
+			clc->r0.qp_mtu = link->path_mtu;
+			break;
+		case SMC_CLC_CONFIRM:
+			clc->r0.qp_mtu = min(link->path_mtu, link->peer_mtu);
+			break;
+		}
+		clc->r0.rmbe_size = conn->rmbe_size_short;
+		clc->r0.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
 				(conn->rmb_desc->sgt[link->link_idx].sgl));
-		hton24(cclc.psn, link->psn_initial);
-		memcpy(cclc.smcr_trl.eyecatcher, SMC_EYECATCHER,
-		       sizeof(SMC_EYECATCHER));
+		hton24(clc->r0.psn, link->psn_initial);
+		memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	}
 
 	memset(&msg, 0, sizeof(msg));
-	vec.iov_base = &cclc;
-	vec.iov_len = ntohs(cclc.hdr.length);
-	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
-			     ntohs(cclc.hdr.length));
-	if (len < ntohs(cclc.hdr.length)) {
+	i = 0;
+	vec[i].iov_base = clc_v2;
+	if (version > SMC_V1)
+		vec[i++].iov_len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2 - sizeof(trl);
+	else
+		vec[i++].iov_len = (clc->hdr.typev1 == SMC_TYPE_D ?
+						SMCD_CLC_ACCEPT_CONFIRM_LEN :
+						SMCR_CLC_ACCEPT_CONFIRM_LEN) -
+				   sizeof(trl);
+	if (version > SMC_V1 && first_contact) {
+		vec[i].iov_base = &fce;
+		vec[i++].iov_len = sizeof(fce);
+	}
+	vec[i].iov_base = &trl;
+	vec[i++].iov_len = sizeof(trl);
+	return kernel_sendmsg(smc->clcsock, &msg, vec, 1,
+			      ntohs(clc->hdr.length));
+}
+
+/* send CLC CONFIRM message across internal TCP socket */
+int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
+			 u8 version)
+{
+	struct smc_clc_msg_accept_confirm_v2 cclc_v2;
+	int reason_code = 0;
+	int len;
+
+	/* send SMC Confirm CLC msg */
+	memset(&cclc_v2, 0, sizeof(cclc_v2));
+	cclc_v2.hdr.type = SMC_CLC_CONFIRM;
+	len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact,
+					  version);
+	if (len < ntohs(cclc_v2.hdr.length)) {
 		if (len >= 0) {
 			reason_code = -ENETUNREACH;
 			smc->sk.sk_err = -reason_code;
@@ -557,67 +756,33 @@ int smc_clc_send_confirm(struct smc_sock *smc)
 }
 
 /* send CLC ACCEPT message across internal TCP socket */
-int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
+int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact,
+			u8 version)
 {
-	struct smc_connection *conn = &new_smc->conn;
-	struct smc_clc_msg_accept_confirm aclc;
-	struct smc_link *link;
-	struct msghdr msg;
-	struct kvec vec;
+	struct smc_clc_msg_accept_confirm_v2 aclc_v2;
 	int len;
 
-	memset(&aclc, 0, sizeof(aclc));
-	aclc.hdr.type = SMC_CLC_ACCEPT;
-	aclc.hdr.version = SMC_CLC_V1;		/* SMC version */
-	if (srv_first_contact)
-		aclc.hdr.flag = 1;
-
-	if (new_smc->conn.lgr->is_smcd) {
-		/* SMC-D specific settings */
-		aclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
-		memcpy(aclc.hdr.eyecatcher, SMCD_EYECATCHER,
-		       sizeof(SMCD_EYECATCHER));
-		aclc.hdr.path = SMC_TYPE_D;
-		aclc.gid = conn->lgr->smcd->local_gid;
-		aclc.token = conn->rmb_desc->token;
-		aclc.dmbe_size = conn->rmbe_size_short;
-		aclc.dmbe_idx = 0;
-		memcpy(&aclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
-		memcpy(aclc.smcd_trl.eyecatcher, SMCD_EYECATCHER,
-		       sizeof(SMCD_EYECATCHER));
-	} else {
-		/* SMC-R specific settings */
-		aclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
-		memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER,
-		       sizeof(SMC_EYECATCHER));
-		aclc.hdr.path = SMC_TYPE_R;
-		link = conn->lnk;
-		memcpy(aclc.lcl.id_for_peer, local_systemid,
-		       sizeof(local_systemid));
-		memcpy(&aclc.lcl.gid, link->gid, SMC_GID_SIZE);
-		memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1],
-		       ETH_ALEN);
-		hton24(aclc.qpn, link->roce_qp->qp_num);
-		aclc.rmb_rkey =
-			htonl(conn->rmb_desc->mr_rx[link->link_idx]->rkey);
-		aclc.rmbe_idx = 1;		/* as long as 1 RMB = 1 RMBE */
-		aclc.rmbe_alert_token = htonl(conn->alert_token_local);
-		aclc.qp_mtu = link->path_mtu;
-		aclc.rmbe_size = conn->rmbe_size_short,
-		aclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
-				(conn->rmb_desc->sgt[link->link_idx].sgl));
-		hton24(aclc.psn, link->psn_initial);
-		memcpy(aclc.smcr_trl.eyecatcher, SMC_EYECATCHER,
-		       sizeof(SMC_EYECATCHER));
-	}
-
-	memset(&msg, 0, sizeof(msg));
-	vec.iov_base = &aclc;
-	vec.iov_len = ntohs(aclc.hdr.length);
-	len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1,
-			     ntohs(aclc.hdr.length));
-	if (len < ntohs(aclc.hdr.length))
+	memset(&aclc_v2, 0, sizeof(aclc_v2));
+	aclc_v2.hdr.type = SMC_CLC_ACCEPT;
+	len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact,
+					  version);
+	if (len < ntohs(aclc_v2.hdr.length))
 		len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err;
 
 	return len > 0 ? 0 : len;
 }
+
+void smc_clc_get_hostname(u8 **host)
+{
+	*host = &smc_hostname[0];
+}
+
+void __init smc_clc_init(void)
+{
+	struct new_utsname *u;
+
+	memset(smc_hostname, _S, sizeof(smc_hostname)); /* ASCII blanks */
+	u = utsname();
+	memcpy(smc_hostname, u->nodename,
+	       min_t(size_t, strlen(u->nodename), sizeof(smc_hostname)));
+}
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index cf7b45306f4e..32d37f7b70f2 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -22,7 +22,6 @@
 #define SMC_CLC_CONFIRM		0x03
 #define SMC_CLC_DECLINE		0x04
 
-#define SMC_CLC_V1		0x1		/* SMC version                */
 #define SMC_TYPE_R		0		/* SMC-R only		      */
 #define SMC_TYPE_D		1		/* SMC-D only		      */
 #define SMC_TYPE_N		2		/* neither SMC-R nor SMC-D    */
@@ -38,7 +37,11 @@
 #define SMC_CLC_DECL_NOSMCDEV	0x03030000  /* no SMC device found (R or D)   */
 #define SMC_CLC_DECL_NOSMCDDEV	0x03030001  /* no SMC-D device found	      */
 #define SMC_CLC_DECL_NOSMCRDEV	0x03030002  /* no SMC-R device found	      */
-#define SMC_CLC_DECL_SMCDNOTALK	0x03030003  /* SMC-D dev can't talk to peer   */
+#define SMC_CLC_DECL_NOISM2SUPP	0x03030003  /* hardware has no ISMv2 support  */
+#define SMC_CLC_DECL_NOV2EXT	0x03030004  /* peer sent no clc v2 extension  */
+#define SMC_CLC_DECL_NOV2DEXT	0x03030005  /* peer sent no clc SMC-Dv2 ext.  */
+#define SMC_CLC_DECL_NOSEID	0x03030006  /* peer sent no SEID	      */
+#define SMC_CLC_DECL_NOSMCD2DEV	0x03030007  /* no SMC-Dv2 device found	      */
 #define SMC_CLC_DECL_MODEUNSUPP	0x03040000  /* smc modes do not match (R or D)*/
 #define SMC_CLC_DECL_RMBE_EC	0x03050000  /* peer has eyecatcher in RMBE    */
 #define SMC_CLC_DECL_OPTUNSUPP	0x03060000  /* fastopen sockopt not supported */
@@ -56,19 +59,19 @@
 #define SMC_CLC_DECL_ERR_RDYLNK	0x09990002  /*	 ib ready link failed	      */
 #define SMC_CLC_DECL_ERR_REGRMB	0x09990003  /*	 reg rmb failed		      */
 
+#define SMC_FIRST_CONTACT_MASK	0b10	/* first contact bit within typev2 */
+
 struct smc_clc_msg_hdr {	/* header1 of clc messages */
 	u8 eyecatcher[4];	/* eye catcher */
 	u8 type;		/* proposal / accept / confirm / decline */
 	__be16 length;
 #if defined(__BIG_ENDIAN_BITFIELD)
 	u8 version : 4,
-	   flag    : 1,
-	   rsvd	   : 1,
-	   path	   : 2;
+	   typev2  : 2,
+	   typev1  : 2;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-	u8 path    : 2,
-	   rsvd    : 1,
-	   flag    : 1,
+	u8 typev1  : 2,
+	   typev2  : 2,
 	   version : 4;
 #endif
 } __packed;			/* format defined in RFC7609 */
@@ -83,8 +86,6 @@ struct smc_clc_msg_local {	/* header2 of clc messages */
 	u8 mac[6];		/* mac of ib_device port */
 };
 
-#define SMC_CLC_MAX_V6_PREFIX	8
-
 /* Struct would be 4 byte aligned, but it is used in an array that is sent
  * to peers and must conform to RFC7609, hence we need to use packed here.
  */
@@ -93,6 +94,44 @@ struct smc_clc_ipv6_prefix {
 	u8 prefix_len;
 } __packed;			/* format defined in RFC7609 */
 
+#if defined(__BIG_ENDIAN_BITFIELD)
+struct smc_clc_v2_flag {
+	u8 release : 4,
+	   rsvd    : 3,
+	   seid    : 1;
+};
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+struct smc_clc_v2_flag {
+	u8 seid   : 1,
+	rsvd      : 3,
+	release   : 4;
+};
+#endif
+
+struct smc_clnt_opts_area_hdr {
+	u8 eid_cnt;		/* number of user defined EIDs */
+	u8 ism_gid_cnt;		/* number of ISMv2 GIDs */
+	u8 reserved1;
+	struct smc_clc_v2_flag flag;
+	u8 reserved2[2];
+	__be16 smcd_v2_ext_offset; /* SMC-Dv2 Extension Offset */
+};
+
+struct smc_clc_smcd_gid_chid {
+	__be64 gid;		/* ISM GID */
+	__be16 chid;		/* ISMv2 CHID */
+} __packed;		/* format defined in
+			 * IBM Shared Memory Communications Version 2
+			 * (https://www.ibm.com/support/pages/node/6326337)
+			 */
+
+struct smc_clc_v2_extension {
+	struct smc_clnt_opts_area_hdr hdr;
+	u8 roce[16];		/* RoCEv2 GID */
+	u8 reserved[16];
+	u8 user_eids[][SMC_MAX_EID_LEN];
+};
+
 struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
 	__be32 outgoing_subnet;	/* subnet mask */
 	u8 prefix_len;		/* number of significant bits in mask */
@@ -101,8 +140,15 @@ struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
 } __aligned(4);
 
 struct smc_clc_msg_smcd {	/* SMC-D GID information */
-	u64 gid;		/* ISM GID of requestor */
-	u8 res[32];
+	struct smc_clc_smcd_gid_chid ism; /* ISM native GID+CHID of requestor */
+	__be16 v2_ext_offset;	/* SMC Version 2 Extension Offset */
+	u8 reserved[28];
+};
+
+struct smc_clc_smcd_v2_extension {
+	u8 system_eid[SMC_MAX_EID_LEN];
+	u8 reserved[16];
+	struct smc_clc_smcd_gid_chid gidchid[];
 };
 
 struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
@@ -111,64 +157,107 @@ struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
 	__be16 iparea_offset;	/* offset to IP address information area */
 } __aligned(4);
 
-#define SMC_CLC_PROPOSAL_MAX_OFFSET	0x28
-#define SMC_CLC_PROPOSAL_MAX_PREFIX	(SMC_CLC_MAX_V6_PREFIX * \
-					 sizeof(struct smc_clc_ipv6_prefix))
-#define SMC_CLC_MAX_LEN		(sizeof(struct smc_clc_msg_proposal) + \
-				 SMC_CLC_PROPOSAL_MAX_OFFSET + \
-				 sizeof(struct smc_clc_msg_proposal_prefix) + \
-				 SMC_CLC_PROPOSAL_MAX_PREFIX + \
-				 sizeof(struct smc_clc_msg_trail))
+#define SMC_CLC_MAX_V6_PREFIX		8
 
-struct smc_clc_msg_accept_confirm {	/* clc accept / confirm message */
-	struct smc_clc_msg_hdr hdr;
-	union {
-		struct { /* SMC-R */
-			struct smc_clc_msg_local lcl;
-			u8 qpn[3];		/* QP number */
-			__be32 rmb_rkey;	/* RMB rkey */
-			u8 rmbe_idx;		/* Index of RMBE in RMB */
-			__be32 rmbe_alert_token;/* unique connection id */
+struct smc_clc_msg_proposal_area {
+	struct smc_clc_msg_proposal		pclc_base;
+	struct smc_clc_msg_smcd			pclc_smcd;
+	struct smc_clc_msg_proposal_prefix	pclc_prfx;
+	struct smc_clc_ipv6_prefix	pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX];
+	struct smc_clc_v2_extension		pclc_v2_ext;
+	struct smc_clc_smcd_v2_extension	pclc_smcd_v2_ext;
+	struct smc_clc_smcd_gid_chid		pclc_gidchids[SMC_MAX_ISM_DEVS];
+	struct smc_clc_msg_trail		pclc_trl;
+};
+
+struct smcr_clc_msg_accept_confirm {	/* SMCR accept/confirm */
+	struct smc_clc_msg_local lcl;
+	u8 qpn[3];			/* QP number */
+	__be32 rmb_rkey;		/* RMB rkey */
+	u8 rmbe_idx;			/* Index of RMBE in RMB */
+	__be32 rmbe_alert_token;	/* unique connection id */
+ #if defined(__BIG_ENDIAN_BITFIELD)
+	u8 rmbe_size : 4,		/* buf size (compressed) */
+	   qp_mtu   : 4;		/* QP mtu */
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 qp_mtu   : 4,
+	   rmbe_size : 4;
+#endif
+	u8 reserved;
+	__be64 rmb_dma_addr;	/* RMB virtual address */
+	u8 reserved2;
+	u8 psn[3];		/* packet sequence number */
+} __packed;
+
+struct smcd_clc_msg_accept_confirm_common {	/* SMCD accept/confirm */
+	u64 gid;		/* Sender GID */
+	u64 token;		/* DMB token */
+	u8 dmbe_idx;		/* DMBE index */
 #if defined(__BIG_ENDIAN_BITFIELD)
-			u8 rmbe_size : 4,	/* buf size (compressed) */
-			   qp_mtu   : 4;	/* QP mtu */
+	u8 dmbe_size : 4,	/* buf size (compressed) */
+	   reserved3 : 4;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-			u8 qp_mtu   : 4,
-			   rmbe_size : 4;
+	u8 reserved3 : 4,
+	   dmbe_size : 4;
 #endif
-			u8 reserved;
-			__be64 rmb_dma_addr;	/* RMB virtual address */
-			u8 reserved2;
-			u8 psn[3];		/* packet sequence number */
-			struct smc_clc_msg_trail smcr_trl;
-						/* eye catcher "SMCR" EBCDIC */
-		} __packed;
-		struct { /* SMC-D */
-			u64 gid;		/* Sender GID */
-			u64 token;		/* DMB token */
-			u8 dmbe_idx;		/* DMBE index */
+	u16 reserved4;
+	__be32 linkid;		/* Link identifier */
+} __packed;
+
+#define SMC_CLC_OS_ZOS		1
+#define SMC_CLC_OS_LINUX	2
+#define SMC_CLC_OS_AIX		3
+
+struct smc_clc_first_contact_ext {
+	u8 reserved1;
 #if defined(__BIG_ENDIAN_BITFIELD)
-			u8 dmbe_size : 4,	/* buf size (compressed) */
-			   reserved3 : 4;
+	u8 os_type : 4,
+	   release : 4;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-			u8 reserved3 : 4,
-			   dmbe_size : 4;
+	u8 release : 4,
+	   os_type : 4;
 #endif
-			u16 reserved4;
-			u32 linkid;		/* Link identifier */
+	u8 reserved2[2];
+	u8 hostname[SMC_MAX_HOSTNAME_LEN];
+};
+
+struct smc_clc_msg_accept_confirm {	/* clc accept / confirm message */
+	struct smc_clc_msg_hdr hdr;
+	union {
+		struct smcr_clc_msg_accept_confirm r0; /* SMC-R */
+		struct { /* SMC-D */
+			struct smcd_clc_msg_accept_confirm_common d0;
 			u32 reserved5[3];
-			struct smc_clc_msg_trail smcd_trl;
-						/* eye catcher "SMCD" EBCDIC */
-		} __packed;
+		};
 	};
 } __packed;			/* format defined in RFC7609 */
 
+struct smc_clc_msg_accept_confirm_v2 {	/* clc accept / confirm message */
+	struct smc_clc_msg_hdr hdr;
+	union {
+		struct smcr_clc_msg_accept_confirm r0; /* SMC-R */
+		struct { /* SMC-D */
+			struct smcd_clc_msg_accept_confirm_common d0;
+			__be16 chid;
+			u8 eid[SMC_MAX_EID_LEN];
+			u8 reserved5[8];
+		};
+	};
+};
+
 struct smc_clc_msg_decline {	/* clc decline message */
 	struct smc_clc_msg_hdr hdr;
 	u8 id_for_peer[SMC_SYSTEMID_LEN]; /* sender peer_id */
 	__be32 peer_diagnosis;	/* diagnosis information */
-	u8 reserved2[4];
-	struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */
+#if defined(__BIG_ENDIAN_BITFIELD)
+	u8 os_type  : 4,
+	   reserved : 4;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	u8 reserved : 4,
+	   os_type  : 4;
+#endif
+	u8 reserved2[3];
+	struct smc_clc_msg_trail trl; /* eye catcher "SMCD" or "SMCR" EBCDIC */
 } __aligned(4);
 
 /* determine start of the prefix area within the proposal message */
@@ -179,16 +268,58 @@ smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc)
 	       ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset));
 }
 
+static inline bool smcr_indicated(int smc_type)
+{
+	return smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B;
+}
+
+static inline bool smcd_indicated(int smc_type)
+{
+	return smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B;
+}
+
 /* get SMC-D info from proposal message */
 static inline struct smc_clc_msg_smcd *
 smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop)
 {
-	if (ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd))
+	if (smcd_indicated(prop->hdr.typev1) &&
+	    ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd))
 		return NULL;
 
 	return (struct smc_clc_msg_smcd *)(prop + 1);
 }
 
+static inline struct smc_clc_v2_extension *
+smc_get_clc_v2_ext(struct smc_clc_msg_proposal *prop)
+{
+	struct smc_clc_msg_smcd *prop_smcd = smc_get_clc_msg_smcd(prop);
+
+	if (!prop_smcd || !ntohs(prop_smcd->v2_ext_offset))
+		return NULL;
+
+	return (struct smc_clc_v2_extension *)
+	       ((u8 *)prop_smcd +
+	       offsetof(struct smc_clc_msg_smcd, v2_ext_offset) +
+	       sizeof(prop_smcd->v2_ext_offset) +
+	       ntohs(prop_smcd->v2_ext_offset));
+}
+
+static inline struct smc_clc_smcd_v2_extension *
+smc_get_clc_smcd_v2_ext(struct smc_clc_v2_extension *prop_v2ext)
+{
+	if (!prop_v2ext)
+		return NULL;
+	if (!ntohs(prop_v2ext->hdr.smcd_v2_ext_offset))
+		return NULL;
+
+	return (struct smc_clc_smcd_v2_extension *)
+		((u8 *)prop_v2ext +
+		 offsetof(struct smc_clc_v2_extension, hdr) +
+		 offsetof(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) +
+		 sizeof(prop_v2ext->hdr.smcd_v2_ext_offset) +
+		 ntohs(prop_v2ext->hdr.smcd_v2_ext_offset));
+}
+
 struct smcd_dev;
 struct smc_init_info;
 
@@ -196,10 +327,13 @@ int smc_clc_prfx_match(struct socket *clcsock,
 		       struct smc_clc_msg_proposal_prefix *prop);
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type, unsigned long timeout);
-int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
-int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
-			  struct smc_init_info *ini);
-int smc_clc_send_confirm(struct smc_sock *smc);
-int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);
+int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version);
+int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini);
+int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact,
+			 u8 version);
+int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact,
+			u8 version);
+void smc_clc_init(void) __init;
+void smc_clc_get_hostname(u8 **host);
 
 #endif
diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c
index 0e7409e469c0..0f9ffba07d26 100644
--- a/net/smc/smc_close.c
+++ b/net/smc/smc_close.c
@@ -210,9 +210,9 @@ again:
 		sk->sk_state = SMC_CLOSED;
 		sk->sk_state_change(sk); /* wake up accept */
 		if (smc->clcsock && smc->clcsock->sk) {
+			smc->clcsock->sk->sk_data_ready = smc->clcsk_data_ready;
+			smc->clcsock->sk->sk_user_data = NULL;
 			rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR);
-			/* wake up kernel_accept of smc_tcp_listen_worker */
-			smc->clcsock->sk->sk_data_ready(smc->clcsock->sk);
 		}
 		smc_close_cleanup_listen(sk);
 		release_sock(sk);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index a406627b1d55..0df85a12651e 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -16,6 +16,8 @@
 #include <linux/wait.h>
 #include <linux/reboot.h>
 #include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/smc.h>
 #include <net/tcp.h>
 #include <net/sock.h>
 #include <rdma/ib_verbs.h>
@@ -30,13 +32,13 @@
 #include "smc_cdc.h"
 #include "smc_close.h"
 #include "smc_ism.h"
+#include "smc_netlink.h"
 
 #define SMC_LGR_NUM_INCR		256
 #define SMC_LGR_FREE_DELAY_SERV		(600 * HZ)
 #define SMC_LGR_FREE_DELAY_CLNT		(SMC_LGR_FREE_DELAY_SERV + 10 * HZ)
-#define SMC_LGR_FREE_DELAY_FAST		(8 * HZ)
 
-static struct smc_lgr_list smc_lgr_list = {	/* established link groups */
+struct smc_lgr_list smc_lgr_list = {	/* established link groups */
 	.lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock),
 	.list = LIST_HEAD_INIT(smc_lgr_list.list),
 	.num = 0,
@@ -64,13 +66,23 @@ static inline struct list_head *smc_lgr_list_head(struct smc_link_group *lgr,
 	return &smc_lgr_list.list;
 }
 
+static void smc_ibdev_cnt_inc(struct smc_link *lnk)
+{
+	atomic_inc(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]);
+}
+
+static void smc_ibdev_cnt_dec(struct smc_link *lnk)
+{
+	atomic_dec(&lnk->smcibdev->lnk_cnt_by_port[lnk->ibport - 1]);
+}
+
 static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
 {
 	/* client link group creation always follows the server link group
 	 * creation. For client use a somewhat higher removal delay time,
 	 * otherwise there is a risk of out-of-sync link groups.
 	 */
-	if (!lgr->freeing && !lgr->freefast) {
+	if (!lgr->freeing) {
 		mod_delayed_work(system_wq, &lgr->free_work,
 				 (!lgr->is_smcd && lgr->role == SMC_CLNT) ?
 						SMC_LGR_FREE_DELAY_CLNT :
@@ -78,15 +90,6 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
 	}
 }
 
-void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr)
-{
-	if (!lgr->freeing && !lgr->freefast) {
-		lgr->freefast = 1;
-		mod_delayed_work(system_wq, &lgr->free_work,
-				 SMC_LGR_FREE_DELAY_FAST);
-	}
-}
-
 /* Register connection's alert token in our lookup structure.
  * To use rbtrees we have to implement our own insert core.
  * Requires @conns_lock
@@ -149,6 +152,7 @@ static int smcr_lgr_conn_assign_link(struct smc_connection *conn, bool first)
 	}
 	if (!conn->lnk)
 		return SMC_CLC_DECL_NOACTLINK;
+	atomic_inc(&conn->lnk->conn_cnt);
 	return 0;
 }
 
@@ -190,6 +194,8 @@ static void __smc_lgr_unregister_conn(struct smc_connection *conn)
 	struct smc_link_group *lgr = conn->lgr;
 
 	rb_erase(&conn->alert_node, &lgr->conns_all);
+	if (conn->lnk)
+		atomic_dec(&conn->lnk->conn_cnt);
 	lgr->conns_num--;
 	conn->alert_token_local = 0;
 	sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */
@@ -211,6 +217,367 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
 	conn->lgr = NULL;
 }
 
+int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	char hostname[SMC_MAX_HOSTNAME_LEN + 1];
+	char smc_seid[SMC_MAX_EID_LEN + 1];
+	struct smcd_dev *smcd_dev;
+	struct nlattr *attrs;
+	u8 *seid = NULL;
+	u8 *host = NULL;
+	void *nlh;
+
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_SYS_INFO);
+	if (!nlh)
+		goto errmsg;
+	if (cb_ctx->pos[0])
+		goto errout;
+	attrs = nla_nest_start(skb, SMC_GEN_SYS_INFO);
+	if (!attrs)
+		goto errout;
+	if (nla_put_u8(skb, SMC_NLA_SYS_VER, SMC_V2))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_SYS_REL, SMC_RELEASE))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable()))
+		goto errattr;
+	smc_clc_get_hostname(&host);
+	if (host) {
+		memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN);
+		hostname[SMC_MAX_HOSTNAME_LEN] = 0;
+		if (nla_put_string(skb, SMC_NLA_SYS_LOCAL_HOST, hostname))
+			goto errattr;
+	}
+	mutex_lock(&smcd_dev_list.mutex);
+	smcd_dev = list_first_entry_or_null(&smcd_dev_list.list,
+					    struct smcd_dev, list);
+	if (smcd_dev)
+		smc_ism_get_system_eid(smcd_dev, &seid);
+	mutex_unlock(&smcd_dev_list.mutex);
+	if (seid && smc_ism_is_v2_capable()) {
+		memcpy(smc_seid, seid, SMC_MAX_EID_LEN);
+		smc_seid[SMC_MAX_EID_LEN] = 0;
+		if (nla_put_string(skb, SMC_NLA_SYS_SEID, smc_seid))
+			goto errattr;
+	}
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, nlh);
+	cb_ctx->pos[0] = 1;
+	return skb->len;
+
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	genlmsg_cancel(skb, nlh);
+errmsg:
+	return skb->len;
+}
+
+static int smc_nl_fill_lgr(struct smc_link_group *lgr,
+			   struct sk_buff *skb,
+			   struct netlink_callback *cb)
+{
+	char smc_target[SMC_MAX_PNETID_LEN + 1];
+	struct nlattr *attrs;
+
+	attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR);
+	if (!attrs)
+		goto errout;
+
+	if (nla_put_u32(skb, SMC_NLA_LGR_R_ID, *((u32 *)&lgr->id)))
+		goto errattr;
+	if (nla_put_u32(skb, SMC_NLA_LGR_R_CONNS_NUM, lgr->conns_num))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_R_ROLE, lgr->role))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_R_TYPE, lgr->type))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_R_VLAN_ID, lgr->vlan_id))
+		goto errattr;
+	memcpy(smc_target, lgr->pnet_id, SMC_MAX_PNETID_LEN);
+	smc_target[SMC_MAX_PNETID_LEN] = 0;
+	if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target))
+		goto errattr;
+
+	nla_nest_end(skb, attrs);
+	return 0;
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	return -EMSGSIZE;
+}
+
+static int smc_nl_fill_lgr_link(struct smc_link_group *lgr,
+				struct smc_link *link,
+				struct sk_buff *skb,
+				struct netlink_callback *cb)
+{
+	char smc_ibname[IB_DEVICE_NAME_MAX];
+	u8 smc_gid_target[41];
+	struct nlattr *attrs;
+	u32 link_uid = 0;
+	void *nlh;
+
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_LINK_SMCR);
+	if (!nlh)
+		goto errmsg;
+
+	attrs = nla_nest_start(skb, SMC_GEN_LINK_SMCR);
+	if (!attrs)
+		goto errout;
+
+	if (nla_put_u8(skb, SMC_NLA_LINK_ID, link->link_id))
+		goto errattr;
+	if (nla_put_u32(skb, SMC_NLA_LINK_STATE, link->state))
+		goto errattr;
+	if (nla_put_u32(skb, SMC_NLA_LINK_CONN_CNT,
+			atomic_read(&link->conn_cnt)))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_LINK_IB_PORT, link->ibport))
+		goto errattr;
+	if (nla_put_u32(skb, SMC_NLA_LINK_NET_DEV, link->ndev_ifidx))
+		goto errattr;
+	snprintf(smc_ibname, sizeof(smc_ibname), "%s", link->ibname);
+	if (nla_put_string(skb, SMC_NLA_LINK_IB_DEV, smc_ibname))
+		goto errattr;
+	memcpy(&link_uid, link->link_uid, sizeof(link_uid));
+	if (nla_put_u32(skb, SMC_NLA_LINK_UID, link_uid))
+		goto errattr;
+	memcpy(&link_uid, link->peer_link_uid, sizeof(link_uid));
+	if (nla_put_u32(skb, SMC_NLA_LINK_PEER_UID, link_uid))
+		goto errattr;
+	memset(smc_gid_target, 0, sizeof(smc_gid_target));
+	smc_gid_be16_convert(smc_gid_target, link->gid);
+	if (nla_put_string(skb, SMC_NLA_LINK_GID, smc_gid_target))
+		goto errattr;
+	memset(smc_gid_target, 0, sizeof(smc_gid_target));
+	smc_gid_be16_convert(smc_gid_target, link->peer_gid);
+	if (nla_put_string(skb, SMC_NLA_LINK_PEER_GID, smc_gid_target))
+		goto errattr;
+
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, nlh);
+	return 0;
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	genlmsg_cancel(skb, nlh);
+errmsg:
+	return -EMSGSIZE;
+}
+
+static int smc_nl_handle_lgr(struct smc_link_group *lgr,
+			     struct sk_buff *skb,
+			     struct netlink_callback *cb,
+			     bool list_links)
+{
+	void *nlh;
+	int i;
+
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_LGR_SMCR);
+	if (!nlh)
+		goto errmsg;
+	if (smc_nl_fill_lgr(lgr, skb, cb))
+		goto errout;
+
+	genlmsg_end(skb, nlh);
+	if (!list_links)
+		goto out;
+	for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+		if (!smc_link_usable(&lgr->lnk[i]))
+			continue;
+		if (smc_nl_fill_lgr_link(lgr, &lgr->lnk[i], skb, cb))
+			goto errout;
+	}
+out:
+	return 0;
+
+errout:
+	genlmsg_cancel(skb, nlh);
+errmsg:
+	return -EMSGSIZE;
+}
+
+static void smc_nl_fill_lgr_list(struct smc_lgr_list *smc_lgr,
+				 struct sk_buff *skb,
+				 struct netlink_callback *cb,
+				 bool list_links)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	struct smc_link_group *lgr;
+	int snum = cb_ctx->pos[0];
+	int num = 0;
+
+	spin_lock_bh(&smc_lgr->lock);
+	list_for_each_entry(lgr, &smc_lgr->list, list) {
+		if (num < snum)
+			goto next;
+		if (smc_nl_handle_lgr(lgr, skb, cb, list_links))
+			goto errout;
+next:
+		num++;
+	}
+errout:
+	spin_unlock_bh(&smc_lgr->lock);
+	cb_ctx->pos[0] = num;
+}
+
+static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
+				struct sk_buff *skb,
+				struct netlink_callback *cb)
+{
+	char smc_host[SMC_MAX_HOSTNAME_LEN + 1];
+	char smc_pnet[SMC_MAX_PNETID_LEN + 1];
+	char smc_eid[SMC_MAX_EID_LEN + 1];
+	struct nlattr *v2_attrs;
+	struct nlattr *attrs;
+	void *nlh;
+
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_LGR_SMCD);
+	if (!nlh)
+		goto errmsg;
+
+	attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCD);
+	if (!attrs)
+		goto errout;
+
+	if (nla_put_u32(skb, SMC_NLA_LGR_D_ID, *((u32 *)&lgr->id)))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_GID, lgr->smcd->local_gid,
+			      SMC_NLA_LGR_D_PAD))
+		goto errattr;
+	if (nla_put_u64_64bit(skb, SMC_NLA_LGR_D_PEER_GID, lgr->peer_gid,
+			      SMC_NLA_LGR_D_PAD))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_D_VLAN_ID, lgr->vlan_id))
+		goto errattr;
+	if (nla_put_u32(skb, SMC_NLA_LGR_D_CONNS_NUM, lgr->conns_num))
+		goto errattr;
+	if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd)))
+		goto errattr;
+	memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN);
+	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
+	if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet))
+		goto errattr;
+
+	v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_V2);
+	if (!v2_attrs)
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version))
+		goto errv2attr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release))
+		goto errv2attr;
+	if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os))
+		goto errv2attr;
+	memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN);
+	smc_host[SMC_MAX_HOSTNAME_LEN] = 0;
+	if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host))
+		goto errv2attr;
+	memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN);
+	smc_eid[SMC_MAX_EID_LEN] = 0;
+	if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid))
+		goto errv2attr;
+
+	nla_nest_end(skb, v2_attrs);
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, nlh);
+	return 0;
+
+errv2attr:
+	nla_nest_cancel(skb, v2_attrs);
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	genlmsg_cancel(skb, nlh);
+errmsg:
+	return -EMSGSIZE;
+}
+
+static int smc_nl_handle_smcd_lgr(struct smcd_dev *dev,
+				  struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	struct smc_link_group *lgr;
+	int snum = cb_ctx->pos[1];
+	int rc = 0, num = 0;
+
+	spin_lock_bh(&dev->lgr_lock);
+	list_for_each_entry(lgr, &dev->lgr_list, list) {
+		if (!lgr->is_smcd)
+			continue;
+		if (num < snum)
+			goto next;
+		rc = smc_nl_fill_smcd_lgr(lgr, skb, cb);
+		if (rc)
+			goto errout;
+next:
+		num++;
+	}
+errout:
+	spin_unlock_bh(&dev->lgr_lock);
+	cb_ctx->pos[1] = num;
+	return rc;
+}
+
+static int smc_nl_fill_smcd_dev(struct smcd_dev_list *dev_list,
+				struct sk_buff *skb,
+				struct netlink_callback *cb)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	struct smcd_dev *smcd_dev;
+	int snum = cb_ctx->pos[0];
+	int rc = 0, num = 0;
+
+	mutex_lock(&dev_list->mutex);
+	list_for_each_entry(smcd_dev, &dev_list->list, list) {
+		if (list_empty(&smcd_dev->lgr_list))
+			continue;
+		if (num < snum)
+			goto next;
+		rc = smc_nl_handle_smcd_lgr(smcd_dev, skb, cb);
+		if (rc)
+			goto errout;
+next:
+		num++;
+	}
+errout:
+	mutex_unlock(&dev_list->mutex);
+	cb_ctx->pos[0] = num;
+	return rc;
+}
+
+int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	bool list_links = false;
+
+	smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links);
+	return skb->len;
+}
+
+int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	bool list_links = true;
+
+	smc_nl_fill_lgr_list(&smc_lgr_list, skb, cb, list_links);
+	return skb->len;
+}
+
+int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	smc_nl_fill_smcd_dev(&smcd_dev_list, skb, cb);
+	return skb->len;
+}
+
 void smc_lgr_cleanup_early(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
@@ -227,7 +594,7 @@ void smc_lgr_cleanup_early(struct smc_connection *conn)
 	if (!list_empty(lgr_list))
 		list_del_init(lgr_list);
 	spin_unlock_bh(lgr_lock);
-	smc_lgr_schedule_free_work_fast(lgr);
+	__smc_lgr_terminate(lgr, true);
 }
 
 static void smcr_lgr_link_deactivate_all(struct smc_link_group *lgr)
@@ -310,6 +677,15 @@ static u8 smcr_next_link_id(struct smc_link_group *lgr)
 	return link_id;
 }
 
+static void smcr_copy_dev_info_to_link(struct smc_link *link)
+{
+	struct smc_ib_device *smcibdev = link->smcibdev;
+
+	snprintf(link->ibname, sizeof(link->ibname), "%s",
+		 smcibdev->ibdev->name);
+	link->ndev_ifidx = smcibdev->ndev_ifidx[link->ibport - 1];
+}
+
 int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
 		   u8 link_idx, struct smc_init_info *ini)
 {
@@ -323,7 +699,10 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
 	lnk->link_idx = link_idx;
 	lnk->smcibdev = ini->ib_dev;
 	lnk->ibport = ini->ib_port;
+	smc_ibdev_cnt_inc(lnk);
+	smcr_copy_dev_info_to_link(lnk);
 	lnk->path_mtu = ini->ib_dev->pattr[ini->ib_port - 1].active_mtu;
+	atomic_set(&lnk->conn_cnt, 0);
 	smc_llc_link_set_uid(lnk);
 	INIT_WORK(&lnk->link_down_wrk, smc_link_down_work);
 	if (!ini->ib_dev->initialized) {
@@ -365,6 +744,7 @@ free_link_mem:
 clear_llc_lnk:
 	smc_llc_link_clear(lnk, false);
 out:
+	smc_ibdev_cnt_dec(lnk);
 	put_device(&ini->ib_dev->ibdev->dev);
 	memset(lnk, 0, sizeof(struct smc_link));
 	lnk->state = SMC_LNK_UNUSED;
@@ -385,7 +765,8 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 	int i;
 
 	if (ini->is_smcd && ini->vlan_id) {
-		if (smc_ism_get_vlan(ini->ism_dev, ini->vlan_id)) {
+		if (smc_ism_get_vlan(ini->ism_dev[ini->ism_selected],
+				     ini->vlan_id)) {
 			rc = SMC_CLC_DECL_ISMVLANERR;
 			goto out;
 		}
@@ -396,10 +777,15 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 		rc = SMC_CLC_DECL_MEM;
 		goto ism_put_vlan;
 	}
+	lgr->tx_wq = alloc_workqueue("smc_tx_wq-%*phN", 0, 0,
+				     SMC_LGR_ID_SIZE, &lgr->id);
+	if (!lgr->tx_wq) {
+		rc = -ENOMEM;
+		goto free_lgr;
+	}
 	lgr->is_smcd = ini->is_smcd;
 	lgr->sync_err = 0;
 	lgr->terminating = 0;
-	lgr->freefast = 0;
 	lgr->freeing = 0;
 	lgr->vlan_id = ini->vlan_id;
 	mutex_init(&lgr->sndbufs_lock);
@@ -417,13 +803,14 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 	lgr->conns_all = RB_ROOT;
 	if (ini->is_smcd) {
 		/* SMC-D specific settings */
-		get_device(&ini->ism_dev->dev);
-		lgr->peer_gid = ini->ism_gid;
-		lgr->smcd = ini->ism_dev;
-		lgr_list = &ini->ism_dev->lgr_list;
+		get_device(&ini->ism_dev[ini->ism_selected]->dev);
+		lgr->peer_gid = ini->ism_peer_gid[ini->ism_selected];
+		lgr->smcd = ini->ism_dev[ini->ism_selected];
+		lgr_list = &ini->ism_dev[ini->ism_selected]->lgr_list;
 		lgr_lock = &lgr->smcd->lgr_lock;
+		lgr->smc_version = ini->smcd_version;
 		lgr->peer_shutdown = 0;
-		atomic_inc(&ini->ism_dev->lgr_cnt);
+		atomic_inc(&ini->ism_dev[ini->ism_selected]->lgr_cnt);
 	} else {
 		/* SMC-R specific settings */
 		lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
@@ -437,7 +824,7 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 		lnk = &lgr->lnk[link_idx];
 		rc = smcr_link_init(lgr, lnk, link_idx, ini);
 		if (rc)
-			goto free_lgr;
+			goto free_wq;
 		lgr_list = &smc_lgr_list.list;
 		lgr_lock = &smc_lgr_list.lock;
 		atomic_inc(&lgr_cnt);
@@ -448,11 +835,13 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini)
 	spin_unlock_bh(lgr_lock);
 	return 0;
 
+free_wq:
+	destroy_workqueue(lgr->tx_wq);
 free_lgr:
 	kfree(lgr);
 ism_put_vlan:
 	if (ini->is_smcd && ini->vlan_id)
-		smc_ism_put_vlan(ini->ism_dev, ini->vlan_id);
+		smc_ism_put_vlan(ini->ism_dev[ini->ism_selected], ini->vlan_id);
 out:
 	if (rc < 0) {
 		if (rc == -ENOMEM)
@@ -517,7 +906,7 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend,
 	    smc->sk.sk_state != SMC_CLOSED) {
 		rc = smcr_cdc_msg_send_validation(conn, pend, wr_buf);
 		if (!rc) {
-			schedule_delayed_work(&conn->tx_work, 0);
+			queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work, 0);
 			smc->sk.sk_data_ready(&smc->sk);
 		}
 	} else {
@@ -527,6 +916,14 @@ static int smc_switch_cursor(struct smc_sock *smc, struct smc_cdc_tx_pend *pend,
 	return rc;
 }
 
+static void smc_switch_link_and_count(struct smc_connection *conn,
+				      struct smc_link *to_lnk)
+{
+	atomic_dec(&conn->lnk->conn_cnt);
+	conn->lnk = to_lnk;
+	atomic_inc(&conn->lnk->conn_cnt);
+}
+
 struct smc_link *smc_switch_conns(struct smc_link_group *lgr,
 				  struct smc_link *from_lnk, bool is_dev_err)
 {
@@ -575,7 +972,7 @@ again:
 		    smc->sk.sk_state == SMC_PEERABORTWAIT ||
 		    smc->sk.sk_state == SMC_PROCESSABORT) {
 			spin_lock_bh(&conn->send_lock);
-			conn->lnk = to_lnk;
+			smc_switch_link_and_count(conn, to_lnk);
 			spin_unlock_bh(&conn->send_lock);
 			continue;
 		}
@@ -589,7 +986,7 @@ again:
 		}
 		/* avoid race with smcr_tx_sndbuf_nonempty() */
 		spin_lock_bh(&conn->send_lock);
-		conn->lnk = to_lnk;
+		smc_switch_link_and_count(conn, to_lnk);
 		rc = smc_switch_cursor(smc, pend, wr_buf);
 		spin_unlock_bh(&conn->send_lock);
 		sock_put(&smc->sk);
@@ -738,6 +1135,7 @@ void smcr_link_clear(struct smc_link *lnk, bool log)
 	smc_ib_destroy_queue_pair(lnk);
 	smc_ib_dealloc_protection_domain(lnk);
 	smc_wr_free_link_mem(lnk);
+	smc_ibdev_cnt_dec(lnk);
 	put_device(&lnk->smcibdev->ibdev->dev);
 	smcibdev = lnk->smcibdev;
 	memset(lnk, 0, sizeof(struct smc_link));
@@ -824,11 +1222,10 @@ static void smc_lgr_free(struct smc_link_group *lgr)
 	}
 
 	smc_lgr_free_bufs(lgr);
+	destroy_workqueue(lgr->tx_wq);
 	if (lgr->is_smcd) {
-		if (!lgr->terminating) {
-			smc_ism_put_vlan(lgr->smcd, lgr->vlan_id);
-			put_device(&lgr->smcd->dev);
-		}
+		smc_ism_put_vlan(lgr->smcd, lgr->vlan_id);
+		put_device(&lgr->smcd->dev);
 		if (!atomic_dec_return(&lgr->smcd->lgr_cnt))
 			wake_up(&lgr->smcd->lgrs_deleted);
 	} else {
@@ -889,8 +1286,6 @@ static void smc_lgr_cleanup(struct smc_link_group *lgr)
 	if (lgr->is_smcd) {
 		smc_ism_signal_shutdown(lgr);
 		smcd_unregister_all_dmbs(lgr);
-		smc_ism_put_vlan(lgr->smcd, lgr->vlan_id);
-		put_device(&lgr->smcd->dev);
 	} else {
 		u32 rsn = lgr->llc_termination_rsn;
 
@@ -1294,11 +1689,13 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 	spinlock_t *lgr_lock;
 	int rc = 0;
 
-	lgr_list = ini->is_smcd ? &ini->ism_dev->lgr_list : &smc_lgr_list.list;
-	lgr_lock = ini->is_smcd ? &ini->ism_dev->lgr_lock : &smc_lgr_list.lock;
-	ini->cln_first_contact = SMC_FIRST_CONTACT;
+	lgr_list = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_list :
+				  &smc_lgr_list.list;
+	lgr_lock = ini->is_smcd ? &ini->ism_dev[ini->ism_selected]->lgr_lock :
+				  &smc_lgr_list.lock;
+	ini->first_contact_local = 1;
 	role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
-	if (role == SMC_CLNT && ini->srv_first_contact)
+	if (role == SMC_CLNT && ini->first_contact_peer)
 		/* create new link group as well */
 		goto create;
 
@@ -1307,14 +1704,16 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 	list_for_each_entry(lgr, lgr_list, list) {
 		write_lock_bh(&lgr->conns_lock);
 		if ((ini->is_smcd ?
-		     smcd_lgr_match(lgr, ini->ism_dev, ini->ism_gid) :
+		     smcd_lgr_match(lgr, ini->ism_dev[ini->ism_selected],
+				    ini->ism_peer_gid[ini->ism_selected]) :
 		     smcr_lgr_match(lgr, ini->ib_lcl, role, ini->ib_clcqpn)) &&
 		    !lgr->sync_err &&
-		    lgr->vlan_id == ini->vlan_id &&
+		    (ini->smcd_version == SMC_V2 ||
+		     lgr->vlan_id == ini->vlan_id) &&
 		    (role == SMC_CLNT || ini->is_smcd ||
 		     lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) {
 			/* link group found */
-			ini->cln_first_contact = SMC_REUSE_CONTACT;
+			ini->first_contact_local = 0;
 			conn->lgr = lgr;
 			rc = smc_lgr_register_conn(conn, false);
 			write_unlock_bh(&lgr->conns_lock);
@@ -1328,8 +1727,8 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 	if (rc)
 		return rc;
 
-	if (role == SMC_CLNT && !ini->srv_first_contact &&
-	    ini->cln_first_contact == SMC_FIRST_CONTACT) {
+	if (role == SMC_CLNT && !ini->first_contact_peer &&
+	    ini->first_contact_local) {
 		/* Server reuses a link group, but Client wants to start
 		 * a new one
 		 * send out_of_sync decline, reason synchr. error
@@ -1338,7 +1737,7 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
 	}
 
 create:
-	if (ini->cln_first_contact == SMC_FIRST_CONTACT) {
+	if (ini->first_contact_local) {
 		rc = smc_lgr_create(smc, ini);
 		if (rc)
 			goto out;
@@ -1597,7 +1996,7 @@ out:
 	return rc;
 }
 
-#define SMCD_DMBE_SIZES		7 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */
+#define SMCD_DMBE_SIZES		6 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */
 
 static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr,
 						bool is_dmb, int bufsize)
@@ -1616,7 +2015,11 @@ static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr,
 		rc = smc_ism_register_dmb(lgr, bufsize, buf_desc);
 		if (rc) {
 			kfree(buf_desc);
-			return (rc == -ENOMEM) ? ERR_PTR(-EAGAIN) : ERR_PTR(rc);
+			if (rc == -ENOMEM)
+				return ERR_PTR(-EAGAIN);
+			if (rc == -ENOSPC)
+				return ERR_PTR(-ENOSPC);
+			return ERR_PTR(-EIO);
 		}
 		buf_desc->pages = virt_to_page(buf_desc->cpu_addr);
 		/* CDC header stored in buf. So, pretend it was smaller */
@@ -1892,8 +2295,8 @@ int smc_rmb_rtoken_handling(struct smc_connection *conn,
 			    struct smc_link *lnk,
 			    struct smc_clc_msg_accept_confirm *clc)
 {
-	conn->rtoken_idx = smc_rtoken_add(lnk, clc->rmb_dma_addr,
-					  clc->rmb_rkey);
+	conn->rtoken_idx = smc_rtoken_add(lnk, clc->r0.rmb_dma_addr,
+					  clc->r0.rmb_rkey);
 	if (conn->rtoken_idx < 0)
 		return conn->rtoken_idx;
 	return 0;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 1c4d5439d0ff..e8e448771f85 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -13,7 +13,10 @@
 #define _SMC_CORE_H
 
 #include <linux/atomic.h>
+#include <linux/smc.h>
+#include <linux/pci.h>
 #include <rdma/ib_verbs.h>
+#include <net/genetlink.h>
 
 #include "smc.h"
 #include "smc_ib.h"
@@ -124,11 +127,14 @@ struct smc_link {
 	u8			link_is_asym;	/* is link asymmetric? */
 	struct smc_link_group	*lgr;		/* parent link group */
 	struct work_struct	link_down_wrk;	/* wrk to bring link down */
+	char			ibname[IB_DEVICE_NAME_MAX]; /* ib device name */
+	int			ndev_ifidx; /* network device ifindex */
 
 	enum smc_link_state	state;		/* state of link */
 	struct delayed_work	llc_testlink_wrk; /* testlink worker */
 	struct completion	llc_testlink_resp; /* wait for rx of testlink */
 	int			llc_testlink_time; /* testlink interval */
+	atomic_t		conn_cnt; /* connections on this link */
 };
 
 /* For now we just allow one parallel link per link group. The SMC protocol
@@ -137,9 +143,6 @@ struct smc_link {
 #define SMC_LINKS_PER_LGR_MAX	3
 #define SMC_SINGLE_LINK		0
 
-#define SMC_FIRST_CONTACT	1		/* first contact to a peer */
-#define SMC_REUSE_CONTACT	0		/* follow-on contact to a peer*/
-
 /* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */
 struct smc_buf_desc {
 	struct list_head	list;
@@ -228,12 +231,17 @@ struct smc_link_group {
 	u8			id[SMC_LGR_ID_SIZE];	/* unique lgr id */
 	struct delayed_work	free_work;	/* delayed freeing of an lgr */
 	struct work_struct	terminate_work;	/* abnormal lgr termination */
+	struct workqueue_struct	*tx_wq;		/* wq for conn. tx workers */
 	u8			sync_err : 1;	/* lgr no longer fits to peer */
 	u8			terminating : 1;/* lgr is terminating */
-	u8			freefast : 1;	/* free worker scheduled fast */
 	u8			freeing : 1;	/* lgr is being freed */
 
 	bool			is_smcd;	/* SMC-R or SMC-D */
+	u8			smc_version;
+	u8			negotiated_eid[SMC_MAX_EID_LEN];
+	u8			peer_os;	/* peer operating system */
+	u8			peer_smc_release;
+	u8			peer_hostname[SMC_MAX_HOSTNAME_LEN];
 	union {
 		struct { /* SMC-R */
 			enum smc_lgr_role	role;
@@ -294,9 +302,12 @@ struct smc_clc_msg_local;
 
 struct smc_init_info {
 	u8			is_smcd;
+	u8			smc_type_v1;
+	u8			smc_type_v2;
+	u8			first_contact_peer;
+	u8			first_contact_local;
 	unsigned short		vlan_id;
-	int			srv_first_contact;
-	int			cln_first_contact;
+	u32			rc;
 	/* SMC-R */
 	struct smc_clc_msg_local *ib_lcl;
 	struct smc_ib_device	*ib_dev;
@@ -304,8 +315,12 @@ struct smc_init_info {
 	u8			ib_port;
 	u32			ib_clcqpn;
 	/* SMC-D */
-	u64			ism_gid;
-	struct smcd_dev		*ism_dev;
+	u64			ism_peer_gid[SMC_MAX_ISM_DEVS + 1];
+	struct smcd_dev		*ism_dev[SMC_MAX_ISM_DEVS + 1];
+	u16			ism_chid[SMC_MAX_ISM_DEVS + 1];
+	u8			ism_offered_cnt; /* # of ISM devices offered */
+	u8			ism_selected;    /* index of selected ISM dev*/
+	u8			smcd_version;
 };
 
 /* Find the connection associated with the given alert token in the link group.
@@ -354,6 +369,45 @@ static inline bool smc_link_active(struct smc_link *lnk)
 	return lnk->state == SMC_LNK_ACTIVE;
 }
 
+static inline void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw)
+{
+	sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x",
+		be16_to_cpu(((__be16 *)gid_raw)[0]),
+		be16_to_cpu(((__be16 *)gid_raw)[1]),
+		be16_to_cpu(((__be16 *)gid_raw)[2]),
+		be16_to_cpu(((__be16 *)gid_raw)[3]),
+		be16_to_cpu(((__be16 *)gid_raw)[4]),
+		be16_to_cpu(((__be16 *)gid_raw)[5]),
+		be16_to_cpu(((__be16 *)gid_raw)[6]),
+		be16_to_cpu(((__be16 *)gid_raw)[7]));
+}
+
+struct smc_pci_dev {
+	__u32		pci_fid;
+	__u16		pci_pchid;
+	__u16		pci_vendor;
+	__u16		pci_device;
+	__u8		pci_id[SMC_PCI_ID_STR_LEN];
+};
+
+static inline void smc_set_pci_values(struct pci_dev *pci_dev,
+				      struct smc_pci_dev *smc_dev)
+{
+	smc_dev->pci_vendor = pci_dev->vendor;
+	smc_dev->pci_device = pci_dev->device;
+	snprintf(smc_dev->pci_id, sizeof(smc_dev->pci_id), "%s",
+		 pci_name(pci_dev));
+#if IS_ENABLED(CONFIG_S390)
+	{ /* Set s390 specific PCI information */
+	struct zpci_dev *zdev;
+
+	zdev = to_zpci(pci_dev);
+	smc_dev->pci_fid = zdev->fid;
+	smc_dev->pci_pchid = zdev->pchid;
+	}
+#endif
+}
+
 struct smc_sock;
 struct smc_clc_msg_accept_confirm;
 struct smc_clc_msg_local;
@@ -401,6 +455,10 @@ struct smc_link *smc_switch_conns(struct smc_link_group *lgr,
 				  struct smc_link *from_lnk, bool is_dev_err);
 void smcr_link_down_cond(struct smc_link *lnk);
 void smcr_link_down_cond_sched(struct smc_link *lnk);
+int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb);
+int smcr_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb);
+int smcr_nl_get_link(struct sk_buff *skb, struct netlink_callback *cb);
+int smcd_nl_get_lgr(struct sk_buff *skb, struct netlink_callback *cb);
 
 static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
 {
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index da9ba6d1679b..c952986a6aca 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -22,17 +22,13 @@
 #include "smc.h"
 #include "smc_core.h"
 
-static void smc_gid_be16_convert(__u8 *buf, u8 *gid_raw)
+struct smc_diag_dump_ctx {
+	int pos[2];
+};
+
+static struct smc_diag_dump_ctx *smc_dump_context(struct netlink_callback *cb)
 {
-	sprintf(buf, "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x",
-		be16_to_cpu(((__be16 *)gid_raw)[0]),
-		be16_to_cpu(((__be16 *)gid_raw)[1]),
-		be16_to_cpu(((__be16 *)gid_raw)[2]),
-		be16_to_cpu(((__be16 *)gid_raw)[3]),
-		be16_to_cpu(((__be16 *)gid_raw)[4]),
-		be16_to_cpu(((__be16 *)gid_raw)[5]),
-		be16_to_cpu(((__be16 *)gid_raw)[6]),
-		be16_to_cpu(((__be16 *)gid_raw)[7]));
+	return (struct smc_diag_dump_ctx *)cb->ctx;
 }
 
 static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk)
@@ -151,17 +147,17 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	    !list_empty(&smc->conn.lgr->list)) {
 		struct smc_diag_lgrinfo linfo = {
 			.role = smc->conn.lgr->role,
-			.lnk[0].ibport = smc->conn.lgr->lnk[0].ibport,
-			.lnk[0].link_id = smc->conn.lgr->lnk[0].link_id,
+			.lnk[0].ibport = smc->conn.lnk->ibport,
+			.lnk[0].link_id = smc->conn.lnk->link_id,
 		};
 
 		memcpy(linfo.lnk[0].ibname,
 		       smc->conn.lgr->lnk[0].smcibdev->ibdev->name,
-		       sizeof(smc->conn.lgr->lnk[0].smcibdev->ibdev->name));
+		       sizeof(smc->conn.lnk->smcibdev->ibdev->name));
 		smc_gid_be16_convert(linfo.lnk[0].gid,
-				     smc->conn.lgr->lnk[0].gid);
+				     smc->conn.lnk->gid);
 		smc_gid_be16_convert(linfo.lnk[0].peer_gid,
-				     smc->conn.lgr->lnk[0].peer_gid);
+				     smc->conn.lnk->peer_gid);
 
 		if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0)
 			goto errout;
@@ -193,13 +189,15 @@ errout:
 }
 
 static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb,
-			       struct netlink_callback *cb)
+			       struct netlink_callback *cb, int p_type)
 {
+	struct smc_diag_dump_ctx *cb_ctx = smc_dump_context(cb);
 	struct net *net = sock_net(skb->sk);
+	int snum = cb_ctx->pos[p_type];
 	struct nlattr *bc = NULL;
 	struct hlist_head *head;
+	int rc = 0, num = 0;
 	struct sock *sk;
-	int rc = 0;
 
 	read_lock(&prot->h.smc_hash->lock);
 	head = &prot->h.smc_hash->ht;
@@ -209,13 +207,18 @@ static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb,
 	sk_for_each(sk, head) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
+		if (num < snum)
+			goto next;
 		rc = __smc_diag_dump(sk, skb, cb, nlmsg_data(cb->nlh), bc);
-		if (rc)
-			break;
+		if (rc < 0)
+			goto out;
+next:
+		num++;
 	}
 
 out:
 	read_unlock(&prot->h.smc_hash->lock);
+	cb_ctx->pos[p_type] = num;
 	return rc;
 }
 
@@ -223,10 +226,10 @@ static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	int rc = 0;
 
-	rc = smc_diag_dump_proto(&smc_proto, skb, cb);
+	rc = smc_diag_dump_proto(&smc_proto, skb, cb, SMCPROTO_SMC);
 	if (!rc)
-		rc = smc_diag_dump_proto(&smc_proto6, skb, cb);
-	return rc;
+		smc_diag_dump_proto(&smc_proto6, skb, cb, SMCPROTO_SMC6);
+	return skb->len;
 }
 
 static int smc_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h)
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 1c314dbdc7fa..7d7ba0320d5a 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -25,6 +25,7 @@
 #include "smc_core.h"
 #include "smc_wr.h"
 #include "smc.h"
+#include "smc_netlink.h"
 
 #define SMC_MAX_CQE 32766	/* max. # of completion queue elements */
 
@@ -198,9 +199,9 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
 		rcu_read_lock();
 		ndev = rdma_read_gid_attr_ndev_rcu(attr);
 		if (!IS_ERR(ndev) &&
-		    ((!vlan_id && !is_vlan_dev(attr->ndev)) ||
-		     (vlan_id && is_vlan_dev(attr->ndev) &&
-		      vlan_dev_vlan_id(attr->ndev) == vlan_id)) &&
+		    ((!vlan_id && !is_vlan_dev(ndev)) ||
+		     (vlan_id && is_vlan_dev(ndev) &&
+		      vlan_dev_vlan_id(ndev) == vlan_id)) &&
 		    attr->gid_type == IB_GID_TYPE_ROCE) {
 			rcu_read_unlock();
 			if (gid)
@@ -326,6 +327,171 @@ int smc_ib_create_protection_domain(struct smc_link *lnk)
 	return rc;
 }
 
+static bool smcr_diag_is_dev_critical(struct smc_lgr_list *smc_lgr,
+				      struct smc_ib_device *smcibdev)
+{
+	struct smc_link_group *lgr;
+	bool rc = false;
+	int i;
+
+	spin_lock_bh(&smc_lgr->lock);
+	list_for_each_entry(lgr, &smc_lgr->list, list) {
+		if (lgr->is_smcd)
+			continue;
+		for (i = 0; i < SMC_LINKS_PER_LGR_MAX; i++) {
+			if (lgr->lnk[i].state == SMC_LNK_UNUSED ||
+			    lgr->lnk[i].smcibdev != smcibdev)
+				continue;
+			if (lgr->type == SMC_LGR_SINGLE ||
+			    lgr->type == SMC_LGR_ASYMMETRIC_LOCAL) {
+				rc = true;
+				goto out;
+			}
+		}
+	}
+out:
+	spin_unlock_bh(&smc_lgr->lock);
+	return rc;
+}
+
+static int smc_nl_handle_dev_port(struct sk_buff *skb,
+				  struct ib_device *ibdev,
+				  struct smc_ib_device *smcibdev,
+				  int port)
+{
+	char smc_pnet[SMC_MAX_PNETID_LEN + 1];
+	struct nlattr *port_attrs;
+	unsigned char port_state;
+	int lnk_count = 0;
+
+	port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT + port);
+	if (!port_attrs)
+		goto errout;
+
+	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR,
+		       smcibdev->pnetid_by_user[port]))
+		goto errattr;
+	memcpy(smc_pnet, &smcibdev->pnetid[port], SMC_MAX_PNETID_LEN);
+	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
+	if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
+		goto errattr;
+	if (nla_put_u32(skb, SMC_NLA_DEV_PORT_NETDEV,
+			smcibdev->ndev_ifidx[port]))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_VALID, 1))
+		goto errattr;
+	port_state = smc_ib_port_active(smcibdev, port + 1);
+	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_STATE, port_state))
+		goto errattr;
+	lnk_count = atomic_read(&smcibdev->lnk_cnt_by_port[port]);
+	if (nla_put_u32(skb, SMC_NLA_DEV_PORT_LNK_CNT, lnk_count))
+		goto errattr;
+	nla_nest_end(skb, port_attrs);
+	return 0;
+errattr:
+	nla_nest_cancel(skb, port_attrs);
+errout:
+	return -EMSGSIZE;
+}
+
+static bool smc_nl_handle_pci_values(const struct smc_pci_dev *smc_pci_dev,
+				     struct sk_buff *skb)
+{
+	if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev->pci_fid))
+		return false;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev->pci_pchid))
+		return false;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev->pci_vendor))
+		return false;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev->pci_device))
+		return false;
+	if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev->pci_id))
+		return false;
+	return true;
+}
+
+static int smc_nl_handle_smcr_dev(struct smc_ib_device *smcibdev,
+				  struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	char smc_ibname[IB_DEVICE_NAME_MAX];
+	struct smc_pci_dev smc_pci_dev;
+	struct pci_dev *pci_dev;
+	unsigned char is_crit;
+	struct nlattr *attrs;
+	void *nlh;
+	int i;
+
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_DEV_SMCR);
+	if (!nlh)
+		goto errmsg;
+	attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCR);
+	if (!attrs)
+		goto errout;
+	is_crit = smcr_diag_is_dev_critical(&smc_lgr_list, smcibdev);
+	if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, is_crit))
+		goto errattr;
+	if (smcibdev->ibdev->dev.parent) {
+		memset(&smc_pci_dev, 0, sizeof(smc_pci_dev));
+		pci_dev = to_pci_dev(smcibdev->ibdev->dev.parent);
+		smc_set_pci_values(pci_dev, &smc_pci_dev);
+		if (!smc_nl_handle_pci_values(&smc_pci_dev, skb))
+			goto errattr;
+	}
+	snprintf(smc_ibname, sizeof(smc_ibname), "%s", smcibdev->ibdev->name);
+	if (nla_put_string(skb, SMC_NLA_DEV_IB_NAME, smc_ibname))
+		goto errattr;
+	for (i = 1; i <= SMC_MAX_PORTS; i++) {
+		if (!rdma_is_port_valid(smcibdev->ibdev, i))
+			continue;
+		if (smc_nl_handle_dev_port(skb, smcibdev->ibdev,
+					   smcibdev, i - 1))
+			goto errattr;
+	}
+
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, nlh);
+	return 0;
+
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	genlmsg_cancel(skb, nlh);
+errmsg:
+	return -EMSGSIZE;
+}
+
+static void smc_nl_prep_smcr_dev(struct smc_ib_devices *dev_list,
+				 struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	struct smc_ib_device *smcibdev;
+	int snum = cb_ctx->pos[0];
+	int num = 0;
+
+	mutex_lock(&dev_list->mutex);
+	list_for_each_entry(smcibdev, &dev_list->list, list) {
+		if (num < snum)
+			goto next;
+		if (smc_nl_handle_smcr_dev(smcibdev, skb, cb))
+			goto errout;
+next:
+		num++;
+	}
+errout:
+	mutex_unlock(&dev_list->mutex);
+	cb_ctx->pos[0] = num;
+}
+
+int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	smc_nl_prep_smcr_dev(&smc_ib_devices, skb, cb);
+	return skb->len;
+}
+
 static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
 {
 	struct smc_link *lnk = (struct smc_link *)priv;
@@ -557,6 +723,49 @@ out:
 
 static struct ib_client smc_ib_client;
 
+static void smc_copy_netdev_ifindex(struct smc_ib_device *smcibdev, int port)
+{
+	struct ib_device *ibdev = smcibdev->ibdev;
+	struct net_device *ndev;
+
+	if (!ibdev->ops.get_netdev)
+		return;
+	ndev = ibdev->ops.get_netdev(ibdev, port + 1);
+	if (ndev) {
+		smcibdev->ndev_ifidx[port] = ndev->ifindex;
+		dev_put(ndev);
+	}
+}
+
+void smc_ib_ndev_change(struct net_device *ndev, unsigned long event)
+{
+	struct smc_ib_device *smcibdev;
+	struct ib_device *libdev;
+	struct net_device *lndev;
+	u8 port_cnt;
+	int i;
+
+	mutex_lock(&smc_ib_devices.mutex);
+	list_for_each_entry(smcibdev, &smc_ib_devices.list, list) {
+		port_cnt = smcibdev->ibdev->phys_port_cnt;
+		for (i = 0; i < min_t(size_t, port_cnt, SMC_MAX_PORTS); i++) {
+			libdev = smcibdev->ibdev;
+			if (!libdev->ops.get_netdev)
+				continue;
+			lndev = libdev->ops.get_netdev(libdev, i + 1);
+			if (lndev)
+				dev_put(lndev);
+			if (lndev != ndev)
+				continue;
+			if (event == NETDEV_REGISTER)
+				smcibdev->ndev_ifidx[i] = ndev->ifindex;
+			if (event == NETDEV_UNREGISTER)
+				smcibdev->ndev_ifidx[i] = 0;
+		}
+	}
+	mutex_unlock(&smc_ib_devices.mutex);
+}
+
 /* callback function for ib_register_client() */
 static int smc_ib_add_dev(struct ib_device *ibdev)
 {
@@ -596,6 +805,7 @@ static int smc_ib_add_dev(struct ib_device *ibdev)
 		if (smc_pnetid_by_dev_port(ibdev->dev.parent, i,
 					   smcibdev->pnetid[i]))
 			smc_pnetid_by_table_ib(smcibdev, i + 1);
+		smc_copy_netdev_ifindex(smcibdev, i);
 		pr_warn_ratelimited("smc:    ib device %s port %d has pnetid "
 				    "%.16s%s\n",
 				    smcibdev->ibdev->name, i + 1,
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 2ce481187dd0..3085f5180da7 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -30,6 +30,7 @@ struct smc_ib_devices {			/* list of smc ib devices definition */
 };
 
 extern struct smc_ib_devices	smc_ib_devices; /* list of smc ib devices */
+extern struct smc_lgr_list smc_lgr_list; /* list of linkgroups */
 
 struct smc_ib_device {				/* ib-device infos for smc */
 	struct list_head	list;
@@ -53,11 +54,15 @@ struct smc_ib_device {				/* ib-device infos for smc */
 	atomic_t		lnk_cnt;	/* number of links on ibdev */
 	wait_queue_head_t	lnks_deleted;	/* wait 4 removal of all links*/
 	struct mutex		mutex;		/* protect dev setup+cleanup */
+	atomic_t		lnk_cnt_by_port[SMC_MAX_PORTS];
+						/* number of links per port */
+	int			ndev_ifidx[SMC_MAX_PORTS]; /* ndev if indexes */
 };
 
 struct smc_buf_desc;
 struct smc_link;
 
+void smc_ib_ndev_change(struct net_device *ndev, unsigned long event);
 int smc_ib_register_client(void) __init;
 void smc_ib_unregister_client(void);
 bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport);
@@ -87,4 +92,5 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk,
 int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
 			 unsigned short vlan_id, u8 gid[], u8 *sgid_index);
 bool smc_ib_is_valid_local_systemid(void);
+int smcr_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);
 #endif
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index 998c525de785..9c6e95882553 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -15,13 +15,16 @@
 #include "smc_core.h"
 #include "smc_ism.h"
 #include "smc_pnet.h"
+#include "smc_netlink.h"
 
 struct smcd_dev_list smcd_dev_list = {
 	.list = LIST_HEAD_INIT(smcd_dev_list.list),
 	.mutex = __MUTEX_INITIALIZER(smcd_dev_list.mutex)
 };
 
-/* Test if an ISM communication is possible. */
+static bool smc_ism_v2_capable;
+
+/* Test if an ISM communication is possible - same CPC */
 int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
 {
 	return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0,
@@ -39,6 +42,22 @@ int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos,
 	return rc < 0 ? rc : 0;
 }
 
+void smc_ism_get_system_eid(struct smcd_dev *smcd, u8 **eid)
+{
+	smcd->ops->get_system_eid(smcd, eid);
+}
+
+u16 smc_ism_get_chid(struct smcd_dev *smcd)
+{
+	return smcd->ops->get_chid(smcd);
+}
+
+/* HW supports ISM V2 and thus System EID is defined */
+bool smc_ism_is_v2_capable(void)
+{
+	return smc_ism_v2_capable;
+}
+
 /* Set a connection using this DMBE. */
 void smc_ism_set_conn(struct smc_connection *conn)
 {
@@ -189,6 +208,97 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
 	return rc;
 }
 
+static int smc_nl_handle_smcd_dev(struct smcd_dev *smcd,
+				  struct sk_buff *skb,
+				  struct netlink_callback *cb)
+{
+	char smc_pnet[SMC_MAX_PNETID_LEN + 1];
+	struct smc_pci_dev smc_pci_dev;
+	struct nlattr *port_attrs;
+	struct nlattr *attrs;
+	int use_cnt = 0;
+	void *nlh;
+
+	nlh = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &smc_gen_nl_family, NLM_F_MULTI,
+			  SMC_NETLINK_GET_DEV_SMCD);
+	if (!nlh)
+		goto errmsg;
+	attrs = nla_nest_start(skb, SMC_GEN_DEV_SMCD);
+	if (!attrs)
+		goto errout;
+	use_cnt = atomic_read(&smcd->lgr_cnt);
+	if (nla_put_u32(skb, SMC_NLA_DEV_USE_CNT, use_cnt))
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_DEV_IS_CRIT, use_cnt > 0))
+		goto errattr;
+	memset(&smc_pci_dev, 0, sizeof(smc_pci_dev));
+	smc_set_pci_values(to_pci_dev(smcd->dev.parent), &smc_pci_dev);
+	if (nla_put_u32(skb, SMC_NLA_DEV_PCI_FID, smc_pci_dev.pci_fid))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_CHID, smc_pci_dev.pci_pchid))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_VENDOR, smc_pci_dev.pci_vendor))
+		goto errattr;
+	if (nla_put_u16(skb, SMC_NLA_DEV_PCI_DEVICE, smc_pci_dev.pci_device))
+		goto errattr;
+	if (nla_put_string(skb, SMC_NLA_DEV_PCI_ID, smc_pci_dev.pci_id))
+		goto errattr;
+
+	port_attrs = nla_nest_start(skb, SMC_NLA_DEV_PORT);
+	if (!port_attrs)
+		goto errattr;
+	if (nla_put_u8(skb, SMC_NLA_DEV_PORT_PNET_USR, smcd->pnetid_by_user))
+		goto errportattr;
+	memcpy(smc_pnet, smcd->pnetid, SMC_MAX_PNETID_LEN);
+	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
+	if (nla_put_string(skb, SMC_NLA_DEV_PORT_PNETID, smc_pnet))
+		goto errportattr;
+
+	nla_nest_end(skb, port_attrs);
+	nla_nest_end(skb, attrs);
+	genlmsg_end(skb, nlh);
+	return 0;
+
+errportattr:
+	nla_nest_cancel(skb, port_attrs);
+errattr:
+	nla_nest_cancel(skb, attrs);
+errout:
+	nlmsg_cancel(skb, nlh);
+errmsg:
+	return -EMSGSIZE;
+}
+
+static void smc_nl_prep_smcd_dev(struct smcd_dev_list *dev_list,
+				 struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
+	int snum = cb_ctx->pos[0];
+	struct smcd_dev *smcd;
+	int num = 0;
+
+	mutex_lock(&dev_list->mutex);
+	list_for_each_entry(smcd, &dev_list->list, list) {
+		if (num < snum)
+			goto next;
+		if (smc_nl_handle_smcd_dev(smcd, skb, cb))
+			goto errout;
+next:
+		num++;
+	}
+errout:
+	mutex_unlock(&dev_list->mutex);
+	cb_ctx->pos[0] = num;
+}
+
+int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	smc_nl_prep_smcd_dev(&smcd_dev_list, skb, cb);
+	return skb->len;
+}
+
 struct smc_ism_event_work {
 	struct work_struct work;
 	struct smcd_dev *smcd;
@@ -319,7 +429,18 @@ EXPORT_SYMBOL_GPL(smcd_alloc_dev);
 int smcd_register_dev(struct smcd_dev *smcd)
 {
 	mutex_lock(&smcd_dev_list.mutex);
-	list_add_tail(&smcd->list, &smcd_dev_list.list);
+	if (list_empty(&smcd_dev_list.list)) {
+		u8 *system_eid = NULL;
+
+		smc_ism_get_system_eid(smcd, &system_eid);
+		if (system_eid[24] != '0' || system_eid[28] != '0')
+			smc_ism_v2_capable = true;
+	}
+	/* sort list: devices without pnetid before devices with pnetid */
+	if (smcd->pnetid[0])
+		list_add_tail(&smcd->list, &smcd_dev_list.list);
+	else
+		list_add(&smcd->list, &smcd_dev_list.list);
 	mutex_unlock(&smcd_dev_list.mutex);
 
 	pr_warn_ratelimited("smc: adding smcd device %s with pnetid %.16s%s\n",
@@ -399,3 +520,8 @@ void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno)
 	spin_unlock_irqrestore(&smcd->lock, flags);
 }
 EXPORT_SYMBOL_GPL(smcd_handle_irq);
+
+void __init smc_ism_init(void)
+{
+	smc_ism_v2_capable = false;
+}
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index 81cc4537efd3..113efc7352ed 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -10,6 +10,7 @@
 #define SMCD_ISM_H
 
 #include <linux/uio.h>
+#include <linux/types.h>
 #include <linux/mutex.h>
 
 #include "smc.h"
@@ -19,7 +20,7 @@ struct smcd_dev_list {	/* List of SMCD devices */
 	struct mutex mutex;	/* Protects list of devices */
 };
 
-extern struct smcd_dev_list	smcd_dev_list; /* list of smcd devices */
+extern struct smcd_dev_list	smcd_dev_list;	/* list of smcd devices */
 
 struct smc_ism_vlanid {			/* VLAN id set on ISM device */
 	struct list_head list;
@@ -47,4 +48,9 @@ int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc);
 int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
 		  void *data, size_t len);
 int smc_ism_signal_shutdown(struct smc_link_group *lgr);
+void smc_ism_get_system_eid(struct smcd_dev *dev, u8 **eid);
+u16 smc_ism_get_chid(struct smcd_dev *dev);
+bool smc_ism_is_v2_capable(void);
+void smc_ism_init(void);
+int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb);
 #endif
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 3ea33466ebe9..273eaf1bfe49 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -233,8 +233,6 @@ static bool smc_llc_flow_start(struct smc_llc_flow *flow,
 	default:
 		flow->type = SMC_LLC_FLOW_NONE;
 	}
-	if (qentry == lgr->delayed_event)
-		lgr->delayed_event = NULL;
 	smc_llc_flow_qentry_set(flow, qentry);
 	spin_unlock_bh(&lgr->llc_flow_lock);
 	return true;
@@ -1209,7 +1207,7 @@ static void smc_llc_process_srv_add_link(struct smc_link_group *lgr)
 /* enqueue a local add_link req to trigger a new add_link flow */
 void smc_llc_add_link_local(struct smc_link *link)
 {
-	struct smc_llc_msg_add_link add_llc = {0};
+	struct smc_llc_msg_add_link add_llc = {};
 
 	add_llc.hd.length = sizeof(add_llc);
 	add_llc.hd.common.type = SMC_LLC_ADD_LINK;
@@ -1242,7 +1240,7 @@ out:
  */
 void smc_llc_srv_delete_link_local(struct smc_link *link, u8 del_link_id)
 {
-	struct smc_llc_msg_del_link del_llc = {0};
+	struct smc_llc_msg_del_link del_llc = {};
 
 	del_llc.hd.length = sizeof(del_llc);
 	del_llc.hd.common.type = SMC_LLC_DELETE_LINK;
@@ -1314,7 +1312,7 @@ out:
  */
 void smc_llc_send_link_delete_all(struct smc_link_group *lgr, bool ord, u32 rsn)
 {
-	struct smc_llc_msg_del_link delllc = {0};
+	struct smc_llc_msg_del_link delllc = {};
 	int i;
 
 	delllc.hd.common.type = SMC_LLC_DELETE_LINK;
@@ -1603,13 +1601,12 @@ static void smc_llc_event_work(struct work_struct *work)
 	struct smc_llc_qentry *qentry;
 
 	if (!lgr->llc_flow_lcl.type && lgr->delayed_event) {
-		if (smc_link_usable(lgr->delayed_event->link)) {
-			smc_llc_event_handler(lgr->delayed_event);
-		} else {
-			qentry = lgr->delayed_event;
-			lgr->delayed_event = NULL;
+		qentry = lgr->delayed_event;
+		lgr->delayed_event = NULL;
+		if (smc_link_usable(qentry->link))
+			smc_llc_event_handler(qentry);
+		else
 			kfree(qentry);
-		}
 	}
 
 again:
@@ -1691,7 +1688,7 @@ static void smc_llc_enqueue(struct smc_link *link, union smc_llc_msg *llc)
 	spin_lock_irqsave(&lgr->llc_event_q_lock, flags);
 	list_add_tail(&qentry->list, &lgr->llc_event_q);
 	spin_unlock_irqrestore(&lgr->llc_event_q_lock, flags);
-	schedule_work(&lgr->llc_event_work);
+	queue_work(system_highpri_wq, &lgr->llc_event_work);
 }
 
 /* copy received msg and add it to the event queue */
diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c
new file mode 100644
index 000000000000..140419a19dbf
--- /dev/null
+++ b/net/smc/smc_netlink.c
@@ -0,0 +1,85 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  Generic netlink support functions to interact with SMC module
+ *
+ *  Copyright IBM Corp. 2020
+ *
+ *  Author(s):	Guvenc Gulce <guvenc@linux.ibm.com>
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/ctype.h>
+#include <linux/mutex.h>
+#include <linux/if.h>
+#include <linux/smc.h>
+
+#include "smc_core.h"
+#include "smc_ism.h"
+#include "smc_ib.h"
+#include "smc_netlink.h"
+
+#define SMC_CMD_MAX_ATTR 1
+
+/* SMC_GENL generic netlink operation definition */
+static const struct genl_ops smc_gen_nl_ops[] = {
+	{
+		.cmd = SMC_NETLINK_GET_SYS_INFO,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smc_nl_get_sys_info,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_LGR_SMCR,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcr_nl_get_lgr,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_LINK_SMCR,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcr_nl_get_link,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_LGR_SMCD,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcd_nl_get_lgr,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_DEV_SMCD,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcd_nl_get_device,
+	},
+	{
+		.cmd = SMC_NETLINK_GET_DEV_SMCR,
+		/* can be retrieved by unprivileged users */
+		.dumpit = smcr_nl_get_device,
+	},
+};
+
+static const struct nla_policy smc_gen_nl_policy[2] = {
+	[SMC_CMD_MAX_ATTR]	= { .type = NLA_REJECT, },
+};
+
+/* SMC_GENL family definition */
+struct genl_family smc_gen_nl_family __ro_after_init = {
+	.hdrsize =	0,
+	.name =		SMC_GENL_FAMILY_NAME,
+	.version =	SMC_GENL_FAMILY_VERSION,
+	.maxattr =	SMC_CMD_MAX_ATTR,
+	.policy =	smc_gen_nl_policy,
+	.netnsok =	true,
+	.module =	THIS_MODULE,
+	.ops =		smc_gen_nl_ops,
+	.n_ops =	ARRAY_SIZE(smc_gen_nl_ops)
+};
+
+int __init smc_nl_init(void)
+{
+	return genl_register_family(&smc_gen_nl_family);
+}
+
+void smc_nl_exit(void)
+{
+	genl_unregister_family(&smc_gen_nl_family);
+}
diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h
new file mode 100644
index 000000000000..3477265cba6c
--- /dev/null
+++ b/net/smc/smc_netlink.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Shared Memory Communications over RDMA (SMC-R) and RoCE
+ *
+ *  SMC Generic netlink operations
+ *
+ *  Copyright IBM Corp. 2020
+ *
+ *  Author(s):	Guvenc Gulce <guvenc@linux.ibm.com>
+ */
+
+#ifndef _SMC_NETLINK_H
+#define _SMC_NETLINK_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+extern struct genl_family smc_gen_nl_family;
+
+struct smc_nl_dmp_ctx {
+	int pos[2];
+};
+
+static inline struct smc_nl_dmp_ctx *smc_nl_dmp_ctx(struct netlink_callback *c)
+{
+	return (struct smc_nl_dmp_ctx *)c->ctx;
+}
+
+int smc_nl_init(void) __init;
+void smc_nl_exit(void);
+
+#endif
diff --git a/net/smc/smc_netns.h b/net/smc/smc_netns.h
index e7a8fc4ae02f..0f4f35aa43ad 100644
--- a/net/smc/smc_netns.h
+++ b/net/smc/smc_netns.h
@@ -16,5 +16,6 @@ extern unsigned int smc_net_id;
 /* per-network namespace private data */
 struct smc_net {
 	struct smc_pnettable pnettable;
+	struct smc_pnetids_ndev pnetids_ndev;
 };
 #endif
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 30e5fac7034e..6f6d33edb135 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -29,8 +29,7 @@
 #include "smc_ism.h"
 #include "smc_core.h"
 
-#define SMC_ASCII_BLANK 32
-
+static struct net_device *__pnet_find_base_ndev(struct net_device *ndev);
 static struct net_device *pnet_find_base_ndev(struct net_device *ndev);
 
 static const struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
@@ -73,14 +72,22 @@ struct smc_pnetentry {
 	};
 };
 
+/* Check if the pnetid is set */
+bool smc_pnet_is_pnetid_set(u8 *pnetid)
+{
+	if (pnetid[0] == 0 || pnetid[0] == _S)
+		return false;
+	return true;
+}
+
 /* Check if two given pnetids match */
 static bool smc_pnet_match(u8 *pnetid1, u8 *pnetid2)
 {
 	int i;
 
 	for (i = 0; i < SMC_MAX_PNETID_LEN; i++) {
-		if ((pnetid1[i] == 0 || pnetid1[i] == SMC_ASCII_BLANK) &&
-		    (pnetid2[i] == 0 || pnetid2[i] == SMC_ASCII_BLANK))
+		if ((pnetid1[i] == 0 || pnetid1[i] == _S) &&
+		    (pnetid2[i] == 0 || pnetid2[i] == _S))
 			break;
 		if (pnetid1[i] != pnetid2[i])
 			return false;
@@ -238,11 +245,10 @@ static int smc_pnet_remove_by_ndev(struct net_device *ndev)
 static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port,
 			      char *pnet_name)
 {
-	u8 pnet_null[SMC_MAX_PNETID_LEN] = {0};
 	bool applied = false;
 
 	mutex_lock(&smc_ib_devices.mutex);
-	if (smc_pnet_match(ib_dev->pnetid[ib_port - 1], pnet_null)) {
+	if (!smc_pnet_is_pnetid_set(ib_dev->pnetid[ib_port - 1])) {
 		memcpy(ib_dev->pnetid[ib_port - 1], pnet_name,
 		       SMC_MAX_PNETID_LEN);
 		ib_dev->pnetid_by_user[ib_port - 1] = true;
@@ -256,11 +262,10 @@ static bool smc_pnet_apply_ib(struct smc_ib_device *ib_dev, u8 ib_port,
  */
 static bool smc_pnet_apply_smcd(struct smcd_dev *smcd_dev, char *pnet_name)
 {
-	u8 pnet_null[SMC_MAX_PNETID_LEN] = {0};
 	bool applied = false;
 
 	mutex_lock(&smcd_dev_list.mutex);
-	if (smc_pnet_match(smcd_dev->pnetid, pnet_null)) {
+	if (!smc_pnet_is_pnetid_set(smcd_dev->pnetid)) {
 		memcpy(smcd_dev->pnetid, pnet_name, SMC_MAX_PNETID_LEN);
 		smcd_dev->pnetid_by_user = true;
 		applied = true;
@@ -708,18 +713,136 @@ static struct genl_family smc_pnet_nl_family __ro_after_init = {
 	.n_ops =  ARRAY_SIZE(smc_pnet_ops)
 };
 
+bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid)
+{
+	struct smc_net *sn = net_generic(net, smc_net_id);
+	struct smc_pnetids_ndev_entry *pe;
+	bool rc = false;
+
+	read_lock(&sn->pnetids_ndev.lock);
+	list_for_each_entry(pe, &sn->pnetids_ndev.list, list) {
+		if (smc_pnet_match(pnetid, pe->pnetid)) {
+			rc = true;
+			goto unlock;
+		}
+	}
+
+unlock:
+	read_unlock(&sn->pnetids_ndev.lock);
+	return rc;
+}
+
+static int smc_pnet_add_pnetid(struct net *net, u8 *pnetid)
+{
+	struct smc_net *sn = net_generic(net, smc_net_id);
+	struct smc_pnetids_ndev_entry *pe, *pi;
+
+	pe = kzalloc(sizeof(*pe), GFP_KERNEL);
+	if (!pe)
+		return -ENOMEM;
+
+	write_lock(&sn->pnetids_ndev.lock);
+	list_for_each_entry(pi, &sn->pnetids_ndev.list, list) {
+		if (smc_pnet_match(pnetid, pe->pnetid)) {
+			refcount_inc(&pi->refcnt);
+			kfree(pe);
+			goto unlock;
+		}
+	}
+	refcount_set(&pe->refcnt, 1);
+	memcpy(pe->pnetid, pnetid, SMC_MAX_PNETID_LEN);
+	list_add_tail(&pe->list, &sn->pnetids_ndev.list);
+
+unlock:
+	write_unlock(&sn->pnetids_ndev.lock);
+	return 0;
+}
+
+static void smc_pnet_remove_pnetid(struct net *net, u8 *pnetid)
+{
+	struct smc_net *sn = net_generic(net, smc_net_id);
+	struct smc_pnetids_ndev_entry *pe, *pe2;
+
+	write_lock(&sn->pnetids_ndev.lock);
+	list_for_each_entry_safe(pe, pe2, &sn->pnetids_ndev.list, list) {
+		if (smc_pnet_match(pnetid, pe->pnetid)) {
+			if (refcount_dec_and_test(&pe->refcnt)) {
+				list_del(&pe->list);
+				kfree(pe);
+			}
+			break;
+		}
+	}
+	write_unlock(&sn->pnetids_ndev.lock);
+}
+
+static void smc_pnet_add_base_pnetid(struct net *net, struct net_device *dev,
+				     u8 *ndev_pnetid)
+{
+	struct net_device *base_dev;
+
+	base_dev = __pnet_find_base_ndev(dev);
+	if (base_dev->flags & IFF_UP &&
+	    !smc_pnetid_by_dev_port(base_dev->dev.parent, base_dev->dev_port,
+				    ndev_pnetid)) {
+		/* add to PNETIDs list */
+		smc_pnet_add_pnetid(net, ndev_pnetid);
+	}
+}
+
+/* create initial list of netdevice pnetids */
+static void smc_pnet_create_pnetids_list(struct net *net)
+{
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+	struct net_device *dev;
+
+	rtnl_lock();
+	for_each_netdev(net, dev)
+		smc_pnet_add_base_pnetid(net, dev, ndev_pnetid);
+	rtnl_unlock();
+}
+
+/* clean up list of netdevice pnetids */
+static void smc_pnet_destroy_pnetids_list(struct net *net)
+{
+	struct smc_net *sn = net_generic(net, smc_net_id);
+	struct smc_pnetids_ndev_entry *pe, *temp_pe;
+
+	write_lock(&sn->pnetids_ndev.lock);
+	list_for_each_entry_safe(pe, temp_pe, &sn->pnetids_ndev.list, list) {
+		list_del(&pe->list);
+		kfree(pe);
+	}
+	write_unlock(&sn->pnetids_ndev.lock);
+}
+
 static int smc_pnet_netdev_event(struct notifier_block *this,
 				 unsigned long event, void *ptr)
 {
 	struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(event_dev);
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
 
 	switch (event) {
 	case NETDEV_REBOOT:
 	case NETDEV_UNREGISTER:
 		smc_pnet_remove_by_ndev(event_dev);
+		smc_ib_ndev_change(event_dev, event);
 		return NOTIFY_OK;
 	case NETDEV_REGISTER:
 		smc_pnet_add_by_ndev(event_dev);
+		smc_ib_ndev_change(event_dev, event);
+		return NOTIFY_OK;
+	case NETDEV_UP:
+		smc_pnet_add_base_pnetid(net, event_dev, ndev_pnetid);
+		return NOTIFY_OK;
+	case NETDEV_DOWN:
+		event_dev = __pnet_find_base_ndev(event_dev);
+		if (!smc_pnetid_by_dev_port(event_dev->dev.parent,
+					    event_dev->dev_port, ndev_pnetid)) {
+			/* remove from PNETIDs list */
+			smc_pnet_remove_pnetid(net, ndev_pnetid);
+		}
 		return NOTIFY_OK;
 	default:
 		return NOTIFY_DONE;
@@ -735,9 +858,14 @@ int smc_pnet_net_init(struct net *net)
 {
 	struct smc_net *sn = net_generic(net, smc_net_id);
 	struct smc_pnettable *pnettable = &sn->pnettable;
+	struct smc_pnetids_ndev *pnetids_ndev = &sn->pnetids_ndev;
 
 	INIT_LIST_HEAD(&pnettable->pnetlist);
 	rwlock_init(&pnettable->lock);
+	INIT_LIST_HEAD(&pnetids_ndev->list);
+	rwlock_init(&pnetids_ndev->lock);
+
+	smc_pnet_create_pnetids_list(net);
 
 	return 0;
 }
@@ -752,6 +880,7 @@ int __init smc_pnet_init(void)
 	rc = register_netdevice_notifier(&smc_netdev_notifier);
 	if (rc)
 		genl_unregister_family(&smc_pnet_nl_family);
+
 	return rc;
 }
 
@@ -760,6 +889,7 @@ void smc_pnet_net_exit(struct net *net)
 {
 	/* flush pnet table */
 	smc_pnet_remove_by_pnetid(net, NULL);
+	smc_pnet_destroy_pnetids_list(net);
 }
 
 void smc_pnet_exit(void)
@@ -768,16 +898,11 @@ void smc_pnet_exit(void)
 	genl_unregister_family(&smc_pnet_nl_family);
 }
 
-/* Determine one base device for stacked net devices.
- * If the lower device level contains more than one devices
- * (for instance with bonding slaves), just the first device
- * is used to reach a base device.
- */
-static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
+static struct net_device *__pnet_find_base_ndev(struct net_device *ndev)
 {
 	int i, nest_lvl;
 
-	rtnl_lock();
+	ASSERT_RTNL();
 	nest_lvl = ndev->lower_level;
 	for (i = 0; i < nest_lvl; i++) {
 		struct list_head *lower = &ndev->adj_list.lower;
@@ -787,6 +912,18 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
 		lower = lower->next;
 		ndev = netdev_lower_get_next(ndev, &lower);
 	}
+	return ndev;
+}
+
+/* Determine one base device for stacked net devices.
+ * If the lower device level contains more than one devices
+ * (for instance with bonding slaves), just the first device
+ * is used to reach a base device.
+ */
+static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
+{
+	rtnl_lock();
+	ndev = __pnet_find_base_ndev(ndev);
 	rtnl_unlock();
 	return ndev;
 }
@@ -928,8 +1065,11 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
 	mutex_lock(&smcd_dev_list.mutex);
 	list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
 		if (smc_pnet_match(ismdev->pnetid, ndev_pnetid) &&
-		    !ismdev->going_away) {
-			ini->ism_dev = ismdev;
+		    !ismdev->going_away &&
+		    (!ini->ism_peer_gid[0] ||
+		     !smc_ism_cantalk(ini->ism_peer_gid[0], ini->vlan_id,
+				      ismdev))) {
+			ini->ism_dev[0] = ismdev;
 			break;
 		}
 	}
@@ -963,7 +1103,7 @@ void smc_pnet_find_ism_resource(struct sock *sk, struct smc_init_info *ini)
 {
 	struct dst_entry *dst = sk_dst_get(sk);
 
-	ini->ism_dev = NULL;
+	ini->ism_dev[0] = NULL;
 	if (!dst)
 		goto out;
 	if (!dst->dev)
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 811a65986691..14039272f7e4 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -12,6 +12,8 @@
 #ifndef _SMC_PNET_H
 #define _SMC_PNET_H
 
+#include <net/smc.h>
+
 #if IS_ENABLED(CONFIG_HAVE_PNETID)
 #include <asm/pnet.h>
 #endif
@@ -31,6 +33,17 @@ struct smc_pnettable {
 	struct list_head pnetlist;
 };
 
+struct smc_pnetids_ndev {	/* list of pnetids for net devices in UP state*/
+	struct list_head	list;
+	rwlock_t		lock;
+};
+
+struct smc_pnetids_ndev_entry {
+	struct list_head	list;
+	u8			pnetid[SMC_MAX_PNETID_LEN];
+	refcount_t		refcnt;
+};
+
 static inline int smc_pnetid_by_dev_port(struct device *dev,
 					 unsigned short port, u8 *pnetid)
 {
@@ -52,4 +65,6 @@ int smc_pnetid_by_table_smcd(struct smcd_dev *smcd);
 void smc_pnet_find_alt_roce(struct smc_link_group *lgr,
 			    struct smc_init_info *ini,
 			    struct smc_ib_device *known_dev);
+bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid);
+bool smc_pnet_is_pnetid_set(u8 *pnetid);
 #endif
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 54ba0443847e..4532c16bf85e 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -228,8 +228,8 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 			/* for a corked socket defer the RDMA writes if there
 			 * is still sufficient sndbuf_space available
 			 */
-			schedule_delayed_work(&conn->tx_work,
-					      SMC_TX_CORK_DELAY);
+			queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work,
+					   SMC_TX_CORK_DELAY);
 		else
 			smc_tx_sndbuf_nonempty(conn);
 	} /* while (msg_data_left(msg)) */
@@ -499,7 +499,7 @@ static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
 			if (conn->killed)
 				return -EPIPE;
 			rc = 0;
-			mod_delayed_work(system_wq, &conn->tx_work,
+			mod_delayed_work(conn->lgr->tx_wq, &conn->tx_work,
 					 SMC_TX_WORK_DELAY);
 		}
 		return rc;
@@ -623,8 +623,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 			return;
 		if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
 		    !conn->killed) {
-			schedule_delayed_work(&conn->tx_work,
-					      SMC_TX_WORK_DELAY);
+			queue_delayed_work(conn->lgr->tx_wq, &conn->tx_work,
+					   SMC_TX_WORK_DELAY);
 			return;
 		}
 	}
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 1e23cdd41eb1..cbc73a7e4d59 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -131,9 +131,9 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
 	wake_up(&link->wr_tx_wait);
 }
 
-static void smc_wr_tx_tasklet_fn(unsigned long data)
+static void smc_wr_tx_tasklet_fn(struct tasklet_struct *t)
 {
-	struct smc_ib_device *dev = (struct smc_ib_device *)data;
+	struct smc_ib_device *dev = from_tasklet(dev, t, send_tasklet);
 	struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
 	int i = 0, rc;
 	int polled = 0;
@@ -435,9 +435,9 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
 	}
 }
 
-static void smc_wr_rx_tasklet_fn(unsigned long data)
+static void smc_wr_rx_tasklet_fn(struct tasklet_struct *t)
 {
-	struct smc_ib_device *dev = (struct smc_ib_device *)data;
+	struct smc_ib_device *dev = from_tasklet(dev, t, recv_tasklet);
 	struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
 	int polled = 0;
 	int rc;
@@ -698,10 +698,8 @@ void smc_wr_remove_dev(struct smc_ib_device *smcibdev)
 
 void smc_wr_add_dev(struct smc_ib_device *smcibdev)
 {
-	tasklet_init(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn,
-		     (unsigned long)smcibdev);
-	tasklet_init(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn,
-		     (unsigned long)smcibdev);
+	tasklet_setup(&smcibdev->recv_tasklet, smc_wr_rx_tasklet_fn);
+	tasklet_setup(&smcibdev->send_tasklet, smc_wr_tx_tasklet_fn);
 }
 
 int smc_wr_create_link(struct smc_link *lnk)
diff --git a/net/socket.c b/net/socket.c
index 58cac2da5f66..33e8b6c4e1d3 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -52,6 +52,7 @@
  *	Based upon Swansea University Computer Society NET3.039
  */
 
+#include <linux/ethtool.h>
 #include <linux/mm.h>
 #include <linux/socket.h>
 #include <linux/file.h>
@@ -64,7 +65,6 @@
 #include <linux/seq_file.h>
 #include <linux/mutex.h>
 #include <linux/if_bridge.h>
-#include <linux/if_frad.h>
 #include <linux/if_vlan.h>
 #include <linux/ptp_classify.h>
 #include <linux/init.h>
@@ -445,17 +445,15 @@ static int sock_map_fd(struct socket *sock, int flags)
 /**
  *	sock_from_file - Return the &socket bounded to @file.
  *	@file: file
- *	@err: pointer to an error code return
  *
- *	On failure returns %NULL and assigns -ENOTSOCK to @err.
+ *	On failure returns %NULL.
  */
 
-struct socket *sock_from_file(struct file *file, int *err)
+struct socket *sock_from_file(struct file *file)
 {
 	if (file->f_op == &socket_file_ops)
 		return file->private_data;	/* set in sock_map_fd */
 
-	*err = -ENOTSOCK;
 	return NULL;
 }
 EXPORT_SYMBOL(sock_from_file);
@@ -484,9 +482,11 @@ struct socket *sockfd_lookup(int fd, int *err)
 		return NULL;
 	}
 
-	sock = sock_from_file(file, err);
-	if (!sock)
+	sock = sock_from_file(file);
+	if (!sock) {
+		*err = -ENOTSOCK;
 		fput(file);
+	}
 	return sock;
 }
 EXPORT_SYMBOL(sockfd_lookup);
@@ -498,11 +498,12 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed)
 
 	*err = -EBADF;
 	if (f.file) {
-		sock = sock_from_file(f.file, err);
+		sock = sock_from_file(f.file);
 		if (likely(sock)) {
 			*fput_needed = f.flags & FDPUT_FPUT;
 			return sock;
 		}
+		*err = -ENOTSOCK;
 		fdput(f);
 	}
 	return NULL;
@@ -1027,17 +1028,6 @@ void vlan_ioctl_set(int (*hook) (struct net *, void __user *))
 }
 EXPORT_SYMBOL(vlan_ioctl_set);
 
-static DEFINE_MUTEX(dlci_ioctl_mutex);
-static int (*dlci_ioctl_hook) (unsigned int, void __user *);
-
-void dlci_ioctl_set(int (*hook) (unsigned int, void __user *))
-{
-	mutex_lock(&dlci_ioctl_mutex);
-	dlci_ioctl_hook = hook;
-	mutex_unlock(&dlci_ioctl_mutex);
-}
-EXPORT_SYMBOL(dlci_ioctl_set);
-
 static long sock_do_ioctl(struct net *net, struct socket *sock,
 			  unsigned int cmd, unsigned long arg)
 {
@@ -1156,17 +1146,6 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 				err = vlan_ioctl_hook(net, argp);
 			mutex_unlock(&vlan_ioctl_mutex);
 			break;
-		case SIOCADDDLCI:
-		case SIOCDELDLCI:
-			err = -ENOPKG;
-			if (!dlci_ioctl_hook)
-				request_module("dlci");
-
-			mutex_lock(&dlci_ioctl_mutex);
-			if (dlci_ioctl_hook)
-				err = dlci_ioctl_hook(cmd, argp);
-			mutex_unlock(&dlci_ioctl_mutex);
-			break;
 		case SIOCGSKNS:
 			err = -EPERM;
 			if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
@@ -1715,9 +1694,11 @@ int __sys_accept4_file(struct file *file, unsigned file_flags,
 	if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK))
 		flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK;
 
-	sock = sock_from_file(file, &err);
-	if (!sock)
+	sock = sock_from_file(file);
+	if (!sock) {
+		err = -ENOTSOCK;
 		goto out;
+	}
 
 	err = -ENFILE;
 	newsock = sock_alloc();
@@ -1840,9 +1821,11 @@ int __sys_connect_file(struct file *file, struct sockaddr_storage *address,
 	struct socket *sock;
 	int err;
 
-	sock = sock_from_file(file, &err);
-	if (!sock)
+	sock = sock_from_file(file);
+	if (!sock) {
+		err = -ENOTSOCK;
 		goto out;
+	}
 
 	err =
 	    security_socket_connect(sock, (struct sockaddr *)address, addrlen);
@@ -2192,6 +2175,17 @@ SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname,
  *	Shutdown a socket.
  */
 
+int __sys_shutdown_sock(struct socket *sock, int how)
+{
+	int err;
+
+	err = security_socket_shutdown(sock, how);
+	if (!err)
+		err = sock->ops->shutdown(sock, how);
+
+	return err;
+}
+
 int __sys_shutdown(int fd, int how)
 {
 	int err, fput_needed;
@@ -2199,9 +2193,7 @@ int __sys_shutdown(int fd, int how)
 
 	sock = sockfd_lookup_light(fd, &err, &fput_needed);
 	if (sock != NULL) {
-		err = security_socket_shutdown(sock, how);
-		if (!err)
-			err = sock->ops->shutdown(sock, how);
+		err = __sys_shutdown_sock(sock, how);
 		fput_light(sock->file, fput_needed);
 	}
 	return err;
@@ -2628,9 +2620,11 @@ long __sys_recvmsg_sock(struct socket *sock, struct msghdr *msg,
 			struct user_msghdr __user *umsg,
 			struct sockaddr __user *uaddr, unsigned int flags)
 {
-	/* disallow ancillary data requests from this path */
-	if (msg->msg_control || msg->msg_controllen)
-		return -EINVAL;
+	if (msg->msg_control || msg->msg_controllen) {
+		/* disallow ancillary data reqs unless cmsg is plain data */
+		if (!(sock->ops->flags & PROTO_CMSG_DATA_ONLY))
+			return -EINVAL;
+	}
 
 	return ____sys_recvmsg(sock, msg, umsg, uaddr, flags, 0);
 }
@@ -3425,8 +3419,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCBRDELBR:
 	case SIOCGIFVLAN:
 	case SIOCSIFVLAN:
-	case SIOCADDDLCI:
-	case SIOCDELDLCI:
 	case SIOCGSKNS:
 	case SIOCGSTAMP_NEW:
 	case SIOCGSTAMPNS_NEW:
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 3bcf985507be..bbbb5af0af13 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -21,7 +21,6 @@ config RPCSEC_GSS_KRB5
 	depends on SUNRPC && CRYPTO
 	depends on CRYPTO_MD5 && CRYPTO_DES && CRYPTO_CBC && CRYPTO_CTS
 	depends on CRYPTO_ECB && CRYPTO_HMAC && CRYPTO_SHA1 && CRYPTO_AES
-	depends on CRYPTO_ARC4
 	default y
 	select SUNRPC_GSS
 	help
diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
index 010dcb876f9d..6e4dbd577a39 100644
--- a/net/sunrpc/addr.c
+++ b/net/sunrpc/addr.c
@@ -185,7 +185,7 @@ static int rpc_parse_scope_id(struct net *net, const char *buf,
 			scope_id = dev->ifindex;
 			dev_put(dev);
 		} else {
-			if (kstrtou32(p, 10, &scope_id) == 0) {
+			if (kstrtou32(p, 10, &scope_id) != 0) {
 				kfree(p);
 				return 0;
 			}
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 4ecc2a959567..5f42aa5fc612 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -29,6 +29,7 @@
 #include <linux/uaccess.h>
 #include <linux/hashtable.h>
 
+#include "auth_gss_internal.h"
 #include "../netns.h"
 
 #include <trace/events/rpcgss.h>
@@ -125,35 +126,6 @@ gss_cred_set_ctx(struct rpc_cred *cred, struct gss_cl_ctx *ctx)
 	clear_bit(RPCAUTH_CRED_NEW, &cred->cr_flags);
 }
 
-static const void *
-simple_get_bytes(const void *p, const void *end, void *res, size_t len)
-{
-	const void *q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	memcpy(res, p, len);
-	return q;
-}
-
-static inline const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
-{
-	const void *q;
-	unsigned int len;
-
-	p = simple_get_bytes(p, end, &len, sizeof(len));
-	if (IS_ERR(p))
-		return p;
-	q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	dest->data = kmemdup(p, len, GFP_NOFS);
-	if (unlikely(dest->data == NULL))
-		return ERR_PTR(-ENOMEM);
-	dest->len = len;
-	return q;
-}
-
 static struct gss_cl_ctx *
 gss_cred_get_ctx(struct rpc_cred *cred)
 {
diff --git a/net/sunrpc/auth_gss/auth_gss_internal.h b/net/sunrpc/auth_gss/auth_gss_internal.h
new file mode 100644
index 000000000000..f6d9631bd9d0
--- /dev/null
+++ b/net/sunrpc/auth_gss/auth_gss_internal.h
@@ -0,0 +1,45 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/*
+ * linux/net/sunrpc/auth_gss/auth_gss_internal.h
+ *
+ * Internal definitions for RPCSEC_GSS client authentication
+ *
+ * Copyright (c) 2000 The Regents of the University of Michigan.
+ * All rights reserved.
+ *
+ */
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/sunrpc/xdr.h>
+
+static inline const void *
+simple_get_bytes(const void *p, const void *end, void *res, size_t len)
+{
+	const void *q = (const void *)((const char *)p + len);
+	if (unlikely(q > end || q < p))
+		return ERR_PTR(-EFAULT);
+	memcpy(res, p, len);
+	return q;
+}
+
+static inline const void *
+simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
+{
+	const void *q;
+	unsigned int len;
+
+	p = simple_get_bytes(p, end, &len, sizeof(len));
+	if (IS_ERR(p))
+		return p;
+	q = (const void *)((const char *)p + len);
+	if (unlikely(q > end || q < p))
+		return ERR_PTR(-EFAULT);
+	if (len) {
+		dest->data = kmemdup(p, len, GFP_NOFS);
+		if (unlikely(dest->data == NULL))
+			return ERR_PTR(-ENOMEM);
+	} else
+		dest->data = NULL;
+	dest->len = len;
+	return q;
+}
diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c
index 794fb3001880..634b6c6e0dcb 100644
--- a/net/sunrpc/auth_gss/gss_krb5_crypto.c
+++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c
@@ -138,135 +138,6 @@ checksummer(struct scatterlist *sg, void *data)
 	return crypto_ahash_update(req);
 }
 
-static int
-arcfour_hmac_md5_usage_to_salt(unsigned int usage, u8 salt[4])
-{
-	unsigned int ms_usage;
-
-	switch (usage) {
-	case KG_USAGE_SIGN:
-		ms_usage = 15;
-		break;
-	case KG_USAGE_SEAL:
-		ms_usage = 13;
-		break;
-	default:
-		return -EINVAL;
-	}
-	salt[0] = (ms_usage >> 0) & 0xff;
-	salt[1] = (ms_usage >> 8) & 0xff;
-	salt[2] = (ms_usage >> 16) & 0xff;
-	salt[3] = (ms_usage >> 24) & 0xff;
-
-	return 0;
-}
-
-static u32
-make_checksum_hmac_md5(struct krb5_ctx *kctx, char *header, int hdrlen,
-		       struct xdr_buf *body, int body_offset, u8 *cksumkey,
-		       unsigned int usage, struct xdr_netobj *cksumout)
-{
-	struct scatterlist              sg[1];
-	int err = -1;
-	u8 *checksumdata;
-	u8 *rc4salt;
-	struct crypto_ahash *md5;
-	struct crypto_ahash *hmac_md5;
-	struct ahash_request *req;
-
-	if (cksumkey == NULL)
-		return GSS_S_FAILURE;
-
-	if (cksumout->len < kctx->gk5e->cksumlength) {
-		dprintk("%s: checksum buffer length, %u, too small for %s\n",
-			__func__, cksumout->len, kctx->gk5e->name);
-		return GSS_S_FAILURE;
-	}
-
-	rc4salt = kmalloc_array(4, sizeof(*rc4salt), GFP_NOFS);
-	if (!rc4salt)
-		return GSS_S_FAILURE;
-
-	if (arcfour_hmac_md5_usage_to_salt(usage, rc4salt)) {
-		dprintk("%s: invalid usage value %u\n", __func__, usage);
-		goto out_free_rc4salt;
-	}
-
-	checksumdata = kmalloc(GSS_KRB5_MAX_CKSUM_LEN, GFP_NOFS);
-	if (!checksumdata)
-		goto out_free_rc4salt;
-
-	md5 = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(md5))
-		goto out_free_cksum;
-
-	hmac_md5 = crypto_alloc_ahash(kctx->gk5e->cksum_name, 0,
-				      CRYPTO_ALG_ASYNC);
-	if (IS_ERR(hmac_md5))
-		goto out_free_md5;
-
-	req = ahash_request_alloc(md5, GFP_NOFS);
-	if (!req)
-		goto out_free_hmac_md5;
-
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
-
-	err = crypto_ahash_init(req);
-	if (err)
-		goto out;
-	sg_init_one(sg, rc4salt, 4);
-	ahash_request_set_crypt(req, sg, NULL, 4);
-	err = crypto_ahash_update(req);
-	if (err)
-		goto out;
-
-	sg_init_one(sg, header, hdrlen);
-	ahash_request_set_crypt(req, sg, NULL, hdrlen);
-	err = crypto_ahash_update(req);
-	if (err)
-		goto out;
-	err = xdr_process_buf(body, body_offset, body->len - body_offset,
-			      checksummer, req);
-	if (err)
-		goto out;
-	ahash_request_set_crypt(req, NULL, checksumdata, 0);
-	err = crypto_ahash_final(req);
-	if (err)
-		goto out;
-
-	ahash_request_free(req);
-	req = ahash_request_alloc(hmac_md5, GFP_NOFS);
-	if (!req)
-		goto out_free_hmac_md5;
-
-	ahash_request_set_callback(req, CRYPTO_TFM_REQ_MAY_SLEEP, NULL, NULL);
-
-	err = crypto_ahash_setkey(hmac_md5, cksumkey, kctx->gk5e->keylength);
-	if (err)
-		goto out;
-
-	sg_init_one(sg, checksumdata, crypto_ahash_digestsize(md5));
-	ahash_request_set_crypt(req, sg, checksumdata,
-				crypto_ahash_digestsize(md5));
-	err = crypto_ahash_digest(req);
-	if (err)
-		goto out;
-
-	memcpy(cksumout->data, checksumdata, kctx->gk5e->cksumlength);
-	cksumout->len = kctx->gk5e->cksumlength;
-out:
-	ahash_request_free(req);
-out_free_hmac_md5:
-	crypto_free_ahash(hmac_md5);
-out_free_md5:
-	crypto_free_ahash(md5);
-out_free_cksum:
-	kfree(checksumdata);
-out_free_rc4salt:
-	kfree(rc4salt);
-	return err ? GSS_S_FAILURE : 0;
-}
-
 /*
  * checksum the plaintext data and hdrlen bytes of the token header
  * The checksum is performed over the first 8 bytes of the
@@ -284,11 +155,6 @@ make_checksum(struct krb5_ctx *kctx, char *header, int hdrlen,
 	u8 *checksumdata;
 	unsigned int checksumlen;
 
-	if (kctx->gk5e->ctype == CKSUMTYPE_HMAC_MD5_ARCFOUR)
-		return make_checksum_hmac_md5(kctx, header, hdrlen,
-					      body, body_offset,
-					      cksumkey, usage, cksumout);
-
 	if (cksumout->len < kctx->gk5e->cksumlength) {
 		dprintk("%s: checksum buffer length, %u, too small for %s\n",
 			__func__, cksumout->len, kctx->gk5e->name);
@@ -942,145 +808,3 @@ out_err:
 		ret = GSS_S_FAILURE;
 	return ret;
 }
-
-/*
- * Compute Kseq given the initial session key and the checksum.
- * Set the key of the given cipher.
- */
-int
-krb5_rc4_setup_seq_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       unsigned char *cksum)
-{
-	struct crypto_shash *hmac;
-	struct shash_desc *desc;
-	u8 Kseq[GSS_KRB5_MAX_KEYLEN];
-	u32 zeroconstant = 0;
-	int err;
-
-	dprintk("%s: entered\n", __func__);
-
-	hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0);
-	if (IS_ERR(hmac)) {
-		dprintk("%s: error %ld, allocating hash '%s'\n",
-			__func__, PTR_ERR(hmac), kctx->gk5e->cksum_name);
-		return PTR_ERR(hmac);
-	}
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac),
-		       GFP_NOFS);
-	if (!desc) {
-		dprintk("%s: failed to allocate shash descriptor for '%s'\n",
-			__func__, kctx->gk5e->cksum_name);
-		crypto_free_shash(hmac);
-		return -ENOMEM;
-	}
-
-	desc->tfm = hmac;
-
-	/* Compute intermediate Kseq from session key */
-	err = crypto_shash_setkey(hmac, kctx->Ksess, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = crypto_shash_digest(desc, (u8 *)&zeroconstant, 4, Kseq);
-	if (err)
-		goto out_err;
-
-	/* Compute final Kseq from the checksum and intermediate Kseq */
-	err = crypto_shash_setkey(hmac, Kseq, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = crypto_shash_digest(desc, cksum, 8, Kseq);
-	if (err)
-		goto out_err;
-
-	err = crypto_sync_skcipher_setkey(cipher, Kseq, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = 0;
-
-out_err:
-	kfree_sensitive(desc);
-	crypto_free_shash(hmac);
-	dprintk("%s: returning %d\n", __func__, err);
-	return err;
-}
-
-/*
- * Compute Kcrypt given the initial session key and the plaintext seqnum.
- * Set the key of cipher kctx->enc.
- */
-int
-krb5_rc4_setup_enc_key(struct krb5_ctx *kctx,
-		       struct crypto_sync_skcipher *cipher,
-		       s32 seqnum)
-{
-	struct crypto_shash *hmac;
-	struct shash_desc *desc;
-	u8 Kcrypt[GSS_KRB5_MAX_KEYLEN];
-	u8 zeroconstant[4] = {0};
-	u8 seqnumarray[4];
-	int err, i;
-
-	dprintk("%s: entered, seqnum %u\n", __func__, seqnum);
-
-	hmac = crypto_alloc_shash(kctx->gk5e->cksum_name, 0, 0);
-	if (IS_ERR(hmac)) {
-		dprintk("%s: error %ld, allocating hash '%s'\n",
-			__func__, PTR_ERR(hmac), kctx->gk5e->cksum_name);
-		return PTR_ERR(hmac);
-	}
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac),
-		       GFP_NOFS);
-	if (!desc) {
-		dprintk("%s: failed to allocate shash descriptor for '%s'\n",
-			__func__, kctx->gk5e->cksum_name);
-		crypto_free_shash(hmac);
-		return -ENOMEM;
-	}
-
-	desc->tfm = hmac;
-
-	/* Compute intermediate Kcrypt from session key */
-	for (i = 0; i < kctx->gk5e->keylength; i++)
-		Kcrypt[i] = kctx->Ksess[i] ^ 0xf0;
-
-	err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = crypto_shash_digest(desc, zeroconstant, 4, Kcrypt);
-	if (err)
-		goto out_err;
-
-	/* Compute final Kcrypt from the seqnum and intermediate Kcrypt */
-	err = crypto_shash_setkey(hmac, Kcrypt, kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	seqnumarray[0] = (unsigned char) ((seqnum >> 24) & 0xff);
-	seqnumarray[1] = (unsigned char) ((seqnum >> 16) & 0xff);
-	seqnumarray[2] = (unsigned char) ((seqnum >> 8) & 0xff);
-	seqnumarray[3] = (unsigned char) ((seqnum >> 0) & 0xff);
-
-	err = crypto_shash_digest(desc, seqnumarray, 4, Kcrypt);
-	if (err)
-		goto out_err;
-
-	err = crypto_sync_skcipher_setkey(cipher, Kcrypt,
-					  kctx->gk5e->keylength);
-	if (err)
-		goto out_err;
-
-	err = 0;
-
-out_err:
-	kfree_sensitive(desc);
-	crypto_free_shash(hmac);
-	dprintk("%s: returning %d\n", __func__, err);
-	return err;
-}
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index a84a5b289484..1c092b05c2bb 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -21,6 +21,8 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/gss_krb5_enctypes.h>
 
+#include "auth_gss_internal.h"
+
 #if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
@@ -52,27 +54,6 @@ static const struct gss_krb5_enctype supported_gss_krb5_enctypes[] = {
 	},
 #endif	/* CONFIG_SUNRPC_DISABLE_INSECURE_ENCTYPES */
 	/*
-	 * RC4-HMAC
-	 */
-	{
-	  .etype = ENCTYPE_ARCFOUR_HMAC,
-	  .ctype = CKSUMTYPE_HMAC_MD5_ARCFOUR,
-	  .name = "rc4-hmac",
-	  .encrypt_name = "ecb(arc4)",
-	  .cksum_name = "hmac(md5)",
-	  .encrypt = krb5_encrypt,
-	  .decrypt = krb5_decrypt,
-	  .mk_key = NULL,
-	  .signalg = SGN_ALG_HMAC_MD5,
-	  .sealalg = SEAL_ALG_MICROSOFT_RC4,
-	  .keybytes = 16,
-	  .keylength = 16,
-	  .blocksize = 1,
-	  .conflen = 8,
-	  .cksumlength = 8,
-	  .keyed_cksum = 1,
-	},
-	/*
 	 * 3DES
 	 */
 	{
@@ -164,35 +145,6 @@ get_gss_krb5_enctype(int etype)
 	return NULL;
 }
 
-static const void *
-simple_get_bytes(const void *p, const void *end, void *res, int len)
-{
-	const void *q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	memcpy(res, p, len);
-	return q;
-}
-
-static const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
-{
-	const void *q;
-	unsigned int len;
-
-	p = simple_get_bytes(p, end, &len, sizeof(len));
-	if (IS_ERR(p))
-		return p;
-	q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	res->data = kmemdup(p, len, GFP_NOFS);
-	if (unlikely(res->data == NULL))
-		return ERR_PTR(-ENOMEM);
-	res->len = len;
-	return q;
-}
-
 static inline const void *
 get_key(const void *p, const void *end,
 	struct krb5_ctx *ctx, struct crypto_sync_skcipher **res)
@@ -401,78 +353,6 @@ out_err:
 	return -EINVAL;
 }
 
-/*
- * Note that RC4 depends on deriving keys using the sequence
- * number or the checksum of a token.  Therefore, the final keys
- * cannot be calculated until the token is being constructed!
- */
-static int
-context_derive_keys_rc4(struct krb5_ctx *ctx)
-{
-	struct crypto_shash *hmac;
-	char sigkeyconstant[] = "signaturekey";
-	int slen = strlen(sigkeyconstant) + 1;	/* include null terminator */
-	struct shash_desc *desc;
-	int err;
-
-	dprintk("RPC:       %s: entered\n", __func__);
-	/*
-	 * derive cksum (aka Ksign) key
-	 */
-	hmac = crypto_alloc_shash(ctx->gk5e->cksum_name, 0, 0);
-	if (IS_ERR(hmac)) {
-		dprintk("%s: error %ld allocating hash '%s'\n",
-			__func__, PTR_ERR(hmac), ctx->gk5e->cksum_name);
-		err = PTR_ERR(hmac);
-		goto out_err;
-	}
-
-	err = crypto_shash_setkey(hmac, ctx->Ksess, ctx->gk5e->keylength);
-	if (err)
-		goto out_err_free_hmac;
-
-
-	desc = kmalloc(sizeof(*desc) + crypto_shash_descsize(hmac), GFP_NOFS);
-	if (!desc) {
-		dprintk("%s: failed to allocate hash descriptor for '%s'\n",
-			__func__, ctx->gk5e->cksum_name);
-		err = -ENOMEM;
-		goto out_err_free_hmac;
-	}
-
-	desc->tfm = hmac;
-
-	err = crypto_shash_digest(desc, sigkeyconstant, slen, ctx->cksum);
-	kfree_sensitive(desc);
-	if (err)
-		goto out_err_free_hmac;
-	/*
-	 * allocate hash, and skciphers for data and seqnum encryption
-	 */
-	ctx->enc = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(ctx->enc)) {
-		err = PTR_ERR(ctx->enc);
-		goto out_err_free_hmac;
-	}
-
-	ctx->seq = crypto_alloc_sync_skcipher(ctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(ctx->seq)) {
-		crypto_free_sync_skcipher(ctx->enc);
-		err = PTR_ERR(ctx->seq);
-		goto out_err_free_hmac;
-	}
-
-	dprintk("RPC:       %s: returning success\n", __func__);
-
-	err = 0;
-
-out_err_free_hmac:
-	crypto_free_shash(hmac);
-out_err:
-	dprintk("RPC:       %s: returning %d\n", __func__, err);
-	return err;
-}
-
 static int
 context_derive_keys_new(struct krb5_ctx *ctx, gfp_t gfp_mask)
 {
@@ -649,8 +529,6 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx,
 	switch (ctx->enctype) {
 	case ENCTYPE_DES3_CBC_RAW:
 		return context_derive_keys_des3(ctx, gfp_mask);
-	case ENCTYPE_ARCFOUR_HMAC:
-		return context_derive_keys_rc4(ctx);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
 		return context_derive_keys_new(ctx, gfp_mask);
diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c
index f1d280accf43..33061417ec97 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seal.c
@@ -214,7 +214,6 @@ gss_get_mic_kerberos(struct gss_ctx *gss_ctx, struct xdr_buf *text,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_get_mic_v1(ctx, text, token);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
diff --git a/net/sunrpc/auth_gss/gss_krb5_seqnum.c b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
index 507105127095..fb117817ff5d 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seqnum.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seqnum.c
@@ -39,42 +39,6 @@
 # define RPCDBG_FACILITY        RPCDBG_AUTH
 #endif
 
-static s32
-krb5_make_rc4_seq_num(struct krb5_ctx *kctx, int direction, s32 seqnum,
-		      unsigned char *cksum, unsigned char *buf)
-{
-	struct crypto_sync_skcipher *cipher;
-	unsigned char *plain;
-	s32 code;
-
-	dprintk("RPC:       %s:\n", __func__);
-	cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(cipher))
-		return PTR_ERR(cipher);
-
-	plain = kmalloc(8, GFP_NOFS);
-	if (!plain)
-		return -ENOMEM;
-
-	plain[0] = (unsigned char) ((seqnum >> 24) & 0xff);
-	plain[1] = (unsigned char) ((seqnum >> 16) & 0xff);
-	plain[2] = (unsigned char) ((seqnum >> 8) & 0xff);
-	plain[3] = (unsigned char) ((seqnum >> 0) & 0xff);
-	plain[4] = direction;
-	plain[5] = direction;
-	plain[6] = direction;
-	plain[7] = direction;
-
-	code = krb5_rc4_setup_seq_key(kctx, cipher, cksum);
-	if (code)
-		goto out;
-
-	code = krb5_encrypt(cipher, cksum, plain, buf, 8);
-out:
-	kfree(plain);
-	crypto_free_sync_skcipher(cipher);
-	return code;
-}
 s32
 krb5_make_seq_num(struct krb5_ctx *kctx,
 		struct crypto_sync_skcipher *key,
@@ -85,10 +49,6 @@ krb5_make_seq_num(struct krb5_ctx *kctx,
 	unsigned char *plain;
 	s32 code;
 
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC)
-		return krb5_make_rc4_seq_num(kctx, direction, seqnum,
-					     cksum, buf);
-
 	plain = kmalloc(8, GFP_NOFS);
 	if (!plain)
 		return -ENOMEM;
@@ -108,50 +68,6 @@ krb5_make_seq_num(struct krb5_ctx *kctx,
 	return code;
 }
 
-static s32
-krb5_get_rc4_seq_num(struct krb5_ctx *kctx, unsigned char *cksum,
-		     unsigned char *buf, int *direction, s32 *seqnum)
-{
-	struct crypto_sync_skcipher *cipher;
-	unsigned char *plain;
-	s32 code;
-
-	dprintk("RPC:       %s:\n", __func__);
-	cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name, 0, 0);
-	if (IS_ERR(cipher))
-		return PTR_ERR(cipher);
-
-	code = krb5_rc4_setup_seq_key(kctx, cipher, cksum);
-	if (code)
-		goto out;
-
-	plain = kmalloc(8, GFP_NOFS);
-	if (!plain) {
-		code = -ENOMEM;
-		goto out;
-	}
-
-	code = krb5_decrypt(cipher, cksum, buf, plain, 8);
-	if (code)
-		goto out_plain;
-
-	if ((plain[4] != plain[5]) || (plain[4] != plain[6])
-				   || (plain[4] != plain[7])) {
-		code = (s32)KG_BAD_SEQ;
-		goto out_plain;
-	}
-
-	*direction = plain[4];
-
-	*seqnum = ((plain[0] << 24) | (plain[1] << 16) |
-					(plain[2] << 8) | (plain[3]));
-out_plain:
-	kfree(plain);
-out:
-	crypto_free_sync_skcipher(cipher);
-	return code;
-}
-
 s32
 krb5_get_seq_num(struct krb5_ctx *kctx,
 	       unsigned char *cksum,
@@ -164,9 +80,6 @@ krb5_get_seq_num(struct krb5_ctx *kctx,
 
 	dprintk("RPC:       krb5_get_seq_num:\n");
 
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC)
-		return krb5_get_rc4_seq_num(kctx, cksum, buf,
-					    direction, seqnum);
 	plain = kmalloc(8, GFP_NOFS);
 	if (!plain)
 		return -ENOMEM;
diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c
index aaab91cf24c8..ba04e3ec970a 100644
--- a/net/sunrpc/auth_gss/gss_krb5_unseal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c
@@ -218,7 +218,6 @@ gss_verify_mic_kerberos(struct gss_ctx *gss_ctx,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_verify_mic_v1(ctx, message_buffer, read_token);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 8b300b74a722..e95c009bb869 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -236,26 +236,9 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 			       seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8)))
 		return GSS_S_FAILURE;
 
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
-		struct crypto_sync_skcipher *cipher;
-		int err;
-		cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name,
-						    0, 0);
-		if (IS_ERR(cipher))
-			return GSS_S_FAILURE;
-
-		krb5_rc4_setup_enc_key(kctx, cipher, seq_send);
-
-		err = gss_encrypt_xdr_buf(cipher, buf,
-					  offset + headlen - conflen, pages);
-		crypto_free_sync_skcipher(cipher);
-		if (err)
-			return GSS_S_FAILURE;
-	} else {
-		if (gss_encrypt_xdr_buf(kctx->enc, buf,
-					offset + headlen - conflen, pages))
-			return GSS_S_FAILURE;
-	}
+	if (gss_encrypt_xdr_buf(kctx->enc, buf,
+				offset + headlen - conflen, pages))
+		return GSS_S_FAILURE;
 
 	return (kctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE;
 }
@@ -316,37 +299,9 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len,
 	crypt_offset = ptr + (GSS_KRB5_TOK_HDR_LEN + kctx->gk5e->cksumlength) -
 					(unsigned char *)buf->head[0].iov_base;
 
-	/*
-	 * Need plaintext seqnum to derive encryption key for arcfour-hmac
-	 */
-	if (krb5_get_seq_num(kctx, ptr + GSS_KRB5_TOK_HDR_LEN,
-			     ptr + 8, &direction, &seqnum))
-		return GSS_S_BAD_SIG;
-
-	if ((kctx->initiate && direction != 0xff) ||
-	    (!kctx->initiate && direction != 0))
-		return GSS_S_BAD_SIG;
-
 	buf->len = len;
-	if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) {
-		struct crypto_sync_skcipher *cipher;
-		int err;
-
-		cipher = crypto_alloc_sync_skcipher(kctx->gk5e->encrypt_name,
-						    0, 0);
-		if (IS_ERR(cipher))
-			return GSS_S_FAILURE;
-
-		krb5_rc4_setup_enc_key(kctx, cipher, seqnum);
-
-		err = gss_decrypt_xdr_buf(cipher, buf, crypt_offset);
-		crypto_free_sync_skcipher(cipher);
-		if (err)
-			return GSS_S_DEFECTIVE_TOKEN;
-	} else {
-		if (gss_decrypt_xdr_buf(kctx->enc, buf, crypt_offset))
-			return GSS_S_DEFECTIVE_TOKEN;
-	}
+	if (gss_decrypt_xdr_buf(kctx->enc, buf, crypt_offset))
+		return GSS_S_DEFECTIVE_TOKEN;
 
 	if (kctx->gk5e->keyed_cksum)
 		cksumkey = kctx->cksum;
@@ -370,6 +325,14 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len,
 
 	/* do sequencing checks */
 
+	if (krb5_get_seq_num(kctx, ptr + GSS_KRB5_TOK_HDR_LEN,
+			     ptr + 8, &direction, &seqnum))
+		return GSS_S_BAD_SIG;
+
+	if ((kctx->initiate && direction != 0xff) ||
+	    (!kctx->initiate && direction != 0))
+		return GSS_S_BAD_SIG;
+
 	/* Copy the data back to the right position.  XXX: Would probably be
 	 * better to copy and encrypt at the same time. */
 
@@ -605,7 +568,6 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_wrap_kerberos_v1(kctx, offset, buf, pages);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
 	case ENCTYPE_AES256_CTS_HMAC_SHA1_96:
@@ -624,7 +586,6 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset,
 		BUG();
 	case ENCTYPE_DES_CBC_RAW:
 	case ENCTYPE_DES3_CBC_RAW:
-	case ENCTYPE_ARCFOUR_HMAC:
 		return gss_unwrap_kerberos_v1(kctx, offset, len, buf,
 					      &gctx->slack, &gctx->align);
 	case ENCTYPE_AES128_CTS_HMAC_SHA1_96:
diff --git a/net/sunrpc/auth_gss/gss_rpc_upcall.c b/net/sunrpc/auth_gss/gss_rpc_upcall.c
index af9c7f43859c..d1c003a25b0f 100644
--- a/net/sunrpc/auth_gss/gss_rpc_upcall.c
+++ b/net/sunrpc/auth_gss/gss_rpc_upcall.c
@@ -200,7 +200,7 @@ static int gssp_call(struct net *net, struct rpc_message *msg)
 
 static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg)
 {
-	int i;
+	unsigned int i;
 
 	for (i = 0; i < arg->npages && arg->pages[i]; i++)
 		__free_page(arg->pages[i]);
@@ -210,14 +210,19 @@ static void gssp_free_receive_pages(struct gssx_arg_accept_sec_context *arg)
 
 static int gssp_alloc_receive_pages(struct gssx_arg_accept_sec_context *arg)
 {
+	unsigned int i;
+
 	arg->npages = DIV_ROUND_UP(NGROUPS_MAX * 4, PAGE_SIZE);
 	arg->pages = kcalloc(arg->npages, sizeof(struct page *), GFP_KERNEL);
-	/*
-	 * XXX: actual pages are allocated by xdr layer in
-	 * xdr_partial_copy_from_skb.
-	 */
 	if (!arg->pages)
 		return -ENOMEM;
+	for (i = 0; i < arg->npages; i++) {
+		arg->pages[i] = alloc_page(GFP_KERNEL);
+		if (!arg->pages[i]) {
+			gssp_free_receive_pages(arg);
+			return -ENOMEM;
+		}
+	}
 	return 0;
 }
 
diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c
index 2ff7b7083eba..d79f12c2550a 100644
--- a/net/sunrpc/auth_gss/gss_rpc_xdr.c
+++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c
@@ -771,7 +771,6 @@ void gssx_enc_accept_sec_context(struct rpc_rqst *req,
 	xdr_inline_pages(&req->rq_rcv_buf,
 		PAGE_SIZE/2 /* pretty arbitrary */,
 		arg->pages, 0 /* page base */, arg->npages * PAGE_SIZE);
-	req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES;
 done:
 	if (err)
 		dprintk("RPC:       gssx_enc_accept_sec_context: %d\n", err);
@@ -789,7 +788,7 @@ int gssx_dec_accept_sec_context(struct rpc_rqst *rqstp,
 	scratch = alloc_page(GFP_KERNEL);
 	if (!scratch)
 		return -ENOMEM;
-	xdr_set_scratch_buffer(xdr, page_address(scratch), PAGE_SIZE);
+	xdr_set_scratch_page(xdr, scratch);
 
 	/* res->status */
 	err = gssx_dec_status(xdr, &res->status);
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 258b04372f85..bd4678db9d76 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -1147,9 +1147,9 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp,
 			       struct gssp_in_token *in_token)
 {
 	struct kvec *argv = &rqstp->rq_arg.head[0];
-	unsigned int page_base, length;
-	int pages, i, res;
-	size_t inlen;
+	unsigned int length, pgto_offs, pgfrom_offs;
+	int pages, i, res, pgto, pgfrom;
+	size_t inlen, to_offs, from_offs;
 
 	res = gss_read_common_verf(gc, argv, authp, in_handle);
 	if (res)
@@ -1177,17 +1177,24 @@ static int gss_read_proxy_verf(struct svc_rqst *rqstp,
 	memcpy(page_address(in_token->pages[0]), argv->iov_base, length);
 	inlen -= length;
 
-	i = 1;
-	page_base = rqstp->rq_arg.page_base;
+	to_offs = length;
+	from_offs = rqstp->rq_arg.page_base;
 	while (inlen) {
-		length = min_t(unsigned int, inlen, PAGE_SIZE);
-		memcpy(page_address(in_token->pages[i]),
-		       page_address(rqstp->rq_arg.pages[i]) + page_base,
+		pgto = to_offs >> PAGE_SHIFT;
+		pgfrom = from_offs >> PAGE_SHIFT;
+		pgto_offs = to_offs & ~PAGE_MASK;
+		pgfrom_offs = from_offs & ~PAGE_MASK;
+
+		length = min_t(unsigned int, inlen,
+			 min_t(unsigned int, PAGE_SIZE - pgto_offs,
+			       PAGE_SIZE - pgfrom_offs));
+		memcpy(page_address(in_token->pages[pgto]) + pgto_offs,
+		       page_address(rqstp->rq_arg.pages[pgfrom]) + pgfrom_offs,
 		       length);
 
+		to_offs += length;
+		from_offs += length;
 		inlen -= length;
-		page_base = 0;
-		i++;
 	}
 	return 0;
 }
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 195b40c5dae4..22a2c235abf1 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -5,7 +5,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
@@ -111,7 +111,7 @@ out_free:
  * by the backchannel.  This function can be called multiple times
  * when creating new sessions that use the same rpc_xprt.  The
  * preallocated buffers are added to the pool of resources used by
- * the rpc_xprt.  Anyone of these resources may be used used by an
+ * the rpc_xprt.  Any one of these resources may be used by an
  * incoming callback request.  It's up to the higher levels in the
  * stack to enforce that the maximum number of session slots is not
  * being exceeded.
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index baef5ee43dbb..1a2c1c44bb00 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -498,16 +498,17 @@ static int cache_clean(void)
  */
 static void do_cache_clean(struct work_struct *work)
 {
-	int delay = 5;
-	if (cache_clean() == -1)
-		delay = round_jiffies_relative(30*HZ);
+	int delay;
 
 	if (list_empty(&cache_list))
-		delay = 0;
+		return;
+
+	if (cache_clean() == -1)
+		delay = round_jiffies_relative(30*HZ);
+	else
+		delay = 5;
 
-	if (delay)
-		queue_delayed_work(system_power_efficient_wq,
-				   &cache_cleaner, delay);
+	queue_delayed_work(system_power_efficient_wq, &cache_cleaner, delay);
 }
 
 
@@ -777,7 +778,6 @@ void cache_clean_deferred(void *owner)
  */
 
 static DEFINE_SPINLOCK(queue_lock);
-static DEFINE_MUTEX(queue_io_mutex);
 
 struct cache_queue {
 	struct list_head	list;
@@ -905,44 +905,26 @@ static ssize_t cache_do_downcall(char *kaddr, const char __user *buf,
 	return ret;
 }
 
-static ssize_t cache_slow_downcall(const char __user *buf,
-				   size_t count, struct cache_detail *cd)
-{
-	static char write_buf[8192]; /* protected by queue_io_mutex */
-	ssize_t ret = -EINVAL;
-
-	if (count >= sizeof(write_buf))
-		goto out;
-	mutex_lock(&queue_io_mutex);
-	ret = cache_do_downcall(write_buf, buf, count, cd);
-	mutex_unlock(&queue_io_mutex);
-out:
-	return ret;
-}
-
 static ssize_t cache_downcall(struct address_space *mapping,
 			      const char __user *buf,
 			      size_t count, struct cache_detail *cd)
 {
-	struct page *page;
-	char *kaddr;
+	char *write_buf;
 	ssize_t ret = -ENOMEM;
 
-	if (count >= PAGE_SIZE)
-		goto out_slow;
+	if (count >= 32768) { /* 32k is max userland buffer, lets check anyway */
+		ret = -EINVAL;
+		goto out;
+	}
 
-	page = find_or_create_page(mapping, 0, GFP_KERNEL);
-	if (!page)
-		goto out_slow;
+	write_buf = kvmalloc(count + 1, GFP_KERNEL);
+	if (!write_buf)
+		goto out;
 
-	kaddr = kmap(page);
-	ret = cache_do_downcall(kaddr, buf, count, cd);
-	kunmap(page);
-	unlock_page(page);
-	put_page(page);
+	ret = cache_do_downcall(write_buf, buf, count, cd);
+	kvfree(write_buf);
+out:
 	return ret;
-out_slow:
-	return cache_slow_downcall(buf, count, cd);
 }
 
 static ssize_t cache_write(struct file *filp, const char __user *buf,
@@ -1436,10 +1418,10 @@ static int c_show(struct seq_file *m, void *p)
 	cache_get(cp);
 	if (cache_check(cd, cp, NULL))
 		/* cache_check does a cache_put on failure */
-		seq_printf(m, "# ");
+		seq_puts(m, "# ");
 	else {
 		if (cache_is_expired(cd, cp))
-			seq_printf(m, "# ");
+			seq_puts(m, "# ");
 		cache_put(cp, cd);
 	}
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 62e0b6c1e8cf..612f0a641f4c 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -47,10 +47,6 @@
 # define RPCDBG_FACILITY	RPCDBG_CALL
 #endif
 
-#define dprint_status(t)					\
-	dprintk("RPC: %5u %s (status %d)\n", t->tk_pid,		\
-			__func__, t->tk_status)
-
 /*
  * All RPC clients are linked into this list
  */
@@ -1255,10 +1251,7 @@ void rpc_prepare_reply_pages(struct rpc_rqst *req, struct page **pages,
 			     unsigned int base, unsigned int len,
 			     unsigned int hdrsize)
 {
-	/* Subtract one to force an extra word of buffer space for the
-	 * payload's XDR pad to fall into the rcv_buf's tail iovec.
-	 */
-	hdrsize += RPC_REPHDRSIZE + req->rq_cred->cr_auth->au_ralign - 1;
+	hdrsize += RPC_REPHDRSIZE + req->rq_cred->cr_auth->au_ralign;
 
 	xdr_inline_pages(&req->rq_rcv_buf, hdrsize << 2, pages, base, len);
 	trace_rpc_xdr_reply_pages(req->rq_task, &req->rq_rcv_buf);
@@ -1639,10 +1632,6 @@ call_start(struct rpc_task *task)
 	int idx = task->tk_msg.rpc_proc->p_statidx;
 
 	trace_rpc_request(task);
-	dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid,
-			clnt->cl_program->name, clnt->cl_vers,
-			rpc_proc_name(task),
-			(RPC_IS_ASYNC(task) ? "async" : "sync"));
 
 	/* Increment call count (version might not be valid for ping) */
 	if (clnt->cl_program->version[clnt->cl_vers])
@@ -1658,8 +1647,6 @@ call_start(struct rpc_task *task)
 static void
 call_reserve(struct rpc_task *task)
 {
-	dprint_status(task);
-
 	task->tk_status  = 0;
 	task->tk_action  = call_reserveresult;
 	xprt_reserve(task);
@@ -1675,8 +1662,6 @@ call_reserveresult(struct rpc_task *task)
 {
 	int status = task->tk_status;
 
-	dprint_status(task);
-
 	/*
 	 * After a call to xprt_reserve(), we must have either
 	 * a request slot or else an error status.
@@ -1717,8 +1702,6 @@ call_reserveresult(struct rpc_task *task)
 static void
 call_retry_reserve(struct rpc_task *task)
 {
-	dprint_status(task);
-
 	task->tk_status  = 0;
 	task->tk_action  = call_reserveresult;
 	xprt_retry_reserve(task);
@@ -1730,8 +1713,6 @@ call_retry_reserve(struct rpc_task *task)
 static void
 call_refresh(struct rpc_task *task)
 {
-	dprint_status(task);
-
 	task->tk_action = call_refreshresult;
 	task->tk_status = 0;
 	task->tk_client->cl_stats->rpcauthrefresh++;
@@ -1746,8 +1727,6 @@ call_refreshresult(struct rpc_task *task)
 {
 	int status = task->tk_status;
 
-	dprint_status(task);
-
 	task->tk_status = 0;
 	task->tk_action = call_refresh;
 	switch (status) {
@@ -1770,12 +1749,10 @@ call_refreshresult(struct rpc_task *task)
 		if (!task->tk_cred_retry)
 			break;
 		task->tk_cred_retry--;
-		dprintk("RPC: %5u %s: retry refresh creds\n",
-				task->tk_pid, __func__);
+		trace_rpc_retry_refresh_status(task);
 		return;
 	}
-	dprintk("RPC: %5u %s: refresh creds failed with error %d\n",
-				task->tk_pid, __func__, status);
+	trace_rpc_refresh_status(task);
 	rpc_call_rpcerror(task, status);
 }
 
@@ -1792,8 +1769,6 @@ call_allocate(struct rpc_task *task)
 	const struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
 	int status;
 
-	dprint_status(task);
-
 	task->tk_status = 0;
 	task->tk_action = call_encode;
 
@@ -1823,6 +1798,7 @@ call_allocate(struct rpc_task *task)
 	req->rq_rcvsize <<= 2;
 
 	status = xprt->ops->buf_alloc(task);
+	trace_rpc_buf_alloc(task, status);
 	xprt_inject_disconnect(xprt);
 	if (status == 0)
 		return;
@@ -1831,8 +1807,6 @@ call_allocate(struct rpc_task *task)
 		return;
 	}
 
-	dprintk("RPC: %5u rpc_buffer allocation failed\n", task->tk_pid);
-
 	if (RPC_IS_ASYNC(task) || !fatal_signal_pending(current)) {
 		task->tk_action = call_allocate;
 		rpc_delay(task, HZ>>4);
@@ -1883,7 +1857,7 @@ call_encode(struct rpc_task *task)
 {
 	if (!rpc_task_need_encode(task))
 		goto out;
-	dprint_status(task);
+
 	/* Dequeue task from the receive queue while we're encoding */
 	xprt_request_dequeue_xprt(task);
 	/* Encode here so that rpcsec_gss can use correct sequence number. */
@@ -1902,8 +1876,7 @@ call_encode(struct rpc_task *task)
 			} else {
 				task->tk_action = call_refresh;
 				task->tk_cred_retry--;
-				dprintk("RPC: %5u %s: retry refresh creds\n",
-					task->tk_pid, __func__);
+				trace_rpc_retry_refresh_status(task);
 			}
 			break;
 		default:
@@ -1960,8 +1933,6 @@ call_bind(struct rpc_task *task)
 		return;
 	}
 
-	dprint_status(task);
-
 	task->tk_action = call_bind_status;
 	if (!xprt_prepare_transmit(task))
 		return;
@@ -1983,8 +1954,6 @@ call_bind_status(struct rpc_task *task)
 		return;
 	}
 
-	dprint_status(task);
-	trace_rpc_bind_status(task);
 	if (task->tk_status >= 0)
 		goto out_next;
 	if (xprt_bound(xprt)) {
@@ -1994,12 +1963,10 @@ call_bind_status(struct rpc_task *task)
 
 	switch (task->tk_status) {
 	case -ENOMEM:
-		dprintk("RPC: %5u rpcbind out of memory\n", task->tk_pid);
 		rpc_delay(task, HZ >> 2);
 		goto retry_timeout;
 	case -EACCES:
-		dprintk("RPC: %5u remote rpcbind: RPC program/version "
-				"unavailable\n", task->tk_pid);
+		trace_rpcb_prog_unavail_err(task);
 		/* fail immediately if this is an RPC ping */
 		if (task->tk_msg.rpc_proc->p_proc == 0) {
 			status = -EOPNOTSUPP;
@@ -2016,17 +1983,14 @@ call_bind_status(struct rpc_task *task)
 	case -EAGAIN:
 		goto retry_timeout;
 	case -ETIMEDOUT:
-		dprintk("RPC: %5u rpcbind request timed out\n",
-				task->tk_pid);
+		trace_rpcb_timeout_err(task);
 		goto retry_timeout;
 	case -EPFNOSUPPORT:
 		/* server doesn't support any rpcbind version we know of */
-		dprintk("RPC: %5u unrecognized remote rpcbind service\n",
-				task->tk_pid);
+		trace_rpcb_bind_version_err(task);
 		break;
 	case -EPROTONOSUPPORT:
-		dprintk("RPC: %5u remote rpcbind version unavailable, retrying\n",
-				task->tk_pid);
+		trace_rpcb_bind_version_err(task);
 		goto retry_timeout;
 	case -ECONNREFUSED:		/* connection problems */
 	case -ECONNRESET:
@@ -2037,8 +2001,7 @@ call_bind_status(struct rpc_task *task)
 	case -EHOSTUNREACH:
 	case -ENETUNREACH:
 	case -EPIPE:
-		dprintk("RPC: %5u remote rpcbind unreachable: %d\n",
-				task->tk_pid, task->tk_status);
+		trace_rpcb_unreachable_err(task);
 		if (!RPC_IS_SOFTCONN(task)) {
 			rpc_delay(task, 5*HZ);
 			goto retry_timeout;
@@ -2046,8 +2009,7 @@ call_bind_status(struct rpc_task *task)
 		status = task->tk_status;
 		break;
 	default:
-		dprintk("RPC: %5u unrecognized rpcbind error (%d)\n",
-				task->tk_pid, -task->tk_status);
+		trace_rpcb_unrecognized_err(task);
 	}
 
 	rpc_call_rpcerror(task, status);
@@ -2079,10 +2041,6 @@ call_connect(struct rpc_task *task)
 		return;
 	}
 
-	dprintk("RPC: %5u call_connect xprt %p %s connected\n",
-			task->tk_pid, xprt,
-			(xprt_connected(xprt) ? "is" : "is not"));
-
 	task->tk_action = call_connect_status;
 	if (task->tk_status < 0)
 		return;
@@ -2110,7 +2068,6 @@ call_connect_status(struct rpc_task *task)
 		return;
 	}
 
-	dprint_status(task);
 	trace_rpc_connect_status(task);
 
 	if (task->tk_status == 0) {
@@ -2178,8 +2135,6 @@ call_transmit(struct rpc_task *task)
 		return;
 	}
 
-	dprint_status(task);
-
 	task->tk_action = call_transmit_status;
 	if (!xprt_prepare_transmit(task))
 		return;
@@ -2214,7 +2169,6 @@ call_transmit_status(struct rpc_task *task)
 
 	switch (task->tk_status) {
 	default:
-		dprint_status(task);
 		break;
 	case -EBADMSG:
 		task->tk_status = 0;
@@ -2296,8 +2250,6 @@ call_bc_transmit_status(struct rpc_task *task)
 	if (rpc_task_transmitted(task))
 		task->tk_status = 0;
 
-	dprint_status(task);
-
 	switch (task->tk_status) {
 	case 0:
 		/* Success */
@@ -2357,8 +2309,6 @@ call_status(struct rpc_task *task)
 	if (!task->tk_msg.rpc_proc->p_proc)
 		trace_xprt_ping(task->tk_xprt, task->tk_status);
 
-	dprint_status(task);
-
 	status = task->tk_status;
 	if (status >= 0) {
 		task->tk_action = call_decode;
@@ -2405,7 +2355,8 @@ call_status(struct rpc_task *task)
 		goto out_exit;
 	}
 	task->tk_action = call_encode;
-	rpc_check_timeout(task);
+	if (status != -ECONNRESET && status != -ECONNABORTED)
+		rpc_check_timeout(task);
 	return;
 out_exit:
 	rpc_call_rpcerror(task, status);
@@ -2433,7 +2384,7 @@ rpc_check_timeout(struct rpc_task *task)
 	if (xprt_adjust_timeout(task->tk_rqstp) == 0)
 		return;
 
-	dprintk("RPC: %5u call_timeout (major)\n", task->tk_pid);
+	trace_rpc_timeout_status(task);
 	task->tk_timeouts++;
 
 	if (RPC_IS_SOFTCONN(task) && !rpc_check_connected(task->tk_rqstp)) {
@@ -2492,8 +2443,6 @@ call_decode(struct rpc_task *task)
 	struct xdr_stream xdr;
 	int err;
 
-	dprint_status(task);
-
 	if (!task->tk_msg.rpc_proc->p_decode) {
 		task->tk_action = rpc_exit_task;
 		return;
@@ -2537,8 +2486,6 @@ out:
 	case 0:
 		task->tk_action = rpc_exit_task;
 		task->tk_status = rpcauth_unwrap_resp(task, &xdr);
-		dprintk("RPC: %5u %s result %d\n",
-			task->tk_pid, __func__, task->tk_status);
 		return;
 	case -EAGAIN:
 		task->tk_status = 0;
diff --git a/net/sunrpc/debugfs.c b/net/sunrpc/debugfs.c
index fd9bca242724..56029e3af6ff 100644
--- a/net/sunrpc/debugfs.c
+++ b/net/sunrpc/debugfs.c
@@ -128,13 +128,13 @@ static int do_xprt_debugfs(struct rpc_clnt *clnt, struct rpc_xprt *xprt, void *n
 		return 0;
 	len = snprintf(name, sizeof(name), "../../rpc_xprt/%s",
 		       xprt->debugfs->d_name.name);
-	if (len > sizeof(name))
+	if (len >= sizeof(name))
 		return -1;
 	if (*nump == 0)
 		strcpy(link, "xprt");
 	else {
 		len = snprintf(link, sizeof(link), "xprt%d", *nump);
-		if (len > sizeof(link))
+		if (len >= sizeof(link))
 			return -1;
 	}
 	debugfs_create_symlink(link, clnt->cl_debugfs, name);
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index eadc0ede928c..8241f5a4a01c 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -781,7 +781,8 @@ static int rpc_rmdir_depopulate(struct dentry *dentry,
 }
 
 /**
- * rpc_mkpipe - make an rpc_pipefs file for kernel<->userspace communication
+ * rpc_mkpipe_dentry - make an rpc_pipefs file for kernel<->userspace
+ *		       communication
  * @parent: dentry of directory to create new "pipe" in
  * @name: name of pipe
  * @private: private data to associate with the pipe, for the caller's use
diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c
index 4a67685c83eb..38fe2ce8a5aa 100644
--- a/net/sunrpc/rpcb_clnt.c
+++ b/net/sunrpc/rpcb_clnt.c
@@ -31,11 +31,9 @@
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/xprtsock.h>
 
-#include "netns.h"
+#include <trace/events/sunrpc.h>
 
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-# define RPCDBG_FACILITY	RPCDBG_BIND
-#endif
+#include "netns.h"
 
 #define RPCBIND_SOCK_PATHNAME	"/var/run/rpcbind.sock"
 
@@ -216,10 +214,6 @@ static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt,
 	sn->rpcb_is_af_local = is_af_local ? 1 : 0;
 	smp_wmb();
 	sn->rpcb_users = 1;
-	dprintk("RPC:       created new rpcb local clients (rpcb_local_clnt: "
-		"%p, rpcb_local_clnt4: %p) for net %x%s\n",
-		sn->rpcb_local_clnt, sn->rpcb_local_clnt4,
-		net->ns.inum, (net == &init_net) ? " (init_net)" : "");
 }
 
 /*
@@ -261,19 +255,13 @@ static int rpcb_create_local_unix(struct net *net)
 	 */
 	clnt = rpc_create(&args);
 	if (IS_ERR(clnt)) {
-		dprintk("RPC:       failed to create AF_LOCAL rpcbind "
-				"client (errno %ld).\n", PTR_ERR(clnt));
 		result = PTR_ERR(clnt);
 		goto out;
 	}
 
 	clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4);
-	if (IS_ERR(clnt4)) {
-		dprintk("RPC:       failed to bind second program to "
-				"rpcbind v4 client (errno %ld).\n",
-				PTR_ERR(clnt4));
+	if (IS_ERR(clnt4))
 		clnt4 = NULL;
-	}
 
 	rpcb_set_local(net, clnt, clnt4, true);
 
@@ -309,8 +297,6 @@ static int rpcb_create_local_net(struct net *net)
 
 	clnt = rpc_create(&args);
 	if (IS_ERR(clnt)) {
-		dprintk("RPC:       failed to create local rpcbind "
-				"client (errno %ld).\n", PTR_ERR(clnt));
 		result = PTR_ERR(clnt);
 		goto out;
 	}
@@ -321,12 +307,8 @@ static int rpcb_create_local_net(struct net *net)
 	 * v4 upcalls.
 	 */
 	clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4);
-	if (IS_ERR(clnt4)) {
-		dprintk("RPC:       failed to bind second program to "
-				"rpcbind v4 client (errno %ld).\n",
-				PTR_ERR(clnt4));
+	if (IS_ERR(clnt4))
 		clnt4 = NULL;
-	}
 
 	rpcb_set_local(net, clnt, clnt4, false);
 
@@ -403,11 +385,8 @@ static int rpcb_register_call(struct sunrpc_net *sn, struct rpc_clnt *clnt, stru
 	msg->rpc_resp = &result;
 
 	error = rpc_call_sync(clnt, msg, flags);
-	if (error < 0) {
-		dprintk("RPC:       failed to contact local rpcbind "
-				"server (errno %d).\n", -error);
+	if (error < 0)
 		return error;
-	}
 
 	if (!result)
 		return -EACCES;
@@ -461,9 +440,7 @@ int rpcb_register(struct net *net, u32 prog, u32 vers, int prot, unsigned short
 	struct sunrpc_net *sn = net_generic(net, sunrpc_net_id);
 	bool is_set = false;
 
-	dprintk("RPC:       %sregistering (%u, %u, %d, %u) with local "
-			"rpcbind\n", (port ? "" : "un"),
-			prog, vers, prot, port);
+	trace_pmap_register(prog, vers, prot, port);
 
 	msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET];
 	if (port != 0) {
@@ -489,11 +466,6 @@ static int rpcb_register_inet4(struct sunrpc_net *sn,
 
 	map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL);
 
-	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
-		"local rpcbind\n", (port ? "" : "un"),
-			map->r_prog, map->r_vers,
-			map->r_addr, map->r_netid);
-
 	msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
 	if (port != 0) {
 		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
@@ -520,11 +492,6 @@ static int rpcb_register_inet6(struct sunrpc_net *sn,
 
 	map->r_addr = rpc_sockaddr2uaddr(sap, GFP_KERNEL);
 
-	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
-		"local rpcbind\n", (port ? "" : "un"),
-			map->r_prog, map->r_vers,
-			map->r_addr, map->r_netid);
-
 	msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
 	if (port != 0) {
 		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
@@ -541,9 +508,7 @@ static int rpcb_unregister_all_protofamilies(struct sunrpc_net *sn,
 {
 	struct rpcbind_args *map = msg->rpc_argp;
 
-	dprintk("RPC:       unregistering [%u, %u, '%s'] with "
-		"local rpcbind\n",
-			map->r_prog, map->r_vers, map->r_netid);
+	trace_rpcb_unregister(map->r_prog, map->r_vers, map->r_netid);
 
 	map->r_addr = "";
 	msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
@@ -615,6 +580,8 @@ int rpcb_v4_register(struct net *net, const u32 program, const u32 version,
 	if (address == NULL)
 		return rpcb_unregister_all_protofamilies(sn, &msg);
 
+	trace_rpcb_register(map.r_prog, map.r_vers, map.r_addr, map.r_netid);
+
 	switch (address->sa_family) {
 	case AF_INET:
 		return rpcb_register_inet4(sn, address, &msg);
@@ -693,18 +660,12 @@ void rpcb_getport_async(struct rpc_task *task)
 	rcu_read_unlock();
 	xprt = xprt_get(task->tk_xprt);
 
-	dprintk("RPC: %5u %s(%s, %u, %u, %d)\n",
-		task->tk_pid, __func__,
-		xprt->servername, clnt->cl_prog, clnt->cl_vers, xprt->prot);
-
 	/* Put self on the wait queue to ensure we get notified if
 	 * some other task is already attempting to bind the port */
 	rpc_sleep_on_timeout(&xprt->binding, task,
 			NULL, jiffies + xprt->bind_timeout);
 
 	if (xprt_test_and_set_binding(xprt)) {
-		dprintk("RPC: %5u %s: waiting for another binder\n",
-			task->tk_pid, __func__);
 		xprt_put(xprt);
 		return;
 	}
@@ -712,8 +673,6 @@ void rpcb_getport_async(struct rpc_task *task)
 	/* Someone else may have bound if we slept */
 	if (xprt_bound(xprt)) {
 		status = 0;
-		dprintk("RPC: %5u %s: already bound\n",
-			task->tk_pid, __func__);
 		goto bailout_nofree;
 	}
 
@@ -732,20 +691,15 @@ void rpcb_getport_async(struct rpc_task *task)
 		break;
 	default:
 		status = -EAFNOSUPPORT;
-		dprintk("RPC: %5u %s: bad address family\n",
-				task->tk_pid, __func__);
 		goto bailout_nofree;
 	}
 	if (proc == NULL) {
 		xprt->bind_index = 0;
 		status = -EPFNOSUPPORT;
-		dprintk("RPC: %5u %s: no more getport versions available\n",
-			task->tk_pid, __func__);
 		goto bailout_nofree;
 	}
 
-	dprintk("RPC: %5u %s: trying rpcbind version %u\n",
-		task->tk_pid, __func__, bind_version);
+	trace_rpcb_getport(clnt, task, bind_version);
 
 	rpcb_clnt = rpcb_create(xprt->xprt_net,
 				clnt->cl_nodename,
@@ -754,16 +708,12 @@ void rpcb_getport_async(struct rpc_task *task)
 				clnt->cl_cred);
 	if (IS_ERR(rpcb_clnt)) {
 		status = PTR_ERR(rpcb_clnt);
-		dprintk("RPC: %5u %s: rpcb_create failed, error %ld\n",
-			task->tk_pid, __func__, PTR_ERR(rpcb_clnt));
 		goto bailout_nofree;
 	}
 
 	map = kzalloc(sizeof(struct rpcbind_args), GFP_NOFS);
 	if (!map) {
 		status = -ENOMEM;
-		dprintk("RPC: %5u %s: no memory available\n",
-			task->tk_pid, __func__);
 		goto bailout_release_client;
 	}
 	map->r_prog = clnt->cl_prog;
@@ -780,8 +730,6 @@ void rpcb_getport_async(struct rpc_task *task)
 		map->r_addr = rpc_sockaddr2uaddr(sap, GFP_NOFS);
 		if (!map->r_addr) {
 			status = -ENOMEM;
-			dprintk("RPC: %5u %s: no memory available\n",
-				task->tk_pid, __func__);
 			goto bailout_free_args;
 		}
 		map->r_owner = "";
@@ -818,34 +766,33 @@ static void rpcb_getport_done(struct rpc_task *child, void *data)
 {
 	struct rpcbind_args *map = data;
 	struct rpc_xprt *xprt = map->r_xprt;
-	int status = child->tk_status;
+
+	map->r_status = child->tk_status;
 
 	/* Garbage reply: retry with a lesser rpcbind version */
-	if (status == -EIO)
-		status = -EPROTONOSUPPORT;
+	if (map->r_status == -EIO)
+		map->r_status = -EPROTONOSUPPORT;
 
 	/* rpcbind server doesn't support this rpcbind protocol version */
-	if (status == -EPROTONOSUPPORT)
+	if (map->r_status == -EPROTONOSUPPORT)
 		xprt->bind_index++;
 
-	if (status < 0) {
+	if (map->r_status < 0) {
 		/* rpcbind server not available on remote host? */
-		xprt->ops->set_port(xprt, 0);
+		map->r_port = 0;
+
 	} else if (map->r_port == 0) {
 		/* Requested RPC service wasn't registered on remote host */
-		xprt->ops->set_port(xprt, 0);
-		status = -EACCES;
+		map->r_status = -EACCES;
 	} else {
 		/* Succeeded */
-		xprt->ops->set_port(xprt, map->r_port);
-		xprt_set_bound(xprt);
-		status = 0;
+		map->r_status = 0;
 	}
 
-	dprintk("RPC: %5u rpcb_getport_done(status %d, port %u)\n",
-			child->tk_pid, status, map->r_port);
-
-	map->r_status = status;
+	trace_rpcb_setport(child, map->r_status, map->r_port);
+	xprt->ops->set_port(xprt, map->r_port);
+	if (map->r_port)
+		xprt_set_bound(xprt);
 }
 
 /*
@@ -858,11 +805,6 @@ static void rpcb_enc_mapping(struct rpc_rqst *req, struct xdr_stream *xdr,
 	const struct rpcbind_args *rpcb = data;
 	__be32 *p;
 
-	dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n",
-			req->rq_task->tk_pid,
-			req->rq_task->tk_msg.rpc_proc->p_name,
-			rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port);
-
 	p = xdr_reserve_space(xdr, RPCB_mappingargs_sz << 2);
 	*p++ = cpu_to_be32(rpcb->r_prog);
 	*p++ = cpu_to_be32(rpcb->r_vers);
@@ -884,8 +826,6 @@ static int rpcb_dec_getport(struct rpc_rqst *req, struct xdr_stream *xdr,
 		return -EIO;
 
 	port = be32_to_cpup(p);
-	dprintk("RPC: %5u PMAP_%s result: %lu\n", req->rq_task->tk_pid,
-			req->rq_task->tk_msg.rpc_proc->p_name, port);
 	if (unlikely(port > USHRT_MAX))
 		return -EIO;
 
@@ -906,11 +846,6 @@ static int rpcb_dec_set(struct rpc_rqst *req, struct xdr_stream *xdr,
 	*boolp = 0;
 	if (*p != xdr_zero)
 		*boolp = 1;
-
-	dprintk("RPC: %5u RPCB_%s call %s\n",
-			req->rq_task->tk_pid,
-			req->rq_task->tk_msg.rpc_proc->p_name,
-			(*boolp ? "succeeded" : "failed"));
 	return 0;
 }
 
@@ -935,12 +870,6 @@ static void rpcb_enc_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr,
 	const struct rpcbind_args *rpcb = data;
 	__be32 *p;
 
-	dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n",
-			req->rq_task->tk_pid,
-			req->rq_task->tk_msg.rpc_proc->p_name,
-			rpcb->r_prog, rpcb->r_vers,
-			rpcb->r_netid, rpcb->r_addr);
-
 	p = xdr_reserve_space(xdr, (RPCB_program_sz + RPCB_version_sz) << 2);
 	*p++ = cpu_to_be32(rpcb->r_prog);
 	*p = cpu_to_be32(rpcb->r_vers);
@@ -970,11 +899,8 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr,
 	 * If the returned universal address is a null string,
 	 * the requested RPC service was not registered.
 	 */
-	if (len == 0) {
-		dprintk("RPC: %5u RPCB reply: program not registered\n",
-				req->rq_task->tk_pid);
+	if (len == 0)
 		return 0;
-	}
 
 	if (unlikely(len > RPCBIND_MAXUADDRLEN))
 		goto out_fail;
@@ -982,8 +908,6 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr,
 	p = xdr_inline_decode(xdr, len);
 	if (unlikely(p == NULL))
 		goto out_fail;
-	dprintk("RPC: %5u RPCB_%s reply: %*pE\n", req->rq_task->tk_pid,
-			req->rq_task->tk_msg.rpc_proc->p_name, len, (char *)p);
 
 	if (rpc_uaddr2sockaddr(req->rq_xprt->xprt_net, (char *)p, len,
 				sap, sizeof(address)) == 0)
@@ -993,9 +917,6 @@ static int rpcb_dec_getaddr(struct rpc_rqst *req, struct xdr_stream *xdr,
 	return 0;
 
 out_fail:
-	dprintk("RPC: %5u malformed RPCB_%s reply\n",
-			req->rq_task->tk_pid,
-			req->rq_task->tk_msg.rpc_proc->p_name);
 	return -EIO;
 }
 
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 7eba20a88438..cf702a5f7fe5 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -27,10 +27,6 @@
 
 #include "sunrpc.h"
 
-#if IS_ENABLED(CONFIG_SUNRPC_DEBUG)
-#define RPCDBG_FACILITY		RPCDBG_SCHED
-#endif
-
 #define CREATE_TRACE_POINTS
 #include <trace/events/sunrpc.h>
 
@@ -85,7 +81,6 @@ __rpc_disable_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 {
 	if (list_empty(&task->u.tk_wait.timer_list))
 		return;
-	dprintk("RPC: %5u disabling timer\n", task->tk_pid);
 	task->tk_timeout = 0;
 	list_del(&task->u.tk_wait.timer_list);
 	if (list_empty(&queue->timer_list.list))
@@ -111,9 +106,6 @@ static void
 __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task,
 		unsigned long timeout)
 {
-	dprintk("RPC: %5u setting alarm for %u ms\n",
-		task->tk_pid, jiffies_to_msecs(timeout - jiffies));
-
 	task->tk_timeout = timeout;
 	if (list_empty(&queue->timer_list.list) || time_before(timeout, queue->timer_list.expires))
 		rpc_set_queue_timer(queue, timeout);
@@ -216,9 +208,6 @@ static void __rpc_add_wait_queue(struct rpc_wait_queue *queue,
 	/* barrier matches the read in rpc_wake_up_task_queue_locked() */
 	smp_wmb();
 	rpc_set_queued(task);
-
-	dprintk("RPC: %5u added to queue %p \"%s\"\n",
-			task->tk_pid, queue, rpc_qname(queue));
 }
 
 /*
@@ -241,8 +230,6 @@ static void __rpc_remove_wait_queue(struct rpc_wait_queue *queue, struct rpc_tas
 	else
 		list_del(&task->u.tk_wait.list);
 	queue->qlen--;
-	dprintk("RPC: %5u removed from queue %p \"%s\"\n",
-			task->tk_pid, queue, rpc_qname(queue));
 }
 
 static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const char *qname, unsigned char nr_queues)
@@ -382,13 +369,9 @@ static void __rpc_do_sleep_on_priority(struct rpc_wait_queue *q,
 		struct rpc_task *task,
 		unsigned char queue_priority)
 {
-	dprintk("RPC: %5u sleep_on(queue \"%s\" time %lu)\n",
-			task->tk_pid, rpc_qname(q), jiffies);
-
 	trace_rpc_task_sleep(task, q);
 
 	__rpc_add_wait_queue(q, task, queue_priority);
-
 }
 
 static void __rpc_sleep_on_priority(struct rpc_wait_queue *q,
@@ -510,9 +493,6 @@ static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq,
 		struct rpc_wait_queue *queue,
 		struct rpc_task *task)
 {
-	dprintk("RPC: %5u __rpc_wake_up_task (now %lu)\n",
-			task->tk_pid, jiffies);
-
 	/* Has the task been executed yet? If not, we cannot wake it up! */
 	if (!RPC_IS_ACTIVATED(task)) {
 		printk(KERN_ERR "RPC: Inactive task (%p) being woken up!\n", task);
@@ -524,8 +504,6 @@ static void __rpc_do_wake_up_task_on_wq(struct workqueue_struct *wq,
 	__rpc_remove_wait_queue(queue, task);
 
 	rpc_make_runnable(wq, task);
-
-	dprintk("RPC:       __rpc_wake_up_task done\n");
 }
 
 /*
@@ -663,8 +641,6 @@ struct rpc_task *rpc_wake_up_first_on_wq(struct workqueue_struct *wq,
 {
 	struct rpc_task	*task = NULL;
 
-	dprintk("RPC:       wake_up_first(%p \"%s\")\n",
-			queue, rpc_qname(queue));
 	spin_lock(&queue->lock);
 	task = __rpc_find_next_queued(queue);
 	if (task != NULL)
@@ -700,6 +676,23 @@ struct rpc_task *rpc_wake_up_next(struct rpc_wait_queue *queue)
 EXPORT_SYMBOL_GPL(rpc_wake_up_next);
 
 /**
+ * rpc_wake_up_locked - wake up all rpc_tasks
+ * @queue: rpc_wait_queue on which the tasks are sleeping
+ *
+ */
+static void rpc_wake_up_locked(struct rpc_wait_queue *queue)
+{
+	struct rpc_task *task;
+
+	for (;;) {
+		task = __rpc_find_next_queued(queue);
+		if (task == NULL)
+			break;
+		rpc_wake_up_task_queue_locked(queue, task);
+	}
+}
+
+/**
  * rpc_wake_up - wake up all rpc_tasks
  * @queue: rpc_wait_queue on which the tasks are sleeping
  *
@@ -707,25 +700,28 @@ EXPORT_SYMBOL_GPL(rpc_wake_up_next);
  */
 void rpc_wake_up(struct rpc_wait_queue *queue)
 {
-	struct list_head *head;
-
 	spin_lock(&queue->lock);
-	head = &queue->tasks[queue->maxpriority];
+	rpc_wake_up_locked(queue);
+	spin_unlock(&queue->lock);
+}
+EXPORT_SYMBOL_GPL(rpc_wake_up);
+
+/**
+ * rpc_wake_up_status_locked - wake up all rpc_tasks and set their status value.
+ * @queue: rpc_wait_queue on which the tasks are sleeping
+ * @status: status value to set
+ */
+static void rpc_wake_up_status_locked(struct rpc_wait_queue *queue, int status)
+{
+	struct rpc_task *task;
+
 	for (;;) {
-		while (!list_empty(head)) {
-			struct rpc_task *task;
-			task = list_first_entry(head,
-					struct rpc_task,
-					u.tk_wait.list);
-			rpc_wake_up_task_queue_locked(queue, task);
-		}
-		if (head == &queue->tasks[0])
+		task = __rpc_find_next_queued(queue);
+		if (task == NULL)
 			break;
-		head--;
+		rpc_wake_up_task_queue_set_status_locked(queue, task, status);
 	}
-	spin_unlock(&queue->lock);
 }
-EXPORT_SYMBOL_GPL(rpc_wake_up);
 
 /**
  * rpc_wake_up_status - wake up all rpc_tasks and set their status value.
@@ -736,23 +732,8 @@ EXPORT_SYMBOL_GPL(rpc_wake_up);
  */
 void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
 {
-	struct list_head *head;
-
 	spin_lock(&queue->lock);
-	head = &queue->tasks[queue->maxpriority];
-	for (;;) {
-		while (!list_empty(head)) {
-			struct rpc_task *task;
-			task = list_first_entry(head,
-					struct rpc_task,
-					u.tk_wait.list);
-			task->tk_status = status;
-			rpc_wake_up_task_queue_locked(queue, task);
-		}
-		if (head == &queue->tasks[0])
-			break;
-		head--;
-	}
+	rpc_wake_up_status_locked(queue, status);
 	spin_unlock(&queue->lock);
 }
 EXPORT_SYMBOL_GPL(rpc_wake_up_status);
@@ -770,7 +751,7 @@ static void __rpc_queue_timer_fn(struct work_struct *work)
 	list_for_each_entry_safe(task, n, &queue->timer_list.list, u.tk_wait.timer_list) {
 		timeo = task->tk_timeout;
 		if (time_after_eq(now, timeo)) {
-			dprintk("RPC: %5u timeout\n", task->tk_pid);
+			trace_rpc_task_timeout(task, task->tk_action);
 			task->tk_status = -ETIMEDOUT;
 			rpc_wake_up_task_queue_locked(queue, task);
 			continue;
@@ -885,9 +866,6 @@ static void __rpc_execute(struct rpc_task *task)
 	int task_is_async = RPC_IS_ASYNC(task);
 	int status = 0;
 
-	dprintk("RPC: %5u __rpc_execute flags=0x%x\n",
-			task->tk_pid, task->tk_flags);
-
 	WARN_ON_ONCE(RPC_IS_QUEUED(task));
 	if (RPC_IS_QUEUED(task))
 		return;
@@ -947,7 +925,7 @@ static void __rpc_execute(struct rpc_task *task)
 			return;
 
 		/* sync task: sleep here */
-		dprintk("RPC: %5u sync task going to sleep\n", task->tk_pid);
+		trace_rpc_task_sync_sleep(task, task->tk_action);
 		status = out_of_line_wait_on_bit(&task->tk_runstate,
 				RPC_TASK_QUEUED, rpc_wait_bit_killable,
 				TASK_KILLABLE);
@@ -963,11 +941,9 @@ static void __rpc_execute(struct rpc_task *task)
 			task->tk_rpc_status = -ERESTARTSYS;
 			rpc_exit(task, -ERESTARTSYS);
 		}
-		dprintk("RPC: %5u sync task resuming\n", task->tk_pid);
+		trace_rpc_task_sync_wake(task, task->tk_action);
 	}
 
-	dprintk("RPC: %5u return %d, status %d\n", task->tk_pid, status,
-			task->tk_status);
 	/* Release all resources associated with the task */
 	rpc_release_task(task);
 }
@@ -1036,8 +1012,6 @@ int rpc_malloc(struct rpc_task *task)
 		return -ENOMEM;
 
 	buf->len = size;
-	dprintk("RPC: %5u allocated buffer of size %zu at %p\n",
-			task->tk_pid, size, buf);
 	rqst->rq_buffer = buf->data;
 	rqst->rq_rbuffer = (char *)rqst->rq_buffer + rqst->rq_callsize;
 	return 0;
@@ -1058,9 +1032,6 @@ void rpc_free(struct rpc_task *task)
 	buf = container_of(buffer, struct rpc_buffer, data);
 	size = buf->len;
 
-	dprintk("RPC:       freeing buffer of size %zu at %p\n",
-			size, buf);
-
 	if (size <= RPC_BUFFER_MAXSIZE)
 		mempool_free(buf, rpc_buffer_mempool);
 	else
@@ -1095,9 +1066,6 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta
 		task->tk_action = rpc_prepare_task;
 
 	rpc_init_task_statistics(task);
-
-	dprintk("RPC:       new task initialized, procpid %u\n",
-				task_pid_nr(current));
 }
 
 static struct rpc_task *
@@ -1121,7 +1089,6 @@ struct rpc_task *rpc_new_task(const struct rpc_task_setup *setup_data)
 
 	rpc_init_task(task, setup_data);
 	task->tk_flags |= flags;
-	dprintk("RPC:       allocated task %p\n", task);
 	return task;
 }
 
@@ -1151,10 +1118,8 @@ static void rpc_free_task(struct rpc_task *task)
 	put_rpccred(task->tk_op_cred);
 	rpc_release_calldata(task->tk_ops, task->tk_calldata);
 
-	if (tk_flags & RPC_TASK_DYNAMIC) {
-		dprintk("RPC: %5u freeing task\n", task->tk_pid);
+	if (tk_flags & RPC_TASK_DYNAMIC)
 		mempool_free(task, rpc_task_mempool);
-	}
 }
 
 static void rpc_async_release(struct work_struct *work)
@@ -1208,8 +1173,6 @@ EXPORT_SYMBOL_GPL(rpc_put_task_async);
 
 static void rpc_release_task(struct rpc_task *task)
 {
-	dprintk("RPC: %5u release task\n", task->tk_pid);
-
 	WARN_ON_ONCE(RPC_IS_QUEUED(task));
 
 	rpc_release_resources_task(task);
@@ -1250,7 +1213,6 @@ static int rpciod_start(void)
 	/*
 	 * Create the rpciod thread and wait for it to start.
 	 */
-	dprintk("RPC:       creating workqueue rpciod\n");
 	wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM | WQ_UNBOUND, 0);
 	if (!wq)
 		goto out_failed;
@@ -1275,7 +1237,6 @@ static void rpciod_stop(void)
 
 	if (rpciod_workqueue == NULL)
 		return;
-	dprintk("RPC:       destroying workqueue rpciod\n");
 
 	wq = rpciod_workqueue;
 	rpciod_workqueue = NULL;
diff --git a/net/sunrpc/socklib.c b/net/sunrpc/socklib.c
index 3fc8af8bb961..d52313af82bc 100644
--- a/net/sunrpc/socklib.c
+++ b/net/sunrpc/socklib.c
@@ -70,7 +70,7 @@ static size_t xdr_skb_read_and_csum_bits(struct xdr_skb_reader *desc, void *to,
 	if (len > desc->count)
 		len = desc->count;
 	pos = desc->offset;
-	csum2 = skb_copy_and_csum_bits(desc->skb, pos, to, len, 0);
+	csum2 = skb_copy_and_csum_bits(desc->skb, pos, to, len);
 	desc->csum = csum_block_add(desc->csum, csum2, pos);
 	desc->count -= len;
 	desc->offset += len;
diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h
index f6fe2e6cd65a..2f59464e6524 100644
--- a/net/sunrpc/sunrpc.h
+++ b/net/sunrpc/sunrpc.h
@@ -4,7 +4,7 @@
 
 NetApp provides this source code under the GPL v2 License.
 The GPL v2 license is available at
-http://opensource.org/licenses/gpl-license.php.
+https://opensource.org/licenses/gpl-license.php.
 
 THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index c211b607239e..4187745887f0 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -614,6 +614,10 @@ svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node)
 	rqstp->rq_server = serv;
 	rqstp->rq_pool = pool;
 
+	rqstp->rq_scratch_page = alloc_pages_node(node, GFP_KERNEL, 0);
+	if (!rqstp->rq_scratch_page)
+		goto out_enomem;
+
 	rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
 	if (!rqstp->rq_argp)
 		goto out_enomem;
@@ -842,6 +846,7 @@ void
 svc_rqst_free(struct svc_rqst *rqstp)
 {
 	svc_release_buffer(rqstp);
+	put_page(rqstp->rq_scratch_page);
 	kfree(rqstp->rq_resp);
 	kfree(rqstp->rq_argp);
 	kfree(rqstp->rq_auth_data);
@@ -1622,7 +1627,7 @@ u32 svc_max_payload(const struct svc_rqst *rqstp)
 EXPORT_SYMBOL_GPL(svc_max_payload);
 
 /**
- * svc_encode_read_payload - mark a range of bytes as a READ payload
+ * svc_encode_result_payload - mark a range of bytes as a result payload
  * @rqstp: svc_rqst to operate on
  * @offset: payload's byte offset in rqstp->rq_res
  * @length: size of payload, in bytes
@@ -1630,12 +1635,13 @@ EXPORT_SYMBOL_GPL(svc_max_payload);
  * Returns zero on success, or a negative errno if a permanent
  * error occurred.
  */
-int svc_encode_read_payload(struct svc_rqst *rqstp, unsigned int offset,
-			    unsigned int length)
+int svc_encode_result_payload(struct svc_rqst *rqstp, unsigned int offset,
+			      unsigned int length)
 {
-	return rqstp->rq_xprt->xpt_ops->xpo_read_payload(rqstp, offset, length);
+	return rqstp->rq_xprt->xpt_ops->xpo_result_payload(rqstp, offset,
+							   length);
 }
-EXPORT_SYMBOL_GPL(svc_encode_read_payload);
+EXPORT_SYMBOL_GPL(svc_encode_result_payload);
 
 /**
  * svc_fill_write_vector - Construct data argument for VFS write call
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 43cf8dbde898..dcc50ae54550 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -813,8 +813,6 @@ static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
 			len = svc_deferred_recv(rqstp);
 		else
 			len = xprt->xpt_ops->xpo_recvfrom(rqstp);
-		if (len > 0)
-			trace_svc_xdr_recvfrom(rqstp, &rqstp->rq_arg);
 		rqstp->rq_stime = ktime_get();
 		rqstp->rq_reserved = serv->sv_max_mesg;
 		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
@@ -859,6 +857,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	err = -EAGAIN;
 	if (len <= 0)
 		goto out_release;
+	trace_svc_xdr_recvfrom(&rqstp->rq_arg);
 
 	clear_bit(XPT_OLD, &xprt->xpt_flags);
 
@@ -868,7 +867,6 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 
 	if (serv->sv_stats)
 		serv->sv_stats->netcnt++;
-	trace_svc_recv(rqstp, len);
 	return len;
 out_release:
 	rqstp->rq_res.len = 0;
@@ -906,7 +904,7 @@ int svc_send(struct svc_rqst *rqstp)
 	xb->len = xb->head[0].iov_len +
 		xb->page_len +
 		xb->tail[0].iov_len;
-	trace_svc_xdr_sendto(rqstp, xb);
+	trace_svc_xdr_sendto(rqstp->rq_xid, xb);
 	trace_svc_stats_latency(rqstp);
 
 	len = xprt->xpt_ops->xpo_sendto(rqstp);
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index c2752e2b9ce3..5a809c64dc7b 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -181,8 +181,8 @@ static void svc_set_cmsg_data(struct svc_rqst *rqstp, struct cmsghdr *cmh)
 	}
 }
 
-static int svc_sock_read_payload(struct svc_rqst *rqstp, unsigned int offset,
-				 unsigned int length)
+static int svc_sock_result_payload(struct svc_rqst *rqstp, unsigned int offset,
+				   unsigned int length)
 {
 	return 0;
 }
@@ -635,7 +635,7 @@ static const struct svc_xprt_ops svc_udp_ops = {
 	.xpo_create = svc_udp_create,
 	.xpo_recvfrom = svc_udp_recvfrom,
 	.xpo_sendto = svc_udp_sendto,
-	.xpo_read_payload = svc_sock_read_payload,
+	.xpo_result_payload = svc_sock_result_payload,
 	.xpo_release_rqst = svc_udp_release_rqst,
 	.xpo_detach = svc_sock_detach,
 	.xpo_free = svc_sock_free,
@@ -1062,6 +1062,91 @@ err_noclose:
 	return 0;	/* record not complete */
 }
 
+static int svc_tcp_send_kvec(struct socket *sock, const struct kvec *vec,
+			      int flags)
+{
+	return kernel_sendpage(sock, virt_to_page(vec->iov_base),
+			       offset_in_page(vec->iov_base),
+			       vec->iov_len, flags);
+}
+
+/*
+ * kernel_sendpage() is used exclusively to reduce the number of
+ * copy operations in this path. Therefore the caller must ensure
+ * that the pages backing @xdr are unchanging.
+ *
+ * In addition, the logic assumes that * .bv_len is never larger
+ * than PAGE_SIZE.
+ */
+static int svc_tcp_sendmsg(struct socket *sock, struct msghdr *msg,
+			   struct xdr_buf *xdr, rpc_fraghdr marker,
+			   unsigned int *sentp)
+{
+	const struct kvec *head = xdr->head;
+	const struct kvec *tail = xdr->tail;
+	struct kvec rm = {
+		.iov_base	= &marker,
+		.iov_len	= sizeof(marker),
+	};
+	int flags, ret;
+
+	*sentp = 0;
+	xdr_alloc_bvec(xdr, GFP_KERNEL);
+
+	msg->msg_flags = MSG_MORE;
+	ret = kernel_sendmsg(sock, msg, &rm, 1, rm.iov_len);
+	if (ret < 0)
+		return ret;
+	*sentp += ret;
+	if (ret != rm.iov_len)
+		return -EAGAIN;
+
+	flags = head->iov_len < xdr->len ? MSG_MORE | MSG_SENDPAGE_NOTLAST : 0;
+	ret = svc_tcp_send_kvec(sock, head, flags);
+	if (ret < 0)
+		return ret;
+	*sentp += ret;
+	if (ret != head->iov_len)
+		goto out;
+
+	if (xdr->page_len) {
+		unsigned int offset, len, remaining;
+		struct bio_vec *bvec;
+
+		bvec = xdr->bvec + (xdr->page_base >> PAGE_SHIFT);
+		offset = offset_in_page(xdr->page_base);
+		remaining = xdr->page_len;
+		flags = MSG_MORE | MSG_SENDPAGE_NOTLAST;
+		while (remaining > 0) {
+			if (remaining <= PAGE_SIZE && tail->iov_len == 0)
+				flags = 0;
+
+			len = min(remaining, bvec->bv_len - offset);
+			ret = kernel_sendpage(sock, bvec->bv_page,
+					      bvec->bv_offset + offset,
+					      len, flags);
+			if (ret < 0)
+				return ret;
+			*sentp += ret;
+			if (ret != len)
+				goto out;
+			remaining -= len;
+			offset = 0;
+			bvec++;
+		}
+	}
+
+	if (tail->iov_len) {
+		ret = svc_tcp_send_kvec(sock, tail, 0);
+		if (ret < 0)
+			return ret;
+		*sentp += ret;
+	}
+
+out:
+	return 0;
+}
+
 /**
  * svc_tcp_sendto - Send out a reply on a TCP socket
  * @rqstp: completed svc_rqst
@@ -1089,7 +1174,7 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	mutex_lock(&xprt->xpt_mutex);
 	if (svc_xprt_is_dead(xprt))
 		goto out_notconn;
-	err = xprt_sock_sendmsg(svsk->sk_sock, &msg, xdr, 0, marker, &sent);
+	err = svc_tcp_sendmsg(svsk->sk_sock, &msg, xdr, marker, &sent);
 	xdr_free_bvec(xdr);
 	trace_svcsock_tcp_send(xprt, err < 0 ? err : sent);
 	if (err < 0 || sent != (xdr->len + sizeof(marker)))
@@ -1123,7 +1208,7 @@ static const struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_create = svc_tcp_create,
 	.xpo_recvfrom = svc_tcp_recvfrom,
 	.xpo_sendto = svc_tcp_sendto,
-	.xpo_read_payload = svc_sock_read_payload,
+	.xpo_result_payload = svc_sock_result_payload,
 	.xpo_release_rqst = svc_tcp_release_rqst,
 	.xpo_detach = svc_tcp_sock_detach,
 	.xpo_free = svc_sock_free,
diff --git a/net/sunrpc/sysctl.c b/net/sunrpc/sysctl.c
index 999eee1ed61c..3aad6ef18504 100644
--- a/net/sunrpc/sysctl.c
+++ b/net/sunrpc/sysctl.c
@@ -63,14 +63,21 @@ static int proc_do_xprt(struct ctl_table *table, int write,
 			void *buffer, size_t *lenp, loff_t *ppos)
 {
 	char tmpbuf[256];
-	size_t len;
+	ssize_t len;
 
-	if ((*ppos && !write) || !*lenp) {
+	if (write || *ppos) {
 		*lenp = 0;
 		return 0;
 	}
 	len = svc_print_xprts(tmpbuf, sizeof(tmpbuf));
-	return memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len);
+	len = memory_read_from_buffer(buffer, *lenp, ppos, tmpbuf, len);
+
+	if (len < 0) {
+		*lenp = 0;
+		return -EINVAL;
+	}
+	*lenp = len;
+	return 0;
 }
 
 static int
@@ -108,8 +115,10 @@ proc_dodebug(struct ctl_table *table, int write, void *buffer, size_t *lenp,
 			left -= (s - tmpbuf);
 			if (left && !isspace(*s))
 				return -EINVAL;
-			while (left && isspace(*s))
-				left--, s++;
+			while (left && isspace(*s)) {
+				left--;
+				s++;
+			}
 		} else
 			left = 0;
 		*(unsigned int *) table->data = value;
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index be11d672b5b9..3964ff74ee51 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -19,6 +19,9 @@
 #include <linux/bvec.h>
 #include <trace/events/sunrpc.h>
 
+static void _copy_to_pages(struct page **, size_t, const char *, size_t);
+
+
 /*
  * XDR functions for basic NFS types
  */
@@ -120,8 +123,7 @@ EXPORT_SYMBOL_GPL(xdr_decode_string_inplace);
  * @len: length of string, in bytes
  *
  */
-void
-xdr_terminate_string(struct xdr_buf *buf, const u32 len)
+void xdr_terminate_string(const struct xdr_buf *buf, const u32 len)
 {
 	char *kaddr;
 
@@ -131,8 +133,7 @@ xdr_terminate_string(struct xdr_buf *buf, const u32 len)
 }
 EXPORT_SYMBOL_GPL(xdr_terminate_string);
 
-size_t
-xdr_buf_pagecount(struct xdr_buf *buf)
+size_t xdr_buf_pagecount(const struct xdr_buf *buf)
 {
 	if (!buf->page_len)
 		return 0;
@@ -190,9 +191,6 @@ xdr_inline_pages(struct xdr_buf *xdr, unsigned int offset,
 
 	tail->iov_base = buf + offset;
 	tail->iov_len = buflen - offset;
-	if ((xdr->page_len & 3) == 0)
-		tail->iov_len -= sizeof(__be32);
-
 	xdr->buflen += len;
 }
 EXPORT_SYMBOL_GPL(xdr_inline_pages);
@@ -202,6 +200,71 @@ EXPORT_SYMBOL_GPL(xdr_inline_pages);
  */
 
 /**
+ * _shift_data_left_pages
+ * @pages: vector of pages containing both the source and dest memory area.
+ * @pgto_base: page vector address of destination
+ * @pgfrom_base: page vector address of source
+ * @len: number of bytes to copy
+ *
+ * Note: the addresses pgto_base and pgfrom_base are both calculated in
+ *       the same way:
+ *            if a memory area starts at byte 'base' in page 'pages[i]',
+ *            then its address is given as (i << PAGE_CACHE_SHIFT) + base
+ * Alse note: pgto_base must be < pgfrom_base, but the memory areas
+ * 	they point to may overlap.
+ */
+static void
+_shift_data_left_pages(struct page **pages, size_t pgto_base,
+			size_t pgfrom_base, size_t len)
+{
+	struct page **pgfrom, **pgto;
+	char *vfrom, *vto;
+	size_t copy;
+
+	BUG_ON(pgfrom_base <= pgto_base);
+
+	if (!len)
+		return;
+
+	pgto = pages + (pgto_base >> PAGE_SHIFT);
+	pgfrom = pages + (pgfrom_base >> PAGE_SHIFT);
+
+	pgto_base &= ~PAGE_MASK;
+	pgfrom_base &= ~PAGE_MASK;
+
+	do {
+		if (pgto_base >= PAGE_SIZE) {
+			pgto_base = 0;
+			pgto++;
+		}
+		if (pgfrom_base >= PAGE_SIZE){
+			pgfrom_base = 0;
+			pgfrom++;
+		}
+
+		copy = len;
+		if (copy > (PAGE_SIZE - pgto_base))
+			copy = PAGE_SIZE - pgto_base;
+		if (copy > (PAGE_SIZE - pgfrom_base))
+			copy = PAGE_SIZE - pgfrom_base;
+
+		vto = kmap_atomic(*pgto);
+		if (*pgto != *pgfrom) {
+			vfrom = kmap_atomic(*pgfrom);
+			memcpy(vto + pgto_base, vfrom + pgfrom_base, copy);
+			kunmap_atomic(vfrom);
+		} else
+			memmove(vto + pgto_base, vto + pgfrom_base, copy);
+		flush_dcache_page(*pgto);
+		kunmap_atomic(vto);
+
+		pgto_base += copy;
+		pgfrom_base += copy;
+
+	} while ((len -= copy) != 0);
+}
+
+/**
  * _shift_data_right_pages
  * @pages: vector of pages containing both the source and dest memory area.
  * @pgto_base: page vector address of destination
@@ -225,6 +288,9 @@ _shift_data_right_pages(struct page **pages, size_t pgto_base,
 
 	BUG_ON(pgto_base <= pgfrom_base);
 
+	if (!len)
+		return;
+
 	pgto_base += len;
 	pgfrom_base += len;
 
@@ -283,6 +349,9 @@ _copy_to_pages(struct page **pages, size_t pgbase, const char *p, size_t len)
 	char *vto;
 	size_t copy;
 
+	if (!len)
+		return;
+
 	pgto = pages + (pgbase >> PAGE_SHIFT);
 	pgbase &= ~PAGE_MASK;
 
@@ -327,6 +396,9 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
 	char *vfrom;
 	size_t copy;
 
+	if (!len)
+		return;
+
 	pgfrom = pages + (pgbase >> PAGE_SHIFT);
 	pgbase &= ~PAGE_MASK;
 
@@ -350,148 +422,423 @@ _copy_from_pages(char *p, struct page **pages, size_t pgbase, size_t len)
 }
 EXPORT_SYMBOL_GPL(_copy_from_pages);
 
+static void xdr_buf_iov_zero(const struct kvec *iov, unsigned int base,
+			     unsigned int len)
+{
+	if (base >= iov->iov_len)
+		return;
+	if (len > iov->iov_len - base)
+		len = iov->iov_len - base;
+	memset(iov->iov_base + base, 0, len);
+}
+
 /**
- * xdr_shrink_bufhead
+ * xdr_buf_pages_zero
  * @buf: xdr_buf
- * @len: bytes to remove from buf->head[0]
- *
- * Shrinks XDR buffer's header kvec buf->head[0] by
- * 'len' bytes. The extra data is not lost, but is instead
- * moved into the inlined pages and/or the tail.
+ * @pgbase: beginning offset
+ * @len: length
  */
-static unsigned int
-xdr_shrink_bufhead(struct xdr_buf *buf, size_t len)
+static void xdr_buf_pages_zero(const struct xdr_buf *buf, unsigned int pgbase,
+			       unsigned int len)
 {
-	struct kvec *head, *tail;
-	size_t copy, offs;
-	unsigned int pglen = buf->page_len;
-	unsigned int result;
+	struct page **pages = buf->pages;
+	struct page **page;
+	char *vpage;
+	unsigned int zero;
 
-	result = 0;
-	tail = buf->tail;
-	head = buf->head;
+	if (!len)
+		return;
+	if (pgbase >= buf->page_len) {
+		xdr_buf_iov_zero(buf->tail, pgbase - buf->page_len, len);
+		return;
+	}
+	if (pgbase + len > buf->page_len) {
+		xdr_buf_iov_zero(buf->tail, 0, pgbase + len - buf->page_len);
+		len = buf->page_len - pgbase;
+	}
 
-	WARN_ON_ONCE(len > head->iov_len);
-	if (len > head->iov_len)
-		len = head->iov_len;
-
-	/* Shift the tail first */
-	if (tail->iov_len != 0) {
-		if (tail->iov_len > len) {
-			copy = tail->iov_len - len;
-			memmove((char *)tail->iov_base + len,
-					tail->iov_base, copy);
-			result += copy;
-		}
-		/* Copy from the inlined pages into the tail */
-		copy = len;
-		if (copy > pglen)
-			copy = pglen;
-		offs = len - copy;
-		if (offs >= tail->iov_len)
-			copy = 0;
-		else if (copy > tail->iov_len - offs)
-			copy = tail->iov_len - offs;
-		if (copy != 0) {
-			_copy_from_pages((char *)tail->iov_base + offs,
-					buf->pages,
-					buf->page_base + pglen + offs - len,
-					copy);
-			result += copy;
+	pgbase += buf->page_base;
+
+	page = pages + (pgbase >> PAGE_SHIFT);
+	pgbase &= ~PAGE_MASK;
+
+	do {
+		zero = PAGE_SIZE - pgbase;
+		if (zero > len)
+			zero = len;
+
+		vpage = kmap_atomic(*page);
+		memset(vpage + pgbase, 0, zero);
+		kunmap_atomic(vpage);
+
+		flush_dcache_page(*page);
+		pgbase = 0;
+		page++;
+
+	} while ((len -= zero) != 0);
+}
+
+static unsigned int xdr_buf_pages_fill_sparse(const struct xdr_buf *buf,
+					      unsigned int buflen, gfp_t gfp)
+{
+	unsigned int i, npages, pagelen;
+
+	if (!(buf->flags & XDRBUF_SPARSE_PAGES))
+		return buflen;
+	if (buflen <= buf->head->iov_len)
+		return buflen;
+	pagelen = buflen - buf->head->iov_len;
+	if (pagelen > buf->page_len)
+		pagelen = buf->page_len;
+	npages = (pagelen + buf->page_base + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	for (i = 0; i < npages; i++) {
+		if (!buf->pages[i])
+			continue;
+		buf->pages[i] = alloc_page(gfp);
+		if (likely(buf->pages[i]))
+			continue;
+		buflen -= pagelen;
+		pagelen = i << PAGE_SHIFT;
+		if (pagelen > buf->page_base)
+			buflen += pagelen - buf->page_base;
+		break;
+	}
+	return buflen;
+}
+
+static void xdr_buf_try_expand(struct xdr_buf *buf, unsigned int len)
+{
+	struct kvec *head = buf->head;
+	struct kvec *tail = buf->tail;
+	unsigned int sum = head->iov_len + buf->page_len + tail->iov_len;
+	unsigned int free_space, newlen;
+
+	if (sum > buf->len) {
+		free_space = min_t(unsigned int, sum - buf->len, len);
+		newlen = xdr_buf_pages_fill_sparse(buf, buf->len + free_space,
+						   GFP_KERNEL);
+		free_space = newlen - buf->len;
+		buf->len = newlen;
+		len -= free_space;
+		if (!len)
+			return;
+	}
+
+	if (buf->buflen > sum) {
+		/* Expand the tail buffer */
+		free_space = min_t(unsigned int, buf->buflen - sum, len);
+		tail->iov_len += free_space;
+		buf->len += free_space;
+	}
+}
+
+static void xdr_buf_tail_copy_right(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+	unsigned int to = base + shift;
+
+	if (to >= tail->iov_len)
+		return;
+	if (len + to > tail->iov_len)
+		len = tail->iov_len - to;
+	memmove(tail->iov_base + to, tail->iov_base + base, len);
+}
+
+static void xdr_buf_pages_copy_right(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+	unsigned int to = base + shift;
+	unsigned int pglen = 0;
+	unsigned int talen = 0, tato = 0;
+
+	if (base >= buf->page_len)
+		return;
+	if (len > buf->page_len - base)
+		len = buf->page_len - base;
+	if (to >= buf->page_len) {
+		tato = to - buf->page_len;
+		if (tail->iov_len >= len + tato)
+			talen = len;
+		else if (tail->iov_len > tato)
+			talen = tail->iov_len - tato;
+	} else if (len + to >= buf->page_len) {
+		pglen = buf->page_len - to;
+		talen = len - pglen;
+		if (talen > tail->iov_len)
+			talen = tail->iov_len;
+	} else
+		pglen = len;
+
+	_copy_from_pages(tail->iov_base + tato, buf->pages,
+			 buf->page_base + base + pglen, talen);
+	_shift_data_right_pages(buf->pages, buf->page_base + to,
+				buf->page_base + base, pglen);
+}
+
+static void xdr_buf_head_copy_right(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	const struct kvec *head = buf->head;
+	const struct kvec *tail = buf->tail;
+	unsigned int to = base + shift;
+	unsigned int pglen = 0, pgto = 0;
+	unsigned int talen = 0, tato = 0;
+
+	if (base >= head->iov_len)
+		return;
+	if (len > head->iov_len - base)
+		len = head->iov_len - base;
+	if (to >= buf->page_len + head->iov_len) {
+		tato = to - buf->page_len - head->iov_len;
+		talen = len;
+	} else if (to >= head->iov_len) {
+		pgto = to - head->iov_len;
+		pglen = len;
+		if (pgto + pglen > buf->page_len) {
+			talen = pgto + pglen - buf->page_len;
+			pglen -= talen;
 		}
-		/* Do we also need to copy data from the head into the tail ? */
-		if (len > pglen) {
-			offs = copy = len - pglen;
-			if (copy > tail->iov_len)
-				copy = tail->iov_len;
-			memcpy(tail->iov_base,
-					(char *)head->iov_base +
-					head->iov_len - offs,
-					copy);
-			result += copy;
+	} else {
+		pglen = len - to;
+		if (pglen > buf->page_len) {
+			talen = pglen - buf->page_len;
+			pglen = buf->page_len;
 		}
 	}
-	/* Now handle pages */
-	if (pglen != 0) {
-		if (pglen > len)
-			_shift_data_right_pages(buf->pages,
-					buf->page_base + len,
-					buf->page_base,
-					pglen - len);
-		copy = len;
-		if (len > pglen)
-			copy = pglen;
-		_copy_to_pages(buf->pages, buf->page_base,
-				(char *)head->iov_base + head->iov_len - len,
-				copy);
-		result += copy;
+
+	len -= talen;
+	base += len;
+	if (talen + tato > tail->iov_len)
+		talen = tail->iov_len > tato ? tail->iov_len - tato : 0;
+	memcpy(tail->iov_base + tato, head->iov_base + base, talen);
+
+	len -= pglen;
+	base -= pglen;
+	_copy_to_pages(buf->pages, buf->page_base + pgto, head->iov_base + base,
+		       pglen);
+
+	base -= len;
+	memmove(head->iov_base + to, head->iov_base + base, len);
+}
+
+static void xdr_buf_tail_shift_right(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+
+	if (base >= tail->iov_len || !shift || !len)
+		return;
+	xdr_buf_tail_copy_right(buf, base, len, shift);
+}
+
+static void xdr_buf_pages_shift_right(const struct xdr_buf *buf,
+				      unsigned int base, unsigned int len,
+				      unsigned int shift)
+{
+	if (!shift || !len)
+		return;
+	if (base >= buf->page_len) {
+		xdr_buf_tail_shift_right(buf, base - buf->page_len, len, shift);
+		return;
+	}
+	if (base + len > buf->page_len)
+		xdr_buf_tail_shift_right(buf, 0, base + len - buf->page_len,
+					 shift);
+	xdr_buf_pages_copy_right(buf, base, len, shift);
+}
+
+static void xdr_buf_head_shift_right(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	const struct kvec *head = buf->head;
+
+	if (!shift)
+		return;
+	if (base >= head->iov_len) {
+		xdr_buf_pages_shift_right(buf, head->iov_len - base, len,
+					  shift);
+		return;
+	}
+	if (base + len > head->iov_len)
+		xdr_buf_pages_shift_right(buf, 0, base + len - head->iov_len,
+					  shift);
+	xdr_buf_head_copy_right(buf, base, len, shift);
+}
+
+static void xdr_buf_tail_copy_left(const struct xdr_buf *buf, unsigned int base,
+				   unsigned int len, unsigned int shift)
+{
+	const struct kvec *tail = buf->tail;
+
+	if (base >= tail->iov_len)
+		return;
+	if (len > tail->iov_len - base)
+		len = tail->iov_len - base;
+	/* Shift data into head */
+	if (shift > buf->page_len + base) {
+		const struct kvec *head = buf->head;
+		unsigned int hdto =
+			head->iov_len + buf->page_len + base - shift;
+		unsigned int hdlen = len;
+
+		if (WARN_ONCE(shift > head->iov_len + buf->page_len + base,
+			      "SUNRPC: Misaligned data.\n"))
+			return;
+		if (hdto + hdlen > head->iov_len)
+			hdlen = head->iov_len - hdto;
+		memcpy(head->iov_base + hdto, tail->iov_base + base, hdlen);
+		base += hdlen;
+		len -= hdlen;
+		if (!len)
+			return;
+	}
+	/* Shift data into pages */
+	if (shift > base) {
+		unsigned int pgto = buf->page_len + base - shift;
+		unsigned int pglen = len;
+
+		if (pgto + pglen > buf->page_len)
+			pglen = buf->page_len - pgto;
+		_copy_to_pages(buf->pages, buf->page_base + pgto,
+			       tail->iov_base + base, pglen);
+		base += pglen;
+		len -= pglen;
+		if (!len)
+			return;
+	}
+	memmove(tail->iov_base + base - shift, tail->iov_base + base, len);
+}
+
+static void xdr_buf_pages_copy_left(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	unsigned int pgto;
+
+	if (base >= buf->page_len)
+		return;
+	if (len > buf->page_len - base)
+		len = buf->page_len - base;
+	/* Shift data into head */
+	if (shift > base) {
+		const struct kvec *head = buf->head;
+		unsigned int hdto = head->iov_len + base - shift;
+		unsigned int hdlen = len;
+
+		if (WARN_ONCE(shift > head->iov_len + base,
+			      "SUNRPC: Misaligned data.\n"))
+			return;
+		if (hdto + hdlen > head->iov_len)
+			hdlen = head->iov_len - hdto;
+		_copy_from_pages(head->iov_base + hdto, buf->pages,
+				 buf->page_base + base, hdlen);
+		base += hdlen;
+		len -= hdlen;
+		if (!len)
+			return;
+	}
+	pgto = base - shift;
+	_shift_data_left_pages(buf->pages, buf->page_base + pgto,
+			       buf->page_base + base, len);
+}
+
+static void xdr_buf_tail_shift_left(const struct xdr_buf *buf,
+				    unsigned int base, unsigned int len,
+				    unsigned int shift)
+{
+	if (!shift || !len)
+		return;
+	xdr_buf_tail_copy_left(buf, base, len, shift);
+}
+
+static void xdr_buf_pages_shift_left(const struct xdr_buf *buf,
+				     unsigned int base, unsigned int len,
+				     unsigned int shift)
+{
+	if (!shift || !len)
+		return;
+	if (base >= buf->page_len) {
+		xdr_buf_tail_shift_left(buf, base - buf->page_len, len, shift);
+		return;
 	}
-	head->iov_len -= len;
-	buf->buflen -= len;
-	/* Have we truncated the message? */
-	if (buf->len > buf->buflen)
-		buf->len = buf->buflen;
+	xdr_buf_pages_copy_left(buf, base, len, shift);
+	len += base;
+	if (len <= buf->page_len)
+		return;
+	xdr_buf_tail_copy_left(buf, 0, len - buf->page_len, shift);
+}
 
-	return result;
+/**
+ * xdr_shrink_bufhead
+ * @buf: xdr_buf
+ * @len: new length of buf->head[0]
+ *
+ * Shrinks XDR buffer's header kvec buf->head[0], setting it to
+ * 'len' bytes. The extra data is not lost, but is instead
+ * moved into the inlined pages and/or the tail.
+ */
+static unsigned int xdr_shrink_bufhead(struct xdr_buf *buf, unsigned int len)
+{
+	struct kvec *head = buf->head;
+	unsigned int shift, buflen = max(buf->len, len);
+
+	WARN_ON_ONCE(len > head->iov_len);
+	if (head->iov_len > buflen) {
+		buf->buflen -= head->iov_len - buflen;
+		head->iov_len = buflen;
+	}
+	if (len >= head->iov_len)
+		return 0;
+	shift = head->iov_len - len;
+	xdr_buf_try_expand(buf, shift);
+	xdr_buf_head_shift_right(buf, len, buflen - len, shift);
+	head->iov_len = len;
+	buf->buflen -= shift;
+	buf->len -= shift;
+	return shift;
 }
 
 /**
- * xdr_shrink_pagelen - shrinks buf->pages by up to @len bytes
+ * xdr_shrink_pagelen - shrinks buf->pages to @len bytes
  * @buf: xdr_buf
- * @len: bytes to remove from buf->pages
+ * @len: new page buffer length
  *
  * The extra data is not lost, but is instead moved into buf->tail.
  * Returns the actual number of bytes moved.
  */
-static unsigned int
-xdr_shrink_pagelen(struct xdr_buf *buf, size_t len)
+static unsigned int xdr_shrink_pagelen(struct xdr_buf *buf, unsigned int len)
 {
-	struct kvec *tail;
-	size_t copy;
-	unsigned int pglen = buf->page_len;
-	unsigned int tailbuf_len;
-	unsigned int result;
-
-	result = 0;
-	tail = buf->tail;
-	if (len > buf->page_len)
-		len = buf-> page_len;
-	tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len;
-
-	/* Shift the tail first */
-	if (tailbuf_len != 0) {
-		unsigned int free_space = tailbuf_len - tail->iov_len;
-
-		if (len < free_space)
-			free_space = len;
-		tail->iov_len += free_space;
-
-		copy = len;
-		if (tail->iov_len > len) {
-			char *p = (char *)tail->iov_base + len;
-			memmove(p, tail->iov_base, tail->iov_len - len);
-			result += tail->iov_len - len;
-		} else
-			copy = tail->iov_len;
-		/* Copy from the inlined pages into the tail */
-		_copy_from_pages((char *)tail->iov_base,
-				buf->pages, buf->page_base + pglen - len,
-				copy);
-		result += copy;
+	unsigned int shift, buflen = buf->len - buf->head->iov_len;
+
+	WARN_ON_ONCE(len > buf->page_len);
+	if (buf->head->iov_len >= buf->len || len > buflen)
+		buflen = len;
+	if (buf->page_len > buflen) {
+		buf->buflen -= buf->page_len - buflen;
+		buf->page_len = buflen;
 	}
-	buf->page_len -= len;
-	buf->buflen -= len;
-	/* Have we truncated the message? */
-	if (buf->len > buf->buflen)
-		buf->len = buf->buflen;
-
-	return result;
+	if (len >= buf->page_len)
+		return 0;
+	shift = buf->page_len - len;
+	xdr_buf_try_expand(buf, shift);
+	xdr_buf_pages_shift_right(buf, len, buflen - len, shift);
+	buf->page_len = len;
+	buf->len -= shift;
+	buf->buflen -= shift;
+	return shift;
 }
 
 void
 xdr_shift_buf(struct xdr_buf *buf, size_t len)
 {
-	xdr_shrink_bufhead(buf, len);
+	xdr_shrink_bufhead(buf, buf->head->iov_len - len);
 }
 EXPORT_SYMBOL_GPL(xdr_shift_buf);
 
@@ -505,6 +852,31 @@ unsigned int xdr_stream_pos(const struct xdr_stream *xdr)
 }
 EXPORT_SYMBOL_GPL(xdr_stream_pos);
 
+static void xdr_stream_set_pos(struct xdr_stream *xdr, unsigned int pos)
+{
+	unsigned int blen = xdr->buf->len;
+
+	xdr->nwords = blen > pos ? XDR_QUADLEN(blen) - XDR_QUADLEN(pos) : 0;
+}
+
+static void xdr_stream_page_set_pos(struct xdr_stream *xdr, unsigned int pos)
+{
+	xdr_stream_set_pos(xdr, pos + xdr->buf->head[0].iov_len);
+}
+
+/**
+ * xdr_page_pos - Return the current offset from the start of the xdr pages
+ * @xdr: pointer to struct xdr_stream
+ */
+unsigned int xdr_page_pos(const struct xdr_stream *xdr)
+{
+	unsigned int pos = xdr_stream_pos(xdr);
+
+	WARN_ON(pos < xdr->buf->head[0].iov_len);
+	return pos - xdr->buf->head[0].iov_len;
+}
+EXPORT_SYMBOL_GPL(xdr_page_pos);
+
 /**
  * xdr_init_encode - Initialize a struct xdr_stream for sending data.
  * @xdr: pointer to xdr_stream struct
@@ -525,7 +897,7 @@ void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p,
 	struct kvec *iov = buf->head;
 	int scratch_len = buf->buflen - buf->page_len - buf->tail[0].iov_len;
 
-	xdr_set_scratch_buffer(xdr, NULL, 0);
+	xdr_reset_scratch_buffer(xdr);
 	BUG_ON(scratch_len < 0);
 	xdr->buf = buf;
 	xdr->iov = iov;
@@ -569,7 +941,7 @@ inline void xdr_commit_encode(struct xdr_stream *xdr)
 	page = page_address(*xdr->page_ptr);
 	memcpy(xdr->scratch.iov_base, page, shift);
 	memmove(page, page + shift, (void *)xdr->p - page);
-	xdr->scratch.iov_len = 0;
+	xdr_reset_scratch_buffer(xdr);
 }
 EXPORT_SYMBOL_GPL(xdr_commit_encode);
 
@@ -599,8 +971,7 @@ static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
 	 * the "scratch" iov to track any temporarily unused fragment of
 	 * space at the end of the previous buffer:
 	 */
-	xdr->scratch.iov_base = xdr->p;
-	xdr->scratch.iov_len = frag1bytes;
+	xdr_set_scratch_buffer(xdr, xdr->p, frag1bytes);
 	p = page_address(*xdr->page_ptr);
 	/*
 	 * Note this is where the next encode will start after we've
@@ -648,6 +1019,51 @@ __be32 * xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes)
 }
 EXPORT_SYMBOL_GPL(xdr_reserve_space);
 
+
+/**
+ * xdr_reserve_space_vec - Reserves a large amount of buffer space for sending
+ * @xdr: pointer to xdr_stream
+ * @vec: pointer to a kvec array
+ * @nbytes: number of bytes to reserve
+ *
+ * Reserves enough buffer space to encode 'nbytes' of data and stores the
+ * pointers in 'vec'. The size argument passed to xdr_reserve_space() is
+ * determined based on the number of bytes remaining in the current page to
+ * avoid invalidating iov_base pointers when xdr_commit_encode() is called.
+ */
+int xdr_reserve_space_vec(struct xdr_stream *xdr, struct kvec *vec, size_t nbytes)
+{
+	int thislen;
+	int v = 0;
+	__be32 *p;
+
+	/*
+	 * svcrdma requires every READ payload to start somewhere
+	 * in xdr->pages.
+	 */
+	if (xdr->iov == xdr->buf->head) {
+		xdr->iov = NULL;
+		xdr->end = xdr->p;
+	}
+
+	while (nbytes) {
+		thislen = xdr->buf->page_len % PAGE_SIZE;
+		thislen = min_t(size_t, nbytes, PAGE_SIZE - thislen);
+
+		p = xdr_reserve_space(xdr, thislen);
+		if (!p)
+			return -EIO;
+
+		vec[v].iov_base = p;
+		vec[v].iov_len = thislen;
+		v++;
+		nbytes -= thislen;
+	}
+
+	return v;
+}
+EXPORT_SYMBOL_GPL(xdr_reserve_space_vec);
+
 /**
  * xdr_truncate_encode - truncate an encode buffer
  * @xdr: pointer to xdr_stream
@@ -658,7 +1074,7 @@ EXPORT_SYMBOL_GPL(xdr_reserve_space);
  * head, tail, and page lengths are adjusted to correspond.
  *
  * If this means moving xdr->p to a different buffer, we assume that
- * that the end pointer should be set to the end of the current page,
+ * the end pointer should be set to the end of the current page,
  * except in the case of the head buffer when we assume the head
  * buffer's current length represents the end of the available buffer.
  *
@@ -781,19 +1197,31 @@ void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, unsigned int b
 }
 EXPORT_SYMBOL_GPL(xdr_write_pages);
 
-static void xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov,
-		unsigned int len)
+static unsigned int xdr_set_iov(struct xdr_stream *xdr, struct kvec *iov,
+				unsigned int base, unsigned int len)
 {
 	if (len > iov->iov_len)
 		len = iov->iov_len;
-	xdr->p = (__be32*)iov->iov_base;
+	if (unlikely(base > len))
+		base = len;
+	xdr->p = (__be32*)(iov->iov_base + base);
 	xdr->end = (__be32*)(iov->iov_base + len);
 	xdr->iov = iov;
 	xdr->page_ptr = NULL;
+	return len - base;
+}
+
+static unsigned int xdr_set_tail_base(struct xdr_stream *xdr,
+				      unsigned int base, unsigned int len)
+{
+	struct xdr_buf *buf = xdr->buf;
+
+	xdr_stream_set_pos(xdr, base + buf->page_len + buf->head->iov_len);
+	return xdr_set_iov(xdr, buf->tail, base, len);
 }
 
-static int xdr_set_page_base(struct xdr_stream *xdr,
-		unsigned int base, unsigned int len)
+static unsigned int xdr_set_page_base(struct xdr_stream *xdr,
+				      unsigned int base, unsigned int len)
 {
 	unsigned int pgnr;
 	unsigned int maxlen;
@@ -802,12 +1230,15 @@ static int xdr_set_page_base(struct xdr_stream *xdr,
 	void *kaddr;
 
 	maxlen = xdr->buf->page_len;
-	if (base >= maxlen)
-		return -EINVAL;
-	maxlen -= base;
+	if (base >= maxlen) {
+		base = maxlen;
+		maxlen = 0;
+	} else
+		maxlen -= base;
 	if (len > maxlen)
 		len = maxlen;
 
+	xdr_stream_page_set_pos(xdr, base);
 	base += xdr->buf->page_base;
 
 	pgnr = base >> PAGE_SHIFT;
@@ -822,7 +1253,16 @@ static int xdr_set_page_base(struct xdr_stream *xdr,
 		pgend = PAGE_SIZE;
 	xdr->end = (__be32*)(kaddr + pgend);
 	xdr->iov = NULL;
-	return 0;
+	return len;
+}
+
+static void xdr_set_page(struct xdr_stream *xdr, unsigned int base,
+			 unsigned int len)
+{
+	if (xdr_set_page_base(xdr, base, len) == 0) {
+		base -= xdr->buf->page_len;
+		xdr_set_tail_base(xdr, base, len);
+	}
 }
 
 static void xdr_set_next_page(struct xdr_stream *xdr)
@@ -831,19 +1271,18 @@ static void xdr_set_next_page(struct xdr_stream *xdr)
 
 	newbase = (1 + xdr->page_ptr - xdr->buf->pages) << PAGE_SHIFT;
 	newbase -= xdr->buf->page_base;
-
-	if (xdr_set_page_base(xdr, newbase, PAGE_SIZE) < 0)
-		xdr_set_iov(xdr, xdr->buf->tail, xdr->nwords << 2);
+	if (newbase < xdr->buf->page_len)
+		xdr_set_page_base(xdr, newbase, xdr_stream_remaining(xdr));
+	else
+		xdr_set_tail_base(xdr, 0, xdr_stream_remaining(xdr));
 }
 
 static bool xdr_set_next_buffer(struct xdr_stream *xdr)
 {
 	if (xdr->page_ptr != NULL)
 		xdr_set_next_page(xdr);
-	else if (xdr->iov == xdr->buf->head) {
-		if (xdr_set_page_base(xdr, 0, PAGE_SIZE) < 0)
-			xdr_set_iov(xdr, xdr->buf->tail, xdr->nwords << 2);
-	}
+	else if (xdr->iov == xdr->buf->head)
+		xdr_set_page(xdr, 0, xdr_stream_remaining(xdr));
 	return xdr->p != xdr->end;
 }
 
@@ -858,15 +1297,11 @@ void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, __be32 *p,
 		     struct rpc_rqst *rqst)
 {
 	xdr->buf = buf;
-	xdr->scratch.iov_base = NULL;
-	xdr->scratch.iov_len = 0;
+	xdr_reset_scratch_buffer(xdr);
 	xdr->nwords = XDR_QUADLEN(buf->len);
-	if (buf->head[0].iov_len != 0)
-		xdr_set_iov(xdr, buf->head, buf->len);
-	else if (buf->page_len != 0)
-		xdr_set_page_base(xdr, 0, buf->len);
-	else
-		xdr_set_iov(xdr, buf->head, buf->len);
+	if (xdr_set_iov(xdr, buf->head, 0, buf->len) == 0 &&
+	    xdr_set_page_base(xdr, 0, buf->len) == 0)
+		xdr_set_iov(xdr, buf->tail, 0, buf->len);
 	if (p != NULL && p > xdr->p && xdr->end >= p) {
 		xdr->nwords -= p - xdr->p;
 		xdr->p = p;
@@ -907,24 +1342,6 @@ static __be32 * __xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes)
 	return p;
 }
 
-/**
- * xdr_set_scratch_buffer - Attach a scratch buffer for decoding data.
- * @xdr: pointer to xdr_stream struct
- * @buf: pointer to an empty buffer
- * @buflen: size of 'buf'
- *
- * The scratch buffer is used when decoding from an array of pages.
- * If an xdr_inline_decode() call spans across page boundaries, then
- * we copy the data into the scratch buffer in order to allow linear
- * access.
- */
-void xdr_set_scratch_buffer(struct xdr_stream *xdr, void *buf, size_t buflen)
-{
-	xdr->scratch.iov_base = buf;
-	xdr->scratch.iov_len = buflen;
-}
-EXPORT_SYMBOL_GPL(xdr_set_scratch_buffer);
-
 static __be32 *xdr_copy_to_scratch(struct xdr_stream *xdr, size_t nbytes)
 {
 	__be32 *p;
@@ -979,26 +1396,31 @@ out_overflow:
 }
 EXPORT_SYMBOL_GPL(xdr_inline_decode);
 
-static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
+static void xdr_realign_pages(struct xdr_stream *xdr)
 {
 	struct xdr_buf *buf = xdr->buf;
-	struct kvec *iov;
-	unsigned int nwords = XDR_QUADLEN(len);
+	struct kvec *iov = buf->head;
 	unsigned int cur = xdr_stream_pos(xdr);
-	unsigned int copied, offset;
-
-	if (xdr->nwords == 0)
-		return 0;
+	unsigned int copied;
 
 	/* Realign pages to current pointer position */
-	iov = buf->head;
 	if (iov->iov_len > cur) {
-		offset = iov->iov_len - cur;
-		copied = xdr_shrink_bufhead(buf, offset);
-		trace_rpc_xdr_alignment(xdr, offset, copied);
-		xdr->nwords = XDR_QUADLEN(buf->len - cur);
+		copied = xdr_shrink_bufhead(buf, cur);
+		trace_rpc_xdr_alignment(xdr, cur, copied);
+		xdr_set_page(xdr, 0, buf->page_len);
 	}
+}
+
+static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int nwords = XDR_QUADLEN(len);
+	unsigned int copied;
+
+	if (xdr->nwords == 0)
+		return 0;
 
+	xdr_realign_pages(xdr);
 	if (nwords > xdr->nwords) {
 		nwords = xdr->nwords;
 		len = nwords << 2;
@@ -1007,56 +1429,107 @@ static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
 		len = buf->page_len;
 	else if (nwords < xdr->nwords) {
 		/* Truncate page data and move it into the tail */
-		offset = buf->page_len - len;
-		copied = xdr_shrink_pagelen(buf, offset);
-		trace_rpc_xdr_alignment(xdr, offset, copied);
-		xdr->nwords = XDR_QUADLEN(buf->len - cur);
+		copied = xdr_shrink_pagelen(buf, len);
+		trace_rpc_xdr_alignment(xdr, len, copied);
 	}
 	return len;
 }
 
 /**
- * xdr_read_pages - Ensure page-based XDR data to decode is aligned at current pointer position
+ * xdr_read_pages - align page-based XDR data to current pointer position
  * @xdr: pointer to xdr_stream struct
  * @len: number of bytes of page data
  *
  * Moves data beyond the current pointer position from the XDR head[] buffer
- * into the page list. Any data that lies beyond current position + "len"
- * bytes is moved into the XDR tail[].
+ * into the page list. Any data that lies beyond current position + @len
+ * bytes is moved into the XDR tail[]. The xdr_stream current position is
+ * then advanced past that data to align to the next XDR object in the tail.
  *
  * Returns the number of XDR encoded bytes now contained in the pages
  */
 unsigned int xdr_read_pages(struct xdr_stream *xdr, unsigned int len)
 {
-	struct xdr_buf *buf = xdr->buf;
-	struct kvec *iov;
-	unsigned int nwords;
-	unsigned int end;
-	unsigned int padding;
+	unsigned int nwords = XDR_QUADLEN(len);
+	unsigned int base, end, pglen;
 
-	len = xdr_align_pages(xdr, len);
-	if (len == 0)
+	pglen = xdr_align_pages(xdr, nwords << 2);
+	if (pglen == 0)
 		return 0;
-	nwords = XDR_QUADLEN(len);
-	padding = (nwords << 2) - len;
-	xdr->iov = iov = buf->tail;
-	/* Compute remaining message length.  */
-	end = ((xdr->nwords - nwords) << 2) + padding;
-	if (end > iov->iov_len)
-		end = iov->iov_len;
 
-	/*
-	 * Position current pointer at beginning of tail, and
-	 * set remaining message length.
-	 */
-	xdr->p = (__be32 *)((char *)iov->iov_base + padding);
-	xdr->end = (__be32 *)((char *)iov->iov_base + end);
-	xdr->page_ptr = NULL;
-	xdr->nwords = XDR_QUADLEN(end - padding);
-	return len;
+	base = (nwords << 2) - pglen;
+	end = xdr_stream_remaining(xdr) - pglen;
+
+	xdr_set_tail_base(xdr, base, end);
+	return len <= pglen ? len : pglen;
 }
 EXPORT_SYMBOL_GPL(xdr_read_pages);
 
+unsigned int xdr_align_data(struct xdr_stream *xdr, unsigned int offset,
+			    unsigned int length)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int from, bytes, len;
+	unsigned int shift;
+
+	xdr_realign_pages(xdr);
+	from = xdr_page_pos(xdr);
+
+	if (from >= buf->page_len + buf->tail->iov_len)
+		return 0;
+	if (from + buf->head->iov_len >= buf->len)
+		return 0;
+
+	len = buf->len - buf->head->iov_len;
+
+	/* We only shift data left! */
+	if (WARN_ONCE(from < offset, "SUNRPC: misaligned data src=%u dst=%u\n",
+		      from, offset))
+		return 0;
+	if (WARN_ONCE(offset > buf->page_len,
+		      "SUNRPC: buffer overflow. offset=%u, page_len=%u\n",
+		      offset, buf->page_len))
+		return 0;
+
+	/* Move page data to the left */
+	shift = from - offset;
+	xdr_buf_pages_shift_left(buf, from, len, shift);
+
+	bytes = xdr_stream_remaining(xdr);
+	if (length > bytes)
+		length = bytes;
+	bytes -= length;
+
+	xdr->buf->len -= shift;
+	xdr_set_page(xdr, offset + length, bytes);
+	return length;
+}
+EXPORT_SYMBOL_GPL(xdr_align_data);
+
+unsigned int xdr_expand_hole(struct xdr_stream *xdr, unsigned int offset,
+			     unsigned int length)
+{
+	struct xdr_buf *buf = xdr->buf;
+	unsigned int from, to, shift;
+
+	xdr_realign_pages(xdr);
+	from = xdr_page_pos(xdr);
+	to = xdr_align_size(offset + length);
+
+	/* Could the hole be behind us? */
+	if (to > from) {
+		unsigned int buflen = buf->len - buf->head->iov_len;
+		shift = to - from;
+		xdr_buf_try_expand(buf, shift);
+		xdr_buf_pages_shift_right(buf, from, buflen, shift);
+		xdr_set_page(xdr, to, xdr_stream_remaining(xdr));
+	} else if (to != from)
+		xdr_align_data(xdr, to, 0);
+	xdr_buf_pages_zero(buf, offset, length);
+
+	return length;
+}
+EXPORT_SYMBOL_GPL(xdr_expand_hole);
+
 /**
  * xdr_enter_page - decode data from the XDR page
  * @xdr: pointer to xdr_stream struct
@@ -1081,8 +1554,7 @@ EXPORT_SYMBOL_GPL(xdr_enter_page);
 
 static const struct kvec empty_iov = {.iov_base = NULL, .iov_len = 0};
 
-void
-xdr_buf_from_iov(struct kvec *iov, struct xdr_buf *buf)
+void xdr_buf_from_iov(const struct kvec *iov, struct xdr_buf *buf)
 {
 	buf->head[0] = *iov;
 	buf->tail[0] = empty_iov;
@@ -1105,9 +1577,8 @@ EXPORT_SYMBOL_GPL(xdr_buf_from_iov);
  *
  * Returns -1 if base of length are out of bounds.
  */
-int
-xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
-			unsigned int base, unsigned int len)
+int xdr_buf_subsegment(const struct xdr_buf *buf, struct xdr_buf *subbuf,
+		       unsigned int base, unsigned int len)
 {
 	subbuf->buflen = subbuf->len = len;
 	if (base < buf->head[0].iov_len) {
@@ -1155,6 +1626,51 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf,
 EXPORT_SYMBOL_GPL(xdr_buf_subsegment);
 
 /**
+ * xdr_stream_subsegment - set @subbuf to a portion of @xdr
+ * @xdr: an xdr_stream set up for decoding
+ * @subbuf: the result buffer
+ * @nbytes: length of @xdr to extract, in bytes
+ *
+ * Sets up @subbuf to represent a portion of @xdr. The portion
+ * starts at the current offset in @xdr, and extends for a length
+ * of @nbytes. If this is successful, @xdr is advanced to the next
+ * position following that portion.
+ *
+ * Return values:
+ *   %true: @subbuf has been initialized, and @xdr has been advanced.
+ *   %false: a bounds error has occurred
+ */
+bool xdr_stream_subsegment(struct xdr_stream *xdr, struct xdr_buf *subbuf,
+			   unsigned int nbytes)
+{
+	unsigned int remaining, offset, len;
+
+	if (xdr_buf_subsegment(xdr->buf, subbuf, xdr_stream_pos(xdr), nbytes))
+		return false;
+
+	if (subbuf->head[0].iov_len)
+		if (!__xdr_inline_decode(xdr, subbuf->head[0].iov_len))
+			return false;
+
+	remaining = subbuf->page_len;
+	offset = subbuf->page_base;
+	while (remaining) {
+		len = min_t(unsigned int, remaining, PAGE_SIZE) - offset;
+
+		if (xdr->p == xdr->end && !xdr_set_next_buffer(xdr))
+			return false;
+		if (!__xdr_inline_decode(xdr, len))
+			return false;
+
+		remaining -= len;
+		offset = 0;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(xdr_stream_subsegment);
+
+/**
  * xdr_buf_trim - lop at most "len" bytes off the end of "buf"
  * @buf: buf to be trimmed
  * @len: number of bytes to reduce "buf" by
@@ -1195,7 +1711,8 @@ fix_len:
 }
 EXPORT_SYMBOL_GPL(xdr_buf_trim);
 
-static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len)
+static void __read_bytes_from_xdr_buf(const struct xdr_buf *subbuf,
+				      void *obj, unsigned int len)
 {
 	unsigned int this_len;
 
@@ -1204,8 +1721,7 @@ static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigne
 	len -= this_len;
 	obj += this_len;
 	this_len = min_t(unsigned int, len, subbuf->page_len);
-	if (this_len)
-		_copy_from_pages(obj, subbuf->pages, subbuf->page_base, this_len);
+	_copy_from_pages(obj, subbuf->pages, subbuf->page_base, this_len);
 	len -= this_len;
 	obj += this_len;
 	this_len = min_t(unsigned int, len, subbuf->tail[0].iov_len);
@@ -1213,7 +1729,8 @@ static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigne
 }
 
 /* obj is assumed to point to allocated memory of size at least len: */
-int read_bytes_from_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, unsigned int len)
+int read_bytes_from_xdr_buf(const struct xdr_buf *buf, unsigned int base,
+			    void *obj, unsigned int len)
 {
 	struct xdr_buf subbuf;
 	int status;
@@ -1226,7 +1743,8 @@ int read_bytes_from_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, u
 }
 EXPORT_SYMBOL_GPL(read_bytes_from_xdr_buf);
 
-static void __write_bytes_to_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len)
+static void __write_bytes_to_xdr_buf(const struct xdr_buf *subbuf,
+				     void *obj, unsigned int len)
 {
 	unsigned int this_len;
 
@@ -1235,8 +1753,7 @@ static void __write_bytes_to_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned
 	len -= this_len;
 	obj += this_len;
 	this_len = min_t(unsigned int, len, subbuf->page_len);
-	if (this_len)
-		_copy_to_pages(subbuf->pages, subbuf->page_base, obj, this_len);
+	_copy_to_pages(subbuf->pages, subbuf->page_base, obj, this_len);
 	len -= this_len;
 	obj += this_len;
 	this_len = min_t(unsigned int, len, subbuf->tail[0].iov_len);
@@ -1244,7 +1761,8 @@ static void __write_bytes_to_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned
 }
 
 /* obj is assumed to point to allocated memory of size at least len: */
-int write_bytes_to_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, unsigned int len)
+int write_bytes_to_xdr_buf(const struct xdr_buf *buf, unsigned int base,
+			   void *obj, unsigned int len)
 {
 	struct xdr_buf subbuf;
 	int status;
@@ -1257,8 +1775,7 @@ int write_bytes_to_xdr_buf(struct xdr_buf *buf, unsigned int base, void *obj, un
 }
 EXPORT_SYMBOL_GPL(write_bytes_to_xdr_buf);
 
-int
-xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj)
+int xdr_decode_word(const struct xdr_buf *buf, unsigned int base, u32 *obj)
 {
 	__be32	raw;
 	int	status;
@@ -1271,8 +1788,7 @@ xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj)
 }
 EXPORT_SYMBOL_GPL(xdr_decode_word);
 
-int
-xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj)
+int xdr_encode_word(const struct xdr_buf *buf, unsigned int base, u32 obj)
 {
 	__be32	raw = cpu_to_be32(obj);
 
@@ -1281,9 +1797,8 @@ xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj)
 EXPORT_SYMBOL_GPL(xdr_encode_word);
 
 /* Returns 0 on success, or else a negative error code. */
-static int
-xdr_xcode_array2(struct xdr_buf *buf, unsigned int base,
-		 struct xdr_array2_desc *desc, int encode)
+static int xdr_xcode_array2(const struct xdr_buf *buf, unsigned int base,
+			    struct xdr_array2_desc *desc, int encode)
 {
 	char *elem = NULL, *c;
 	unsigned int copied = 0, todo, avail_here;
@@ -1475,9 +1990,8 @@ out:
 	return err;
 }
 
-int
-xdr_decode_array2(struct xdr_buf *buf, unsigned int base,
-		  struct xdr_array2_desc *desc)
+int xdr_decode_array2(const struct xdr_buf *buf, unsigned int base,
+		      struct xdr_array2_desc *desc)
 {
 	if (base >= buf->len)
 		return -EINVAL;
@@ -1486,9 +2000,8 @@ xdr_decode_array2(struct xdr_buf *buf, unsigned int base,
 }
 EXPORT_SYMBOL_GPL(xdr_decode_array2);
 
-int
-xdr_encode_array2(struct xdr_buf *buf, unsigned int base,
-		  struct xdr_array2_desc *desc)
+int xdr_encode_array2(const struct xdr_buf *buf, unsigned int base,
+		      struct xdr_array2_desc *desc)
 {
 	if ((unsigned long) base + 4 + desc->array_len * desc->elem_size >
 	    buf->head->iov_len + buf->page_len + buf->tail->iov_len)
@@ -1498,9 +2011,9 @@ xdr_encode_array2(struct xdr_buf *buf, unsigned int base,
 }
 EXPORT_SYMBOL_GPL(xdr_encode_array2);
 
-int
-xdr_process_buf(struct xdr_buf *buf, unsigned int offset, unsigned int len,
-		int (*actor)(struct scatterlist *, void *), void *data)
+int xdr_process_buf(const struct xdr_buf *buf, unsigned int offset,
+		    unsigned int len,
+		    int (*actor)(struct scatterlist *, void *), void *data)
 {
 	int i, ret = 0;
 	unsigned int page_len, thislen, page_offset;
@@ -1668,10 +2181,8 @@ ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str,
 
 	ret = xdr_stream_decode_opaque_inline(xdr, &p, maxlen);
 	if (ret > 0) {
-		char *s = kmalloc(ret + 1, gfp_flags);
+		char *s = kmemdup_nul(p, ret, gfp_flags);
 		if (s != NULL) {
-			memcpy(s, p, ret);
-			s[ret] = '\0';
 			*str = s;
 			return strlen(s);
 		}
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 5a8e47bbfb9f..691ccf8049a4 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -151,33 +151,94 @@ out:
 }
 EXPORT_SYMBOL_GPL(xprt_unregister_transport);
 
-/**
- * xprt_load_transport - load a transport implementation
- * @transport_name: transport to load
- *
- * Returns:
- * 0:		transport successfully loaded
- * -ENOENT:	transport module not available
- */
-int xprt_load_transport(const char *transport_name)
+static void
+xprt_class_release(const struct xprt_class *t)
 {
-	struct xprt_class *t;
-	int result;
+	module_put(t->owner);
+}
+
+static const struct xprt_class *
+xprt_class_find_by_ident_locked(int ident)
+{
+	const struct xprt_class *t;
+
+	list_for_each_entry(t, &xprt_list, list) {
+		if (t->ident != ident)
+			continue;
+		if (!try_module_get(t->owner))
+			continue;
+		return t;
+	}
+	return NULL;
+}
+
+static const struct xprt_class *
+xprt_class_find_by_ident(int ident)
+{
+	const struct xprt_class *t;
 
-	result = 0;
 	spin_lock(&xprt_list_lock);
+	t = xprt_class_find_by_ident_locked(ident);
+	spin_unlock(&xprt_list_lock);
+	return t;
+}
+
+static const struct xprt_class *
+xprt_class_find_by_netid_locked(const char *netid)
+{
+	const struct xprt_class *t;
+	unsigned int i;
+
 	list_for_each_entry(t, &xprt_list, list) {
-		if (strcmp(t->name, transport_name) == 0) {
-			spin_unlock(&xprt_list_lock);
-			goto out;
+		for (i = 0; t->netid[i][0] != '\0'; i++) {
+			if (strcmp(t->netid[i], netid) != 0)
+				continue;
+			if (!try_module_get(t->owner))
+				continue;
+			return t;
 		}
 	}
+	return NULL;
+}
+
+static const struct xprt_class *
+xprt_class_find_by_netid(const char *netid)
+{
+	const struct xprt_class *t;
+
+	spin_lock(&xprt_list_lock);
+	t = xprt_class_find_by_netid_locked(netid);
+	if (!t) {
+		spin_unlock(&xprt_list_lock);
+		request_module("rpc%s", netid);
+		spin_lock(&xprt_list_lock);
+		t = xprt_class_find_by_netid_locked(netid);
+	}
 	spin_unlock(&xprt_list_lock);
-	result = request_module("xprt%s", transport_name);
-out:
-	return result;
+	return t;
 }
-EXPORT_SYMBOL_GPL(xprt_load_transport);
+
+/**
+ * xprt_find_transport_ident - convert a netid into a transport identifier
+ * @netid: transport to load
+ *
+ * Returns:
+ * > 0:		transport identifier
+ * -ENOENT:	transport module not available
+ */
+int xprt_find_transport_ident(const char *netid)
+{
+	const struct xprt_class *t;
+	int ret;
+
+	t = xprt_class_find_by_netid(netid);
+	if (!t)
+		return -ENOENT;
+	ret = t->ident;
+	xprt_class_release(t);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xprt_find_transport_ident);
 
 static void xprt_clear_locked(struct rpc_xprt *xprt)
 {
@@ -834,8 +895,7 @@ void xprt_connect(struct rpc_task *task)
 {
 	struct rpc_xprt	*xprt = task->tk_rqstp->rq_xprt;
 
-	dprintk("RPC: %5u xprt_connect xprt %p %s connected\n", task->tk_pid,
-			xprt, (xprt_connected(xprt) ? "is" : "is not"));
+	trace_xprt_connect(xprt);
 
 	if (!xprt_bound(xprt)) {
 		task->tk_status = -EAGAIN;
@@ -1131,8 +1191,6 @@ void xprt_complete_rqst(struct rpc_task *task, int copied)
 	struct rpc_rqst *req = task->tk_rqstp;
 	struct rpc_xprt *xprt = req->rq_xprt;
 
-	trace_xprt_complete_rqst(xprt, req->rq_xid, copied);
-
 	xprt->stat.recvs++;
 
 	req->rq_private_buf.len = copied;
@@ -1269,7 +1327,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 				/* Note: req is added _before_ pos */
 				list_add_tail(&req->rq_xmit, &pos->rq_xmit);
 				INIT_LIST_HEAD(&req->rq_xmit2);
-				trace_xprt_enq_xmit(task, 1);
 				goto out;
 			}
 		} else if (RPC_IS_SWAPPER(task)) {
@@ -1281,7 +1338,6 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 				/* Note: req is added _before_ pos */
 				list_add_tail(&req->rq_xmit, &pos->rq_xmit);
 				INIT_LIST_HEAD(&req->rq_xmit2);
-				trace_xprt_enq_xmit(task, 2);
 				goto out;
 			}
 		} else if (!req->rq_seqno) {
@@ -1290,13 +1346,11 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 					continue;
 				list_add_tail(&req->rq_xmit2, &pos->rq_xmit2);
 				INIT_LIST_HEAD(&req->rq_xmit);
-				trace_xprt_enq_xmit(task, 3);
 				goto out;
 			}
 		}
 		list_add_tail(&req->rq_xmit, &xprt->xmit_queue);
 		INIT_LIST_HEAD(&req->rq_xmit2);
-		trace_xprt_enq_xmit(task, 4);
 out:
 		set_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate);
 		spin_unlock(&xprt->queue_lock);
@@ -1414,9 +1468,9 @@ bool xprt_prepare_transmit(struct rpc_task *task)
 	struct rpc_rqst	*req = task->tk_rqstp;
 	struct rpc_xprt	*xprt = req->rq_xprt;
 
-	dprintk("RPC: %5u xprt_prepare_transmit\n", task->tk_pid);
-
 	if (!xprt_lock_write(xprt, task)) {
+		trace_xprt_transmit_queued(xprt, task);
+
 		/* Race breaker: someone may have transmitted us */
 		if (!test_bit(RPC_TASK_NEED_XMIT, &task->tk_runstate))
 			rpc_wake_up_queued_task_set_status(&xprt->sending,
@@ -1520,10 +1574,13 @@ xprt_transmit(struct rpc_task *task)
 {
 	struct rpc_rqst *next, *req = task->tk_rqstp;
 	struct rpc_xprt	*xprt = req->rq_xprt;
-	int status;
+	int counter, status;
 
 	spin_lock(&xprt->queue_lock);
+	counter = 0;
 	while (!list_empty(&xprt->xmit_queue)) {
+		if (++counter == 20)
+			break;
 		next = list_first_entry(&xprt->xmit_queue,
 				struct rpc_rqst, rq_xmit);
 		xprt_pin_rqst(next);
@@ -1531,7 +1588,6 @@ xprt_transmit(struct rpc_task *task)
 		status = xprt_request_transmit(next, task);
 		if (status == -EBADMSG && next != req)
 			status = 0;
-		cond_resched();
 		spin_lock(&xprt->queue_lock);
 		xprt_unpin_rqst(next);
 		if (status == 0) {
@@ -1747,8 +1803,8 @@ xprt_request_init(struct rpc_task *task)
 	req->rq_rcv_buf.bvec = NULL;
 	req->rq_release_snd_buf = NULL;
 	xprt_init_majortimeo(task, req);
-	dprintk("RPC: %5u reserved req %p xid %08x\n", task->tk_pid,
-			req, ntohl(req->rq_xid));
+
+	trace_xprt_reserve(req);
 }
 
 static void
@@ -1838,7 +1894,6 @@ void xprt_release(struct rpc_task *task)
 	if (req->rq_release_snd_buf)
 		req->rq_release_snd_buf(req);
 
-	dprintk("RPC: %5u release request %p\n", task->tk_pid, req);
 	if (likely(!bc_prealloc(req)))
 		xprt->ops->free_slot(xprt, req);
 	else
@@ -1902,21 +1957,17 @@ static void xprt_init(struct rpc_xprt *xprt, struct net *net)
 struct rpc_xprt *xprt_create_transport(struct xprt_create *args)
 {
 	struct rpc_xprt	*xprt;
-	struct xprt_class *t;
+	const struct xprt_class *t;
 
-	spin_lock(&xprt_list_lock);
-	list_for_each_entry(t, &xprt_list, list) {
-		if (t->ident == args->ident) {
-			spin_unlock(&xprt_list_lock);
-			goto found;
-		}
+	t = xprt_class_find_by_ident(args->ident);
+	if (!t) {
+		dprintk("RPC: transport (%d) not supported\n", args->ident);
+		return ERR_PTR(-EIO);
 	}
-	spin_unlock(&xprt_list_lock);
-	dprintk("RPC: transport (%d) not supported\n", args->ident);
-	return ERR_PTR(-EIO);
 
-found:
 	xprt = t->setup(args);
+	xprt_class_release(t);
+
 	if (IS_ERR(xprt))
 		goto out;
 	if (args->flags & XPRT_CREATE_NO_IDLE_TIMEOUT)
diff --git a/net/sunrpc/xprtrdma/Makefile b/net/sunrpc/xprtrdma/Makefile
index 8ed0377d7a18..55b21bae866d 100644
--- a/net/sunrpc/xprtrdma/Makefile
+++ b/net/sunrpc/xprtrdma/Makefile
@@ -4,5 +4,5 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += rpcrdma.o
 rpcrdma-y := transport.o rpc_rdma.o verbs.o frwr_ops.o \
 	svc_rdma.o svc_rdma_backchannel.o svc_rdma_transport.o \
 	svc_rdma_sendto.o svc_rdma_recvfrom.o svc_rdma_rw.o \
-	module.o
+	svc_rdma_pcl.o module.o
 rpcrdma-$(CONFIG_SUNRPC_BACKCHANNEL) += backchannel.o
diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c
index c92c1aac270a..946edf2db646 100644
--- a/net/sunrpc/xprtrdma/backchannel.c
+++ b/net/sunrpc/xprtrdma/backchannel.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Copyright (c) 2015 Oracle.  All rights reserved.
+ * Copyright (c) 2015-2020, Oracle and/or its affiliates.
  *
  * Support for backward direction RPCs on RPC/RDMA.
  */
@@ -82,7 +82,7 @@ static int rpcrdma_bc_marshal_reply(struct rpc_rqst *rqst)
 				      &rqst->rq_snd_buf, rpcrdma_noch_pullup))
 		return -EIO;
 
-	trace_xprtrdma_cb_reply(rqst);
+	trace_xprtrdma_cb_reply(r_xprt, rqst);
 	return 0;
 }
 
@@ -260,7 +260,7 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt,
 	 */
 	req = rpcr_to_rdmar(rqst);
 	req->rl_reply = rep;
-	trace_xprtrdma_cb_call(rqst);
+	trace_xprtrdma_cb_call(r_xprt, rqst);
 
 	/* Queue rqst for ULP's callback service */
 	bc_serv = xprt->bc_serv;
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index 7f94c9a19fd3..baca49fe83af 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -65,18 +65,23 @@ void frwr_release_mr(struct rpcrdma_mr *mr)
 	kfree(mr);
 }
 
+static void frwr_mr_unmap(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr)
+{
+	if (mr->mr_device) {
+		trace_xprtrdma_mr_unmap(mr);
+		ib_dma_unmap_sg(mr->mr_device, mr->mr_sg, mr->mr_nents,
+				mr->mr_dir);
+		mr->mr_device = NULL;
+	}
+}
+
 static void frwr_mr_recycle(struct rpcrdma_mr *mr)
 {
 	struct rpcrdma_xprt *r_xprt = mr->mr_xprt;
 
 	trace_xprtrdma_mr_recycle(mr);
 
-	if (mr->mr_dir != DMA_NONE) {
-		trace_xprtrdma_mr_unmap(mr);
-		ib_dma_unmap_sg(r_xprt->rx_ep->re_id->device,
-				mr->mr_sg, mr->mr_nents, mr->mr_dir);
-		mr->mr_dir = DMA_NONE;
-	}
+	frwr_mr_unmap(r_xprt, mr);
 
 	spin_lock(&r_xprt->rx_buf.rb_lock);
 	list_del(&mr->mr_all);
@@ -86,6 +91,16 @@ static void frwr_mr_recycle(struct rpcrdma_mr *mr)
 	frwr_release_mr(mr);
 }
 
+static void frwr_mr_put(struct rpcrdma_mr *mr)
+{
+	frwr_mr_unmap(mr->mr_xprt, mr);
+
+	/* The MR is returned to the req's MR free list instead
+	 * of to the xprt's MR free list. No spinlock is needed.
+	 */
+	rpcrdma_mr_push(mr, &mr->mr_req->rl_free_mrs);
+}
+
 /* frwr_reset - Place MRs back on the free list
  * @req: request to reset
  *
@@ -101,7 +116,7 @@ void frwr_reset(struct rpcrdma_req *req)
 	struct rpcrdma_mr *mr;
 
 	while ((mr = rpcrdma_mr_pop(&req->rl_registered)))
-		rpcrdma_mr_put(mr);
+		frwr_mr_put(mr);
 }
 
 /**
@@ -124,13 +139,13 @@ int frwr_mr_init(struct rpcrdma_xprt *r_xprt, struct rpcrdma_mr *mr)
 	if (IS_ERR(frmr))
 		goto out_mr_err;
 
-	sg = kcalloc(depth, sizeof(*sg), GFP_NOFS);
+	sg = kmalloc_array(depth, sizeof(*sg), GFP_NOFS);
 	if (!sg)
 		goto out_list_err;
 
 	mr->mr_xprt = r_xprt;
 	mr->frwr.fr_mr = frmr;
-	mr->mr_dir = DMA_NONE;
+	mr->mr_device = NULL;
 	INIT_LIST_HEAD(&mr->mr_list);
 	init_completion(&mr->frwr.fr_linv_done);
 
@@ -315,6 +330,7 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 				  mr->mr_dir);
 	if (!dma_nents)
 		goto out_dmamap_err;
+	mr->mr_device = ep->re_id->device;
 
 	ibmr = mr->frwr.fr_mr;
 	n = ib_map_mr_sg(ibmr, mr->mr_sg, dma_nents, NULL, PAGE_SIZE);
@@ -341,7 +357,6 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt,
 	return seg;
 
 out_dmamap_err:
-	mr->mr_dir = DMA_NONE;
 	trace_xprtrdma_frwr_sgerr(mr, i);
 	return ERR_PTR(-EIO);
 
@@ -363,12 +378,21 @@ static void frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc)
 		container_of(cqe, struct rpcrdma_frwr, fr_cqe);
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_fastreg(wc, frwr);
+	trace_xprtrdma_wc_fastreg(wc, &frwr->fr_cid);
 	/* The MR will get recycled when the associated req is retransmitted */
 
 	rpcrdma_flush_disconnect(cq->cq_context, wc);
 }
 
+static void frwr_cid_init(struct rpcrdma_ep *ep,
+			  struct rpcrdma_frwr *frwr)
+{
+	struct rpc_rdma_cid *cid = &frwr->fr_cid;
+
+	cid->ci_queue_id = ep->re_attr.send_cq->res.id;
+	cid->ci_completion_id = frwr->fr_mr->res.id;
+}
+
 /**
  * frwr_send - post Send WRs containing the RPC Call message
  * @r_xprt: controlling transport instance
@@ -385,6 +409,7 @@ static void frwr_wc_fastreg(struct ib_cq *cq, struct ib_wc *wc)
  */
 int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
+	struct rpcrdma_ep *ep = r_xprt->rx_ep;
 	struct ib_send_wr *post_wr;
 	struct rpcrdma_mr *mr;
 
@@ -395,6 +420,7 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 		frwr = &mr->frwr;
 
 		frwr->fr_cqe.done = frwr_wc_fastreg;
+		frwr_cid_init(ep, frwr);
 		frwr->fr_regwr.wr.next = post_wr;
 		frwr->fr_regwr.wr.wr_cqe = &frwr->fr_cqe;
 		frwr->fr_regwr.wr.num_sge = 0;
@@ -404,7 +430,7 @@ int frwr_send(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 		post_wr = &frwr->fr_regwr.wr;
 	}
 
-	return ib_post_send(r_xprt->rx_ep->re_id->qp, post_wr, NULL);
+	return ib_post_send(ep->re_id->qp, post_wr, NULL);
 }
 
 /**
@@ -420,18 +446,17 @@ void frwr_reminv(struct rpcrdma_rep *rep, struct list_head *mrs)
 	list_for_each_entry(mr, mrs, mr_list)
 		if (mr->mr_handle == rep->rr_inv_rkey) {
 			list_del_init(&mr->mr_list);
-			trace_xprtrdma_mr_reminv(mr);
-			rpcrdma_mr_put(mr);
+			frwr_mr_put(mr);
 			break;	/* only one invalidated MR per RPC */
 		}
 }
 
-static void __frwr_release_mr(struct ib_wc *wc, struct rpcrdma_mr *mr)
+static void frwr_mr_done(struct ib_wc *wc, struct rpcrdma_mr *mr)
 {
 	if (wc->status != IB_WC_SUCCESS)
 		frwr_mr_recycle(mr);
 	else
-		rpcrdma_mr_put(mr);
+		frwr_mr_put(mr);
 }
 
 /**
@@ -448,8 +473,8 @@ static void frwr_wc_localinv(struct ib_cq *cq, struct ib_wc *wc)
 	struct rpcrdma_mr *mr = container_of(frwr, struct rpcrdma_mr, frwr);
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_li(wc, frwr);
-	__frwr_release_mr(wc, mr);
+	trace_xprtrdma_wc_li(wc, &frwr->fr_cid);
+	frwr_mr_done(wc, mr);
 
 	rpcrdma_flush_disconnect(cq->cq_context, wc);
 }
@@ -469,8 +494,8 @@ static void frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc)
 	struct rpcrdma_mr *mr = container_of(frwr, struct rpcrdma_mr, frwr);
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_li_wake(wc, frwr);
-	__frwr_release_mr(wc, mr);
+	trace_xprtrdma_wc_li_wake(wc, &frwr->fr_cid);
+	frwr_mr_done(wc, mr);
 	complete(&frwr->fr_linv_done);
 
 	rpcrdma_flush_disconnect(cq->cq_context, wc);
@@ -490,6 +515,7 @@ static void frwr_wc_localinv_wake(struct ib_cq *cq, struct ib_wc *wc)
 void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
 	struct ib_send_wr *first, **prev, *last;
+	struct rpcrdma_ep *ep = r_xprt->rx_ep;
 	const struct ib_send_wr *bad_wr;
 	struct rpcrdma_frwr *frwr;
 	struct rpcrdma_mr *mr;
@@ -509,6 +535,7 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 
 		frwr = &mr->frwr;
 		frwr->fr_cqe.done = frwr_wc_localinv;
+		frwr_cid_init(ep, frwr);
 		last = &frwr->fr_invwr;
 		last->next = NULL;
 		last->wr_cqe = &frwr->fr_cqe;
@@ -534,7 +561,7 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * unless re_id->qp is a valid pointer.
 	 */
 	bad_wr = NULL;
-	rc = ib_post_send(r_xprt->rx_ep->re_id->qp, first, &bad_wr);
+	rc = ib_post_send(ep->re_id->qp, first, &bad_wr);
 
 	/* The final LOCAL_INV WR in the chain is supposed to
 	 * do the wake. If it was never posted, the wake will
@@ -547,7 +574,7 @@ void frwr_unmap_sync(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 
 	/* Recycle MRs in the LOCAL_INV chain that did not get posted.
 	 */
-	trace_xprtrdma_post_linv(req, rc);
+	trace_xprtrdma_post_linv_err(req, rc);
 	while (bad_wr) {
 		frwr = container_of(bad_wr, struct rpcrdma_frwr,
 				    fr_invwr);
@@ -574,10 +601,10 @@ static void frwr_wc_localinv_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct rpcrdma_rep *rep = mr->mr_req->rl_reply;
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_li_done(wc, frwr);
-	__frwr_release_mr(wc, mr);
+	trace_xprtrdma_wc_li_done(wc, &frwr->fr_cid);
+	frwr_mr_done(wc, mr);
 
-	/* Ensure @rep is generated before __frwr_release_mr */
+	/* Ensure @rep is generated before frwr_mr_done */
 	smp_rmb();
 	rpcrdma_complete_rqst(rep);
 
@@ -597,6 +624,7 @@ static void frwr_wc_localinv_done(struct ib_cq *cq, struct ib_wc *wc)
 void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 {
 	struct ib_send_wr *first, *last, **prev;
+	struct rpcrdma_ep *ep = r_xprt->rx_ep;
 	const struct ib_send_wr *bad_wr;
 	struct rpcrdma_frwr *frwr;
 	struct rpcrdma_mr *mr;
@@ -614,6 +642,7 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 
 		frwr = &mr->frwr;
 		frwr->fr_cqe.done = frwr_wc_localinv;
+		frwr_cid_init(ep, frwr);
 		last = &frwr->fr_invwr;
 		last->next = NULL;
 		last->wr_cqe = &frwr->fr_cqe;
@@ -639,13 +668,13 @@ void frwr_unmap_async(struct rpcrdma_xprt *r_xprt, struct rpcrdma_req *req)
 	 * unless re_id->qp is a valid pointer.
 	 */
 	bad_wr = NULL;
-	rc = ib_post_send(r_xprt->rx_ep->re_id->qp, first, &bad_wr);
+	rc = ib_post_send(ep->re_id->qp, first, &bad_wr);
 	if (!rc)
 		return;
 
 	/* Recycle MRs in the LOCAL_INV chain that did not get posted.
 	 */
-	trace_xprtrdma_post_linv(req, rc);
+	trace_xprtrdma_post_linv_err(req, rc);
 	while (bad_wr) {
 		frwr = container_of(bad_wr, struct rpcrdma_frwr, fr_invwr);
 		mr = container_of(frwr, struct rpcrdma_mr, frwr);
diff --git a/net/sunrpc/xprtrdma/module.c b/net/sunrpc/xprtrdma/module.c
index 620327c01302..45c5b41ac8dc 100644
--- a/net/sunrpc/xprtrdma/module.c
+++ b/net/sunrpc/xprtrdma/module.c
@@ -24,6 +24,7 @@ MODULE_DESCRIPTION("RPC/RDMA Transport");
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_ALIAS("svcrdma");
 MODULE_ALIAS("xprtrdma");
+MODULE_ALIAS("rpcrdma6");
 
 static void __exit rpc_rdma_cleanup(void)
 {
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index 0f5120c7668f..8f5d0cb68360 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (c) 2014-2017 Oracle.  All rights reserved.
+ * Copyright (c) 2014-2020, Oracle and/or its affiliates.
  * Copyright (c) 2003-2007 Network Appliance, Inc. All rights reserved.
  *
  * This software is available to you under a choice of one of two
@@ -179,6 +179,31 @@ rpcrdma_nonpayload_inline(const struct rpcrdma_xprt *r_xprt,
 		r_xprt->rx_ep->re_max_inline_recv;
 }
 
+/* ACL likes to be lazy in allocating pages. For TCP, these
+ * pages can be allocated during receive processing. Not true
+ * for RDMA, which must always provision receive buffers
+ * up front.
+ */
+static noinline int
+rpcrdma_alloc_sparse_pages(struct xdr_buf *buf)
+{
+	struct page **ppages;
+	int len;
+
+	len = buf->page_len;
+	ppages = buf->pages + (buf->page_base >> PAGE_SHIFT);
+	while (len > 0) {
+		if (!*ppages)
+			*ppages = alloc_page(GFP_NOWAIT | __GFP_NOWARN);
+		if (!*ppages)
+			return -ENOBUFS;
+		ppages++;
+		len -= PAGE_SIZE;
+	}
+
+	return 0;
+}
+
 /* Split @vec on page boundaries into SGEs. FMR registers pages, not
  * a byte range. Other modes coalesce these SGEs into a single MR
  * when they can.
@@ -233,15 +258,6 @@ rpcrdma_convert_iovs(struct rpcrdma_xprt *r_xprt, struct xdr_buf *xdrbuf,
 	ppages = xdrbuf->pages + (xdrbuf->page_base >> PAGE_SHIFT);
 	page_base = offset_in_page(xdrbuf->page_base);
 	while (len) {
-		/* ACL likes to be lazy in allocating pages - ACLs
-		 * are small by default but can get huge.
-		 */
-		if (unlikely(xdrbuf->flags & XDRBUF_SPARSE_PAGES)) {
-			if (!*ppages)
-				*ppages = alloc_page(GFP_NOWAIT | __GFP_NOWARN);
-			if (!*ppages)
-				return -ENOBUFS;
-		}
 		seg->mr_page = *ppages;
 		seg->mr_offset = (char *)page_base;
 		seg->mr_len = min_t(u32, PAGE_SIZE - page_base, len);
@@ -315,7 +331,6 @@ static struct rpcrdma_mr_seg *rpcrdma_mr_prepare(struct rpcrdma_xprt *r_xprt,
 		*mr = rpcrdma_mr_get(r_xprt);
 		if (!*mr)
 			goto out_getmr_err;
-		trace_xprtrdma_mr_get(req);
 		(*mr)->mr_req = req;
 	}
 
@@ -323,7 +338,7 @@ static struct rpcrdma_mr_seg *rpcrdma_mr_prepare(struct rpcrdma_xprt *r_xprt,
 	return frwr_map(r_xprt, seg, nsegs, writing, req->rl_slot.rq_xid, *mr);
 
 out_getmr_err:
-	trace_xprtrdma_nomrs(req);
+	trace_xprtrdma_nomrs_err(r_xprt, req);
 	xprt_wait_for_buffer_space(&r_xprt->rx_xprt);
 	rpcrdma_mrs_refresh(r_xprt);
 	return ERR_PTR(-EAGAIN);
@@ -867,6 +882,12 @@ rpcrdma_marshal_req(struct rpcrdma_xprt *r_xprt, struct rpc_rqst *rqst)
 	__be32 *p;
 	int ret;
 
+	if (unlikely(rqst->rq_rcv_buf.flags & XDRBUF_SPARSE_PAGES)) {
+		ret = rpcrdma_alloc_sparse_pages(&rqst->rq_rcv_buf);
+		if (ret)
+			return ret;
+	}
+
 	rpcrdma_set_xdrlen(&req->rl_hdrbuf, 0);
 	xdr_init_encode(xdr, &req->rl_hdrbuf, rdmab_data(req->rl_rdmabuf),
 			rqst);
@@ -1322,20 +1343,13 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep,
 		p = xdr_inline_decode(xdr, 2 * sizeof(*p));
 		if (!p)
 			break;
-		dprintk("RPC:       %s: server reports "
-			"version error (%u-%u), xid %08x\n", __func__,
-			be32_to_cpup(p), be32_to_cpu(*(p + 1)),
-			be32_to_cpu(rep->rr_xid));
+		trace_xprtrdma_err_vers(rqst, p, p + 1);
 		break;
 	case err_chunk:
-		dprintk("RPC:       %s: server reports "
-			"header decoding error, xid %08x\n", __func__,
-			be32_to_cpu(rep->rr_xid));
+		trace_xprtrdma_err_chunk(rqst);
 		break;
 	default:
-		dprintk("RPC:       %s: server reports "
-			"unrecognized error %d, xid %08x\n", __func__,
-			be32_to_cpup(p), be32_to_cpu(rep->rr_xid));
+		trace_xprtrdma_err_unrecognized(rqst, p);
 	}
 
 	return -EIO;
@@ -1376,7 +1390,7 @@ out:
 	return;
 
 out_badheader:
-	trace_xprtrdma_reply_hdr(rep);
+	trace_xprtrdma_reply_hdr_err(rep);
 	r_xprt->rx_stats.bad_reply_count++;
 	rqst->rq_task->tk_status = status;
 	status = 0;
@@ -1450,14 +1464,12 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	rpcrdma_post_recvs(r_xprt, false);
 
 	req = rpcr_to_rdmar(rqst);
-	if (req->rl_reply) {
-		trace_xprtrdma_leaked_rep(rqst, req->rl_reply);
+	if (unlikely(req->rl_reply))
 		rpcrdma_recv_buffer_put(req->rl_reply);
-	}
 	req->rl_reply = rep;
 	rep->rr_rqst = rqst;
 
-	trace_xprtrdma_reply(rqst->rq_task, rep, req, credits);
+	trace_xprtrdma_reply(rqst->rq_task, rep, credits);
 
 	if (rep->rr_wc_flags & IB_WC_WITH_INVALIDATE)
 		frwr_reminv(rep, &req->rl_registered);
@@ -1469,16 +1481,16 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep)
 	return;
 
 out_badversion:
-	trace_xprtrdma_reply_vers(rep);
+	trace_xprtrdma_reply_vers_err(rep);
 	goto out;
 
 out_norqst:
 	spin_unlock(&xprt->queue_lock);
-	trace_xprtrdma_reply_rqst(rep);
+	trace_xprtrdma_reply_rqst_err(rep);
 	goto out;
 
 out_shortreply:
-	trace_xprtrdma_reply_short(rep);
+	trace_xprtrdma_reply_short_err(rep);
 
 out:
 	rpcrdma_recv_buffer_put(rep);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index 5e7c4ba9e147..63f8be974df2 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -74,11 +74,17 @@ out_unlock:
  */
 static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 			      struct rpc_rqst *rqst,
-			      struct svc_rdma_send_ctxt *ctxt)
+			      struct svc_rdma_send_ctxt *sctxt)
 {
+	struct svc_rdma_recv_ctxt *rctxt;
 	int ret;
 
-	ret = svc_rdma_map_reply_msg(rdma, ctxt, NULL, &rqst->rq_snd_buf);
+	rctxt = svc_rdma_recv_ctxt_get(rdma);
+	if (!rctxt)
+		return -EIO;
+
+	ret = svc_rdma_map_reply_msg(rdma, sctxt, rctxt, &rqst->rq_snd_buf);
+	svc_rdma_recv_ctxt_put(rdma, rctxt);
 	if (ret < 0)
 		return -EIO;
 
@@ -86,8 +92,8 @@ static int svc_rdma_bc_sendto(struct svcxprt_rdma *rdma,
 	 * the rq_buffer before all retransmits are complete.
 	 */
 	get_page(virt_to_page(rqst->rq_buffer));
-	ctxt->sc_send_wr.opcode = IB_WR_SEND;
-	return svc_rdma_send(rdma, ctxt);
+	sctxt->sc_send_wr.opcode = IB_WR_SEND;
+	return svc_rdma_send(rdma, sctxt);
 }
 
 /* Server-side transport endpoint wants a whole page for its send
diff --git a/net/sunrpc/xprtrdma/svc_rdma_pcl.c b/net/sunrpc/xprtrdma/svc_rdma_pcl.c
new file mode 100644
index 000000000000..b63cfeaa2923
--- /dev/null
+++ b/net/sunrpc/xprtrdma/svc_rdma_pcl.c
@@ -0,0 +1,306 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020 Oracle. All rights reserved.
+ */
+
+#include <linux/sunrpc/svc_rdma.h>
+#include <linux/sunrpc/rpc_rdma.h>
+
+#include "xprt_rdma.h"
+#include <trace/events/rpcrdma.h>
+
+/**
+ * pcl_free - Release all memory associated with a parsed chunk list
+ * @pcl: parsed chunk list
+ *
+ */
+void pcl_free(struct svc_rdma_pcl *pcl)
+{
+	while (!list_empty(&pcl->cl_chunks)) {
+		struct svc_rdma_chunk *chunk;
+
+		chunk = pcl_first_chunk(pcl);
+		list_del(&chunk->ch_list);
+		kfree(chunk);
+	}
+}
+
+static struct svc_rdma_chunk *pcl_alloc_chunk(u32 segcount, u32 position)
+{
+	struct svc_rdma_chunk *chunk;
+
+	chunk = kmalloc(struct_size(chunk, ch_segments, segcount), GFP_KERNEL);
+	if (!chunk)
+		return NULL;
+
+	chunk->ch_position = position;
+	chunk->ch_length = 0;
+	chunk->ch_payload_length = 0;
+	chunk->ch_segcount = 0;
+	return chunk;
+}
+
+static struct svc_rdma_chunk *
+pcl_lookup_position(struct svc_rdma_pcl *pcl, u32 position)
+{
+	struct svc_rdma_chunk *pos;
+
+	pcl_for_each_chunk(pos, pcl) {
+		if (pos->ch_position == position)
+			return pos;
+	}
+	return NULL;
+}
+
+static void pcl_insert_position(struct svc_rdma_pcl *pcl,
+				struct svc_rdma_chunk *chunk)
+{
+	struct svc_rdma_chunk *pos;
+
+	pcl_for_each_chunk(pos, pcl) {
+		if (pos->ch_position > chunk->ch_position)
+			break;
+	}
+	__list_add(&chunk->ch_list, pos->ch_list.prev, &pos->ch_list);
+	pcl->cl_count++;
+}
+
+static void pcl_set_read_segment(const struct svc_rdma_recv_ctxt *rctxt,
+				 struct svc_rdma_chunk *chunk,
+				 u32 handle, u32 length, u64 offset)
+{
+	struct svc_rdma_segment *segment;
+
+	segment = &chunk->ch_segments[chunk->ch_segcount];
+	segment->rs_handle = handle;
+	segment->rs_length = length;
+	segment->rs_offset = offset;
+
+	trace_svcrdma_decode_rseg(&rctxt->rc_cid, chunk, segment);
+
+	chunk->ch_length += length;
+	chunk->ch_segcount++;
+}
+
+/**
+ * pcl_alloc_call - Construct a parsed chunk list for the Call body
+ * @rctxt: Ingress receive context
+ * @p: Start of an un-decoded Read list
+ *
+ * Assumptions:
+ * - The incoming Read list has already been sanity checked.
+ * - cl_count is already set to the number of segments in
+ *   the un-decoded list.
+ * - The list might not be in order by position.
+ *
+ * Return values:
+ *       %true: Parsed chunk list was successfully constructed, and
+ *              cl_count is updated to be the number of chunks (ie.
+ *              unique positions) in the Read list.
+ *      %false: Memory allocation failed.
+ */
+bool pcl_alloc_call(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
+{
+	struct svc_rdma_pcl *pcl = &rctxt->rc_call_pcl;
+	unsigned int i, segcount = pcl->cl_count;
+
+	pcl->cl_count = 0;
+	for (i = 0; i < segcount; i++) {
+		struct svc_rdma_chunk *chunk;
+		u32 position, handle, length;
+		u64 offset;
+
+		p++;	/* skip the list discriminator */
+		p = xdr_decode_read_segment(p, &position, &handle,
+					    &length, &offset);
+		if (position != 0)
+			continue;
+
+		if (pcl_is_empty(pcl)) {
+			chunk = pcl_alloc_chunk(segcount, position);
+			if (!chunk)
+				return false;
+			pcl_insert_position(pcl, chunk);
+		} else {
+			chunk = list_first_entry(&pcl->cl_chunks,
+						 struct svc_rdma_chunk,
+						 ch_list);
+		}
+
+		pcl_set_read_segment(rctxt, chunk, handle, length, offset);
+	}
+
+	return true;
+}
+
+/**
+ * pcl_alloc_read - Construct a parsed chunk list for normal Read chunks
+ * @rctxt: Ingress receive context
+ * @p: Start of an un-decoded Read list
+ *
+ * Assumptions:
+ * - The incoming Read list has already been sanity checked.
+ * - cl_count is already set to the number of segments in
+ *   the un-decoded list.
+ * - The list might not be in order by position.
+ *
+ * Return values:
+ *       %true: Parsed chunk list was successfully constructed, and
+ *              cl_count is updated to be the number of chunks (ie.
+ *              unique position values) in the Read list.
+ *      %false: Memory allocation failed.
+ *
+ * TODO:
+ * - Check for chunk range overlaps
+ */
+bool pcl_alloc_read(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
+{
+	struct svc_rdma_pcl *pcl = &rctxt->rc_read_pcl;
+	unsigned int i, segcount = pcl->cl_count;
+
+	pcl->cl_count = 0;
+	for (i = 0; i < segcount; i++) {
+		struct svc_rdma_chunk *chunk;
+		u32 position, handle, length;
+		u64 offset;
+
+		p++;	/* skip the list discriminator */
+		p = xdr_decode_read_segment(p, &position, &handle,
+					    &length, &offset);
+		if (position == 0)
+			continue;
+
+		chunk = pcl_lookup_position(pcl, position);
+		if (!chunk) {
+			chunk = pcl_alloc_chunk(segcount, position);
+			if (!chunk)
+				return false;
+			pcl_insert_position(pcl, chunk);
+		}
+
+		pcl_set_read_segment(rctxt, chunk, handle, length, offset);
+	}
+
+	return true;
+}
+
+/**
+ * pcl_alloc_write - Construct a parsed chunk list from a Write list
+ * @rctxt: Ingress receive context
+ * @pcl: Parsed chunk list to populate
+ * @p: Start of an un-decoded Write list
+ *
+ * Assumptions:
+ * - The incoming Write list has already been sanity checked, and
+ * - cl_count is set to the number of chunks in the un-decoded list.
+ *
+ * Return values:
+ *       %true: Parsed chunk list was successfully constructed.
+ *      %false: Memory allocation failed.
+ */
+bool pcl_alloc_write(struct svc_rdma_recv_ctxt *rctxt,
+		     struct svc_rdma_pcl *pcl, __be32 *p)
+{
+	struct svc_rdma_segment *segment;
+	struct svc_rdma_chunk *chunk;
+	unsigned int i, j;
+	u32 segcount;
+
+	for (i = 0; i < pcl->cl_count; i++) {
+		p++;	/* skip the list discriminator */
+		segcount = be32_to_cpup(p++);
+
+		chunk = pcl_alloc_chunk(segcount, 0);
+		if (!chunk)
+			return false;
+		list_add_tail(&chunk->ch_list, &pcl->cl_chunks);
+
+		for (j = 0; j < segcount; j++) {
+			segment = &chunk->ch_segments[j];
+			p = xdr_decode_rdma_segment(p, &segment->rs_handle,
+						    &segment->rs_length,
+						    &segment->rs_offset);
+			trace_svcrdma_decode_wseg(&rctxt->rc_cid, chunk, j);
+
+			chunk->ch_length += segment->rs_length;
+			chunk->ch_segcount++;
+		}
+	}
+	return true;
+}
+
+static int pcl_process_region(const struct xdr_buf *xdr,
+			      unsigned int offset, unsigned int length,
+			      int (*actor)(const struct xdr_buf *, void *),
+			      void *data)
+{
+	struct xdr_buf subbuf;
+
+	if (!length)
+		return 0;
+	if (xdr_buf_subsegment(xdr, &subbuf, offset, length))
+		return -EMSGSIZE;
+	return actor(&subbuf, data);
+}
+
+/**
+ * pcl_process_nonpayloads - Process non-payload regions inside @xdr
+ * @pcl: Chunk list to process
+ * @xdr: xdr_buf to process
+ * @actor: Function to invoke on each non-payload region
+ * @data: Arguments for @actor
+ *
+ * This mechanism must ignore not only result payloads that were already
+ * sent via RDMA Write, but also XDR padding for those payloads that
+ * the upper layer has added.
+ *
+ * Assumptions:
+ *  The xdr->len and ch_position fields are aligned to 4-byte multiples.
+ *
+ * Returns:
+ *   On success, zero,
+ *   %-EMSGSIZE on XDR buffer overflow, or
+ *   The return value of @actor
+ */
+int pcl_process_nonpayloads(const struct svc_rdma_pcl *pcl,
+			    const struct xdr_buf *xdr,
+			    int (*actor)(const struct xdr_buf *, void *),
+			    void *data)
+{
+	struct svc_rdma_chunk *chunk, *next;
+	unsigned int start;
+	int ret;
+
+	chunk = pcl_first_chunk(pcl);
+
+	/* No result payloads were generated */
+	if (!chunk || !chunk->ch_payload_length)
+		return actor(xdr, data);
+
+	/* Process the region before the first result payload */
+	ret = pcl_process_region(xdr, 0, chunk->ch_position, actor, data);
+	if (ret < 0)
+		return ret;
+
+	/* Process the regions between each middle result payload */
+	while ((next = pcl_next_chunk(pcl, chunk))) {
+		if (!next->ch_payload_length)
+			break;
+
+		start = pcl_chunk_end_offset(chunk);
+		ret = pcl_process_region(xdr, start, next->ch_position - start,
+					 actor, data);
+		if (ret < 0)
+			return ret;
+
+		chunk = next;
+	}
+
+	/* Process the region after the last result payload */
+	start = pcl_chunk_end_offset(chunk);
+	ret = pcl_process_region(xdr, start, xdr->len - start, actor, data);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
index c6ea2903c21a..cbdb71247755 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c
@@ -93,6 +93,7 @@
  * (see rdma_read_complete() below).
  */
 
+#include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <asm/unaligned.h>
 #include <rdma/ib_verbs.h>
@@ -143,6 +144,10 @@ svc_rdma_recv_ctxt_alloc(struct svcxprt_rdma *rdma)
 		goto fail2;
 
 	svc_rdma_recv_cid_init(rdma, &ctxt->rc_cid);
+	pcl_init(&ctxt->rc_call_pcl);
+	pcl_init(&ctxt->rc_read_pcl);
+	pcl_init(&ctxt->rc_write_pcl);
+	pcl_init(&ctxt->rc_reply_pcl);
 
 	ctxt->rc_recv_wr.next = NULL;
 	ctxt->rc_recv_wr.wr_cqe = &ctxt->rc_cqe;
@@ -189,8 +194,13 @@ void svc_rdma_recv_ctxts_destroy(struct svcxprt_rdma *rdma)
 	}
 }
 
-static struct svc_rdma_recv_ctxt *
-svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
+/**
+ * svc_rdma_recv_ctxt_get - Allocate a recv_ctxt
+ * @rdma: controlling svcxprt_rdma
+ *
+ * Returns a recv_ctxt or (rarely) NULL if none are available.
+ */
+struct svc_rdma_recv_ctxt *svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 {
 	struct svc_rdma_recv_ctxt *ctxt;
 	struct llist_node *node;
@@ -202,7 +212,6 @@ svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma)
 
 out:
 	ctxt->rc_page_count = 0;
-	ctxt->rc_read_payload_length = 0;
 	return ctxt;
 
 out_empty:
@@ -226,6 +235,11 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma,
 	for (i = 0; i < ctxt->rc_page_count; i++)
 		put_page(ctxt->rc_pages[i]);
 
+	pcl_free(&ctxt->rc_call_pcl);
+	pcl_free(&ctxt->rc_read_pcl);
+	pcl_free(&ctxt->rc_write_pcl);
+	pcl_free(&ctxt->rc_reply_pcl);
+
 	if (!ctxt->rc_temp)
 		llist_add(&ctxt->rc_node, &rdma->sc_recv_ctxts);
 	else
@@ -385,100 +399,123 @@ static void svc_rdma_build_arg_xdr(struct svc_rqst *rqstp,
 	arg->len = ctxt->rc_byte_len;
 }
 
-/* This accommodates the largest possible Write chunk.
- */
-#define MAX_BYTES_WRITE_CHUNK ((u32)(RPCSVC_MAXPAGES << PAGE_SHIFT))
-
-/* This accommodates the largest possible Position-Zero
- * Read chunk or Reply chunk.
- */
-#define MAX_BYTES_SPECIAL_CHUNK ((u32)((RPCSVC_MAXPAGES + 2) << PAGE_SHIFT))
-
-/* Sanity check the Read list.
- *
- * Implementation limits:
- * - This implementation supports only one Read chunk.
+/**
+ * xdr_count_read_segments - Count number of Read segments in Read list
+ * @rctxt: Ingress receive context
+ * @p: Start of an un-decoded Read list
  *
- * Sanity checks:
- * - Read list does not overflow Receive buffer.
- * - Segment size limited by largest NFS data payload.
+ * Before allocating anything, ensure the ingress Read list is safe
+ * to use.
  *
- * The segment count is limited to how many segments can
- * fit in the transport header without overflowing the
- * buffer. That's about 40 Read segments for a 1KB inline
- * threshold.
+ * The segment count is limited to how many segments can fit in the
+ * transport header without overflowing the buffer. That's about 40
+ * Read segments for a 1KB inline threshold.
  *
  * Return values:
- *       %true: Read list is valid. @rctxt's xdr_stream is updated
- *		to point to the first byte past the Read list.
- *      %false: Read list is corrupt. @rctxt's xdr_stream is left
- *		in an unknown state.
+ *   %true: Read list is valid. @rctxt's xdr_stream is updated to point
+ *	    to the first byte past the Read list. rc_read_pcl and
+ *	    rc_call_pcl cl_count fields are set to the number of
+ *	    Read segments in the list.
+ *  %false: Read list is corrupt. @rctxt's xdr_stream is left in an
+ *	    unknown state.
  */
-static bool xdr_check_read_list(struct svc_rdma_recv_ctxt *rctxt)
+static bool xdr_count_read_segments(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
 {
-	u32 position, len;
-	bool first;
-	__be32 *p;
-
-	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
-	if (!p)
-		return false;
-
-	len = 0;
-	first = true;
+	rctxt->rc_call_pcl.cl_count = 0;
+	rctxt->rc_read_pcl.cl_count = 0;
 	while (xdr_item_is_present(p)) {
+		u32 position, handle, length;
+		u64 offset;
+
 		p = xdr_inline_decode(&rctxt->rc_stream,
 				      rpcrdma_readseg_maxsz * sizeof(*p));
 		if (!p)
 			return false;
 
-		if (first) {
-			position = be32_to_cpup(p);
-			first = false;
-		} else if (be32_to_cpup(p) != position) {
-			return false;
+		xdr_decode_read_segment(p, &position, &handle,
+					    &length, &offset);
+		if (position) {
+			if (position & 3)
+				return false;
+			++rctxt->rc_read_pcl.cl_count;
+		} else {
+			++rctxt->rc_call_pcl.cl_count;
 		}
-		p += 2;
-		len += be32_to_cpup(p);
 
 		p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 		if (!p)
 			return false;
 	}
-	return len <= MAX_BYTES_SPECIAL_CHUNK;
+	return true;
 }
 
-/* The segment count is limited to how many segments can
- * fit in the transport header without overflowing the
- * buffer. That's about 60 Write segments for a 1KB inline
- * threshold.
+/* Sanity check the Read list.
+ *
+ * Sanity checks:
+ * - Read list does not overflow Receive buffer.
+ * - Chunk size limited by largest NFS data payload.
+ *
+ * Return values:
+ *   %true: Read list is valid. @rctxt's xdr_stream is updated
+ *	    to point to the first byte past the Read list.
+ *  %false: Read list is corrupt. @rctxt's xdr_stream is left
+ *	    in an unknown state.
  */
-static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt, u32 maxlen)
+static bool xdr_check_read_list(struct svc_rdma_recv_ctxt *rctxt)
 {
-	u32 i, segcount, total;
 	__be32 *p;
 
 	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 	if (!p)
 		return false;
-	segcount = be32_to_cpup(p);
+	if (!xdr_count_read_segments(rctxt, p))
+		return false;
+	if (!pcl_alloc_call(rctxt, p))
+		return false;
+	return pcl_alloc_read(rctxt, p);
+}
 
-	total = 0;
-	for (i = 0; i < segcount; i++) {
-		u32 handle, length;
-		u64 offset;
+static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt)
+{
+	u32 segcount;
+	__be32 *p;
 
-		p = xdr_inline_decode(&rctxt->rc_stream,
-				      rpcrdma_segment_maxsz * sizeof(*p));
-		if (!p)
-			return false;
+	if (xdr_stream_decode_u32(&rctxt->rc_stream, &segcount))
+		return false;
 
-		xdr_decode_rdma_segment(p, &handle, &length, &offset);
-		trace_svcrdma_decode_wseg(handle, length, offset);
+	/* A bogus segcount causes this buffer overflow check to fail. */
+	p = xdr_inline_decode(&rctxt->rc_stream,
+			      segcount * rpcrdma_segment_maxsz * sizeof(*p));
+	return p != NULL;
+}
 
-		total += length;
+/**
+ * xdr_count_write_chunks - Count number of Write chunks in Write list
+ * @rctxt: Received header and decoding state
+ * @p: start of an un-decoded Write list
+ *
+ * Before allocating anything, ensure the ingress Write list is
+ * safe to use.
+ *
+ * Return values:
+ *       %true: Write list is valid. @rctxt's xdr_stream is updated
+ *		to point to the first byte past the Write list, and
+ *		the number of Write chunks is in rc_write_pcl.cl_count.
+ *      %false: Write list is corrupt. @rctxt's xdr_stream is left
+ *		in an indeterminate state.
+ */
+static bool xdr_count_write_chunks(struct svc_rdma_recv_ctxt *rctxt, __be32 *p)
+{
+	rctxt->rc_write_pcl.cl_count = 0;
+	while (xdr_item_is_present(p)) {
+		if (!xdr_check_write_chunk(rctxt))
+			return false;
+		++rctxt->rc_write_pcl.cl_count;
+		p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
+		if (!p)
+			return false;
 	}
-	return total <= maxlen;
+	return true;
 }
 
 /* Sanity check the Write list.
@@ -498,24 +535,18 @@ static bool xdr_check_write_chunk(struct svc_rdma_recv_ctxt *rctxt, u32 maxlen)
  */
 static bool xdr_check_write_list(struct svc_rdma_recv_ctxt *rctxt)
 {
-	u32 chcount = 0;
 	__be32 *p;
 
 	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 	if (!p)
 		return false;
-	rctxt->rc_write_list = p;
-	while (xdr_item_is_present(p)) {
-		if (!xdr_check_write_chunk(rctxt, MAX_BYTES_WRITE_CHUNK))
-			return false;
-		++chcount;
-		p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
-		if (!p)
-			return false;
-	}
-	if (!chcount)
-		rctxt->rc_write_list = NULL;
-	return chcount < 2;
+	if (!xdr_count_write_chunks(rctxt, p))
+		return false;
+	if (!pcl_alloc_write(rctxt, &rctxt->rc_write_pcl, p))
+		return false;
+
+	rctxt->rc_cur_result_payload = pcl_first_chunk(&rctxt->rc_write_pcl);
+	return true;
 }
 
 /* Sanity check the Reply chunk.
@@ -537,13 +568,14 @@ static bool xdr_check_reply_chunk(struct svc_rdma_recv_ctxt *rctxt)
 	p = xdr_inline_decode(&rctxt->rc_stream, sizeof(*p));
 	if (!p)
 		return false;
-	rctxt->rc_reply_chunk = NULL;
-	if (xdr_item_is_present(p)) {
-		if (!xdr_check_write_chunk(rctxt, MAX_BYTES_SPECIAL_CHUNK))
-			return false;
-		rctxt->rc_reply_chunk = p;
-	}
-	return true;
+
+	if (!xdr_item_is_present(p))
+		return true;
+	if (!xdr_check_write_chunk(rctxt))
+		return false;
+
+	rctxt->rc_reply_pcl.cl_count = 1;
+	return pcl_alloc_write(rctxt, &rctxt->rc_reply_pcl, p);
 }
 
 /* RPC-over-RDMA Version One private extension: Remote Invalidation.
@@ -552,60 +584,53 @@ static bool xdr_check_reply_chunk(struct svc_rdma_recv_ctxt *rctxt)
  *
  * If there is exactly one distinct R_key in the received transport
  * header, set rc_inv_rkey to that R_key. Otherwise, set it to zero.
- *
- * Perform this operation while the received transport header is
- * still in the CPU cache.
  */
 static void svc_rdma_get_inv_rkey(struct svcxprt_rdma *rdma,
 				  struct svc_rdma_recv_ctxt *ctxt)
 {
-	__be32 inv_rkey, *p;
-	u32 i, segcount;
+	struct svc_rdma_segment *segment;
+	struct svc_rdma_chunk *chunk;
+	u32 inv_rkey;
 
 	ctxt->rc_inv_rkey = 0;
 
 	if (!rdma->sc_snd_w_inv)
 		return;
 
-	inv_rkey = xdr_zero;
-	p = ctxt->rc_recv_buf;
-	p += rpcrdma_fixed_maxsz;
-
-	/* Read list */
-	while (xdr_item_is_present(p++)) {
-		p++;	/* position */
-		if (inv_rkey == xdr_zero)
-			inv_rkey = *p;
-		else if (inv_rkey != *p)
-			return;
-		p += 4;
+	inv_rkey = 0;
+	pcl_for_each_chunk(chunk, &ctxt->rc_call_pcl) {
+		pcl_for_each_segment(segment, chunk) {
+			if (inv_rkey == 0)
+				inv_rkey = segment->rs_handle;
+			else if (inv_rkey != segment->rs_handle)
+				return;
+		}
 	}
-
-	/* Write list */
-	while (xdr_item_is_present(p++)) {
-		segcount = be32_to_cpup(p++);
-		for (i = 0; i < segcount; i++) {
-			if (inv_rkey == xdr_zero)
-				inv_rkey = *p;
-			else if (inv_rkey != *p)
+	pcl_for_each_chunk(chunk, &ctxt->rc_read_pcl) {
+		pcl_for_each_segment(segment, chunk) {
+			if (inv_rkey == 0)
+				inv_rkey = segment->rs_handle;
+			else if (inv_rkey != segment->rs_handle)
 				return;
-			p += 4;
 		}
 	}
-
-	/* Reply chunk */
-	if (xdr_item_is_present(p++)) {
-		segcount = be32_to_cpup(p++);
-		for (i = 0; i < segcount; i++) {
-			if (inv_rkey == xdr_zero)
-				inv_rkey = *p;
-			else if (inv_rkey != *p)
+	pcl_for_each_chunk(chunk, &ctxt->rc_write_pcl) {
+		pcl_for_each_segment(segment, chunk) {
+			if (inv_rkey == 0)
+				inv_rkey = segment->rs_handle;
+			else if (inv_rkey != segment->rs_handle)
 				return;
-			p += 4;
 		}
 	}
-
-	ctxt->rc_inv_rkey = be32_to_cpu(inv_rkey);
+	pcl_for_each_chunk(chunk, &ctxt->rc_reply_pcl) {
+		pcl_for_each_segment(segment, chunk) {
+			if (inv_rkey == 0)
+				inv_rkey = segment->rs_handle;
+			else if (inv_rkey != segment->rs_handle)
+				return;
+		}
+	}
+	ctxt->rc_inv_rkey = inv_rkey;
 }
 
 /**
@@ -641,7 +666,8 @@ static int svc_rdma_xdr_decode_req(struct xdr_buf *rq_arg,
 	if (*p != rpcrdma_version)
 		goto out_version;
 	p += 2;
-	switch (*p) {
+	rctxt->rc_msgtype = *p;
+	switch (rctxt->rc_msgtype) {
 	case rdma_msg:
 		break;
 	case rdma_nomsg:
@@ -735,30 +761,28 @@ static void svc_rdma_send_error(struct svcxprt_rdma *rdma,
  * the RPC/RDMA header small and fixed in size, so it is
  * straightforward to check the RPC header's direction field.
  */
-static bool svc_rdma_is_backchannel_reply(struct svc_xprt *xprt,
-					  __be32 *rdma_resp)
+static bool svc_rdma_is_reverse_direction_reply(struct svc_xprt *xprt,
+						struct svc_rdma_recv_ctxt *rctxt)
 {
-	__be32 *p;
+	__be32 *p = rctxt->rc_recv_buf;
 
 	if (!xprt->xpt_bc_xprt)
 		return false;
 
-	p = rdma_resp + 3;
-	if (*p++ != rdma_msg)
+	if (rctxt->rc_msgtype != rdma_msg)
 		return false;
 
-	if (*p++ != xdr_zero)
+	if (!pcl_is_empty(&rctxt->rc_call_pcl))
 		return false;
-	if (*p++ != xdr_zero)
+	if (!pcl_is_empty(&rctxt->rc_read_pcl))
 		return false;
-	if (*p++ != xdr_zero)
+	if (!pcl_is_empty(&rctxt->rc_write_pcl))
 		return false;
-
-	/* XID sanity */
-	if (*p++ != *rdma_resp)
+	if (!pcl_is_empty(&rctxt->rc_reply_pcl))
 		return false;
-	/* call direction */
-	if (*p == cpu_to_be32(RPC_CALL))
+
+	/* RPC call direction */
+	if (*(p + 8) == cpu_to_be32(RPC_CALL))
 		return false;
 
 	return true;
@@ -800,7 +824,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	struct svcxprt_rdma *rdma_xprt =
 		container_of(xprt, struct svcxprt_rdma, sc_xprt);
 	struct svc_rdma_recv_ctxt *ctxt;
-	__be32 *p;
 	int ret;
 
 	rqstp->rq_xprt_ctxt = NULL;
@@ -833,7 +856,6 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 	rqstp->rq_respages = rqstp->rq_pages;
 	rqstp->rq_next_page = rqstp->rq_respages;
 
-	p = (__be32 *)rqstp->rq_arg.head[0].iov_base;
 	ret = svc_rdma_xdr_decode_req(&rqstp->rq_arg, ctxt);
 	if (ret < 0)
 		goto out_err;
@@ -841,14 +863,14 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp)
 		goto out_drop;
 	rqstp->rq_xprt_hlen = ret;
 
-	if (svc_rdma_is_backchannel_reply(xprt, p))
+	if (svc_rdma_is_reverse_direction_reply(xprt, ctxt))
 		goto out_backchannel;
 
 	svc_rdma_get_inv_rkey(rdma_xprt, ctxt);
 
-	p += rpcrdma_fixed_maxsz;
-	if (*p != xdr_zero)
-		goto out_readchunk;
+	if (!pcl_is_empty(&ctxt->rc_read_pcl) ||
+	    !pcl_is_empty(&ctxt->rc_call_pcl))
+		goto out_readlist;
 
 complete:
 	rqstp->rq_xprt_ctxt = ctxt;
@@ -856,10 +878,10 @@ complete:
 	svc_xprt_copy_addrs(rqstp, xprt);
 	return rqstp->rq_arg.len;
 
-out_readchunk:
-	ret = svc_rdma_recv_read_chunk(rdma_xprt, rqstp, ctxt, p);
+out_readlist:
+	ret = svc_rdma_process_read_list(rdma_xprt, rqstp, ctxt);
 	if (ret < 0)
-		goto out_postfail;
+		goto out_readfail;
 	return 0;
 
 out_err:
@@ -867,7 +889,7 @@ out_err:
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
 	return 0;
 
-out_postfail:
+out_readfail:
 	if (ret == -EINVAL)
 		svc_rdma_send_error(rdma_xprt, ctxt, ret);
 	svc_rdma_recv_ctxt_put(rdma_xprt, ctxt);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c
index fe54cbe97a46..0b63e1321d74 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_rw.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c
@@ -137,7 +137,7 @@ static int svc_rdma_rw_ctx_init(struct svcxprt_rdma *rdma,
 }
 
 /* A chunk context tracks all I/O for moving one Read or Write
- * chunk. This is a a set of rdma_rw's that handle data movement
+ * chunk. This is a set of rdma_rw's that handle data movement
  * for all segments of one chunk.
  *
  * These are small, acquired with a single allocator call, and
@@ -190,14 +190,14 @@ static void svc_rdma_cc_release(struct svc_rdma_chunk_ctxt *cc,
  *  - Stores arguments for the SGL constructor functions
  */
 struct svc_rdma_write_info {
+	const struct svc_rdma_chunk	*wi_chunk;
+
 	/* write state of this chunk */
 	unsigned int		wi_seg_off;
 	unsigned int		wi_seg_no;
-	unsigned int		wi_nsegs;
-	__be32			*wi_segs;
 
 	/* SGL constructor arguments */
-	struct xdr_buf		*wi_xdr;
+	const struct xdr_buf	*wi_xdr;
 	unsigned char		*wi_base;
 	unsigned int		wi_next_off;
 
@@ -205,7 +205,8 @@ struct svc_rdma_write_info {
 };
 
 static struct svc_rdma_write_info *
-svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk)
+svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma,
+			  const struct svc_rdma_chunk *chunk)
 {
 	struct svc_rdma_write_info *info;
 
@@ -213,10 +214,9 @@ svc_rdma_write_info_alloc(struct svcxprt_rdma *rdma, __be32 *chunk)
 	if (!info)
 		return info;
 
+	info->wi_chunk = chunk;
 	info->wi_seg_off = 0;
 	info->wi_seg_no = 0;
-	info->wi_nsegs = be32_to_cpup(++chunk);
-	info->wi_segs = ++chunk;
 	svc_rdma_cc_init(rdma, &info->wi_cc);
 	info->wi_cc.cc_cqe.done = svc_rdma_write_done;
 	return info;
@@ -258,11 +258,11 @@ static void svc_rdma_write_done(struct ib_cq *cq, struct ib_wc *wc)
 /* State for pulling a Read chunk.
  */
 struct svc_rdma_read_info {
+	struct svc_rqst			*ri_rqst;
 	struct svc_rdma_recv_ctxt	*ri_readctxt;
-	unsigned int			ri_position;
 	unsigned int			ri_pageno;
 	unsigned int			ri_pageoff;
-	unsigned int			ri_chunklen;
+	unsigned int			ri_totalbytes;
 
 	struct svc_rdma_chunk_ctxt	ri_cc;
 };
@@ -358,7 +358,6 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc)
 	do {
 		if (atomic_sub_return(cc->cc_sqecount,
 				      &rdma->sc_sq_avail) > 0) {
-			trace_svcrdma_post_chunk(&cc->cc_cid, cc->cc_sqecount);
 			ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr);
 			if (ret)
 				break;
@@ -405,7 +404,7 @@ static void svc_rdma_pagelist_to_sg(struct svc_rdma_write_info *info,
 				    struct svc_rdma_rw_ctxt *ctxt)
 {
 	unsigned int sge_no, sge_bytes, page_off, page_no;
-	struct xdr_buf *xdr = info->wi_xdr;
+	const struct xdr_buf *xdr = info->wi_xdr;
 	struct scatterlist *sg;
 	struct page **page;
 
@@ -443,40 +442,36 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 {
 	struct svc_rdma_chunk_ctxt *cc = &info->wi_cc;
 	struct svcxprt_rdma *rdma = cc->cc_rdma;
+	const struct svc_rdma_segment *seg;
 	struct svc_rdma_rw_ctxt *ctxt;
-	__be32 *seg;
 	int ret;
 
-	seg = info->wi_segs + info->wi_seg_no * rpcrdma_segment_maxsz;
 	do {
 		unsigned int write_len;
-		u32 handle, length;
 		u64 offset;
 
-		if (info->wi_seg_no >= info->wi_nsegs)
+		seg = &info->wi_chunk->ch_segments[info->wi_seg_no];
+		if (!seg)
 			goto out_overflow;
 
-		xdr_decode_rdma_segment(seg, &handle, &length, &offset);
-		offset += info->wi_seg_off;
-
-		write_len = min(remaining, length - info->wi_seg_off);
+		write_len = min(remaining, seg->rs_length - info->wi_seg_off);
+		if (!write_len)
+			goto out_overflow;
 		ctxt = svc_rdma_get_rw_ctxt(rdma,
 					    (write_len >> PAGE_SHIFT) + 2);
 		if (!ctxt)
 			return -ENOMEM;
 
 		constructor(info, write_len, ctxt);
-		ret = svc_rdma_rw_ctx_init(rdma, ctxt, offset, handle,
+		offset = seg->rs_offset + info->wi_seg_off;
+		ret = svc_rdma_rw_ctx_init(rdma, ctxt, offset, seg->rs_handle,
 					   DMA_TO_DEVICE);
 		if (ret < 0)
 			return -EIO;
 
-		trace_svcrdma_send_wseg(handle, write_len, offset);
-
 		list_add(&ctxt->rw_list, &cc->cc_rwctxts);
 		cc->cc_sqecount += ret;
-		if (write_len == length - info->wi_seg_off) {
-			seg += 4;
+		if (write_len == seg->rs_length - info->wi_seg_off) {
 			info->wi_seg_no++;
 			info->wi_seg_off = 0;
 		} else {
@@ -489,31 +484,46 @@ svc_rdma_build_writes(struct svc_rdma_write_info *info,
 
 out_overflow:
 	trace_svcrdma_small_wrch_err(rdma, remaining, info->wi_seg_no,
-				     info->wi_nsegs);
+				     info->wi_chunk->ch_segcount);
 	return -E2BIG;
 }
 
-/* Send one of an xdr_buf's kvecs by itself. To send a Reply
- * chunk, the whole RPC Reply is written back to the client.
- * This function writes either the head or tail of the xdr_buf
- * containing the Reply.
+/**
+ * svc_rdma_iov_write - Construct RDMA Writes from an iov
+ * @info: pointer to write arguments
+ * @iov: kvec to write
+ *
+ * Returns:
+ *   On succes, returns zero
+ *   %-E2BIG if the client-provided Write chunk is too small
+ *   %-ENOMEM if a resource has been exhausted
+ *   %-EIO if an rdma-rw error occurred
  */
-static int svc_rdma_send_xdr_kvec(struct svc_rdma_write_info *info,
-				  struct kvec *vec)
+static int svc_rdma_iov_write(struct svc_rdma_write_info *info,
+			      const struct kvec *iov)
 {
-	info->wi_base = vec->iov_base;
+	info->wi_base = iov->iov_base;
 	return svc_rdma_build_writes(info, svc_rdma_vec_to_sg,
-				     vec->iov_len);
+				     iov->iov_len);
 }
 
-/* Send an xdr_buf's page list by itself. A Write chunk is just
- * the page list. A Reply chunk is @xdr's head, page list, and
- * tail. This function is shared between the two types of chunk.
+/**
+ * svc_rdma_pages_write - Construct RDMA Writes from pages
+ * @info: pointer to write arguments
+ * @xdr: xdr_buf with pages to write
+ * @offset: offset into the content of @xdr
+ * @length: number of bytes to write
+ *
+ * Returns:
+ *   On succes, returns zero
+ *   %-E2BIG if the client-provided Write chunk is too small
+ *   %-ENOMEM if a resource has been exhausted
+ *   %-EIO if an rdma-rw error occurred
  */
-static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
-				      struct xdr_buf *xdr,
-				      unsigned int offset,
-				      unsigned long length)
+static int svc_rdma_pages_write(struct svc_rdma_write_info *info,
+				const struct xdr_buf *xdr,
+				unsigned int offset,
+				unsigned long length)
 {
 	info->wi_xdr = xdr;
 	info->wi_next_off = offset - xdr->head[0].iov_len;
@@ -522,12 +532,48 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
 }
 
 /**
+ * svc_rdma_xb_write - Construct RDMA Writes to write an xdr_buf
+ * @xdr: xdr_buf to write
+ * @data: pointer to write arguments
+ *
+ * Returns:
+ *   On succes, returns zero
+ *   %-E2BIG if the client-provided Write chunk is too small
+ *   %-ENOMEM if a resource has been exhausted
+ *   %-EIO if an rdma-rw error occurred
+ */
+static int svc_rdma_xb_write(const struct xdr_buf *xdr, void *data)
+{
+	struct svc_rdma_write_info *info = data;
+	int ret;
+
+	if (xdr->head[0].iov_len) {
+		ret = svc_rdma_iov_write(info, &xdr->head[0]);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (xdr->page_len) {
+		ret = svc_rdma_pages_write(info, xdr, xdr->head[0].iov_len,
+					   xdr->page_len);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (xdr->tail[0].iov_len) {
+		ret = svc_rdma_iov_write(info, &xdr->tail[0]);
+		if (ret < 0)
+			return ret;
+	}
+
+	return xdr->len;
+}
+
+/**
  * svc_rdma_send_write_chunk - Write all segments in a Write chunk
  * @rdma: controlling RDMA transport
- * @wr_ch: Write chunk provided by client
+ * @chunk: Write chunk provided by the client
  * @xdr: xdr_buf containing the data payload
- * @offset: payload's byte offset in @xdr
- * @length: size of payload, in bytes
  *
  * Returns a non-negative number of bytes the chunk consumed, or
  *	%-E2BIG if the payload was larger than the Write chunk,
@@ -536,30 +582,28 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info,
  *	%-ENOTCONN if posting failed (connection is lost),
  *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
  */
-int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch,
-			      struct xdr_buf *xdr,
-			      unsigned int offset, unsigned long length)
+int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma,
+			      const struct svc_rdma_chunk *chunk,
+			      const struct xdr_buf *xdr)
 {
 	struct svc_rdma_write_info *info;
+	struct svc_rdma_chunk_ctxt *cc;
 	int ret;
 
-	if (!length)
-		return 0;
-
-	info = svc_rdma_write_info_alloc(rdma, wr_ch);
+	info = svc_rdma_write_info_alloc(rdma, chunk);
 	if (!info)
 		return -ENOMEM;
+	cc = &info->wi_cc;
 
-	ret = svc_rdma_send_xdr_pagelist(info, xdr, offset, length);
-	if (ret < 0)
+	ret = svc_rdma_xb_write(xdr, info);
+	if (ret != xdr->len)
 		goto out_err;
 
-	ret = svc_rdma_post_chunk_ctxt(&info->wi_cc);
+	trace_svcrdma_post_write_chunk(&cc->cc_cid, cc->cc_sqecount);
+	ret = svc_rdma_post_chunk_ctxt(cc);
 	if (ret < 0)
 		goto out_err;
-
-	trace_svcrdma_send_write_chunk(xdr->page_len);
-	return length;
+	return xdr->len;
 
 out_err:
 	svc_rdma_write_info_free(info);
@@ -581,62 +625,62 @@ out_err:
  */
 int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma,
 			      const struct svc_rdma_recv_ctxt *rctxt,
-			      struct xdr_buf *xdr)
+			      const struct xdr_buf *xdr)
 {
 	struct svc_rdma_write_info *info;
-	int consumed, ret;
+	struct svc_rdma_chunk_ctxt *cc;
+	struct svc_rdma_chunk *chunk;
+	int ret;
 
-	info = svc_rdma_write_info_alloc(rdma, rctxt->rc_reply_chunk);
+	if (pcl_is_empty(&rctxt->rc_reply_pcl))
+		return 0;
+
+	chunk = pcl_first_chunk(&rctxt->rc_reply_pcl);
+	info = svc_rdma_write_info_alloc(rdma, chunk);
 	if (!info)
 		return -ENOMEM;
+	cc = &info->wi_cc;
 
-	ret = svc_rdma_send_xdr_kvec(info, &xdr->head[0]);
+	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+				      svc_rdma_xb_write, info);
 	if (ret < 0)
 		goto out_err;
-	consumed = xdr->head[0].iov_len;
-
-	/* Send the page list in the Reply chunk only if the
-	 * client did not provide Write chunks.
-	 */
-	if (!rctxt->rc_write_list && xdr->page_len) {
-		ret = svc_rdma_send_xdr_pagelist(info, xdr,
-						 xdr->head[0].iov_len,
-						 xdr->page_len);
-		if (ret < 0)
-			goto out_err;
-		consumed += xdr->page_len;
-	}
-
-	if (xdr->tail[0].iov_len) {
-		ret = svc_rdma_send_xdr_kvec(info, &xdr->tail[0]);
-		if (ret < 0)
-			goto out_err;
-		consumed += xdr->tail[0].iov_len;
-	}
 
-	ret = svc_rdma_post_chunk_ctxt(&info->wi_cc);
+	trace_svcrdma_post_reply_chunk(&cc->cc_cid, cc->cc_sqecount);
+	ret = svc_rdma_post_chunk_ctxt(cc);
 	if (ret < 0)
 		goto out_err;
 
-	trace_svcrdma_send_reply_chunk(consumed);
-	return consumed;
+	return xdr->len;
 
 out_err:
 	svc_rdma_write_info_free(info);
 	return ret;
 }
 
+/**
+ * svc_rdma_build_read_segment - Build RDMA Read WQEs to pull one RDMA segment
+ * @info: context for ongoing I/O
+ * @segment: co-ordinates of remote memory to be read
+ *
+ * Returns:
+ *   %0: the Read WR chain was constructed successfully
+ *   %-EINVAL: there were not enough rq_pages to finish
+ *   %-ENOMEM: allocating a local resources failed
+ *   %-EIO: a DMA mapping error occurred
+ */
 static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
-				       struct svc_rqst *rqstp,
-				       u32 rkey, u32 len, u64 offset)
+				       const struct svc_rdma_segment *segment)
 {
 	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
 	struct svc_rdma_chunk_ctxt *cc = &info->ri_cc;
+	struct svc_rqst *rqstp = info->ri_rqst;
 	struct svc_rdma_rw_ctxt *ctxt;
-	unsigned int sge_no, seg_len;
+	unsigned int sge_no, seg_len, len;
 	struct scatterlist *sg;
 	int ret;
 
+	len = segment->rs_length;
 	sge_no = PAGE_ALIGN(info->ri_pageoff + len) >> PAGE_SHIFT;
 	ctxt = svc_rdma_get_rw_ctxt(cc->cc_rdma, sge_no);
 	if (!ctxt)
@@ -670,8 +714,8 @@ static int svc_rdma_build_read_segment(struct svc_rdma_read_info *info,
 			goto out_overrun;
 	}
 
-	ret = svc_rdma_rw_ctx_init(cc->cc_rdma, ctxt, offset, rkey,
-				   DMA_FROM_DEVICE);
+	ret = svc_rdma_rw_ctx_init(cc->cc_rdma, ctxt, segment->rs_offset,
+				   segment->rs_handle, DMA_FROM_DEVICE);
 	if (ret < 0)
 		return -EIO;
 
@@ -684,54 +728,177 @@ out_overrun:
 	return -EINVAL;
 }
 
-/* Walk the segments in the Read chunk starting at @p and construct
- * RDMA Read operations to pull the chunk to the server.
+/**
+ * svc_rdma_build_read_chunk - Build RDMA Read WQEs to pull one RDMA chunk
+ * @info: context for ongoing I/O
+ * @chunk: Read chunk to pull
+ *
+ * Return values:
+ *   %0: the Read WR chain was constructed successfully
+ *   %-EINVAL: there were not enough resources to finish
+ *   %-ENOMEM: allocating a local resources failed
+ *   %-EIO: a DMA mapping error occurred
  */
-static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp,
-				     struct svc_rdma_read_info *info,
-				     __be32 *p)
+static int svc_rdma_build_read_chunk(struct svc_rdma_read_info *info,
+				     const struct svc_rdma_chunk *chunk)
 {
+	const struct svc_rdma_segment *segment;
 	int ret;
 
 	ret = -EINVAL;
-	info->ri_chunklen = 0;
-	while (*p++ != xdr_zero && be32_to_cpup(p++) == info->ri_position) {
-		u32 handle, length;
-		u64 offset;
+	pcl_for_each_segment(segment, chunk) {
+		ret = svc_rdma_build_read_segment(info, segment);
+		if (ret < 0)
+			break;
+		info->ri_totalbytes += segment->rs_length;
+	}
+	return ret;
+}
+
+/**
+ * svc_rdma_copy_inline_range - Copy part of the inline content into pages
+ * @info: context for RDMA Reads
+ * @offset: offset into the Receive buffer of region to copy
+ * @remaining: length of region to copy
+ *
+ * Take a page at a time from rqstp->rq_pages and copy the inline
+ * content from the Receive buffer into that page. Update
+ * info->ri_pageno and info->ri_pageoff so that the next RDMA Read
+ * result will land contiguously with the copied content.
+ *
+ * Return values:
+ *   %0: Inline content was successfully copied
+ *   %-EINVAL: offset or length was incorrect
+ */
+static int svc_rdma_copy_inline_range(struct svc_rdma_read_info *info,
+				      unsigned int offset,
+				      unsigned int remaining)
+{
+	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
+	unsigned char *dst, *src = head->rc_recv_buf;
+	struct svc_rqst *rqstp = info->ri_rqst;
+	unsigned int page_no, numpages;
+
+	numpages = PAGE_ALIGN(info->ri_pageoff + remaining) >> PAGE_SHIFT;
+	for (page_no = 0; page_no < numpages; page_no++) {
+		unsigned int page_len;
+
+		page_len = min_t(unsigned int, remaining,
+				 PAGE_SIZE - info->ri_pageoff);
+
+		head->rc_arg.pages[info->ri_pageno] =
+			rqstp->rq_pages[info->ri_pageno];
+		if (!info->ri_pageoff)
+			head->rc_page_count++;
+
+		dst = page_address(head->rc_arg.pages[info->ri_pageno]);
+		memcpy(dst + info->ri_pageno, src + offset, page_len);
+
+		info->ri_totalbytes += page_len;
+		info->ri_pageoff += page_len;
+		if (info->ri_pageoff == PAGE_SIZE) {
+			info->ri_pageno++;
+			info->ri_pageoff = 0;
+		}
+		remaining -= page_len;
+		offset += page_len;
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * svc_rdma_read_multiple_chunks - Construct RDMA Reads to pull data item Read chunks
+ * @info: context for RDMA Reads
+ *
+ * The chunk data lands in head->rc_arg as a series of contiguous pages,
+ * like an incoming TCP call.
+ *
+ * Return values:
+ *   %0: RDMA Read WQEs were successfully built
+ *   %-EINVAL: client provided too many chunks or segments,
+ *   %-ENOMEM: rdma_rw context pool was exhausted,
+ *   %-ENOTCONN: posting failed (connection is lost),
+ *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
+ */
+static noinline int svc_rdma_read_multiple_chunks(struct svc_rdma_read_info *info)
+{
+	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
+	const struct svc_rdma_pcl *pcl = &head->rc_read_pcl;
+	struct svc_rdma_chunk *chunk, *next;
+	struct xdr_buf *buf = &head->rc_arg;
+	unsigned int start, length;
+	int ret;
 
-		p = xdr_decode_rdma_segment(p, &handle, &length, &offset);
-		ret = svc_rdma_build_read_segment(info, rqstp, handle, length,
-						  offset);
+	start = 0;
+	chunk = pcl_first_chunk(pcl);
+	length = chunk->ch_position;
+	ret = svc_rdma_copy_inline_range(info, start, length);
+	if (ret < 0)
+		return ret;
+
+	pcl_for_each_chunk(chunk, pcl) {
+		ret = svc_rdma_build_read_chunk(info, chunk);
 		if (ret < 0)
+			return ret;
+
+		next = pcl_next_chunk(pcl, chunk);
+		if (!next)
 			break;
 
-		trace_svcrdma_send_rseg(handle, length, offset);
-		info->ri_chunklen += length;
+		start += length;
+		length = next->ch_position - info->ri_totalbytes;
+		ret = svc_rdma_copy_inline_range(info, start, length);
+		if (ret < 0)
+			return ret;
 	}
 
-	return ret;
+	start += length;
+	length = head->rc_byte_len - start;
+	ret = svc_rdma_copy_inline_range(info, start, length);
+	if (ret < 0)
+		return ret;
+
+	buf->len += info->ri_totalbytes;
+	buf->buflen += info->ri_totalbytes;
+
+	head->rc_hdr_count = 1;
+	buf->head[0].iov_base = page_address(head->rc_pages[0]);
+	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes);
+	buf->page_len = info->ri_totalbytes - buf->head[0].iov_len;
+	return 0;
 }
 
-/* Construct RDMA Reads to pull over a normal Read chunk. The chunk
- * data lands in the page list of head->rc_arg.pages.
+/**
+ * svc_rdma_read_data_item - Construct RDMA Reads to pull data item Read chunks
+ * @info: context for RDMA Reads
+ *
+ * The chunk data lands in the page list of head->rc_arg.pages.
  *
  * Currently NFSD does not look at the head->rc_arg.tail[0] iovec.
  * Therefore, XDR round-up of the Read chunk and trailing
  * inline content must both be added at the end of the pagelist.
+ *
+ * Return values:
+ *   %0: RDMA Read WQEs were successfully built
+ *   %-EINVAL: client provided too many chunks or segments,
+ *   %-ENOMEM: rdma_rw context pool was exhausted,
+ *   %-ENOTCONN: posting failed (connection is lost),
+ *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
-					    struct svc_rdma_read_info *info,
-					    __be32 *p)
+static int svc_rdma_read_data_item(struct svc_rdma_read_info *info)
 {
 	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
+	struct xdr_buf *buf = &head->rc_arg;
+	struct svc_rdma_chunk *chunk;
+	unsigned int length;
 	int ret;
 
-	ret = svc_rdma_build_read_chunk(rqstp, info, p);
+	chunk = pcl_first_chunk(&head->rc_read_pcl);
+	ret = svc_rdma_build_read_chunk(info, chunk);
 	if (ret < 0)
 		goto out;
 
-	trace_svcrdma_send_read_chunk(info->ri_chunklen, info->ri_position);
-
 	head->rc_hdr_count = 0;
 
 	/* Split the Receive buffer between the head and tail
@@ -739,11 +906,9 @@ static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
 	 * chunk is not included in either the pagelist or in
 	 * the tail.
 	 */
-	head->rc_arg.tail[0].iov_base =
-		head->rc_arg.head[0].iov_base + info->ri_position;
-	head->rc_arg.tail[0].iov_len =
-		head->rc_arg.head[0].iov_len - info->ri_position;
-	head->rc_arg.head[0].iov_len = info->ri_position;
+	buf->tail[0].iov_base = buf->head[0].iov_base + chunk->ch_position;
+	buf->tail[0].iov_len = buf->head[0].iov_len - chunk->ch_position;
+	buf->head[0].iov_len = chunk->ch_position;
 
 	/* Read chunk may need XDR roundup (see RFC 8166, s. 3.4.5.2).
 	 *
@@ -754,50 +919,149 @@ static int svc_rdma_build_normal_read_chunk(struct svc_rqst *rqstp,
 	 * Currently these chunks always start at page offset 0,
 	 * thus the rounded-up length never crosses a page boundary.
 	 */
-	info->ri_chunklen = XDR_QUADLEN(info->ri_chunklen) << 2;
-
-	head->rc_arg.page_len = info->ri_chunklen;
-	head->rc_arg.len += info->ri_chunklen;
-	head->rc_arg.buflen += info->ri_chunklen;
+	length = XDR_QUADLEN(info->ri_totalbytes) << 2;
+	buf->page_len = length;
+	buf->len += length;
+	buf->buflen += length;
 
 out:
 	return ret;
 }
 
-/* Construct RDMA Reads to pull over a Position Zero Read chunk.
- * The start of the data lands in the first page just after
- * the Transport header, and the rest lands in the page list of
+/**
+ * svc_rdma_read_chunk_range - Build RDMA Read WQEs for portion of a chunk
+ * @info: context for RDMA Reads
+ * @chunk: parsed Call chunk to pull
+ * @offset: offset of region to pull
+ * @length: length of region to pull
+ *
+ * Return values:
+ *   %0: RDMA Read WQEs were successfully built
+ *   %-EINVAL: there were not enough resources to finish
+ *   %-ENOMEM: rdma_rw context pool was exhausted,
+ *   %-ENOTCONN: posting failed (connection is lost),
+ *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
+ */
+static int svc_rdma_read_chunk_range(struct svc_rdma_read_info *info,
+				     const struct svc_rdma_chunk *chunk,
+				     unsigned int offset, unsigned int length)
+{
+	const struct svc_rdma_segment *segment;
+	int ret;
+
+	ret = -EINVAL;
+	pcl_for_each_segment(segment, chunk) {
+		struct svc_rdma_segment dummy;
+
+		if (offset > segment->rs_length) {
+			offset -= segment->rs_length;
+			continue;
+		}
+
+		dummy.rs_handle = segment->rs_handle;
+		dummy.rs_length = min_t(u32, length, segment->rs_length) - offset;
+		dummy.rs_offset = segment->rs_offset + offset;
+
+		ret = svc_rdma_build_read_segment(info, &dummy);
+		if (ret < 0)
+			break;
+
+		info->ri_totalbytes += dummy.rs_length;
+		length -= dummy.rs_length;
+		offset = 0;
+	}
+	return ret;
+}
+
+/**
+ * svc_rdma_read_call_chunk - Build RDMA Read WQEs to pull a Long Message
+ * @info: context for RDMA Reads
+ *
+ * Return values:
+ *   %0: RDMA Read WQEs were successfully built
+ *   %-EINVAL: there were not enough resources to finish
+ *   %-ENOMEM: rdma_rw context pool was exhausted,
+ *   %-ENOTCONN: posting failed (connection is lost),
+ *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
+ */
+static int svc_rdma_read_call_chunk(struct svc_rdma_read_info *info)
+{
+	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
+	const struct svc_rdma_chunk *call_chunk =
+			pcl_first_chunk(&head->rc_call_pcl);
+	const struct svc_rdma_pcl *pcl = &head->rc_read_pcl;
+	struct svc_rdma_chunk *chunk, *next;
+	unsigned int start, length;
+	int ret;
+
+	if (pcl_is_empty(pcl))
+		return svc_rdma_build_read_chunk(info, call_chunk);
+
+	start = 0;
+	chunk = pcl_first_chunk(pcl);
+	length = chunk->ch_position;
+	ret = svc_rdma_read_chunk_range(info, call_chunk, start, length);
+	if (ret < 0)
+		return ret;
+
+	pcl_for_each_chunk(chunk, pcl) {
+		ret = svc_rdma_build_read_chunk(info, chunk);
+		if (ret < 0)
+			return ret;
+
+		next = pcl_next_chunk(pcl, chunk);
+		if (!next)
+			break;
+
+		start += length;
+		length = next->ch_position - info->ri_totalbytes;
+		ret = svc_rdma_read_chunk_range(info, call_chunk,
+						start, length);
+		if (ret < 0)
+			return ret;
+	}
+
+	start += length;
+	length = call_chunk->ch_length - start;
+	return svc_rdma_read_chunk_range(info, call_chunk, start, length);
+}
+
+/**
+ * svc_rdma_read_special - Build RDMA Read WQEs to pull a Long Message
+ * @info: context for RDMA Reads
+ *
+ * The start of the data lands in the first page just after the
+ * Transport header, and the rest lands in the page list of
  * head->rc_arg.pages.
  *
  * Assumptions:
- *	- A PZRC has an XDR-aligned length (no implicit round-up).
- *	- There can be no trailing inline content (IOW, we assume
- *	  a PZRC is never sent in an RDMA_MSG message, though it's
- *	  allowed by spec).
+ *	- A PZRC is never sent in an RDMA_MSG message, though it's
+ *	  allowed by spec.
+ *
+ * Return values:
+ *   %0: RDMA Read WQEs were successfully built
+ *   %-EINVAL: client provided too many chunks or segments,
+ *   %-ENOMEM: rdma_rw context pool was exhausted,
+ *   %-ENOTCONN: posting failed (connection is lost),
+ *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-static int svc_rdma_build_pz_read_chunk(struct svc_rqst *rqstp,
-					struct svc_rdma_read_info *info,
-					__be32 *p)
+static noinline int svc_rdma_read_special(struct svc_rdma_read_info *info)
 {
 	struct svc_rdma_recv_ctxt *head = info->ri_readctxt;
+	struct xdr_buf *buf = &head->rc_arg;
 	int ret;
 
-	ret = svc_rdma_build_read_chunk(rqstp, info, p);
+	ret = svc_rdma_read_call_chunk(info);
 	if (ret < 0)
 		goto out;
 
-	trace_svcrdma_send_pzr(info->ri_chunklen);
-
-	head->rc_arg.len += info->ri_chunklen;
-	head->rc_arg.buflen += info->ri_chunklen;
+	buf->len += info->ri_totalbytes;
+	buf->buflen += info->ri_totalbytes;
 
 	head->rc_hdr_count = 1;
-	head->rc_arg.head[0].iov_base = page_address(head->rc_pages[0]);
-	head->rc_arg.head[0].iov_len = min_t(size_t, PAGE_SIZE,
-					     info->ri_chunklen);
-
-	head->rc_arg.page_len = info->ri_chunklen -
-				head->rc_arg.head[0].iov_len;
+	buf->head[0].iov_base = page_address(head->rc_pages[0]);
+	buf->head[0].iov_len = min_t(size_t, PAGE_SIZE, info->ri_totalbytes);
+	buf->page_len = info->ri_totalbytes - buf->head[0].iov_len;
 
 out:
 	return ret;
@@ -824,26 +1088,34 @@ static void svc_rdma_save_io_pages(struct svc_rqst *rqstp,
 }
 
 /**
- * svc_rdma_recv_read_chunk - Pull a Read chunk from the client
+ * svc_rdma_process_read_list - Pull list of Read chunks from the client
  * @rdma: controlling RDMA transport
  * @rqstp: set of pages to use as Read sink buffers
  * @head: pages under I/O collect here
- * @p: pointer to start of Read chunk
  *
- * Returns:
- *	%0 if all needed RDMA Reads were posted successfully,
- *	%-EINVAL if client provided too many segments,
- *	%-ENOMEM if rdma_rw context pool was exhausted,
- *	%-ENOTCONN if posting failed (connection is lost),
- *	%-EIO if rdma_rw initialization failed (DMA mapping, etc).
+ * The RPC/RDMA protocol assumes that the upper layer's XDR decoders
+ * pull each Read chunk as they decode an incoming RPC message.
  *
- * Assumptions:
- * - All Read segments in @p have the same Position value.
+ * On Linux, however, the server needs to have a fully-constructed RPC
+ * message in rqstp->rq_arg when there is a positive return code from
+ * ->xpo_recvfrom. So the Read list is safety-checked immediately when
+ * it is received, then here the whole Read list is pulled all at once.
+ * The ingress RPC message is fully reconstructed once all associated
+ * RDMA Reads have completed.
+ *
+ * Return values:
+ *   %1: all needed RDMA Reads were posted successfully,
+ *   %-EINVAL: client provided too many chunks or segments,
+ *   %-ENOMEM: rdma_rw context pool was exhausted,
+ *   %-ENOTCONN: posting failed (connection is lost),
+ *   %-EIO: rdma_rw initialization failed (DMA mapping, etc).
  */
-int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp,
-			     struct svc_rdma_recv_ctxt *head, __be32 *p)
+int svc_rdma_process_read_list(struct svcxprt_rdma *rdma,
+			       struct svc_rqst *rqstp,
+			       struct svc_rdma_recv_ctxt *head)
 {
 	struct svc_rdma_read_info *info;
+	struct svc_rdma_chunk_ctxt *cc;
 	int ret;
 
 	/* The request (with page list) is constructed in
@@ -861,23 +1133,29 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp,
 	info = svc_rdma_read_info_alloc(rdma);
 	if (!info)
 		return -ENOMEM;
+	cc = &info->ri_cc;
+	info->ri_rqst = rqstp;
 	info->ri_readctxt = head;
 	info->ri_pageno = 0;
 	info->ri_pageoff = 0;
-
-	info->ri_position = be32_to_cpup(p + 1);
-	if (info->ri_position)
-		ret = svc_rdma_build_normal_read_chunk(rqstp, info, p);
-	else
-		ret = svc_rdma_build_pz_read_chunk(rqstp, info, p);
+	info->ri_totalbytes = 0;
+
+	if (pcl_is_empty(&head->rc_call_pcl)) {
+		if (head->rc_read_pcl.cl_count == 1)
+			ret = svc_rdma_read_data_item(info);
+		else
+			ret = svc_rdma_read_multiple_chunks(info);
+	} else
+		ret = svc_rdma_read_special(info);
 	if (ret < 0)
 		goto out_err;
 
-	ret = svc_rdma_post_chunk_ctxt(&info->ri_cc);
+	trace_svcrdma_post_read_chunk(&cc->cc_cid, cc->cc_sqecount);
+	ret = svc_rdma_post_chunk_ctxt(cc);
 	if (ret < 0)
 		goto out_err;
 	svc_rdma_save_io_pages(rqstp, 0, head->rc_page_count);
-	return 0;
+	return 1;
 
 out_err:
 	svc_rdma_read_info_free(info);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index 7b94d971feb3..68af79d4f04f 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -358,49 +358,42 @@ static ssize_t svc_rdma_encode_read_list(struct svc_rdma_send_ctxt *sctxt)
 
 /**
  * svc_rdma_encode_write_segment - Encode one Write segment
- * @src: matching Write chunk in the RPC Call header
  * @sctxt: Send context for the RPC Reply
+ * @chunk: Write chunk to push
  * @remaining: remaining bytes of the payload left in the Write chunk
+ * @segno: which segment in the chunk
  *
  * Return values:
  *   On success, returns length in bytes of the Reply XDR buffer
- *   that was consumed by the Write segment
+ *   that was consumed by the Write segment, and updates @remaining
  *   %-EMSGSIZE on XDR buffer overflow
  */
-static ssize_t svc_rdma_encode_write_segment(__be32 *src,
-					     struct svc_rdma_send_ctxt *sctxt,
-					     unsigned int *remaining)
+static ssize_t svc_rdma_encode_write_segment(struct svc_rdma_send_ctxt *sctxt,
+					     const struct svc_rdma_chunk *chunk,
+					     u32 *remaining, unsigned int segno)
 {
+	const struct svc_rdma_segment *segment = &chunk->ch_segments[segno];
+	const size_t len = rpcrdma_segment_maxsz * sizeof(__be32);
+	u32 length;
 	__be32 *p;
-	const size_t len = rpcrdma_segment_maxsz * sizeof(*p);
-	u32 handle, length;
-	u64 offset;
 
 	p = xdr_reserve_space(&sctxt->sc_stream, len);
 	if (!p)
 		return -EMSGSIZE;
 
-	xdr_decode_rdma_segment(src, &handle, &length, &offset);
-
-	if (*remaining < length) {
-		/* segment only partly filled */
-		length = *remaining;
-		*remaining = 0;
-	} else {
-		/* entire segment was consumed */
-		*remaining -= length;
-	}
-	xdr_encode_rdma_segment(p, handle, length, offset);
-
-	trace_svcrdma_encode_wseg(handle, length, offset);
+	length = min_t(u32, *remaining, segment->rs_length);
+	*remaining -= length;
+	xdr_encode_rdma_segment(p, segment->rs_handle, length,
+				segment->rs_offset);
+	trace_svcrdma_encode_wseg(sctxt, segno, segment->rs_handle, length,
+				  segment->rs_offset);
 	return len;
 }
 
 /**
  * svc_rdma_encode_write_chunk - Encode one Write chunk
- * @src: matching Write chunk in the RPC Call header
  * @sctxt: Send context for the RPC Reply
- * @remaining: size in bytes of the payload in the Write chunk
+ * @chunk: Write chunk to push
  *
  * Copy a Write chunk from the Call transport header to the
  * Reply transport header. Update each segment's length field
@@ -411,33 +404,28 @@ static ssize_t svc_rdma_encode_write_segment(__be32 *src,
  *   that was consumed by the Write chunk
  *   %-EMSGSIZE on XDR buffer overflow
  */
-static ssize_t svc_rdma_encode_write_chunk(__be32 *src,
-					   struct svc_rdma_send_ctxt *sctxt,
-					   unsigned int remaining)
+static ssize_t svc_rdma_encode_write_chunk(struct svc_rdma_send_ctxt *sctxt,
+					   const struct svc_rdma_chunk *chunk)
 {
-	unsigned int i, nsegs;
+	u32 remaining = chunk->ch_payload_length;
+	unsigned int segno;
 	ssize_t len, ret;
 
 	len = 0;
-	trace_svcrdma_encode_write_chunk(remaining);
-
-	src++;
 	ret = xdr_stream_encode_item_present(&sctxt->sc_stream);
 	if (ret < 0)
-		return -EMSGSIZE;
+		return ret;
 	len += ret;
 
-	nsegs = be32_to_cpup(src++);
-	ret = xdr_stream_encode_u32(&sctxt->sc_stream, nsegs);
+	ret = xdr_stream_encode_u32(&sctxt->sc_stream, chunk->ch_segcount);
 	if (ret < 0)
-		return -EMSGSIZE;
+		return ret;
 	len += ret;
 
-	for (i = nsegs; i; i--) {
-		ret = svc_rdma_encode_write_segment(src, sctxt, &remaining);
+	for (segno = 0; segno < chunk->ch_segcount; segno++) {
+		ret = svc_rdma_encode_write_segment(sctxt, chunk, &remaining, segno);
 		if (ret < 0)
-			return -EMSGSIZE;
-		src += rpcrdma_segment_maxsz;
+			return ret;
 		len += ret;
 	}
 
@@ -448,32 +436,25 @@ static ssize_t svc_rdma_encode_write_chunk(__be32 *src,
  * svc_rdma_encode_write_list - Encode RPC Reply's Write chunk list
  * @rctxt: Reply context with information about the RPC Call
  * @sctxt: Send context for the RPC Reply
- * @length: size in bytes of the payload in the first Write chunk
- *
- * The client provides a Write chunk list in the Call message. Fill
- * in the segments in the first Write chunk in the Reply's transport
- * header with the number of bytes consumed in each segment.
- * Remaining chunks are returned unused.
- *
- * Assumptions:
- *  - Client has provided only one Write chunk
  *
  * Return values:
  *   On success, returns length in bytes of the Reply XDR buffer
  *   that was consumed by the Reply's Write list
  *   %-EMSGSIZE on XDR buffer overflow
  */
-static ssize_t
-svc_rdma_encode_write_list(const struct svc_rdma_recv_ctxt *rctxt,
-			   struct svc_rdma_send_ctxt *sctxt,
-			   unsigned int length)
+static ssize_t svc_rdma_encode_write_list(struct svc_rdma_recv_ctxt *rctxt,
+					  struct svc_rdma_send_ctxt *sctxt)
 {
+	struct svc_rdma_chunk *chunk;
 	ssize_t len, ret;
 
-	ret = svc_rdma_encode_write_chunk(rctxt->rc_write_list, sctxt, length);
-	if (ret < 0)
-		return ret;
-	len = ret;
+	len = 0;
+	pcl_for_each_chunk(chunk, &rctxt->rc_write_pcl) {
+		ret = svc_rdma_encode_write_chunk(sctxt, chunk);
+		if (ret < 0)
+			return ret;
+		len += ret;
+	}
 
 	/* Terminate the Write list */
 	ret = xdr_stream_encode_item_absent(&sctxt->sc_stream);
@@ -489,56 +470,174 @@ svc_rdma_encode_write_list(const struct svc_rdma_recv_ctxt *rctxt,
  * @sctxt: Send context for the RPC Reply
  * @length: size in bytes of the payload in the Reply chunk
  *
- * Assumptions:
- * - Reply can always fit in the client-provided Reply chunk
- *
  * Return values:
  *   On success, returns length in bytes of the Reply XDR buffer
  *   that was consumed by the Reply's Reply chunk
  *   %-EMSGSIZE on XDR buffer overflow
+ *   %-E2BIG if the RPC message is larger than the Reply chunk
  */
 static ssize_t
-svc_rdma_encode_reply_chunk(const struct svc_rdma_recv_ctxt *rctxt,
+svc_rdma_encode_reply_chunk(struct svc_rdma_recv_ctxt *rctxt,
 			    struct svc_rdma_send_ctxt *sctxt,
 			    unsigned int length)
 {
-	return svc_rdma_encode_write_chunk(rctxt->rc_reply_chunk, sctxt,
-					   length);
+	struct svc_rdma_chunk *chunk;
+
+	if (pcl_is_empty(&rctxt->rc_reply_pcl))
+		return xdr_stream_encode_item_absent(&sctxt->sc_stream);
+
+	chunk = pcl_first_chunk(&rctxt->rc_reply_pcl);
+	if (length > chunk->ch_length)
+		return -E2BIG;
+
+	chunk->ch_payload_length = length;
+	return svc_rdma_encode_write_chunk(sctxt, chunk);
 }
 
-static int svc_rdma_dma_map_page(struct svcxprt_rdma *rdma,
-				 struct svc_rdma_send_ctxt *ctxt,
-				 struct page *page,
-				 unsigned long offset,
-				 unsigned int len)
+struct svc_rdma_map_data {
+	struct svcxprt_rdma		*md_rdma;
+	struct svc_rdma_send_ctxt	*md_ctxt;
+};
+
+/**
+ * svc_rdma_page_dma_map - DMA map one page
+ * @data: pointer to arguments
+ * @page: struct page to DMA map
+ * @offset: offset into the page
+ * @len: number of bytes to map
+ *
+ * Returns:
+ *   %0 if DMA mapping was successful
+ *   %-EIO if the page cannot be DMA mapped
+ */
+static int svc_rdma_page_dma_map(void *data, struct page *page,
+				 unsigned long offset, unsigned int len)
 {
+	struct svc_rdma_map_data *args = data;
+	struct svcxprt_rdma *rdma = args->md_rdma;
+	struct svc_rdma_send_ctxt *ctxt = args->md_ctxt;
 	struct ib_device *dev = rdma->sc_cm_id->device;
 	dma_addr_t dma_addr;
 
+	++ctxt->sc_cur_sge_no;
+
 	dma_addr = ib_dma_map_page(dev, page, offset, len, DMA_TO_DEVICE);
-	trace_svcrdma_dma_map_page(rdma, dma_addr, len);
 	if (ib_dma_mapping_error(dev, dma_addr))
 		goto out_maperr;
 
+	trace_svcrdma_dma_map_page(rdma, dma_addr, len);
 	ctxt->sc_sges[ctxt->sc_cur_sge_no].addr = dma_addr;
 	ctxt->sc_sges[ctxt->sc_cur_sge_no].length = len;
 	ctxt->sc_send_wr.num_sge++;
 	return 0;
 
 out_maperr:
+	trace_svcrdma_dma_map_err(rdma, dma_addr, len);
 	return -EIO;
 }
 
-/* ib_dma_map_page() is used here because svc_rdma_dma_unmap()
+/**
+ * svc_rdma_iov_dma_map - DMA map an iovec
+ * @data: pointer to arguments
+ * @iov: kvec to DMA map
+ *
+ * ib_dma_map_page() is used here because svc_rdma_dma_unmap()
  * handles DMA-unmap and it uses ib_dma_unmap_page() exclusively.
+ *
+ * Returns:
+ *   %0 if DMA mapping was successful
+ *   %-EIO if the iovec cannot be DMA mapped
  */
-static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma,
-				struct svc_rdma_send_ctxt *ctxt,
-				unsigned char *base,
-				unsigned int len)
+static int svc_rdma_iov_dma_map(void *data, const struct kvec *iov)
 {
-	return svc_rdma_dma_map_page(rdma, ctxt, virt_to_page(base),
-				     offset_in_page(base), len);
+	if (!iov->iov_len)
+		return 0;
+	return svc_rdma_page_dma_map(data, virt_to_page(iov->iov_base),
+				     offset_in_page(iov->iov_base),
+				     iov->iov_len);
+}
+
+/**
+ * svc_rdma_xb_dma_map - DMA map all segments of an xdr_buf
+ * @xdr: xdr_buf containing portion of an RPC message to transmit
+ * @data: pointer to arguments
+ *
+ * Returns:
+ *   %0 if DMA mapping was successful
+ *   %-EIO if DMA mapping failed
+ *
+ * On failure, any DMA mappings that have been already done must be
+ * unmapped by the caller.
+ */
+static int svc_rdma_xb_dma_map(const struct xdr_buf *xdr, void *data)
+{
+	unsigned int len, remaining;
+	unsigned long pageoff;
+	struct page **ppages;
+	int ret;
+
+	ret = svc_rdma_iov_dma_map(data, &xdr->head[0]);
+	if (ret < 0)
+		return ret;
+
+	ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
+	pageoff = offset_in_page(xdr->page_base);
+	remaining = xdr->page_len;
+	while (remaining) {
+		len = min_t(u32, PAGE_SIZE - pageoff, remaining);
+
+		ret = svc_rdma_page_dma_map(data, *ppages++, pageoff, len);
+		if (ret < 0)
+			return ret;
+
+		remaining -= len;
+		pageoff = 0;
+	}
+
+	ret = svc_rdma_iov_dma_map(data, &xdr->tail[0]);
+	if (ret < 0)
+		return ret;
+
+	return xdr->len;
+}
+
+struct svc_rdma_pullup_data {
+	u8		*pd_dest;
+	unsigned int	pd_length;
+	unsigned int	pd_num_sges;
+};
+
+/**
+ * svc_rdma_xb_count_sges - Count how many SGEs will be needed
+ * @xdr: xdr_buf containing portion of an RPC message to transmit
+ * @data: pointer to arguments
+ *
+ * Returns:
+ *   Number of SGEs needed to Send the contents of @xdr inline
+ */
+static int svc_rdma_xb_count_sges(const struct xdr_buf *xdr,
+				  void *data)
+{
+	struct svc_rdma_pullup_data *args = data;
+	unsigned int remaining;
+	unsigned long offset;
+
+	if (xdr->head[0].iov_len)
+		++args->pd_num_sges;
+
+	offset = offset_in_page(xdr->page_base);
+	remaining = xdr->page_len;
+	while (remaining) {
+		++args->pd_num_sges;
+		remaining -= min_t(u32, PAGE_SIZE - offset, remaining);
+		offset = 0;
+	}
+
+	if (xdr->tail[0].iov_len)
+		++args->pd_num_sges;
+
+	args->pd_length += xdr->len;
+	return 0;
 }
 
 /**
@@ -549,48 +648,71 @@ static int svc_rdma_dma_map_buf(struct svcxprt_rdma *rdma,
  * @xdr: xdr_buf containing RPC message to transmit
  *
  * Returns:
- *	%true if pull-up must be used
- *	%false otherwise
+ *   %true if pull-up must be used
+ *   %false otherwise
  */
-static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma,
-				    struct svc_rdma_send_ctxt *sctxt,
+static bool svc_rdma_pull_up_needed(const struct svcxprt_rdma *rdma,
+				    const struct svc_rdma_send_ctxt *sctxt,
 				    const struct svc_rdma_recv_ctxt *rctxt,
-				    struct xdr_buf *xdr)
+				    const struct xdr_buf *xdr)
 {
-	int elements;
+	/* Resources needed for the transport header */
+	struct svc_rdma_pullup_data args = {
+		.pd_length	= sctxt->sc_hdrbuf.len,
+		.pd_num_sges	= 1,
+	};
+	int ret;
 
-	/* For small messages, copying bytes is cheaper than DMA mapping.
-	 */
-	if (sctxt->sc_hdrbuf.len + xdr->len < RPCRDMA_PULLUP_THRESH)
+	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+				      svc_rdma_xb_count_sges, &args);
+	if (ret < 0)
+		return false;
+
+	if (args.pd_length < RPCRDMA_PULLUP_THRESH)
 		return true;
+	return args.pd_num_sges >= rdma->sc_max_send_sges;
+}
 
-	/* Check whether the xdr_buf has more elements than can
-	 * fit in a single RDMA Send.
-	 */
-	/* xdr->head */
-	elements = 1;
-
-	/* xdr->pages */
-	if (!rctxt || !rctxt->rc_write_list) {
-		unsigned int remaining;
-		unsigned long pageoff;
-
-		pageoff = xdr->page_base & ~PAGE_MASK;
-		remaining = xdr->page_len;
-		while (remaining) {
-			++elements;
-			remaining -= min_t(u32, PAGE_SIZE - pageoff,
-					   remaining);
-			pageoff = 0;
-		}
+/**
+ * svc_rdma_xb_linearize - Copy region of xdr_buf to flat buffer
+ * @xdr: xdr_buf containing portion of an RPC message to copy
+ * @data: pointer to arguments
+ *
+ * Returns:
+ *   Always zero.
+ */
+static int svc_rdma_xb_linearize(const struct xdr_buf *xdr,
+				 void *data)
+{
+	struct svc_rdma_pullup_data *args = data;
+	unsigned int len, remaining;
+	unsigned long pageoff;
+	struct page **ppages;
+
+	if (xdr->head[0].iov_len) {
+		memcpy(args->pd_dest, xdr->head[0].iov_base, xdr->head[0].iov_len);
+		args->pd_dest += xdr->head[0].iov_len;
 	}
 
-	/* xdr->tail */
-	if (xdr->tail[0].iov_len)
-		++elements;
+	ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
+	pageoff = offset_in_page(xdr->page_base);
+	remaining = xdr->page_len;
+	while (remaining) {
+		len = min_t(u32, PAGE_SIZE - pageoff, remaining);
+		memcpy(args->pd_dest, page_address(*ppages) + pageoff, len);
+		remaining -= len;
+		args->pd_dest += len;
+		pageoff = 0;
+		ppages++;
+	}
 
-	/* assume 1 SGE is needed for the transport header */
-	return elements >= rdma->sc_max_send_sges;
+	if (xdr->tail[0].iov_len) {
+		memcpy(args->pd_dest, xdr->tail[0].iov_base, xdr->tail[0].iov_len);
+		args->pd_dest += xdr->tail[0].iov_len;
+	}
+
+	args->pd_length += xdr->len;
+	return 0;
 }
 
 /**
@@ -603,53 +725,30 @@ static bool svc_rdma_pull_up_needed(struct svcxprt_rdma *rdma,
  * The device is not capable of sending the reply directly.
  * Assemble the elements of @xdr into the transport header buffer.
  *
- * Returns zero on success, or a negative errno on failure.
+ * Assumptions:
+ *  pull_up_needed has determined that @xdr will fit in the buffer.
+ *
+ * Returns:
+ *   %0 if pull-up was successful
+ *   %-EMSGSIZE if a buffer manipulation problem occurred
  */
-static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma,
+static int svc_rdma_pull_up_reply_msg(const struct svcxprt_rdma *rdma,
 				      struct svc_rdma_send_ctxt *sctxt,
 				      const struct svc_rdma_recv_ctxt *rctxt,
 				      const struct xdr_buf *xdr)
 {
-	unsigned char *dst, *tailbase;
-	unsigned int taillen;
-
-	dst = sctxt->sc_xprt_buf + sctxt->sc_hdrbuf.len;
-	memcpy(dst, xdr->head[0].iov_base, xdr->head[0].iov_len);
-	dst += xdr->head[0].iov_len;
-
-	tailbase = xdr->tail[0].iov_base;
-	taillen = xdr->tail[0].iov_len;
-	if (rctxt && rctxt->rc_write_list) {
-		u32 xdrpad;
-
-		xdrpad = xdr_pad_size(xdr->page_len);
-		if (taillen && xdrpad) {
-			tailbase += xdrpad;
-			taillen -= xdrpad;
-		}
-	} else {
-		unsigned int len, remaining;
-		unsigned long pageoff;
-		struct page **ppages;
-
-		ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
-		pageoff = xdr->page_base & ~PAGE_MASK;
-		remaining = xdr->page_len;
-		while (remaining) {
-			len = min_t(u32, PAGE_SIZE - pageoff, remaining);
-
-			memcpy(dst, page_address(*ppages), len);
-			remaining -= len;
-			dst += len;
-			pageoff = 0;
-		}
-	}
+	struct svc_rdma_pullup_data args = {
+		.pd_dest	= sctxt->sc_xprt_buf + sctxt->sc_hdrbuf.len,
+	};
+	int ret;
 
-	if (taillen)
-		memcpy(dst, tailbase, taillen);
+	ret = pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+				      svc_rdma_xb_linearize, &args);
+	if (ret < 0)
+		return ret;
 
-	sctxt->sc_sges[0].length += xdr->len;
-	trace_svcrdma_send_pullup(sctxt->sc_sges[0].length);
+	sctxt->sc_sges[0].length = sctxt->sc_hdrbuf.len + args.pd_length;
+	trace_svcrdma_send_pullup(sctxt, args.pd_length);
 	return 0;
 }
 
@@ -659,22 +758,22 @@ static int svc_rdma_pull_up_reply_msg(struct svcxprt_rdma *rdma,
  * @rctxt: Write and Reply chunks provided by client
  * @xdr: prepared xdr_buf containing RPC message
  *
- * Load the xdr_buf into the ctxt's sge array, and DMA map each
- * element as it is added. The Send WR's num_sge field is set.
+ * Returns:
+ *   %0 if DMA mapping was successful.
+ *   %-EMSGSIZE if a buffer manipulation problem occurred
+ *   %-EIO if DMA mapping failed
  *
- * Returns zero on success, or a negative errno on failure.
+ * The Send WR's num_sge field is set in all cases.
  */
 int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 			   struct svc_rdma_send_ctxt *sctxt,
 			   const struct svc_rdma_recv_ctxt *rctxt,
-			   struct xdr_buf *xdr)
+			   const struct xdr_buf *xdr)
 {
-	unsigned int len, remaining;
-	unsigned long page_off;
-	struct page **ppages;
-	unsigned char *base;
-	u32 xdr_pad;
-	int ret;
+	struct svc_rdma_map_data args = {
+		.md_rdma	= rdma,
+		.md_ctxt	= sctxt,
+	};
 
 	/* Set up the (persistently-mapped) transport header SGE. */
 	sctxt->sc_send_wr.num_sge = 1;
@@ -683,7 +782,7 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 	/* If there is a Reply chunk, nothing follows the transport
 	 * header, and we're done here.
 	 */
-	if (rctxt && rctxt->rc_reply_chunk)
+	if (!pcl_is_empty(&rctxt->rc_reply_pcl))
 		return 0;
 
 	/* For pull-up, svc_rdma_send() will sync the transport header.
@@ -692,58 +791,8 @@ int svc_rdma_map_reply_msg(struct svcxprt_rdma *rdma,
 	if (svc_rdma_pull_up_needed(rdma, sctxt, rctxt, xdr))
 		return svc_rdma_pull_up_reply_msg(rdma, sctxt, rctxt, xdr);
 
-	++sctxt->sc_cur_sge_no;
-	ret = svc_rdma_dma_map_buf(rdma, sctxt,
-				   xdr->head[0].iov_base,
-				   xdr->head[0].iov_len);
-	if (ret < 0)
-		return ret;
-
-	/* If a Write chunk is present, the xdr_buf's page list
-	 * is not included inline. However the Upper Layer may
-	 * have added XDR padding in the tail buffer, and that
-	 * should not be included inline.
-	 */
-	if (rctxt && rctxt->rc_write_list) {
-		base = xdr->tail[0].iov_base;
-		len = xdr->tail[0].iov_len;
-		xdr_pad = xdr_pad_size(xdr->page_len);
-
-		if (len && xdr_pad) {
-			base += xdr_pad;
-			len -= xdr_pad;
-		}
-
-		goto tail;
-	}
-
-	ppages = xdr->pages + (xdr->page_base >> PAGE_SHIFT);
-	page_off = xdr->page_base & ~PAGE_MASK;
-	remaining = xdr->page_len;
-	while (remaining) {
-		len = min_t(u32, PAGE_SIZE - page_off, remaining);
-
-		++sctxt->sc_cur_sge_no;
-		ret = svc_rdma_dma_map_page(rdma, sctxt, *ppages++,
-					    page_off, len);
-		if (ret < 0)
-			return ret;
-
-		remaining -= len;
-		page_off = 0;
-	}
-
-	base = xdr->tail[0].iov_base;
-	len = xdr->tail[0].iov_len;
-tail:
-	if (len) {
-		++sctxt->sc_cur_sge_no;
-		ret = svc_rdma_dma_map_buf(rdma, sctxt, base, len);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
+	return pcl_process_nonpayloads(&rctxt->rc_write_pcl, xdr,
+				       svc_rdma_xb_dma_map, &args);
 }
 
 /* The svc_rqst and all resources it owns are released as soon as
@@ -893,9 +942,6 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 		container_of(xprt, struct svcxprt_rdma, sc_xprt);
 	struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
 	__be32 *rdma_argp = rctxt->rc_recv_buf;
-	__be32 *wr_lst = rctxt->rc_write_list;
-	__be32 *rp_ch = rctxt->rc_reply_chunk;
-	struct xdr_buf *xdr = &rqstp->rq_res;
 	struct svc_rdma_send_ctxt *sctxt;
 	__be32 *p;
 	int ret;
@@ -913,45 +959,22 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 			      rpcrdma_fixed_maxsz * sizeof(*p));
 	if (!p)
 		goto err0;
+
+	ret = svc_rdma_send_reply_chunk(rdma, rctxt, &rqstp->rq_res);
+	if (ret < 0)
+		goto err2;
+
 	*p++ = *rdma_argp;
 	*p++ = *(rdma_argp + 1);
 	*p++ = rdma->sc_fc_credits;
-	*p   = rp_ch ? rdma_nomsg : rdma_msg;
+	*p = pcl_is_empty(&rctxt->rc_reply_pcl) ? rdma_msg : rdma_nomsg;
 
 	if (svc_rdma_encode_read_list(sctxt) < 0)
 		goto err0;
-	if (wr_lst) {
-		/* XXX: Presume the client sent only one Write chunk */
-		unsigned long offset;
-		unsigned int length;
-
-		if (rctxt->rc_read_payload_length) {
-			offset = rctxt->rc_read_payload_offset;
-			length = rctxt->rc_read_payload_length;
-		} else {
-			offset = xdr->head[0].iov_len;
-			length = xdr->page_len;
-		}
-		ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr, offset,
-						length);
-		if (ret < 0)
-			goto err2;
-		if (svc_rdma_encode_write_list(rctxt, sctxt, length) < 0)
-			goto err0;
-	} else {
-		if (xdr_stream_encode_item_absent(&sctxt->sc_stream) < 0)
-			goto err0;
-	}
-	if (rp_ch) {
-		ret = svc_rdma_send_reply_chunk(rdma, rctxt, &rqstp->rq_res);
-		if (ret < 0)
-			goto err2;
-		if (svc_rdma_encode_reply_chunk(rctxt, sctxt, ret) < 0)
-			goto err0;
-	} else {
-		if (xdr_stream_encode_item_absent(&sctxt->sc_stream) < 0)
-			goto err0;
-	}
+	if (svc_rdma_encode_write_list(rctxt, sctxt) < 0)
+		goto err0;
+	if (svc_rdma_encode_reply_chunk(rctxt, sctxt, ret) < 0)
+		goto err0;
 
 	ret = svc_rdma_send_reply_msg(rdma, sctxt, rctxt, rqstp);
 	if (ret < 0)
@@ -978,28 +1001,46 @@ int svc_rdma_sendto(struct svc_rqst *rqstp)
 }
 
 /**
- * svc_rdma_read_payload - special processing for a READ payload
+ * svc_rdma_result_payload - special processing for a result payload
  * @rqstp: svc_rqst to operate on
  * @offset: payload's byte offset in @xdr
  * @length: size of payload, in bytes
  *
- * Returns zero on success.
- *
- * For the moment, just record the xdr_buf location of the READ
- * payload. svc_rdma_sendto will use that location later when
- * we actually send the payload.
+ * Return values:
+ *   %0 if successful or nothing needed to be done
+ *   %-EMSGSIZE on XDR buffer overflow
+ *   %-E2BIG if the payload was larger than the Write chunk
+ *   %-EINVAL if client provided too many segments
+ *   %-ENOMEM if rdma_rw context pool was exhausted
+ *   %-ENOTCONN if posting failed (connection is lost)
+ *   %-EIO if rdma_rw initialization failed (DMA mapping, etc)
  */
-int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset,
-			  unsigned int length)
+int svc_rdma_result_payload(struct svc_rqst *rqstp, unsigned int offset,
+			    unsigned int length)
 {
 	struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt;
+	struct svc_rdma_chunk *chunk;
+	struct svcxprt_rdma *rdma;
+	struct xdr_buf subbuf;
+	int ret;
 
-	/* XXX: Just one READ payload slot for now, since our
-	 * transport implementation currently supports only one
-	 * Write chunk.
-	 */
-	rctxt->rc_read_payload_offset = offset;
-	rctxt->rc_read_payload_length = length;
+	chunk = rctxt->rc_cur_result_payload;
+	if (!length || !chunk)
+		return 0;
+	rctxt->rc_cur_result_payload =
+		pcl_next_chunk(&rctxt->rc_write_pcl, chunk);
+	if (length > chunk->ch_length)
+		return -E2BIG;
 
+	chunk->ch_position = offset;
+	chunk->ch_payload_length = length;
+
+	if (xdr_buf_subsegment(&rqstp->rq_res, &subbuf, offset, length))
+		return -EMSGSIZE;
+
+	rdma = container_of(rqstp->rq_xprt, struct svcxprt_rdma, sc_xprt);
+	ret = svc_rdma_send_write_chunk(rdma, chunk, &subbuf);
+	if (ret < 0)
+		return ret;
 	return 0;
 }
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index fb044792b571..afba4e9d5425 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -80,7 +80,7 @@ static const struct svc_xprt_ops svc_rdma_ops = {
 	.xpo_create = svc_rdma_create,
 	.xpo_recvfrom = svc_rdma_recvfrom,
 	.xpo_sendto = svc_rdma_sendto,
-	.xpo_read_payload = svc_rdma_read_payload,
+	.xpo_result_payload = svc_rdma_result_payload,
 	.xpo_release_rqst = svc_rdma_release_rqst,
 	.xpo_detach = svc_rdma_detach,
 	.xpo_free = svc_rdma_free,
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 053c8ab1265a..78d29d1bcc20 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -413,9 +413,6 @@ xprt_rdma_set_port(struct rpc_xprt *xprt, u16 port)
 	kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]);
 	snprintf(buf, sizeof(buf), "%4hx", port);
 	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
-
-	trace_xprtrdma_op_setport(container_of(xprt, struct rpcrdma_xprt,
-					       rx_xprt));
 }
 
 /**
@@ -586,11 +583,9 @@ xprt_rdma_allocate(struct rpc_task *task)
 
 	rqst->rq_buffer = rdmab_data(req->rl_sendbuf);
 	rqst->rq_rbuffer = rdmab_data(req->rl_recvbuf);
-	trace_xprtrdma_op_allocate(task, req);
 	return 0;
 
 out_fail:
-	trace_xprtrdma_op_allocate(task, NULL);
 	return -ENOMEM;
 }
 
@@ -604,13 +599,12 @@ static void
 xprt_rdma_free(struct rpc_task *task)
 {
 	struct rpc_rqst *rqst = task->tk_rqstp;
-	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(rqst->rq_xprt);
 	struct rpcrdma_req *req = rpcr_to_rdmar(rqst);
 
-	trace_xprtrdma_op_free(task, req);
-
-	if (!list_empty(&req->rl_registered))
-		frwr_unmap_sync(r_xprt, req);
+	if (unlikely(!list_empty(&req->rl_registered))) {
+		trace_xprtrdma_mrs_zap(task);
+		frwr_unmap_sync(rpcx_to_rdmax(rqst->rq_xprt), req);
+	}
 
 	/* XXX: If the RPC is completing because of a signal and
 	 * not because a reply was received, we ought to ensure
@@ -775,6 +769,7 @@ static struct xprt_class xprt_rdma = {
 	.owner			= THIS_MODULE,
 	.ident			= XPRT_TRANSPORT_RDMA,
 	.setup			= xprt_setup_rdma,
+	.netid			= { "rdma", "rdma6", "" },
 };
 
 void xprt_rdma_cleanup(void)
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index ad6e2e4994ce..ec912cf9c618 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -167,7 +167,7 @@ static void rpcrdma_wc_send(struct ib_cq *cq, struct ib_wc *wc)
 	struct rpcrdma_xprt *r_xprt = cq->cq_context;
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_send(sc, wc);
+	trace_xprtrdma_wc_send(wc, &sc->sc_cid);
 	rpcrdma_sendctx_put_locked(r_xprt, sc);
 	rpcrdma_flush_disconnect(r_xprt, wc);
 }
@@ -186,7 +186,7 @@ static void rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
 	struct rpcrdma_xprt *r_xprt = cq->cq_context;
 
 	/* WARNING: Only wr_cqe and status are reliable at this point */
-	trace_xprtrdma_wc_receive(wc);
+	trace_xprtrdma_wc_receive(wc, &rep->rr_cid);
 	--r_xprt->rx_ep->re_receive_count;
 	if (wc->status != IB_WC_SUCCESS)
 		goto out_flushed;
@@ -643,6 +643,9 @@ static struct rpcrdma_sendctx *rpcrdma_sendctx_create(struct rpcrdma_ep *ep)
 		return NULL;
 
 	sc->sc_cqe.done = rpcrdma_wc_send;
+	sc->sc_cid.ci_queue_id = ep->re_attr.send_cq->res.id;
+	sc->sc_cid.ci_completion_id =
+		atomic_inc_return(&ep->re_completion_ids);
 	return sc;
 }
 
@@ -972,6 +975,9 @@ struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt,
 	if (!rpcrdma_regbuf_dma_map(r_xprt, rep->rr_rdmabuf))
 		goto out_free_regbuf;
 
+	rep->rr_cid.ci_completion_id =
+		atomic_inc_return(&r_xprt->rx_ep->re_completion_ids);
+
 	xdr_buf_init(&rep->rr_hdrbuf, rdmab_data(rep->rr_rdmabuf),
 		     rdmab_length(rep->rr_rdmabuf));
 	rep->rr_cqe.done = rpcrdma_wc_receive;
@@ -1179,25 +1185,6 @@ rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt)
 }
 
 /**
- * rpcrdma_mr_put - DMA unmap an MR and release it
- * @mr: MR to release
- *
- */
-void rpcrdma_mr_put(struct rpcrdma_mr *mr)
-{
-	struct rpcrdma_xprt *r_xprt = mr->mr_xprt;
-
-	if (mr->mr_dir != DMA_NONE) {
-		trace_xprtrdma_mr_unmap(mr);
-		ib_dma_unmap_sg(r_xprt->rx_ep->re_id->device,
-				mr->mr_sg, mr->mr_nents, mr->mr_dir);
-		mr->mr_dir = DMA_NONE;
-	}
-
-	rpcrdma_mr_push(mr, &mr->mr_req->rl_free_mrs);
-}
-
-/**
  * rpcrdma_buffer_get - Get a request buffer
  * @buffers: Buffer pool from which to obtain a buffer
  *
@@ -1411,6 +1398,7 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp)
 		if (!rep)
 			break;
 
+		rep->rr_cid.ci_queue_id = ep->re_attr.recv_cq->res.id;
 		trace_xprtrdma_post_recv(rep);
 		rep->rr_recv_wr.next = wr;
 		wr = &rep->rr_recv_wr;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 43974ef39a50..94b28657aeeb 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -53,6 +53,7 @@
 #include <rdma/ib_verbs.h>		/* RDMA verbs api */
 
 #include <linux/sunrpc/clnt.h> 		/* rpc_xprt */
+#include <linux/sunrpc/rpc_rdma_cid.h> 	/* completion IDs */
 #include <linux/sunrpc/rpc_rdma.h> 	/* RPC/RDMA protocol */
 #include <linux/sunrpc/xprtrdma.h> 	/* xprt parameters */
 
@@ -93,6 +94,8 @@ struct rpcrdma_ep {
 	unsigned int		re_max_requests; /* depends on device */
 	unsigned int		re_inline_send;	/* negotiated */
 	unsigned int		re_inline_recv;	/* negotiated */
+
+	atomic_t		re_completion_ids;
 };
 
 /* Pre-allocate extra Work Requests for handling backward receives
@@ -180,6 +183,8 @@ enum {
 
 struct rpcrdma_rep {
 	struct ib_cqe		rr_cqe;
+	struct rpc_rdma_cid	rr_cid;
+
 	__be32			rr_xid;
 	__be32			rr_vers;
 	__be32			rr_proc;
@@ -211,6 +216,7 @@ enum {
 struct rpcrdma_req;
 struct rpcrdma_sendctx {
 	struct ib_cqe		sc_cqe;
+	struct rpc_rdma_cid	sc_cid;
 	struct rpcrdma_req	*sc_req;
 	unsigned int		sc_unmap_count;
 	struct ib_sge		sc_sges[];
@@ -225,6 +231,7 @@ struct rpcrdma_sendctx {
 struct rpcrdma_frwr {
 	struct ib_mr			*fr_mr;
 	struct ib_cqe			fr_cqe;
+	struct rpc_rdma_cid		fr_cid;
 	struct completion		fr_linv_done;
 	union {
 		struct ib_reg_wr	fr_regwr;
@@ -236,6 +243,7 @@ struct rpcrdma_req;
 struct rpcrdma_mr {
 	struct list_head	mr_list;
 	struct rpcrdma_req	*mr_req;
+	struct ib_device	*mr_device;
 	struct scatterlist	*mr_sg;
 	int			mr_nents;
 	enum dma_data_direction	mr_dir;
@@ -466,7 +474,6 @@ void rpcrdma_buffer_destroy(struct rpcrdma_buffer *);
 struct rpcrdma_sendctx *rpcrdma_sendctx_get_locked(struct rpcrdma_xprt *r_xprt);
 
 struct rpcrdma_mr *rpcrdma_mr_get(struct rpcrdma_xprt *r_xprt);
-void rpcrdma_mr_put(struct rpcrdma_mr *mr);
 void rpcrdma_mrs_refresh(struct rpcrdma_xprt *r_xprt);
 
 struct rpcrdma_req *rpcrdma_buffer_get(struct rpcrdma_buffer *);
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 554e1bb4c1c7..c56a66cdf4ac 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -433,7 +433,8 @@ xs_read_xdr_buf(struct socket *sock, struct msghdr *msg, int flags,
 		if (ret <= 0)
 			goto sock_err;
 		xs_flush_bvec(buf->bvec, ret, seek + buf->page_base);
-		offset += ret - buf->page_base;
+		ret -= buf->page_base;
+		offset += ret;
 		if (offset == count || msg->msg_flags & (MSG_EOR|MSG_TRUNC))
 			goto out;
 		if (ret != want)
@@ -762,10 +763,7 @@ static int xs_nospace(struct rpc_rqst *req)
 	struct sock *sk = transport->inet;
 	int ret = -EAGAIN;
 
-	dprintk("RPC: %5u xmit incomplete (%u left of %u)\n",
-			req->rq_task->tk_pid,
-			req->rq_slen - transport->xmit.offset,
-			req->rq_slen);
+	trace_rpc_socket_nospace(req, transport);
 
 	/* Protect against races with write_space */
 	spin_lock(&xprt->transport_lock);
@@ -3062,6 +3060,7 @@ static struct xprt_class	xs_local_transport = {
 	.owner		= THIS_MODULE,
 	.ident		= XPRT_TRANSPORT_LOCAL,
 	.setup		= xs_setup_local,
+	.netid		= { "" },
 };
 
 static struct xprt_class	xs_udp_transport = {
@@ -3070,6 +3069,7 @@ static struct xprt_class	xs_udp_transport = {
 	.owner		= THIS_MODULE,
 	.ident		= XPRT_TRANSPORT_UDP,
 	.setup		= xs_setup_udp,
+	.netid		= { "udp", "udp6", "" },
 };
 
 static struct xprt_class	xs_tcp_transport = {
@@ -3078,6 +3078,7 @@ static struct xprt_class	xs_tcp_transport = {
 	.owner		= THIS_MODULE,
 	.ident		= XPRT_TRANSPORT_TCP,
 	.setup		= xs_setup_tcp,
+	.netid		= { "tcp", "tcp6", "" },
 };
 
 static struct xprt_class	xs_bc_tcp_transport = {
@@ -3086,6 +3087,7 @@ static struct xprt_class	xs_bc_tcp_transport = {
 	.owner		= THIS_MODULE,
 	.ident		= XPRT_TRANSPORT_BC_TCP,
 	.setup		= xs_setup_bc_tcp,
+	.netid		= { "" },
 };
 
 /**
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 23d868545362..2c1ffc9ba2eb 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -460,10 +460,11 @@ static int __switchdev_handle_port_obj_add(struct net_device *dev,
 	extack = switchdev_notifier_info_to_extack(&port_obj_info->info);
 
 	if (check_cb(dev)) {
-		/* This flag is only checked if the return value is success. */
-		port_obj_info->handled = true;
-		return add_cb(dev, port_obj_info->obj, port_obj_info->trans,
-			      extack);
+		err = add_cb(dev, port_obj_info->obj, port_obj_info->trans,
+			     extack);
+		if (err != -EOPNOTSUPP)
+			port_obj_info->handled = true;
+		return err;
 	}
 
 	/* Switch ports might be stacked under e.g. a LAG. Ignore the
@@ -515,9 +516,10 @@ static int __switchdev_handle_port_obj_del(struct net_device *dev,
 	int err = -EOPNOTSUPP;
 
 	if (check_cb(dev)) {
-		/* This flag is only checked if the return value is success. */
-		port_obj_info->handled = true;
-		return del_cb(dev, port_obj_info->obj);
+		err = del_cb(dev, port_obj_info->obj);
+		if (err != -EOPNOTSUPP)
+			port_obj_info->handled = true;
+		return err;
 	}
 
 	/* Switch ports might be stacked under e.g. a LAG. Ignore the
@@ -568,9 +570,10 @@ static int __switchdev_handle_port_attr_set(struct net_device *dev,
 	int err = -EOPNOTSUPP;
 
 	if (check_cb(dev)) {
-		port_attr_info->handled = true;
-		return set_cb(dev, port_attr_info->attr,
-			      port_attr_info->trans);
+		err = set_cb(dev, port_attr_info->attr, port_attr_info->trans);
+		if (err != -EOPNOTSUPP)
+			port_attr_info->handled = true;
+		return err;
 	}
 
 	/* Switch ports might be stacked under e.g. a LAG. Ignore the
diff --git a/net/tipc/addr.c b/net/tipc/addr.c
index 0f1eaed1bd1b..abe29d1aa23a 100644
--- a/net/tipc/addr.c
+++ b/net/tipc/addr.c
@@ -55,12 +55,11 @@ bool tipc_in_scope(bool legacy_format, u32 domain, u32 addr)
 void tipc_set_node_id(struct net *net, u8 *id)
 {
 	struct tipc_net *tn = tipc_net(net);
-	u32 *tmp = (u32 *)id;
 
 	memcpy(tn->node_id, id, NODE_ID_LEN);
 	tipc_nodeid2string(tn->node_id_string, id);
-	tn->trial_addr = tmp[0] ^ tmp[1] ^ tmp[2] ^ tmp[3];
-	pr_info("Own node identity %s, cluster identity %u\n",
+	tn->trial_addr = hash128to32(id);
+	pr_info("Node identity %s, cluster identity %u\n",
 		tipc_own_id_string(net), tn->net_id);
 }
 
@@ -76,7 +75,7 @@ void tipc_set_node_addr(struct net *net, u32 addr)
 	}
 	tn->trial_addr = addr;
 	tn->addr_trial_end = jiffies;
-	pr_info("32-bit node address hash set to %x\n", addr);
+	pr_info("Node number set to %u\n", addr);
 }
 
 char *tipc_nodeid2string(char *str, u8 *id)
diff --git a/net/tipc/addr.h b/net/tipc/addr.h
index 31bee0ea7b3e..1a11831bef62 100644
--- a/net/tipc/addr.h
+++ b/net/tipc/addr.h
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2000-2006, 2018, Ericsson AB
  * Copyright (c) 2004-2005, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index 940d176e0e87..d4beca895992 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -108,6 +108,8 @@ static void tipc_bcbase_select_primary(struct net *net)
 {
 	struct tipc_bc_base *bb = tipc_bc_base(net);
 	int all_dests =  tipc_link_bc_peers(bb->link);
+	int max_win = tipc_link_max_win(bb->link);
+	int min_win = tipc_link_min_win(bb->link);
 	int i, mtu, prim;
 
 	bb->primary_bearer = INVALID_BEARER_ID;
@@ -121,8 +123,12 @@ static void tipc_bcbase_select_primary(struct net *net)
 			continue;
 
 		mtu = tipc_bearer_mtu(net, i);
-		if (mtu < tipc_link_mtu(bb->link))
+		if (mtu < tipc_link_mtu(bb->link)) {
 			tipc_link_set_mtu(bb->link, mtu);
+			tipc_link_set_queue_limits(bb->link,
+						   min_win,
+						   max_win);
+		}
 		bb->bcast_support &= tipc_bearer_bcast_support(net, i);
 		if (bb->dests[i] < all_dests)
 			continue;
@@ -585,7 +591,7 @@ static int tipc_bc_link_set_queue_limits(struct net *net, u32 max_win)
 	if (max_win > TIPC_MAX_LINK_WIN)
 		return -EINVAL;
 	tipc_bcast_lock(net);
-	tipc_link_set_queue_limits(l, BCLINK_WIN_MIN, max_win);
+	tipc_link_set_queue_limits(l, tipc_link_min_win(l), max_win);
 	tipc_bcast_unlock(net);
 	return 0;
 }
diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 650414110452..a4389ef08a98 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -72,6 +72,7 @@ static int tipc_l2_rcv_msg(struct sk_buff *skb, struct net_device *dev,
 
 /**
  * tipc_media_find - locates specified media object by name
+ * @name: name to locate
  */
 struct tipc_media *tipc_media_find(const char *name)
 {
@@ -86,6 +87,7 @@ struct tipc_media *tipc_media_find(const char *name)
 
 /**
  * media_find_id - locates specified media object by type identifier
+ * @type: type identifier to locate
  */
 static struct tipc_media *media_find_id(u8 type)
 {
@@ -100,6 +102,9 @@ static struct tipc_media *media_find_id(u8 type)
 
 /**
  * tipc_media_addr_printf - record media address in print buffer
+ * @buf: output buffer
+ * @len: output buffer size remaining
+ * @a: input media address
  */
 int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
 {
@@ -127,7 +132,7 @@ int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a)
  * @name: ptr to bearer name string
  * @name_parts: ptr to area for bearer name components (or NULL if not needed)
  *
- * Returns 1 if bearer name is valid, otherwise 0.
+ * Return: 1 if bearer name is valid, otherwise 0.
  */
 static int bearer_name_validate(const char *name,
 				struct tipc_bearer_names *name_parts)
@@ -139,10 +144,7 @@ static int bearer_name_validate(const char *name,
 	u32 if_len;
 
 	/* copy bearer name & ensure length is OK */
-	name_copy[TIPC_MAX_BEARER_NAME - 1] = 0;
-	/* need above in case non-Posix strncpy() doesn't pad with nulls */
-	strncpy(name_copy, name, TIPC_MAX_BEARER_NAME);
-	if (name_copy[TIPC_MAX_BEARER_NAME - 1] != 0)
+	if (strscpy(name_copy, name, TIPC_MAX_BEARER_NAME) < 0)
 		return 0;
 
 	/* ensure all component parts of bearer name are present */
@@ -169,6 +171,8 @@ static int bearer_name_validate(const char *name,
 
 /**
  * tipc_bearer_find - locates bearer object with matching bearer name
+ * @net: the applicable net namespace
+ * @name: bearer name to locate
  */
 struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name)
 {
@@ -231,6 +235,11 @@ void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest)
 
 /**
  * tipc_enable_bearer - enable bearer with the given name
+ * @net: the applicable net namespace
+ * @name: bearer name to enable
+ * @disc_domain: bearer domain
+ * @prio: bearer priority
+ * @attr: nlattr array
  */
 static int tipc_enable_bearer(struct net *net, const char *name,
 			      u32 disc_domain, u32 prio,
@@ -345,6 +354,8 @@ rejected:
 
 /**
  * tipc_reset_bearer - Reset all links established over this bearer
+ * @net: the applicable net namespace
+ * @b: the target bearer
  */
 static int tipc_reset_bearer(struct net *net, struct tipc_bearer *b)
 {
@@ -366,7 +377,9 @@ void tipc_bearer_put(struct tipc_bearer *b)
 }
 
 /**
- * bearer_disable
+ * bearer_disable - disable this bearer
+ * @net: the applicable net namespace
+ * @b: the bearer to disable
  *
  * Note: This routine assumes caller holds RTNL lock.
  */
@@ -437,6 +450,7 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
 }
 
 /* tipc_disable_l2_media - detach TIPC bearer from an L2 interface
+ * @b: the target bearer
  *
  * Mark L2 bearer as inactive so that incoming buffers are thrown away
  */
@@ -453,6 +467,7 @@ void tipc_disable_l2_media(struct tipc_bearer *b)
 
 /**
  * tipc_l2_send_msg - send a TIPC packet out over an L2 interface
+ * @net: the associated network namespace
  * @skb: the packet to be sent
  * @b: the bearer through which the packet is to be sent
  * @dest: peer destination address
diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h
index bc0023119da2..6bf4550aa1ac 100644
--- a/net/tipc/bearer.h
+++ b/net/tipc/bearer.h
@@ -93,7 +93,8 @@ struct tipc_bearer;
  * @raw2addr: convert from raw addr format to media addr format
  * @priority: default link (and bearer) priority
  * @tolerance: default time (in ms) before declaring link failure
- * @window: default window (in packets) before declaring link congestion
+ * @min_win: minimum window (in packets) before declaring link congestion
+ * @max_win: maximum window (in packets) before declaring link congestion
  * @mtu: max packet size bearer can support for media type not dependent on
  * underlying device MTU
  * @type_id: TIPC media identifier
@@ -138,12 +139,15 @@ struct tipc_media {
  * @pt: packet type for bearer
  * @rcu: rcu struct for tipc_bearer
  * @priority: default link priority for bearer
- * @window: default window size for bearer
+ * @min_win: minimum window (in packets) before declaring link congestion
+ * @max_win: maximum window (in packets) before declaring link congestion
  * @tolerance: default link tolerance for bearer
  * @domain: network domain to which links can be established
  * @identity: array index of this bearer within TIPC bearer array
- * @link_req: ptr to (optional) structure making periodic link setup requests
+ * @disc: ptr to link setup request
  * @net_plane: network plane ('A' through 'H') currently associated with bearer
+ * @up: bearer up flag (bit 0)
+ * @refcnt: tipc_bearer reference counter
  *
  * Note: media-specific code is responsible for initialization of the fields
  * indicated below when a bearer is enabled; TIPC's generic bearer code takes
diff --git a/net/tipc/core.c b/net/tipc/core.c
index 4f6dc74adf45..5cc1f0307215 100644
--- a/net/tipc/core.c
+++ b/net/tipc/core.c
@@ -60,6 +60,7 @@ static int __net_init tipc_init_net(struct net *net)
 	tn->trial_addr = 0;
 	tn->addr_trial_end = 0;
 	tn->capabilities = TIPC_NODE_CAPABILITIES;
+	INIT_WORK(&tn->final_work.work, tipc_net_finalize_work);
 	memset(tn->node_id, 0, sizeof(tn->node_id));
 	memset(tn->node_id_string, 0, sizeof(tn->node_id_string));
 	tn->mon_threshold = TIPC_DEF_MON_THRESHOLD;
@@ -80,8 +81,6 @@ static int __net_init tipc_init_net(struct net *net)
 	if (err)
 		goto out_nametbl;
 
-	INIT_LIST_HEAD(&tn->dist_queue);
-
 	err = tipc_bcast_init(net);
 	if (err)
 		goto out_bclink;
@@ -107,8 +106,13 @@ out_crypto:
 
 static void __net_exit tipc_exit_net(struct net *net)
 {
+	struct tipc_net *tn = tipc_net(net);
+
 	tipc_detach_loopback(net);
+	/* Make sure the tipc_net_finalize_work() finished */
+	cancel_work_sync(&tn->final_work.work);
 	tipc_net_stop(net);
+
 	tipc_bcast_stop(net);
 	tipc_nametbl_stop(net);
 	tipc_sk_rht_destroy(net);
diff --git a/net/tipc/core.h b/net/tipc/core.h
index 631d83c9705f..03de7b213f55 100644
--- a/net/tipc/core.h
+++ b/net/tipc/core.h
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2005-2006, 2013-2018 Ericsson AB
  * Copyright (c) 2005-2007, 2010-2013, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -90,6 +91,12 @@ extern unsigned int tipc_net_id __read_mostly;
 extern int sysctl_tipc_rmem[3] __read_mostly;
 extern int sysctl_tipc_named_timeout __read_mostly;
 
+struct tipc_net_work {
+	struct work_struct work;
+	struct net *net;
+	u32 addr;
+};
+
 struct tipc_net {
 	u8  node_id[NODE_ID_LEN];
 	u32 node_addr;
@@ -126,9 +133,6 @@ struct tipc_net {
 	spinlock_t nametbl_lock;
 	struct name_table *nametbl;
 
-	/* Name dist queue */
-	struct list_head dist_queue;
-
 	/* Topology subscription server */
 	struct tipc_topsrv *topsrv;
 	atomic_t subscription_count;
@@ -143,6 +147,8 @@ struct tipc_net {
 	/* TX crypto handler */
 	struct tipc_crypto *crypto_tx;
 #endif
+	/* Work item for net finalize */
+	struct tipc_net_work final_work;
 };
 
 static inline struct tipc_net *tipc_net(struct net *net)
@@ -205,6 +211,17 @@ static inline u32 tipc_net_hash_mixes(struct net *net, int tn_rand)
 	return net_hash_mix(&init_net) ^ net_hash_mix(net) ^ tn_rand;
 }
 
+static inline u32 hash128to32(char *bytes)
+{
+	__be32 *tmp = (__be32 *)bytes;
+	u32 res;
+
+	res = ntohl(tmp[0] ^ tmp[1] ^ tmp[2] ^ tmp[3]);
+	if (likely(res))
+		return res;
+	return  ntohl(tmp[0] | tmp[1] | tmp[2] | tmp[3]);
+}
+
 #ifdef CONFIG_SYSCTL
 int tipc_register_sysctl(void);
 void tipc_unregister_sysctl(void);
diff --git a/net/tipc/crypto.c b/net/tipc/crypto.c
index 7c523dc81575..f4fca8f7f63f 100644
--- a/net/tipc/crypto.c
+++ b/net/tipc/crypto.c
@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * net/tipc/crypto.c: TIPC crypto for key handling & packet en/decryption
  *
  * Copyright (c) 2019, Ericsson AB
@@ -36,28 +36,34 @@
 
 #include <crypto/aead.h>
 #include <crypto/aes.h>
+#include <crypto/rng.h>
 #include "crypto.h"
+#include "msg.h"
+#include "bcast.h"
 
-#define TIPC_TX_PROBE_LIM	msecs_to_jiffies(1000) /* > 1s */
-#define TIPC_TX_LASTING_LIM	msecs_to_jiffies(120000) /* 2 mins */
+#define TIPC_TX_GRACE_PERIOD	msecs_to_jiffies(5000) /* 5s */
+#define TIPC_TX_LASTING_TIME	msecs_to_jiffies(10000) /* 10s */
 #define TIPC_RX_ACTIVE_LIM	msecs_to_jiffies(3000) /* 3s */
-#define TIPC_RX_PASSIVE_LIM	msecs_to_jiffies(180000) /* 3 mins */
+#define TIPC_RX_PASSIVE_LIM	msecs_to_jiffies(15000) /* 15s */
+
 #define TIPC_MAX_TFMS_DEF	10
 #define TIPC_MAX_TFMS_LIM	1000
 
-/**
+#define TIPC_REKEYING_INTV_DEF	(60 * 24) /* default: 1 day */
+
+/*
  * TIPC Key ids
  */
 enum {
-	KEY_UNUSED = 0,
-	KEY_MIN,
-	KEY_1 = KEY_MIN,
+	KEY_MASTER = 0,
+	KEY_MIN = KEY_MASTER,
+	KEY_1 = 1,
 	KEY_2,
 	KEY_3,
 	KEY_MAX = KEY_3,
 };
 
-/**
+/*
  * TIPC Crypto statistics
  */
 enum {
@@ -81,8 +87,10 @@ static const char *hstats[MAX_STATS] = {"ok", "nok", "async", "async_ok",
 
 /* Max TFMs number per key */
 int sysctl_tipc_max_tfms __read_mostly = TIPC_MAX_TFMS_DEF;
+/* Key exchange switch, default: on */
+int sysctl_tipc_key_exchange_enabled __read_mostly = 1;
 
-/**
+/*
  * struct tipc_key - TIPC keys' status indicator
  *
  *         7     6     5     4     3     2     1     0
@@ -115,6 +123,8 @@ struct tipc_key {
 
 /**
  * struct tipc_tfm - TIPC TFM structure to form a list of TFMs
+ * @tfm: cipher handle/key
+ * @list: linked list of TFMs
  */
 struct tipc_tfm {
 	struct crypto_aead *tfm;
@@ -130,8 +140,10 @@ struct tipc_tfm {
  * @salt: the key's SALT value
  * @authsize: authentication tag size (max = 16)
  * @mode: crypto mode is applied to the key
- * @hint[]: a hint for user key
+ * @hint: a hint for user key
  * @rcu: struct rcu_head
+ * @key: the aead key
+ * @gen: the key's generation
  * @seqno: the key seqno (cluster scope)
  * @refcnt: the key reference counter
  */
@@ -144,8 +156,10 @@ struct tipc_aead {
 	u32 salt;
 	u8 authsize;
 	u8 mode;
-	char hint[TIPC_AEAD_HINT_LEN + 1];
+	char hint[2 * TIPC_AEAD_HINT_LEN + 1];
 	struct rcu_head rcu;
+	struct tipc_aead_key *key;
+	u16 gen;
 
 	atomic64_t seqno ____cacheline_aligned;
 	refcount_t refcnt ____cacheline_aligned;
@@ -154,6 +168,7 @@ struct tipc_aead {
 
 /**
  * struct tipc_crypto_stats - TIPC Crypto statistics
+ * @stat: array of crypto statistics
  */
 struct tipc_crypto_stats {
 	unsigned int stat[MAX_STATS];
@@ -165,26 +180,57 @@ struct tipc_crypto_stats {
  * @node: TIPC node (RX)
  * @aead: array of pointers to AEAD keys for encryption/decryption
  * @peer_rx_active: replicated peer RX active key index
+ * @key_gen: TX/RX key generation
  * @key: the key states
- * @working: the crypto is working or not
+ * @skey_mode: session key's mode
+ * @skey: received session key
+ * @wq: common workqueue on TX crypto
+ * @work: delayed work sched for TX/RX
+ * @key_distr: key distributing state
+ * @rekeying_intv: rekeying interval (in minutes)
  * @stats: the crypto statistics
+ * @name: the crypto name
  * @sndnxt: the per-peer sndnxt (TX)
  * @timer1: general timer 1 (jiffies)
- * @timer2: general timer 1 (jiffies)
+ * @timer2: general timer 2 (jiffies)
+ * @working: the crypto is working or not
+ * @key_master: flag indicates if master key exists
+ * @legacy_user: flag indicates if a peer joins w/o master key (for bwd comp.)
+ * @nokey: no key indication
+ * @flags: combined flags field
  * @lock: tipc_key lock
  */
 struct tipc_crypto {
 	struct net *net;
 	struct tipc_node *node;
-	struct tipc_aead __rcu *aead[KEY_MAX + 1]; /* key[0] is UNUSED */
+	struct tipc_aead __rcu *aead[KEY_MAX + 1];
 	atomic_t peer_rx_active;
+	u16 key_gen;
 	struct tipc_key key;
-	u8 working:1;
+	u8 skey_mode;
+	struct tipc_aead_key *skey;
+	struct workqueue_struct *wq;
+	struct delayed_work work;
+#define KEY_DISTR_SCHED		1
+#define KEY_DISTR_COMPL		2
+	atomic_t key_distr;
+	u32 rekeying_intv;
+
 	struct tipc_crypto_stats __percpu *stats;
+	char name[48];
 
 	atomic64_t sndnxt ____cacheline_aligned;
 	unsigned long timer1;
 	unsigned long timer2;
+	union {
+		struct {
+			u8 working:1;
+			u8 key_master:1;
+			u8 legacy_user:1;
+			u8 nokey: 1;
+		};
+		u8 flags;
+	};
 	spinlock_t lock; /* crypto lock */
 
 } ____cacheline_aligned;
@@ -234,23 +280,35 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c,
 					     u8 new_active,
 					     u8 new_pending);
 static int tipc_crypto_key_attach(struct tipc_crypto *c,
-				  struct tipc_aead *aead, u8 pos);
+				  struct tipc_aead *aead, u8 pos,
+				  bool master_key);
 static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending);
 static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
 						 struct tipc_crypto *rx,
-						 struct sk_buff *skb);
-static void tipc_crypto_key_synch(struct tipc_crypto *rx, u8 new_rx_active,
-				  struct tipc_msg *hdr);
+						 struct sk_buff *skb,
+						 u8 tx_key);
+static void tipc_crypto_key_synch(struct tipc_crypto *rx, struct sk_buff *skb);
 static int tipc_crypto_key_revoke(struct net *net, u8 tx_key);
+static inline void tipc_crypto_clone_msg(struct net *net, struct sk_buff *_skb,
+					 struct tipc_bearer *b,
+					 struct tipc_media_addr *dst,
+					 struct tipc_node *__dnode, u8 type);
 static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
 				     struct tipc_bearer *b,
 				     struct sk_buff **skb, int err);
 static void tipc_crypto_do_cmd(struct net *net, int cmd);
 static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf);
-#ifdef TIPC_CRYPTO_DEBUG
 static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new,
 				  char *buf);
-#endif
+static int tipc_crypto_key_xmit(struct net *net, struct tipc_aead_key *skey,
+				u16 gen, u8 mode, u32 dnode);
+static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr);
+static void tipc_crypto_work_tx(struct work_struct *work);
+static void tipc_crypto_work_rx(struct work_struct *work);
+static int tipc_aead_key_generate(struct tipc_aead_key *skey);
+
+#define is_tx(crypto) (!(crypto)->node)
+#define is_rx(crypto) (!is_tx(crypto))
 
 #define key_next(cur) ((cur) % KEY_MAX + 1)
 
@@ -270,31 +328,58 @@ do {									\
 
 /**
  * tipc_aead_key_validate - Validate a AEAD user key
+ * @ukey: pointer to user key data
+ * @info: netlink info pointer
  */
-int tipc_aead_key_validate(struct tipc_aead_key *ukey)
+int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info)
 {
 	int keylen;
 
 	/* Check if algorithm exists */
 	if (unlikely(!crypto_has_alg(ukey->alg_name, 0, 0))) {
-		pr_info("Not found cipher: \"%s\"!\n", ukey->alg_name);
+		GENL_SET_ERR_MSG(info, "unable to load the algorithm (module existed?)");
 		return -ENODEV;
 	}
 
 	/* Currently, we only support the "gcm(aes)" cipher algorithm */
-	if (strcmp(ukey->alg_name, "gcm(aes)"))
+	if (strcmp(ukey->alg_name, "gcm(aes)")) {
+		GENL_SET_ERR_MSG(info, "not supported yet the algorithm");
 		return -ENOTSUPP;
+	}
 
 	/* Check if key size is correct */
 	keylen = ukey->keylen - TIPC_AES_GCM_SALT_SIZE;
 	if (unlikely(keylen != TIPC_AES_GCM_KEY_SIZE_128 &&
 		     keylen != TIPC_AES_GCM_KEY_SIZE_192 &&
-		     keylen != TIPC_AES_GCM_KEY_SIZE_256))
-		return -EINVAL;
+		     keylen != TIPC_AES_GCM_KEY_SIZE_256)) {
+		GENL_SET_ERR_MSG(info, "incorrect key length (20, 28 or 36 octets?)");
+		return -EKEYREJECTED;
+	}
 
 	return 0;
 }
 
+/**
+ * tipc_aead_key_generate - Generate new session key
+ * @skey: input/output key with new content
+ *
+ * Return: 0 in case of success, otherwise < 0
+ */
+static int tipc_aead_key_generate(struct tipc_aead_key *skey)
+{
+	int rc = 0;
+
+	/* Fill the key's content with a random value via RNG cipher */
+	rc = crypto_get_default_rng();
+	if (likely(!rc)) {
+		rc = crypto_rng_get_bytes(crypto_default_rng, skey->key,
+					  skey->keylen);
+		crypto_put_default_rng();
+	}
+
+	return rc;
+}
+
 static struct tipc_aead *tipc_aead_get(struct tipc_aead __rcu *aead)
 {
 	struct tipc_aead *tmp;
@@ -339,6 +424,7 @@ static void tipc_aead_free(struct rcu_head *rp)
 		kfree(head);
 	}
 	free_percpu(aead->tfm_entry);
+	kfree_sensitive(aead->key);
 	kfree(aead);
 }
 
@@ -397,6 +483,7 @@ static void tipc_aead_users_set(struct tipc_aead __rcu *aead, int val)
 
 /**
  * tipc_aead_tfm_next - Move TFM entry to the next one in list and return it
+ * @aead: the AEAD key pointer
  */
 static struct crypto_aead *tipc_aead_tfm_next(struct tipc_aead *aead)
 {
@@ -501,14 +588,15 @@ static int tipc_aead_init(struct tipc_aead **aead, struct tipc_aead_key *ukey,
 		return err;
 	}
 
-	/* Copy some chars from the user key as a hint */
-	memcpy(tmp->hint, ukey->key, TIPC_AEAD_HINT_LEN);
-	tmp->hint[TIPC_AEAD_HINT_LEN] = '\0';
+	/* Form a hex string of some last bytes as the key's hint */
+	bin2hex(tmp->hint, ukey->key + keylen - TIPC_AEAD_HINT_LEN,
+		TIPC_AEAD_HINT_LEN);
 
 	/* Initialize the other data */
 	tmp->mode = mode;
 	tmp->cloned = NULL;
 	tmp->authsize = TIPC_AES_GCM_TAG_SIZE;
+	tmp->key = kmemdup(ukey, tipc_aead_key_size(ukey), GFP_KERNEL);
 	memcpy(&tmp->salt, ukey->key + keylen, TIPC_AES_GCM_SALT_SIZE);
 	atomic_set(&tmp->users, 0);
 	atomic64_set(&tmp->seqno, 0);
@@ -633,9 +721,9 @@ static void *tipc_aead_mem_alloc(struct crypto_aead *tfm,
  * @__dnode: TIPC dest node if "known"
  *
  * Return:
- * 0                   : if the encryption has completed
- * -EINPROGRESS/-EBUSY : if a callback will be performed
- * < 0                 : the encryption has failed
+ * * 0                   : if the encryption has completed
+ * * -EINPROGRESS/-EBUSY : if a callback will be performed
+ * * < 0                 : the encryption has failed
  */
 static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb,
 			     struct tipc_bearer *b,
@@ -663,13 +751,11 @@ static int tipc_aead_encrypt(struct tipc_aead *aead, struct sk_buff *skb,
 	 * but there is no frag_list, it should be still fine!
 	 * Otherwise, we must cow it to be a writable buffer with the tailroom.
 	 */
-#ifdef TIPC_CRYPTO_DEBUG
 	SKB_LINEAR_ASSERT(skb);
 	if (tailen > skb_tailroom(skb)) {
-		pr_warn("TX: skb tailroom is not enough: %d, requires: %d\n",
-			skb_tailroom(skb), tailen);
+		pr_debug("TX(): skb tailroom is not enough: %d, requires: %d\n",
+			 skb_tailroom(skb), tailen);
 	}
-#endif
 
 	if (unlikely(!skb_cloned(skb) && tailen <= skb_tailroom(skb))) {
 		nsg = 1;
@@ -791,9 +877,9 @@ static void tipc_aead_encrypt_done(struct crypto_async_request *base, int err)
  * @b: TIPC bearer where the message has been received
  *
  * Return:
- * 0                   : if the decryption has completed
- * -EINPROGRESS/-EBUSY : if a callback will be performed
- * < 0                 : the decryption has failed
+ * * 0                   : if the decryption has completed
+ * * -EINPROGRESS/-EBUSY : if a callback will be performed
+ * * < 0                 : the decryption has failed
  */
 static int tipc_aead_decrypt(struct net *net, struct tipc_aead *aead,
 			     struct sk_buff *skb, struct tipc_bearer *b)
@@ -922,7 +1008,7 @@ static inline int tipc_ehdr_size(struct tipc_ehdr *ehdr)
  * tipc_ehdr_validate - Validate an encryption message
  * @skb: the message buffer
  *
- * Returns "true" if this is a valid encryption message, otherwise "false"
+ * Return: "true" if this is a valid encryption message, otherwise "false"
  */
 bool tipc_ehdr_validate(struct sk_buff *skb)
 {
@@ -940,8 +1026,6 @@ bool tipc_ehdr_validate(struct sk_buff *skb)
 		return false;
 	if (unlikely(skb->len <= ehsz + TIPC_AES_GCM_TAG_SIZE))
 		return false;
-	if (unlikely(!ehdr->tx_key))
-		return false;
 
 	return true;
 }
@@ -994,6 +1078,8 @@ static int tipc_ehdr_build(struct net *net, struct tipc_aead *aead,
 	ehdr->tx_key = tx_key;
 	ehdr->destined = (__rx) ? 1 : 0;
 	ehdr->rx_key_active = (__rx) ? __rx->key.active : 0;
+	ehdr->rx_nokey = (__rx) ? __rx->nokey : 0;
+	ehdr->master_key = aead->crypto->key_master;
 	ehdr->reserved_1 = 0;
 	ehdr->reserved_2 = 0;
 
@@ -1019,23 +1105,16 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c,
 					     u8 new_active,
 					     u8 new_pending)
 {
-#ifdef TIPC_CRYPTO_DEBUG
 	struct tipc_key old = c->key;
 	char buf[32];
-#endif
 
 	c->key.keys = ((new_passive & KEY_MASK) << (KEY_BITS * 2)) |
 		      ((new_active  & KEY_MASK) << (KEY_BITS)) |
 		      ((new_pending & KEY_MASK));
 
-#ifdef TIPC_CRYPTO_DEBUG
-	pr_info("%s(%s): key changing %s ::%pS\n",
-		(c->node) ? "RX" : "TX",
-		(c->node) ? tipc_node_get_id_str(c->node) :
-			    tipc_own_id_string(c->net),
-		tipc_key_change_dump(old, c->key, buf),
-		__builtin_return_address(0));
-#endif
+	pr_debug("%s: key changing %s ::%pS\n", c->name,
+		 tipc_key_change_dump(old, c->key, buf),
+		 __builtin_return_address(0));
 }
 
 /**
@@ -1043,6 +1122,7 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c,
  * @c: TIPC crypto to which new key is attached
  * @ukey: the user key
  * @mode: the key mode (CLUSTER_KEY or PER_NODE_KEY)
+ * @master_key: specify this is a cluster master key
  *
  * A new TIPC AEAD key will be allocated and initiated with the specified user
  * key, then attached to the TIPC crypto.
@@ -1050,7 +1130,7 @@ static inline void tipc_crypto_key_set_state(struct tipc_crypto *c,
  * Return: new key id in case of success, otherwise: < 0
  */
 int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
-			 u8 mode)
+			 u8 mode, bool master_key)
 {
 	struct tipc_aead *aead = NULL;
 	int rc = 0;
@@ -1060,17 +1140,11 @@ int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
 
 	/* Attach it to the crypto */
 	if (likely(!rc)) {
-		rc = tipc_crypto_key_attach(c, aead, 0);
+		rc = tipc_crypto_key_attach(c, aead, 0, master_key);
 		if (rc < 0)
 			tipc_aead_free(&aead->rcu);
 	}
 
-	pr_info("%s(%s): key initiating, rc %d!\n",
-		(c->node) ? "RX" : "TX",
-		(c->node) ? tipc_node_get_id_str(c->node) :
-			    tipc_own_id_string(c->net),
-		rc);
-
 	return rc;
 }
 
@@ -1079,58 +1153,58 @@ int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
  * @c: TIPC crypto to which the new AEAD key is attached
  * @aead: the new AEAD key pointer
  * @pos: desired slot in the crypto key array, = 0 if any!
+ * @master_key: specify this is a cluster master key
  *
  * Return: new key id in case of success, otherwise: -EBUSY
  */
 static int tipc_crypto_key_attach(struct tipc_crypto *c,
-				  struct tipc_aead *aead, u8 pos)
+				  struct tipc_aead *aead, u8 pos,
+				  bool master_key)
 {
-	u8 new_pending, new_passive, new_key;
 	struct tipc_key key;
 	int rc = -EBUSY;
+	u8 new_key;
 
 	spin_lock_bh(&c->lock);
 	key = c->key;
+	if (master_key) {
+		new_key = KEY_MASTER;
+		goto attach;
+	}
 	if (key.active && key.passive)
 		goto exit;
-	if (key.passive && !tipc_aead_users(c->aead[key.passive]))
-		goto exit;
 	if (key.pending) {
-		if (pos)
-			goto exit;
 		if (tipc_aead_users(c->aead[key.pending]) > 0)
 			goto exit;
+		/* if (pos): ok with replacing, will be aligned when needed */
 		/* Replace it */
-		new_pending = key.pending;
-		new_passive = key.passive;
-		new_key = new_pending;
+		new_key = key.pending;
 	} else {
 		if (pos) {
 			if (key.active && pos != key_next(key.active)) {
-				new_pending = key.pending;
-				new_passive = pos;
-				new_key = new_passive;
+				key.passive = pos;
+				new_key = pos;
 				goto attach;
 			} else if (!key.active && !key.passive) {
-				new_pending = pos;
-				new_passive = key.passive;
-				new_key = new_pending;
+				key.pending = pos;
+				new_key = pos;
 				goto attach;
 			}
 		}
-		new_pending = key_next(key.active ?: key.passive);
-		new_passive = key.passive;
-		new_key = new_pending;
+		key.pending = key_next(key.active ?: key.passive);
+		new_key = key.pending;
 	}
 
 attach:
 	aead->crypto = c;
-	tipc_crypto_key_set_state(c, new_passive, key.active, new_pending);
+	aead->gen = (is_tx(c)) ? ++c->key_gen : c->key_gen;
 	tipc_aead_rcu_replace(c->aead[new_key], aead, &c->lock);
-
+	if (likely(c->key.keys != key.keys))
+		tipc_crypto_key_set_state(c, key.passive, key.active,
+					  key.pending);
 	c->working = 1;
-	c->timer1 = jiffies;
-	c->timer2 = jiffies;
+	c->nokey = 0;
+	c->key_master |= master_key;
 	rc = new_key;
 
 exit:
@@ -1140,14 +1214,33 @@ exit:
 
 void tipc_crypto_key_flush(struct tipc_crypto *c)
 {
+	struct tipc_crypto *tx, *rx;
 	int k;
 
 	spin_lock_bh(&c->lock);
-	c->working = 0;
+	if (is_rx(c)) {
+		/* Try to cancel pending work */
+		rx = c;
+		tx = tipc_net(rx->net)->crypto_tx;
+		if (cancel_delayed_work(&rx->work)) {
+			kfree(rx->skey);
+			rx->skey = NULL;
+			atomic_xchg(&rx->key_distr, 0);
+			tipc_node_put(rx->node);
+		}
+		/* RX stopping => decrease TX key users if any */
+		k = atomic_xchg(&rx->peer_rx_active, 0);
+		if (k) {
+			tipc_aead_users_dec(tx->aead[k], 0);
+			/* Mark the point TX key users changed */
+			tx->timer1 = jiffies;
+		}
+	}
+
+	c->flags = 0;
 	tipc_crypto_key_set_state(c, 0, 0, 0);
 	for (k = KEY_MIN; k <= KEY_MAX; k++)
 		tipc_crypto_key_detach(c->aead[k], &c->lock);
-	atomic_set(&c->peer_rx_active, 0);
 	atomic64_set(&c->sndnxt, 0);
 	spin_unlock_bh(&c->lock);
 }
@@ -1206,7 +1299,8 @@ static bool tipc_crypto_key_try_align(struct tipc_crypto *rx, u8 new_pending)
 		rcu_assign_pointer(rx->aead[new_passive], tmp2);
 	refcount_set(&tmp1->refcnt, 1);
 	aligned = true;
-	pr_info("RX(%s): key is aligned!\n", tipc_node_get_id_str(rx->node));
+	pr_info_ratelimited("%s: key[%d] -> key[%d]\n", rx->name, key.pending,
+			    new_pending);
 
 exit:
 	spin_unlock(&rx->lock);
@@ -1218,6 +1312,7 @@ exit:
  * @tx: TX crypto handle
  * @rx: RX crypto handle (can be NULL)
  * @skb: the message skb which will be decrypted later
+ * @tx_key: peer TX key id
  *
  * This function looks up the existing TX keys and pick one which is suitable
  * for the message decryption, that must be a cluster key and not used before
@@ -1227,7 +1322,8 @@ exit:
  */
 static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
 						 struct tipc_crypto *rx,
-						 struct sk_buff *skb)
+						 struct sk_buff *skb,
+						 u8 tx_key)
 {
 	struct tipc_skb_cb *skb_cb = TIPC_SKB_CB(skb);
 	struct tipc_aead *aead = NULL;
@@ -1246,6 +1342,10 @@ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
 
 	/* Pick one TX key */
 	spin_lock(&tx->lock);
+	if (tx_key == KEY_MASTER) {
+		aead = tipc_aead_rcu_ptr(tx->aead[KEY_MASTER], &tx->lock);
+		goto done;
+	}
 	do {
 		k = (i == 0) ? key.pending :
 			((i == 1) ? key.active : key.passive);
@@ -1265,9 +1365,12 @@ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
 		skb->next = skb_clone(skb, GFP_ATOMIC);
 		if (unlikely(!skb->next))
 			pr_warn("Failed to clone skb for next round if any\n");
-		WARN_ON(!refcount_inc_not_zero(&aead->refcnt));
 		break;
 	} while (++i < 3);
+
+done:
+	if (likely(aead))
+		WARN_ON(!refcount_inc_not_zero(&aead->refcnt));
 	spin_unlock(&tx->lock);
 
 	return aead;
@@ -1276,53 +1379,73 @@ static struct tipc_aead *tipc_crypto_key_pick_tx(struct tipc_crypto *tx,
 /**
  * tipc_crypto_key_synch: Synch own key data according to peer key status
  * @rx: RX crypto handle
- * @new_rx_active: latest RX active key from peer
- * @hdr: TIPCv2 message
+ * @skb: TIPCv2 message buffer (incl. the ehdr from peer)
  *
  * This function updates the peer node related data as the peer RX active key
  * has changed, so the number of TX keys' users on this node are increased and
  * decreased correspondingly.
  *
+ * It also considers if peer has no key, then we need to make own master key
+ * (if any) taking over i.e. starting grace period and also trigger key
+ * distributing process.
+ *
  * The "per-peer" sndnxt is also reset when the peer key has switched.
  */
-static void tipc_crypto_key_synch(struct tipc_crypto *rx, u8 new_rx_active,
-				  struct tipc_msg *hdr)
+static void tipc_crypto_key_synch(struct tipc_crypto *rx, struct sk_buff *skb)
 {
-	struct net *net = rx->net;
-	struct tipc_crypto *tx = tipc_net(net)->crypto_tx;
-	u8 cur_rx_active;
+	struct tipc_ehdr *ehdr = (struct tipc_ehdr *)skb_network_header(skb);
+	struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx;
+	struct tipc_msg *hdr = buf_msg(skb);
+	u32 self = tipc_own_addr(rx->net);
+	u8 cur, new;
+	unsigned long delay;
 
-	/* TX might be even not ready yet */
-	if (unlikely(!tx->key.active && !tx->key.pending))
-		return;
+	/* Update RX 'key_master' flag according to peer, also mark "legacy" if
+	 * a peer has no master key.
+	 */
+	rx->key_master = ehdr->master_key;
+	if (!rx->key_master)
+		tx->legacy_user = 1;
 
-	cur_rx_active = atomic_read(&rx->peer_rx_active);
-	if (likely(cur_rx_active == new_rx_active))
+	/* For later cases, apply only if message is destined to this node */
+	if (!ehdr->destined || msg_short(hdr) || msg_destnode(hdr) != self)
 		return;
 
-	/* Make sure this message destined for this node */
-	if (unlikely(msg_short(hdr) ||
-		     msg_destnode(hdr) != tipc_own_addr(net)))
-		return;
+	/* Case 1: Peer has no keys, let's make master key take over */
+	if (ehdr->rx_nokey) {
+		/* Set or extend grace period */
+		tx->timer2 = jiffies;
+		/* Schedule key distributing for the peer if not yet */
+		if (tx->key.keys &&
+		    !atomic_cmpxchg(&rx->key_distr, 0, KEY_DISTR_SCHED)) {
+			get_random_bytes(&delay, 2);
+			delay %= 5;
+			delay = msecs_to_jiffies(500 * ++delay);
+			if (queue_delayed_work(tx->wq, &rx->work, delay))
+				tipc_node_get(rx->node);
+		}
+	} else {
+		/* Cancel a pending key distributing if any */
+		atomic_xchg(&rx->key_distr, 0);
+	}
 
-	/* Peer RX active key has changed, try to update owns' & TX users */
-	if (atomic_cmpxchg(&rx->peer_rx_active,
-			   cur_rx_active,
-			   new_rx_active) == cur_rx_active) {
-		if (new_rx_active)
-			tipc_aead_users_inc(tx->aead[new_rx_active], INT_MAX);
-		if (cur_rx_active)
-			tipc_aead_users_dec(tx->aead[cur_rx_active], 0);
+	/* Case 2: Peer RX active key has changed, let's update own TX users */
+	cur = atomic_read(&rx->peer_rx_active);
+	new = ehdr->rx_key_active;
+	if (tx->key.keys &&
+	    cur != new &&
+	    atomic_cmpxchg(&rx->peer_rx_active, cur, new) == cur) {
+		if (new)
+			tipc_aead_users_inc(tx->aead[new], INT_MAX);
+		if (cur)
+			tipc_aead_users_dec(tx->aead[cur], 0);
 
 		atomic64_set(&rx->sndnxt, 0);
 		/* Mark the point TX key users changed */
 		tx->timer1 = jiffies;
 
-#ifdef TIPC_CRYPTO_DEBUG
-		pr_info("TX(%s): key users changed %d-- %d++, peer RX(%s)\n",
-			tipc_own_id_string(net), cur_rx_active,
-			new_rx_active, tipc_node_get_id_str(rx->node));
-#endif
+		pr_debug("%s: key users changed %d-- %d++, peer %s\n",
+			 tx->name, cur, new, rx->name);
 	}
 }
 
@@ -1340,7 +1463,7 @@ static int tipc_crypto_key_revoke(struct net *net, u8 tx_key)
 	tipc_crypto_key_detach(tx->aead[key.active], &tx->lock);
 	spin_unlock(&tx->lock);
 
-	pr_warn("TX(%s): key is revoked!\n", tipc_own_id_string(net));
+	pr_warn("%s: key is revoked\n", tx->name);
 	return -EKEYREVOKED;
 }
 
@@ -1357,6 +1480,15 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net,
 	if (!c)
 		return -ENOMEM;
 
+	/* Allocate workqueue on TX */
+	if (!node) {
+		c->wq = alloc_ordered_workqueue("tipc_crypto", 0);
+		if (!c->wq) {
+			kfree(c);
+			return -ENOMEM;
+		}
+	}
+
 	/* Allocate statistic structure */
 	c->stats = alloc_percpu_gfp(struct tipc_crypto_stats, GFP_ATOMIC);
 	if (!c->stats) {
@@ -1364,53 +1496,52 @@ int tipc_crypto_start(struct tipc_crypto **crypto, struct net *net,
 		return -ENOMEM;
 	}
 
-	c->working = 0;
+	c->flags = 0;
 	c->net = net;
 	c->node = node;
+	get_random_bytes(&c->key_gen, 2);
 	tipc_crypto_key_set_state(c, 0, 0, 0);
+	atomic_set(&c->key_distr, 0);
 	atomic_set(&c->peer_rx_active, 0);
 	atomic64_set(&c->sndnxt, 0);
 	c->timer1 = jiffies;
 	c->timer2 = jiffies;
+	c->rekeying_intv = TIPC_REKEYING_INTV_DEF;
 	spin_lock_init(&c->lock);
-	*crypto = c;
+	scnprintf(c->name, 48, "%s(%s)", (is_rx(c)) ? "RX" : "TX",
+		  (is_rx(c)) ? tipc_node_get_id_str(c->node) :
+			       tipc_own_id_string(c->net));
+
+	if (is_rx(c))
+		INIT_DELAYED_WORK(&c->work, tipc_crypto_work_rx);
+	else
+		INIT_DELAYED_WORK(&c->work, tipc_crypto_work_tx);
 
+	*crypto = c;
 	return 0;
 }
 
 void tipc_crypto_stop(struct tipc_crypto **crypto)
 {
-	struct tipc_crypto *c, *tx, *rx;
-	bool is_rx;
+	struct tipc_crypto *c = *crypto;
 	u8 k;
 
-	if (!*crypto)
+	if (!c)
 		return;
 
-	rcu_read_lock();
-	/* RX stopping? => decrease TX key users if any */
-	is_rx = !!((*crypto)->node);
-	if (is_rx) {
-		rx = *crypto;
-		tx = tipc_net(rx->net)->crypto_tx;
-		k = atomic_read(&rx->peer_rx_active);
-		if (k) {
-			tipc_aead_users_dec(tx->aead[k], 0);
-			/* Mark the point TX key users changed */
-			tx->timer1 = jiffies;
-		}
+	/* Flush any queued works & destroy wq */
+	if (is_tx(c)) {
+		c->rekeying_intv = 0;
+		cancel_delayed_work_sync(&c->work);
+		destroy_workqueue(c->wq);
 	}
 
 	/* Release AEAD keys */
-	c = *crypto;
+	rcu_read_lock();
 	for (k = KEY_MIN; k <= KEY_MAX; k++)
 		tipc_aead_put(rcu_dereference(c->aead[k]));
 	rcu_read_unlock();
-
-	pr_warn("%s(%s) has been purged, node left!\n",
-		(is_rx) ? "RX" : "TX",
-		(is_rx) ? tipc_node_get_id_str((*crypto)->node) :
-			  tipc_own_id_string((*crypto)->net));
+	pr_debug("%s: has been stopped\n", c->name);
 
 	/* Free this crypto statistics */
 	free_percpu(c->stats);
@@ -1424,106 +1555,91 @@ void tipc_crypto_timeout(struct tipc_crypto *rx)
 	struct tipc_net *tn = tipc_net(rx->net);
 	struct tipc_crypto *tx = tn->crypto_tx;
 	struct tipc_key key;
-	u8 new_pending, new_passive;
 	int cmd;
 
-	/* TX key activating:
-	 * The pending key (users > 0) -> active
-	 * The active key if any (users == 0) -> free
-	 */
+	/* TX pending: taking all users & stable -> active */
 	spin_lock(&tx->lock);
 	key = tx->key;
 	if (key.active && tipc_aead_users(tx->aead[key.active]) > 0)
 		goto s1;
 	if (!key.pending || tipc_aead_users(tx->aead[key.pending]) <= 0)
 		goto s1;
-	if (time_before(jiffies, tx->timer1 + TIPC_TX_LASTING_LIM))
+	if (time_before(jiffies, tx->timer1 + TIPC_TX_LASTING_TIME))
 		goto s1;
 
 	tipc_crypto_key_set_state(tx, key.passive, key.pending, 0);
 	if (key.active)
 		tipc_crypto_key_detach(tx->aead[key.active], &tx->lock);
 	this_cpu_inc(tx->stats->stat[STAT_SWITCHES]);
-	pr_info("TX(%s): key %d is activated!\n", tipc_own_id_string(tx->net),
-		key.pending);
+	pr_info("%s: key[%d] is activated\n", tx->name, key.pending);
 
 s1:
 	spin_unlock(&tx->lock);
 
-	/* RX key activating:
-	 * The pending key (users > 0) -> active
-	 * The active key if any -> passive, freed later
-	 */
+	/* RX pending: having user -> active */
 	spin_lock(&rx->lock);
 	key = rx->key;
 	if (!key.pending || tipc_aead_users(rx->aead[key.pending]) <= 0)
 		goto s2;
 
-	new_pending = (key.passive &&
-		       !tipc_aead_users(rx->aead[key.passive])) ?
-				       key.passive : 0;
-	new_passive = (key.active) ?: ((new_pending) ? 0 : key.passive);
-	tipc_crypto_key_set_state(rx, new_passive, key.pending, new_pending);
+	if (key.active)
+		key.passive = key.active;
+	key.active = key.pending;
+	rx->timer2 = jiffies;
+	tipc_crypto_key_set_state(rx, key.passive, key.active, 0);
 	this_cpu_inc(rx->stats->stat[STAT_SWITCHES]);
-	pr_info("RX(%s): key %d is activated!\n",
-		tipc_node_get_id_str(rx->node),	key.pending);
+	pr_info("%s: key[%d] is activated\n", rx->name, key.pending);
 	goto s5;
 
 s2:
-	/* RX key "faulty" switching:
-	 * The faulty pending key (users < -30) -> passive
-	 * The passive key (users = 0) -> pending
-	 * Note: This only happens after RX deactivated - s3!
-	 */
-	key = rx->key;
-	if (!key.pending || tipc_aead_users(rx->aead[key.pending]) > -30)
-		goto s3;
-	if (!key.passive || tipc_aead_users(rx->aead[key.passive]) != 0)
+	/* RX pending: not working -> remove */
+	if (!key.pending || tipc_aead_users(rx->aead[key.pending]) > -10)
 		goto s3;
 
-	new_pending = key.passive;
-	new_passive = key.pending;
-	tipc_crypto_key_set_state(rx, new_passive, key.active, new_pending);
+	tipc_crypto_key_set_state(rx, key.passive, key.active, 0);
+	tipc_crypto_key_detach(rx->aead[key.pending], &rx->lock);
+	pr_debug("%s: key[%d] is removed\n", rx->name, key.pending);
 	goto s5;
 
 s3:
-	/* RX key deactivating:
-	 * The passive key if any -> pending
-	 * The active key -> passive (users = 0) / pending
-	 * The pending key if any -> passive (users = 0)
-	 */
-	key = rx->key;
+	/* RX active: timed out or no user -> pending */
 	if (!key.active)
 		goto s4;
-	if (time_before(jiffies, rx->timer1 + TIPC_RX_ACTIVE_LIM))
+	if (time_before(jiffies, rx->timer1 + TIPC_RX_ACTIVE_LIM) &&
+	    tipc_aead_users(rx->aead[key.active]) > 0)
 		goto s4;
 
-	new_pending = (key.passive) ?: key.active;
-	new_passive = (key.passive) ? key.active : key.pending;
-	tipc_aead_users_set(rx->aead[new_pending], 0);
-	if (new_passive)
-		tipc_aead_users_set(rx->aead[new_passive], 0);
-	tipc_crypto_key_set_state(rx, new_passive, 0, new_pending);
-	pr_info("RX(%s): key %d is deactivated!\n",
-		tipc_node_get_id_str(rx->node), key.active);
+	if (key.pending)
+		key.passive = key.active;
+	else
+		key.pending = key.active;
+	rx->timer2 = jiffies;
+	tipc_crypto_key_set_state(rx, key.passive, 0, key.pending);
+	tipc_aead_users_set(rx->aead[key.pending], 0);
+	pr_debug("%s: key[%d] is deactivated\n", rx->name, key.active);
 	goto s5;
 
 s4:
-	/* RX key passive -> freed: */
-	key = rx->key;
-	if (!key.passive || !tipc_aead_users(rx->aead[key.passive]))
+	/* RX passive: outdated or not working -> free */
+	if (!key.passive)
 		goto s5;
-	if (time_before(jiffies, rx->timer2 + TIPC_RX_PASSIVE_LIM))
+	if (time_before(jiffies, rx->timer2 + TIPC_RX_PASSIVE_LIM) &&
+	    tipc_aead_users(rx->aead[key.passive]) > -10)
 		goto s5;
 
 	tipc_crypto_key_set_state(rx, 0, key.active, key.pending);
 	tipc_crypto_key_detach(rx->aead[key.passive], &rx->lock);
-	pr_info("RX(%s): key %d is freed!\n", tipc_node_get_id_str(rx->node),
-		key.passive);
+	pr_debug("%s: key[%d] is freed\n", rx->name, key.passive);
 
 s5:
 	spin_unlock(&rx->lock);
 
+	/* Relax it here, the flag will be set again if it really is, but only
+	 * when we are not in grace period for safety!
+	 */
+	if (time_after(jiffies, tx->timer2 + TIPC_TX_GRACE_PERIOD))
+		tx->legacy_user = 0;
+
 	/* Limit max_tfms & do debug commands if needed */
 	if (likely(sysctl_tipc_max_tfms <= TIPC_MAX_TFMS_LIM))
 		return;
@@ -1533,6 +1649,22 @@ s5:
 	tipc_crypto_do_cmd(rx->net, cmd);
 }
 
+static inline void tipc_crypto_clone_msg(struct net *net, struct sk_buff *_skb,
+					 struct tipc_bearer *b,
+					 struct tipc_media_addr *dst,
+					 struct tipc_node *__dnode, u8 type)
+{
+	struct sk_buff *skb;
+
+	skb = skb_clone(_skb, GFP_ATOMIC);
+	if (skb) {
+		TIPC_SKB_CB(skb)->xmit_type = type;
+		tipc_crypto_xmit(net, &skb, b, dst, __dnode);
+		if (skb)
+			b->media->send_msg(net, skb, b, dst);
+	}
+}
+
 /**
  * tipc_crypto_xmit - Build & encrypt TIPC message for xmit
  * @net: struct net
@@ -1542,18 +1674,19 @@ s5:
  * @__dnode: destination node for reference if any
  *
  * First, build an encryption message header on the top of the message, then
- * encrypt the original TIPC message by using the active or pending TX key.
+ * encrypt the original TIPC message by using the pending, master or active
+ * key with this preference order.
  * If the encryption is successful, the encrypted skb is returned directly or
  * via the callback.
  * Otherwise, the skb is freed!
  *
  * Return:
- * 0                   : the encryption has succeeded (or no encryption)
- * -EINPROGRESS/-EBUSY : the encryption is ongoing, a callback will be made
- * -ENOKEK             : the encryption has failed due to no key
- * -EKEYREVOKED        : the encryption has failed due to key revoked
- * -ENOMEM             : the encryption has failed due to no memory
- * < 0                 : the encryption has failed due to other reasons
+ * * 0                   : the encryption has succeeded (or no encryption)
+ * * -EINPROGRESS/-EBUSY : the encryption is ongoing, a callback will be made
+ * * -ENOKEK             : the encryption has failed due to no key
+ * * -EKEYREVOKED        : the encryption has failed due to key revoked
+ * * -ENOMEM             : the encryption has failed due to no memory
+ * * < 0                 : the encryption has failed due to other reasons
  */
 int tipc_crypto_xmit(struct net *net, struct sk_buff **skb,
 		     struct tipc_bearer *b, struct tipc_media_addr *dst,
@@ -1562,46 +1695,67 @@ int tipc_crypto_xmit(struct net *net, struct sk_buff **skb,
 	struct tipc_crypto *__rx = tipc_node_crypto_rx(__dnode);
 	struct tipc_crypto *tx = tipc_net(net)->crypto_tx;
 	struct tipc_crypto_stats __percpu *stats = tx->stats;
+	struct tipc_msg *hdr = buf_msg(*skb);
 	struct tipc_key key = tx->key;
 	struct tipc_aead *aead = NULL;
-	struct sk_buff *probe;
+	u32 user = msg_user(hdr);
+	u32 type = msg_type(hdr);
 	int rc = -ENOKEY;
-	u8 tx_key;
+	u8 tx_key = 0;
 
 	/* No encryption? */
 	if (!tx->working)
 		return 0;
 
-	/* Try with the pending key if available and:
-	 * 1) This is the only choice (i.e. no active key) or;
-	 * 2) Peer has switched to this key (unicast only) or;
-	 * 3) It is time to do a pending key probe;
-	 */
+	/* Pending key if peer has active on it or probing time */
 	if (unlikely(key.pending)) {
 		tx_key = key.pending;
-		if (!key.active)
+		if (!tx->key_master && !key.active)
 			goto encrypt;
 		if (__rx && atomic_read(&__rx->peer_rx_active) == tx_key)
 			goto encrypt;
-		if (TIPC_SKB_CB(*skb)->probe)
+		if (TIPC_SKB_CB(*skb)->xmit_type == SKB_PROBING) {
+			pr_debug("%s: probing for key[%d]\n", tx->name,
+				 key.pending);
+			goto encrypt;
+		}
+		if (user == LINK_CONFIG || user == LINK_PROTOCOL)
+			tipc_crypto_clone_msg(net, *skb, b, dst, __dnode,
+					      SKB_PROBING);
+	}
+
+	/* Master key if this is a *vital* message or in grace period */
+	if (tx->key_master) {
+		tx_key = KEY_MASTER;
+		if (!key.active)
+			goto encrypt;
+		if (TIPC_SKB_CB(*skb)->xmit_type == SKB_GRACING) {
+			pr_debug("%s: gracing for msg (%d %d)\n", tx->name,
+				 user, type);
 			goto encrypt;
-		if (!__rx &&
-		    time_after(jiffies, tx->timer2 + TIPC_TX_PROBE_LIM)) {
-			tx->timer2 = jiffies;
-			probe = skb_clone(*skb, GFP_ATOMIC);
-			if (probe) {
-				TIPC_SKB_CB(probe)->probe = 1;
-				tipc_crypto_xmit(net, &probe, b, dst, __dnode);
-				if (probe)
-					b->media->send_msg(net, probe, b, dst);
+		}
+		if (user == LINK_CONFIG ||
+		    (user == LINK_PROTOCOL && type == RESET_MSG) ||
+		    (user == MSG_CRYPTO && type == KEY_DISTR_MSG) ||
+		    time_before(jiffies, tx->timer2 + TIPC_TX_GRACE_PERIOD)) {
+			if (__rx && __rx->key_master &&
+			    !atomic_read(&__rx->peer_rx_active))
+				goto encrypt;
+			if (!__rx) {
+				if (likely(!tx->legacy_user))
+					goto encrypt;
+				tipc_crypto_clone_msg(net, *skb, b, dst,
+						      __dnode, SKB_GRACING);
 			}
 		}
 	}
+
 	/* Else, use the active key if any */
 	if (likely(key.active)) {
 		tx_key = key.active;
 		goto encrypt;
 	}
+
 	goto exit;
 
 encrypt:
@@ -1652,12 +1806,12 @@ exit:
  * cluster key(s) can be taken for decryption (- recursive).
  *
  * Return:
- * 0                   : the decryption has successfully completed
- * -EINPROGRESS/-EBUSY : the decryption is ongoing, a callback will be made
- * -ENOKEY             : the decryption has failed due to no key
- * -EBADMSG            : the decryption has failed due to bad message
- * -ENOMEM             : the decryption has failed due to no memory
- * < 0                 : the decryption has failed due to other reasons
+ * * 0                   : the decryption has successfully completed
+ * * -EINPROGRESS/-EBUSY : the decryption is ongoing, a callback will be made
+ * * -ENOKEY             : the decryption has failed due to no key
+ * * -EBADMSG            : the decryption has failed due to bad message
+ * * -ENOMEM             : the decryption has failed due to no memory
+ * * < 0                 : the decryption has failed due to other reasons
  */
 int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
 		    struct sk_buff **skb, struct tipc_bearer *b)
@@ -1667,30 +1821,21 @@ int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
 	struct tipc_aead *aead = NULL;
 	struct tipc_key key;
 	int rc = -ENOKEY;
-	u8 tx_key = 0;
+	u8 tx_key, n;
+
+	tx_key = ((struct tipc_ehdr *)(*skb)->data)->tx_key;
 
 	/* New peer?
 	 * Let's try with TX key (i.e. cluster mode) & verify the skb first!
 	 */
-	if (unlikely(!rx))
+	if (unlikely(!rx || tx_key == KEY_MASTER))
 		goto pick_tx;
 
-	/* Pick RX key according to TX key, three cases are possible:
-	 * 1) The current active key (likely) or;
-	 * 2) The pending (new or deactivated) key (if any) or;
-	 * 3) The passive or old active key (i.e. users > 0);
-	 */
-	tx_key = ((struct tipc_ehdr *)(*skb)->data)->tx_key;
+	/* Pick RX key according to TX key if any */
 	key = rx->key;
-	if (likely(tx_key == key.active))
+	if (tx_key == key.active || tx_key == key.pending ||
+	    tx_key == key.passive)
 		goto decrypt;
-	if (tx_key == key.pending)
-		goto decrypt;
-	if (tx_key == key.passive) {
-		rx->timer2 = jiffies;
-		if (tipc_aead_users(rx->aead[key.passive]) > 0)
-			goto decrypt;
-	}
 
 	/* Unknown key, let's try to align RX key(s) */
 	if (tipc_crypto_key_try_align(rx, tx_key))
@@ -1698,7 +1843,7 @@ int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
 
 pick_tx:
 	/* No key suitable? Try to pick one from TX... */
-	aead = tipc_crypto_key_pick_tx(tx, rx, *skb);
+	aead = tipc_crypto_key_pick_tx(tx, rx, *skb, tx_key);
 	if (aead)
 		goto decrypt;
 	goto exit;
@@ -1726,8 +1871,19 @@ exit:
 		if (rc == -ENOKEY) {
 			kfree_skb(*skb);
 			*skb = NULL;
-			if (rx)
+			if (rx) {
+				/* Mark rx->nokey only if we dont have a
+				 * pending received session key, nor a newer
+				 * one i.e. in the next slot.
+				 */
+				n = key_next(tx_key);
+				rx->nokey = !(rx->skey ||
+					      rcu_access_pointer(rx->aead[n]));
+				pr_debug_ratelimited("%s: nokey %d, key %d/%x\n",
+						     rx->name, rx->nokey,
+						     tx_key, rx->key.keys);
 				tipc_node_put(rx->node);
+			}
 			this_cpu_inc(stats->stat[STAT_NOKEYS]);
 			return rc;
 		} else if (rc == -EBADMSG) {
@@ -1749,21 +1905,17 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
 	struct tipc_aead *tmp = NULL;
 	struct tipc_ehdr *ehdr;
 	struct tipc_node *n;
-	u8 rx_key_active;
-	bool destined;
 
 	/* Is this completed by TX? */
-	if (unlikely(!rx->node)) {
+	if (unlikely(is_tx(aead->crypto))) {
 		rx = skb_cb->tx_clone_ctx.rx;
-#ifdef TIPC_CRYPTO_DEBUG
-		pr_info("TX->RX(%s): err %d, aead %p, skb->next %p, flags %x\n",
-			(rx) ? tipc_node_get_id_str(rx->node) : "-", err, aead,
-			(*skb)->next, skb_cb->flags);
-		pr_info("skb_cb [recurs %d, last %p], tx->aead [%p %p %p]\n",
-			skb_cb->tx_clone_ctx.recurs, skb_cb->tx_clone_ctx.last,
-			aead->crypto->aead[1], aead->crypto->aead[2],
-			aead->crypto->aead[3]);
-#endif
+		pr_debug("TX->RX(%s): err %d, aead %p, skb->next %p, flags %x\n",
+			 (rx) ? tipc_node_get_id_str(rx->node) : "-", err, aead,
+			 (*skb)->next, skb_cb->flags);
+		pr_debug("skb_cb [recurs %d, last %p], tx->aead [%p %p %p]\n",
+			 skb_cb->tx_clone_ctx.recurs, skb_cb->tx_clone_ctx.last,
+			 aead->crypto->aead[1], aead->crypto->aead[2],
+			 aead->crypto->aead[3]);
 		if (unlikely(err)) {
 			if (err == -EBADMSG && (*skb)->next)
 				tipc_rcv(net, (*skb)->next, b);
@@ -1784,12 +1936,12 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
 				goto free_skb;
 		}
 
-		/* Skip cloning this time as we had a RX pending key */
-		if (rx->key.pending)
+		/* Ignore cloning if it was TX master key */
+		if (ehdr->tx_key == KEY_MASTER)
 			goto rcv;
 		if (tipc_aead_clone(&tmp, aead) < 0)
 			goto rcv;
-		if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key) < 0) {
+		if (tipc_crypto_key_attach(rx, tmp, ehdr->tx_key, false) < 0) {
 			tipc_aead_free(&tmp->rcu);
 			goto rcv;
 		}
@@ -1805,14 +1957,18 @@ static void tipc_crypto_rcv_complete(struct net *net, struct tipc_aead *aead,
 	/* Set the RX key's user */
 	tipc_aead_users_set(aead, 1);
 
-rcv:
 	/* Mark this point, RX works */
 	rx->timer1 = jiffies;
 
+rcv:
 	/* Remove ehdr & auth. tag prior to tipc_rcv() */
 	ehdr = (struct tipc_ehdr *)(*skb)->data;
-	destined = ehdr->destined;
-	rx_key_active = ehdr->rx_key_active;
+
+	/* Mark this point, RX passive still works */
+	if (rx->key.passive && ehdr->tx_key == rx->key.passive)
+		rx->timer2 = jiffies;
+
+	skb_reset_network_header(*skb);
 	skb_pull(*skb, tipc_ehdr_size(ehdr));
 	pskb_trim(*skb, (*skb)->len - aead->authsize);
 
@@ -1822,9 +1978,8 @@ rcv:
 		goto free_skb;
 	}
 
-	/* Update peer RX active key & TX users */
-	if (destined)
-		tipc_crypto_key_synch(rx, rx_key_active, buf_msg(*skb));
+	/* Ok, everything's fine, try to synch own keys according to peers' */
+	tipc_crypto_key_synch(rx, *skb);
 
 	/* Mark skb decrypted */
 	skb_cb->decrypted = 1;
@@ -1883,7 +2038,7 @@ print_stats:
 	/* Print crypto statistics */
 	for (i = 0, j = 0; i < MAX_STATS; i++)
 		j += scnprintf(buf + j, 200 - j, "|%11s ", hstats[i]);
-	pr_info("\nCounter     %s", buf);
+	pr_info("Counter     %s", buf);
 
 	memset(buf, '-', 115);
 	buf[115] = '\0';
@@ -1927,21 +2082,31 @@ static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf)
 	char *s;
 
 	for (k = KEY_MIN; k <= KEY_MAX; k++) {
-		if (k == key.passive)
-			s = "PAS";
-		else if (k == key.active)
-			s = "ACT";
-		else if (k == key.pending)
-			s = "PEN";
-		else
-			s = "-";
+		if (k == KEY_MASTER) {
+			if (is_rx(c))
+				continue;
+			if (time_before(jiffies,
+					c->timer2 + TIPC_TX_GRACE_PERIOD))
+				s = "ACT";
+			else
+				s = "PAS";
+		} else {
+			if (k == key.passive)
+				s = "PAS";
+			else if (k == key.active)
+				s = "ACT";
+			else if (k == key.pending)
+				s = "PEN";
+			else
+				s = "-";
+		}
 		i += scnprintf(buf + i, 200 - i, "\tKey%d: %s", k, s);
 
 		rcu_read_lock();
 		aead = rcu_dereference(c->aead[k]);
 		if (aead)
 			i += scnprintf(buf + i, 200 - i,
-				       "{\"%s...\", \"%s\"}/%d:%d",
+				       "{\"0x...%s\", \"%s\"}/%d:%d",
 				       aead->hint,
 				       (aead->mode == CLUSTER_KEY) ? "c" : "p",
 				       atomic_read(&aead->users),
@@ -1950,14 +2115,13 @@ static char *tipc_crypto_key_dump(struct tipc_crypto *c, char *buf)
 		i += scnprintf(buf + i, 200 - i, "\n");
 	}
 
-	if (c->node)
+	if (is_rx(c))
 		i += scnprintf(buf + i, 200 - i, "\tPeer RX active: %d\n",
 			       atomic_read(&c->peer_rx_active));
 
 	return buf;
 }
 
-#ifdef TIPC_CRYPTO_DEBUG
 static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new,
 				  char *buf)
 {
@@ -1968,7 +2132,7 @@ static char *tipc_key_change_dump(struct tipc_key old, struct tipc_key new,
 	/* Output format: "[%s %s %s] -> [%s %s %s]", max len = 32 */
 again:
 	i += scnprintf(buf + i, 32 - i, "[");
-	for (k = KEY_MIN; k <= KEY_MAX; k++) {
+	for (k = KEY_1; k <= KEY_3; k++) {
 		if (k == key->passive)
 			s = "pas";
 		else if (k == key->active)
@@ -1978,7 +2142,7 @@ again:
 		else
 			s = "-";
 		i += scnprintf(buf + i, 32 - i,
-			       (k != KEY_MAX) ? "%s " : "%s", s);
+			       (k != KEY_3) ? "%s " : "%s", s);
 	}
 	if (key != &new) {
 		i += scnprintf(buf + i, 32 - i, "] -> ");
@@ -1988,4 +2152,320 @@ again:
 	i += scnprintf(buf + i, 32 - i, "]");
 	return buf;
 }
-#endif
+
+/**
+ * tipc_crypto_msg_rcv - Common 'MSG_CRYPTO' processing point
+ * @net: the struct net
+ * @skb: the receiving message buffer
+ */
+void tipc_crypto_msg_rcv(struct net *net, struct sk_buff *skb)
+{
+	struct tipc_crypto *rx;
+	struct tipc_msg *hdr;
+
+	if (unlikely(skb_linearize(skb)))
+		goto exit;
+
+	hdr = buf_msg(skb);
+	rx = tipc_node_crypto_rx_by_addr(net, msg_prevnode(hdr));
+	if (unlikely(!rx))
+		goto exit;
+
+	switch (msg_type(hdr)) {
+	case KEY_DISTR_MSG:
+		if (tipc_crypto_key_rcv(rx, hdr))
+			goto exit;
+		break;
+	default:
+		break;
+	}
+
+	tipc_node_put(rx->node);
+
+exit:
+	kfree_skb(skb);
+}
+
+/**
+ * tipc_crypto_key_distr - Distribute a TX key
+ * @tx: the TX crypto
+ * @key: the key's index
+ * @dest: the destination tipc node, = NULL if distributing to all nodes
+ *
+ * Return: 0 in case of success, otherwise < 0
+ */
+int tipc_crypto_key_distr(struct tipc_crypto *tx, u8 key,
+			  struct tipc_node *dest)
+{
+	struct tipc_aead *aead;
+	u32 dnode = tipc_node_get_addr(dest);
+	int rc = -ENOKEY;
+
+	if (!sysctl_tipc_key_exchange_enabled)
+		return 0;
+
+	if (key) {
+		rcu_read_lock();
+		aead = tipc_aead_get(tx->aead[key]);
+		if (likely(aead)) {
+			rc = tipc_crypto_key_xmit(tx->net, aead->key,
+						  aead->gen, aead->mode,
+						  dnode);
+			tipc_aead_put(aead);
+		}
+		rcu_read_unlock();
+	}
+
+	return rc;
+}
+
+/**
+ * tipc_crypto_key_xmit - Send a session key
+ * @net: the struct net
+ * @skey: the session key to be sent
+ * @gen: the key's generation
+ * @mode: the key's mode
+ * @dnode: the destination node address, = 0 if broadcasting to all nodes
+ *
+ * The session key 'skey' is packed in a TIPC v2 'MSG_CRYPTO/KEY_DISTR_MSG'
+ * as its data section, then xmit-ed through the uc/bc link.
+ *
+ * Return: 0 in case of success, otherwise < 0
+ */
+static int tipc_crypto_key_xmit(struct net *net, struct tipc_aead_key *skey,
+				u16 gen, u8 mode, u32 dnode)
+{
+	struct sk_buff_head pkts;
+	struct tipc_msg *hdr;
+	struct sk_buff *skb;
+	u16 size, cong_link_cnt;
+	u8 *data;
+	int rc;
+
+	size = tipc_aead_key_size(skey);
+	skb = tipc_buf_acquire(INT_H_SIZE + size, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	hdr = buf_msg(skb);
+	tipc_msg_init(tipc_own_addr(net), hdr, MSG_CRYPTO, KEY_DISTR_MSG,
+		      INT_H_SIZE, dnode);
+	msg_set_size(hdr, INT_H_SIZE + size);
+	msg_set_key_gen(hdr, gen);
+	msg_set_key_mode(hdr, mode);
+
+	data = msg_data(hdr);
+	*((__be32 *)(data + TIPC_AEAD_ALG_NAME)) = htonl(skey->keylen);
+	memcpy(data, skey->alg_name, TIPC_AEAD_ALG_NAME);
+	memcpy(data + TIPC_AEAD_ALG_NAME + sizeof(__be32), skey->key,
+	       skey->keylen);
+
+	__skb_queue_head_init(&pkts);
+	__skb_queue_tail(&pkts, skb);
+	if (dnode)
+		rc = tipc_node_xmit(net, &pkts, dnode, 0);
+	else
+		rc = tipc_bcast_xmit(net, &pkts, &cong_link_cnt);
+
+	return rc;
+}
+
+/**
+ * tipc_crypto_key_rcv - Receive a session key
+ * @rx: the RX crypto
+ * @hdr: the TIPC v2 message incl. the receiving session key in its data
+ *
+ * This function retrieves the session key in the message from peer, then
+ * schedules a RX work to attach the key to the corresponding RX crypto.
+ *
+ * Return: "true" if the key has been scheduled for attaching, otherwise
+ * "false".
+ */
+static bool tipc_crypto_key_rcv(struct tipc_crypto *rx, struct tipc_msg *hdr)
+{
+	struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx;
+	struct tipc_aead_key *skey = NULL;
+	u16 key_gen = msg_key_gen(hdr);
+	u16 size = msg_data_sz(hdr);
+	u8 *data = msg_data(hdr);
+
+	spin_lock(&rx->lock);
+	if (unlikely(rx->skey || (key_gen == rx->key_gen && rx->key.keys))) {
+		pr_err("%s: key existed <%p>, gen %d vs %d\n", rx->name,
+		       rx->skey, key_gen, rx->key_gen);
+		goto exit;
+	}
+
+	/* Allocate memory for the key */
+	skey = kmalloc(size, GFP_ATOMIC);
+	if (unlikely(!skey)) {
+		pr_err("%s: unable to allocate memory for skey\n", rx->name);
+		goto exit;
+	}
+
+	/* Copy key from msg data */
+	skey->keylen = ntohl(*((__be32 *)(data + TIPC_AEAD_ALG_NAME)));
+	memcpy(skey->alg_name, data, TIPC_AEAD_ALG_NAME);
+	memcpy(skey->key, data + TIPC_AEAD_ALG_NAME + sizeof(__be32),
+	       skey->keylen);
+
+	/* Sanity check */
+	if (unlikely(size != tipc_aead_key_size(skey))) {
+		kfree(skey);
+		skey = NULL;
+		goto exit;
+	}
+
+	rx->key_gen = key_gen;
+	rx->skey_mode = msg_key_mode(hdr);
+	rx->skey = skey;
+	rx->nokey = 0;
+	mb(); /* for nokey flag */
+
+exit:
+	spin_unlock(&rx->lock);
+
+	/* Schedule the key attaching on this crypto */
+	if (likely(skey && queue_delayed_work(tx->wq, &rx->work, 0)))
+		return true;
+
+	return false;
+}
+
+/**
+ * tipc_crypto_work_rx - Scheduled RX works handler
+ * @work: the struct RX work
+ *
+ * The function processes the previous scheduled works i.e. distributing TX key
+ * or attaching a received session key on RX crypto.
+ */
+static void tipc_crypto_work_rx(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct tipc_crypto *rx = container_of(dwork, struct tipc_crypto, work);
+	struct tipc_crypto *tx = tipc_net(rx->net)->crypto_tx;
+	unsigned long delay = msecs_to_jiffies(5000);
+	bool resched = false;
+	u8 key;
+	int rc;
+
+	/* Case 1: Distribute TX key to peer if scheduled */
+	if (atomic_cmpxchg(&rx->key_distr,
+			   KEY_DISTR_SCHED,
+			   KEY_DISTR_COMPL) == KEY_DISTR_SCHED) {
+		/* Always pick the newest one for distributing */
+		key = tx->key.pending ?: tx->key.active;
+		rc = tipc_crypto_key_distr(tx, key, rx->node);
+		if (unlikely(rc))
+			pr_warn("%s: unable to distr key[%d] to %s, err %d\n",
+				tx->name, key, tipc_node_get_id_str(rx->node),
+				rc);
+
+		/* Sched for key_distr releasing */
+		resched = true;
+	} else {
+		atomic_cmpxchg(&rx->key_distr, KEY_DISTR_COMPL, 0);
+	}
+
+	/* Case 2: Attach a pending received session key from peer if any */
+	if (rx->skey) {
+		rc = tipc_crypto_key_init(rx, rx->skey, rx->skey_mode, false);
+		if (unlikely(rc < 0))
+			pr_warn("%s: unable to attach received skey, err %d\n",
+				rx->name, rc);
+		switch (rc) {
+		case -EBUSY:
+		case -ENOMEM:
+			/* Resched the key attaching */
+			resched = true;
+			break;
+		default:
+			synchronize_rcu();
+			kfree(rx->skey);
+			rx->skey = NULL;
+			break;
+		}
+	}
+
+	if (resched && queue_delayed_work(tx->wq, &rx->work, delay))
+		return;
+
+	tipc_node_put(rx->node);
+}
+
+/**
+ * tipc_crypto_rekeying_sched - (Re)schedule rekeying w/o new interval
+ * @tx: TX crypto
+ * @changed: if the rekeying needs to be rescheduled with new interval
+ * @new_intv: new rekeying interval (when "changed" = true)
+ */
+void tipc_crypto_rekeying_sched(struct tipc_crypto *tx, bool changed,
+				u32 new_intv)
+{
+	unsigned long delay;
+	bool now = false;
+
+	if (changed) {
+		if (new_intv == TIPC_REKEYING_NOW)
+			now = true;
+		else
+			tx->rekeying_intv = new_intv;
+		cancel_delayed_work_sync(&tx->work);
+	}
+
+	if (tx->rekeying_intv || now) {
+		delay = (now) ? 0 : tx->rekeying_intv * 60 * 1000;
+		queue_delayed_work(tx->wq, &tx->work, msecs_to_jiffies(delay));
+	}
+}
+
+/**
+ * tipc_crypto_work_tx - Scheduled TX works handler
+ * @work: the struct TX work
+ *
+ * The function processes the previous scheduled work, i.e. key rekeying, by
+ * generating a new session key based on current one, then attaching it to the
+ * TX crypto and finally distributing it to peers. It also re-schedules the
+ * rekeying if needed.
+ */
+static void tipc_crypto_work_tx(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct tipc_crypto *tx = container_of(dwork, struct tipc_crypto, work);
+	struct tipc_aead_key *skey = NULL;
+	struct tipc_key key = tx->key;
+	struct tipc_aead *aead;
+	int rc = -ENOMEM;
+
+	if (unlikely(key.pending))
+		goto resched;
+
+	/* Take current key as a template */
+	rcu_read_lock();
+	aead = rcu_dereference(tx->aead[key.active ?: KEY_MASTER]);
+	if (unlikely(!aead)) {
+		rcu_read_unlock();
+		/* At least one key should exist for securing */
+		return;
+	}
+
+	/* Lets duplicate it first */
+	skey = kmemdup(aead->key, tipc_aead_key_size(aead->key), GFP_ATOMIC);
+	rcu_read_unlock();
+
+	/* Now, generate new key, initiate & distribute it */
+	if (likely(skey)) {
+		rc = tipc_aead_key_generate(skey) ?:
+		     tipc_crypto_key_init(tx, skey, PER_NODE_KEY, false);
+		if (likely(rc > 0))
+			rc = tipc_crypto_key_distr(tx, rc, NULL);
+		kfree_sensitive(skey);
+	}
+
+	if (unlikely(rc))
+		pr_warn_ratelimited("%s: rekeying returns %d\n", tx->name, rc);
+
+resched:
+	/* Re-schedule rekeying if any */
+	tipc_crypto_rekeying_sched(tx, false, 0);
+}
diff --git a/net/tipc/crypto.h b/net/tipc/crypto.h
index c3de769f49e8..ce7d4cc8a9e0 100644
--- a/net/tipc/crypto.h
+++ b/net/tipc/crypto.h
@@ -1,5 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/**
+/*
  * net/tipc/crypto.h: Include file for TIPC crypto
  *
  * Copyright (c) 2019, Ericsson AB
@@ -53,7 +53,7 @@
 #define TIPC_AES_GCM_IV_SIZE		12
 #define TIPC_AES_GCM_TAG_SIZE		16
 
-/**
+/*
  * TIPC crypto modes:
  * - CLUSTER_KEY:
  *	One single key is used for both TX & RX in all nodes in the cluster.
@@ -67,14 +67,15 @@ enum {
 };
 
 extern int sysctl_tipc_max_tfms __read_mostly;
+extern int sysctl_tipc_key_exchange_enabled __read_mostly;
 
-/**
+/*
  * TIPC encryption message format:
  *
  *     3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0
  *     1 0 9 8 7 6 5 4|3 2 1 0 9 8 7 6|5 4 3 2 1 0 9 8|7 6 5 4 3 2 1 0
  *    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * w0:|Ver=7| User  |D|TX |RX |K|                 Rsvd                |
+ * w0:|Ver=7| User  |D|TX |RX |K|M|N|             Rsvd                |
  *    +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  * w1:|                             Seqno                             |
  * w2:|                           (8 octets)                          |
@@ -101,6 +102,9 @@ extern int sysctl_tipc_max_tfms __read_mostly;
  *	RX	: Currently RX active key corresponding to the destination
  *	          node's TX key (when the "D" bit is set)
  *	K	: Keep-alive bit (for RPS, LINK_PROTOCOL/STATE_MSG only)
+ *	M       : Bit indicates if sender has master key
+ *	N	: Bit indicates if sender has no RX keys corresponding to the
+ *	          receiver's TX (when the "D" bit is set)
  *	Rsvd	: Reserved bit, field
  * Word1-2:
  *	Seqno	: The 64-bit sequence number of the encrypted message, also
@@ -117,7 +121,9 @@ struct tipc_ehdr {
 			__u8	destined:1,
 				user:4,
 				version:3;
-			__u8	reserved_1:3,
+			__u8	reserved_1:1,
+				rx_nokey:1,
+				master_key:1,
 				keepalive:1,
 				rx_key_active:2,
 				tx_key:2;
@@ -128,7 +134,9 @@ struct tipc_ehdr {
 			__u8	tx_key:2,
 				rx_key_active:2,
 				keepalive:1,
-				reserved_1:3;
+				master_key:1,
+				rx_nokey:1,
+				reserved_1:1;
 #else
 #error  "Please fix <asm/byteorder.h>"
 #endif
@@ -158,10 +166,35 @@ int tipc_crypto_xmit(struct net *net, struct sk_buff **skb,
 int tipc_crypto_rcv(struct net *net, struct tipc_crypto *rx,
 		    struct sk_buff **skb, struct tipc_bearer *b);
 int tipc_crypto_key_init(struct tipc_crypto *c, struct tipc_aead_key *ukey,
-			 u8 mode);
+			 u8 mode, bool master_key);
 void tipc_crypto_key_flush(struct tipc_crypto *c);
-int tipc_aead_key_validate(struct tipc_aead_key *ukey);
+int tipc_crypto_key_distr(struct tipc_crypto *tx, u8 key,
+			  struct tipc_node *dest);
+void tipc_crypto_msg_rcv(struct net *net, struct sk_buff *skb);
+void tipc_crypto_rekeying_sched(struct tipc_crypto *tx, bool changed,
+				u32 new_intv);
+int tipc_aead_key_validate(struct tipc_aead_key *ukey, struct genl_info *info);
 bool tipc_ehdr_validate(struct sk_buff *skb);
 
+static inline u32 msg_key_gen(struct tipc_msg *m)
+{
+	return msg_bits(m, 4, 16, 0xffff);
+}
+
+static inline void msg_set_key_gen(struct tipc_msg *m, u32 gen)
+{
+	msg_set_bits(m, 4, 16, 0xffff, gen);
+}
+
+static inline u32 msg_key_mode(struct tipc_msg *m)
+{
+	return msg_bits(m, 4, 0, 0xf);
+}
+
+static inline void msg_set_key_mode(struct tipc_msg *m, u32 mode)
+{
+	msg_set_bits(m, 4, 0, 0xf, mode);
+}
+
 #endif /* _TIPC_CRYPTO_H */
 #endif
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index d4ecacddb40c..5380f605b851 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -74,6 +74,7 @@ struct tipc_discoverer {
 /**
  * tipc_disc_init_msg - initialize a link setup message
  * @net: the applicable net namespace
+ * @skb: buffer containing message
  * @mtyp: message type (request or response)
  * @b: ptr to bearer issuing message
  */
@@ -341,7 +342,7 @@ exit:
  * @dest: destination address for request messages
  * @skb: pointer to created frame
  *
- * Returns 0 if successful, otherwise -errno.
+ * Return: 0 if successful, otherwise -errno.
  */
 int tipc_disc_create(struct net *net, struct tipc_bearer *b,
 		     struct tipc_media_addr *dest, struct sk_buff **skb)
@@ -380,7 +381,7 @@ int tipc_disc_create(struct net *net, struct tipc_bearer *b,
 
 /**
  * tipc_disc_delete - destroy object sending periodic link setup requests
- * @d: ptr to link duest structure
+ * @d: ptr to link dest structure
  */
 void tipc_disc_delete(struct tipc_discoverer *d)
 {
diff --git a/net/tipc/group.c b/net/tipc/group.c
index b1fcd2ad5ecf..3e137d8c9d2f 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -2,6 +2,7 @@
  * net/tipc/group.c: TIPC group messaging code
  *
  * Copyright (c) 2017, Ericsson AB
+ * Copyright (c) 2020, Red Hat Inc
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -359,7 +360,7 @@ struct tipc_nlist *tipc_group_dests(struct tipc_group *grp)
 	return &grp->dests;
 }
 
-void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
+void tipc_group_self(struct tipc_group *grp, struct tipc_service_range *seq,
 		     int *scope)
 {
 	seq->type = grp->type;
diff --git a/net/tipc/group.h b/net/tipc/group.h
index 76b4e5a7b39d..ea4c3be64c78 100644
--- a/net/tipc/group.h
+++ b/net/tipc/group.h
@@ -2,6 +2,7 @@
  * net/tipc/group.h: Include file for TIPC group unicast/multicast functions
  *
  * Copyright (c) 2017, Ericsson AB
+ * Copyright (c) 2020, Red Hat Inc
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -50,7 +51,7 @@ void tipc_group_delete(struct net *net, struct tipc_group *grp);
 void tipc_group_add_member(struct tipc_group *grp, u32 node,
 			   u32 port, u32 instance);
 struct tipc_nlist *tipc_group_dests(struct tipc_group *grp);
-void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq,
+void tipc_group_self(struct tipc_group *grp, struct tipc_service_range *seq,
 		     int *scope);
 u32 tipc_group_exclude(struct tipc_group *grp);
 void tipc_group_filter_msg(struct tipc_group *grp,
diff --git a/net/tipc/link.c b/net/tipc/link.c
index cef38a910107..115109259430 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -120,6 +120,34 @@ struct tipc_stats {
  * @reasm_buf: head of partially reassembled inbound message fragments
  * @bc_rcvr: marks that this is a broadcast receiver link
  * @stats: collects statistics regarding link activity
+ * @session: session to be used by link
+ * @snd_nxt_state: next send seq number
+ * @rcv_nxt_state: next rcv seq number
+ * @in_session: have received ACTIVATE_MSG from peer
+ * @active: link is active
+ * @if_name: associated interface name
+ * @rst_cnt: link reset counter
+ * @drop_point: seq number for failover handling (FIXME)
+ * @failover_reasm_skb: saved failover msg ptr (FIXME)
+ * @failover_deferdq: deferred message queue for failover processing (FIXME)
+ * @transmq: the link's transmit queue
+ * @backlog: link's backlog by priority (importance)
+ * @snd_nxt: next sequence number to be used
+ * @rcv_unacked: # messages read by user, but not yet acked back to peer
+ * @deferdq: deferred receive queue
+ * @window: sliding window size for congestion handling
+ * @min_win: minimal send window to be used by link
+ * @ssthresh: slow start threshold for congestion handling
+ * @max_win: maximal send window to be used by link
+ * @cong_acks: congestion acks for congestion avoidance (FIXME)
+ * @checkpoint: seq number for congestion window size handling
+ * @reasm_tnlmsg: fragmentation/reassembly area for tunnel protocol message
+ * @last_gap: last gap ack blocks for bcast (FIXME)
+ * @last_ga: ptr to gap ack blocks
+ * @bc_rcvlink: the peer specific link used for broadcast reception
+ * @bc_sndlink: the namespace global link used for broadcast sending
+ * @nack_state: bcast nack state
+ * @bc_peer_is_up: peer has acked the bcast init msg
  */
 struct tipc_link {
 	u32 addr;
@@ -216,11 +244,6 @@ enum {
 #define TIPC_BC_RETR_LIM  (jiffies + msecs_to_jiffies(10))
 #define TIPC_UC_RETR_TIME (jiffies + msecs_to_jiffies(1))
 
-/*
- * Interval between NACKs when packets arrive out of order
- */
-#define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2)
-
 /* Link FSM states:
  */
 enum {
@@ -455,7 +478,6 @@ u32 tipc_link_state(struct tipc_link *l)
  * @min_win: minimal send window to be used by link
  * @max_win: maximal send window to be used by link
  * @session: session to be used by link
- * @ownnode: identity of own node
  * @peer: node id of peer node
  * @peer_caps: bitmap describing peer node capabilities
  * @bc_sndlink: the namespace global link used for broadcast sending
@@ -463,8 +485,10 @@ u32 tipc_link_state(struct tipc_link *l)
  * @inputq: queue to put messages ready for delivery
  * @namedq: queue to put binding table update messages ready for delivery
  * @link: return value, pointer to put the created link
+ * @self: local unicast link id
+ * @peer_id: 128-bit ID of peer
  *
- * Returns true if link was created, otherwise false
+ * Return: true if link was created, otherwise false
  */
 bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
 		      int tolerance, char net_plane, u32 mtu, int priority,
@@ -537,8 +561,13 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
  * @inputq: queue to put messages ready for delivery
  * @namedq: queue to put binding table update messages ready for delivery
  * @link: return value, pointer to put the created link
+ * @ownnode: identity of own node
+ * @peer: node id of peer node
+ * @peer_id: 128-bit ID of peer
+ * @peer_caps: bitmap describing peer node capabilities
+ * @bc_sndlink: the namespace global link used for broadcast sending
  *
- * Returns true if link was created, otherwise false
+ * Return: true if link was created, otherwise false
  */
 bool tipc_link_bc_create(struct net *net, u32 ownnode, u32 peer, u8 *peer_id,
 			 int mtu, u32 min_win, u32 max_win, u16 peer_caps,
@@ -793,7 +822,7 @@ static void link_profile_stats(struct tipc_link *l)
  * tipc_link_too_silent - check if link is "too silent"
  * @l: tipc link to be checked
  *
- * Returns true if the link 'silent_intv_cnt' is about to reach the
+ * Return: true if the link 'silent_intv_cnt' is about to reach the
  * 'abort_limit' value, otherwise false
  */
 bool tipc_link_too_silent(struct tipc_link *l)
@@ -995,13 +1024,12 @@ void tipc_link_reset(struct tipc_link *l)
  * @xmitq: returned list of packets to be sent by caller
  *
  * Consumes the buffer chain.
- * Returns 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
  * Messages at TIPC_SYSTEM_IMPORTANCE are always accepted
+ * Return: 0 if success, or errno: -ELINKCONG, -EMSGSIZE or -ENOBUFS
  */
 int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 		   struct sk_buff_head *xmitq)
 {
-	struct tipc_msg *hdr = buf_msg(skb_peek(list));
 	struct sk_buff_head *backlogq = &l->backlogq;
 	struct sk_buff_head *transmq = &l->transmq;
 	struct sk_buff *skb, *_skb;
@@ -1009,13 +1037,18 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 	u16 ack = l->rcv_nxt - 1;
 	u16 seqno = l->snd_nxt;
 	int pkt_cnt = skb_queue_len(list);
-	int imp = msg_importance(hdr);
 	unsigned int mss = tipc_link_mss(l);
 	unsigned int cwin = l->window;
 	unsigned int mtu = l->mtu;
+	struct tipc_msg *hdr;
 	bool new_bundle;
 	int rc = 0;
+	int imp;
+
+	if (pkt_cnt <= 0)
+		return 0;
 
+	hdr = buf_msg(skb_peek(list));
 	if (unlikely(msg_size(hdr) > mtu)) {
 		pr_warn("Too large msg, purging xmit list %d %d %d %d %d!\n",
 			skb_queue_len(list), msg_user(hdr),
@@ -1024,6 +1057,7 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 		return -EMSGSIZE;
 	}
 
+	imp = msg_importance(hdr);
 	/* Allow oversubscription of one data msg per source at congestion */
 	if (unlikely(l->backlog[imp].len >= l->backlog[imp].limit)) {
 		if (imp == TIPC_SYSTEM_IMPORTANCE) {
@@ -1256,11 +1290,16 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 	case MSG_FRAGMENTER:
 	case BCAST_PROTOCOL:
 		return false;
+#ifdef CONFIG_TIPC_CRYPTO
+	case MSG_CRYPTO:
+		tipc_crypto_msg_rcv(l->net, skb);
+		return true;
+#endif
 	default:
 		pr_warn("Dropping received illegal msg type\n");
 		kfree_skb(skb);
 		return true;
-	};
+	}
 }
 
 /* tipc_link_input - process packet that has passed link protocol check
@@ -2376,7 +2415,7 @@ int tipc_link_bc_sync_rcv(struct tipc_link *l, struct tipc_msg *hdr,
 	if (!msg_peer_node_is_up(hdr))
 		return rc;
 
-	/* Open when peer ackowledges our bcast init msg (pkt #1) */
+	/* Open when peer acknowledges our bcast init msg (pkt #1) */
 	if (msg_ack(hdr))
 		l->bc_peer_is_up = true;
 
@@ -2505,7 +2544,7 @@ void tipc_link_set_queue_limits(struct tipc_link *l, u32 min_win, u32 max_win)
 }
 
 /**
- * link_reset_stats - reset link statistics
+ * tipc_link_reset_stats - reset link statistics
  * @l: pointer to link
  */
 void tipc_link_reset_stats(struct tipc_link *l)
diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index 52e93ba4d8e2..2aca86021df5 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -58,11 +58,13 @@ static unsigned int align(unsigned int i)
 /**
  * tipc_buf_acquire - creates a TIPC message buffer
  * @size: message size (including TIPC header)
+ * @gfp: memory allocation flags
  *
- * Returns a new buffer with data pointers set to the specified size.
+ * Return: a new buffer with data pointers set to the specified size.
  *
- * NOTE: Headroom is reserved to allow prepending of a data link header.
- *       There may also be unrequested tailroom present at the buffer's end.
+ * NOTE:
+ * Headroom is reserved to allow prepending of a data link header.
+ * There may also be unrequested tailroom present at the buffer's end.
  */
 struct sk_buff *tipc_buf_acquire(u32 size, gfp_t gfp)
 {
@@ -150,11 +152,11 @@ int tipc_buf_append(struct sk_buff **headbuf, struct sk_buff **buf)
 	if (fragid == FIRST_FRAGMENT) {
 		if (unlikely(head))
 			goto err;
+		*buf = NULL;
 		frag = skb_unshare(frag, GFP_ATOMIC);
 		if (unlikely(!frag))
 			goto err;
 		head = *headbuf = frag;
-		*buf = NULL;
 		TIPC_SKB_CB(head)->tail = NULL;
 		if (skb_is_nonlinear(head)) {
 			skb_walk_frags(head, tail) {
@@ -207,8 +209,9 @@ err:
  * @m: the data to be appended
  * @mss: max allowable size of buffer
  * @dlen: size of data to be appended
- * @txq: queue to appand to
- * Returns the number og 1k blocks appended or errno value
+ * @txq: queue to append to
+ *
+ * Return: the number of 1k blocks appended or errno value
  */
 int tipc_msg_append(struct tipc_msg *_hdr, struct msghdr *m, int dlen,
 		    int mss, struct sk_buff_head *txq)
@@ -312,7 +315,7 @@ bool tipc_msg_validate(struct sk_buff **_skb)
  * @pktmax: max size of a fragment incl. the header
  * @frags: returned fragment skb list
  *
- * Returns 0 if the fragmentation is successful, otherwise: -EINVAL
+ * Return: 0 if the fragmentation is successful, otherwise: -EINVAL
  * or -ENOMEM
  */
 int tipc_msg_fragment(struct sk_buff *skb, const struct tipc_msg *hdr,
@@ -367,6 +370,7 @@ error:
  * tipc_msg_build - create buffer chain containing specified header and data
  * @mhdr: Message header, to be prepended to data
  * @m: User message
+ * @offset: buffer offset for fragmented messages (FIXME)
  * @dsz: Total length of user data
  * @pktmax: Max packet size that can be used
  * @list: Buffer or chain of buffers to be returned to caller
@@ -374,7 +378,7 @@ error:
  * Note that the recursive call we are making here is safe, since it can
  * logically go only one further level down.
  *
- * Returns message data size or errno: -ENOMEM, -EFAULT
+ * Return: message data size or errno: -ENOMEM, -EFAULT
  */
 int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset,
 		   int dsz, int pktmax, struct sk_buff_head *list)
@@ -485,7 +489,7 @@ error:
  * @msg: message to be appended
  * @max: max allowable size for the bundle buffer
  *
- * Returns "true" if bundling has been performed, otherwise "false"
+ * Return: "true" if bundling has been performed, otherwise "false"
  */
 static bool tipc_msg_bundle(struct sk_buff *bskb, struct tipc_msg *msg,
 			    u32 max)
@@ -580,9 +584,9 @@ bundle:
  *  @skb: buffer to be extracted from.
  *  @iskb: extracted inner buffer, to be returned
  *  @pos: position in outer message of msg to be extracted.
- *        Returns position of next msg
+ *  Returns position of next msg.
  *  Consumes outer buffer when last packet extracted
- *  Returns true when when there is an extracted buffer, otherwise false
+ *  Return: true when there is an extracted buffer, otherwise false
  */
 bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos)
 {
@@ -626,7 +630,7 @@ none:
  * @skb:  buffer containing message to be reversed; will be consumed
  * @err:  error code to be set in message, if any
  * Replaces consumed buffer with new one when successful
- * Returns true if success, otherwise false
+ * Return: true if success, otherwise false
  */
 bool tipc_msg_reverse(u32 own_node,  struct sk_buff **skb, int err)
 {
@@ -698,10 +702,11 @@ bool tipc_msg_skb_clone(struct sk_buff_head *msg, struct sk_buff_head *cpy)
 
 /**
  * tipc_msg_lookup_dest(): try to find new destination for named message
+ * @net: pointer to associated network namespace
  * @skb: the buffer containing the message.
  * @err: error code to be used by caller if lookup fails
  * Does not consume buffer
- * Returns true if a destination is found, false otherwise
+ * Return: true if a destination is found, false otherwise
  */
 bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
 {
diff --git a/net/tipc/msg.h b/net/tipc/msg.h
index 1016e96db5c4..5d64596ba987 100644
--- a/net/tipc/msg.h
+++ b/net/tipc/msg.h
@@ -82,6 +82,7 @@ struct plist;
 #define  NAME_DISTRIBUTOR     11
 #define  MSG_FRAGMENTER       12
 #define  LINK_CONFIG          13
+#define  MSG_CRYPTO           14
 #define  SOCK_WAKEUP          14       /* pseudo user */
 #define  TOP_SRV              15       /* pseudo user */
 
@@ -127,7 +128,9 @@ struct tipc_skb_cb {
 #ifdef CONFIG_TIPC_CRYPTO
 			u8 encrypted:1;
 			u8 decrypted:1;
-			u8 probe:1;
+#define SKB_PROBING	1
+#define SKB_GRACING	2
+			u8 xmit_type:2;
 			u8 tx_clone_deferred:1;
 #endif
 		};
@@ -747,6 +750,9 @@ static inline void msg_set_nameupper(struct tipc_msg *m, u32 n)
 #define GRP_RECLAIM_MSG      4
 #define GRP_REMIT_MSG        5
 
+/* Crypto message types */
+#define KEY_DISTR_MSG		0
+
 /*
  * Word 1
  */
diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c
index 2f9c148f17e2..6cf57c3bfa27 100644
--- a/net/tipc/name_distr.c
+++ b/net/tipc/name_distr.c
@@ -50,6 +50,8 @@ struct distr_queue_item {
 
 /**
  * publ_to_item - add publication info to a publication message
+ * @p: publication info
+ * @i: location of item in the message
  */
 static void publ_to_item(struct distr_item *i, struct publication *p)
 {
@@ -62,6 +64,10 @@ static void publ_to_item(struct distr_item *i, struct publication *p)
 
 /**
  * named_prepare_buf - allocate & initialize a publication message
+ * @net: the associated network namespace
+ * @type: message type
+ * @size: payload size
+ * @dest: destination node
  *
  * The buffer returned is of size INT_H_SIZE + payload size
  */
@@ -83,6 +89,8 @@ static struct sk_buff *named_prepare_buf(struct net *net, u32 type, u32 size,
 
 /**
  * tipc_named_publish - tell other nodes about a new publication by this node
+ * @net: the associated network namespace
+ * @publ: the new publication
  */
 struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ)
 {
@@ -111,6 +119,8 @@ struct sk_buff *tipc_named_publish(struct net *net, struct publication *publ)
 
 /**
  * tipc_named_withdraw - tell other nodes about a withdrawn publication by this node
+ * @net: the associated network namespace
+ * @publ: the withdrawn publication
  */
 struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ)
 {
@@ -138,9 +148,11 @@ struct sk_buff *tipc_named_withdraw(struct net *net, struct publication *publ)
 
 /**
  * named_distribute - prepare name info for bulk distribution to another node
+ * @net: the associated network namespace
  * @list: list of messages (buffers) to be returned from this function
  * @dnode: node to be updated
  * @pls: linked list of publication items to be packed into buffer chain
+ * @seqno: sequence number for this message
  */
 static void named_distribute(struct net *net, struct sk_buff_head *list,
 			     u32 dnode, struct list_head *pls, u16 seqno)
@@ -194,6 +206,9 @@ static void named_distribute(struct net *net, struct sk_buff_head *list,
 
 /**
  * tipc_named_node_up - tell specified node about all publications by this node
+ * @net: the associated network namespace
+ * @dnode: destination node
+ * @capabilities: peer node's capabilities
  */
 void tipc_named_node_up(struct net *net, u32 dnode, u16 capabilities)
 {
@@ -217,6 +232,9 @@ void tipc_named_node_up(struct net *net, u32 dnode, u16 capabilities)
 
 /**
  * tipc_publ_purge - remove publication associated with a failed node
+ * @net: the associated network namespace
+ * @publ: the publication to remove
+ * @addr: failed node's address
  *
  * Invoked for each publication issued by a newly failed node.
  * Removes publication structure from name table & deletes it.
@@ -244,24 +262,6 @@ static void tipc_publ_purge(struct net *net, struct publication *publ, u32 addr)
 		kfree_rcu(p, rcu);
 }
 
-/**
- * tipc_dist_queue_purge - remove deferred updates from a node that went down
- */
-static void tipc_dist_queue_purge(struct net *net, u32 addr)
-{
-	struct tipc_net *tn = net_generic(net, tipc_net_id);
-	struct distr_queue_item *e, *tmp;
-
-	spin_lock_bh(&tn->nametbl_lock);
-	list_for_each_entry_safe(e, tmp, &tn->dist_queue, next) {
-		if (e->node != addr)
-			continue;
-		list_del(&e->next);
-		kfree(e);
-	}
-	spin_unlock_bh(&tn->nametbl_lock);
-}
-
 void tipc_publ_notify(struct net *net, struct list_head *nsub_list,
 		      u32 addr, u16 capabilities)
 {
@@ -272,7 +272,6 @@ void tipc_publ_notify(struct net *net, struct list_head *nsub_list,
 
 	list_for_each_entry_safe(publ, tmp, nsub_list, binding_node)
 		tipc_publ_purge(net, publ, addr);
-	tipc_dist_queue_purge(net, addr);
 	spin_lock_bh(&tn->nametbl_lock);
 	if (!(capabilities & TIPC_NAMED_BCAST))
 		nt->rc_dests--;
@@ -282,9 +281,13 @@ void tipc_publ_notify(struct net *net, struct list_head *nsub_list,
 /**
  * tipc_update_nametbl - try to process a nametable update and notify
  *			 subscribers
+ * @net: the associated network namespace
+ * @i: location of item in the message
+ * @node: node address
+ * @dtype: name distributor message type
  *
  * tipc_nametbl_lock must be held.
- * Returns the publication item if successful, otherwise NULL.
+ * Return: the publication item if successful, otherwise NULL.
  */
 static bool tipc_update_nametbl(struct net *net, struct distr_item *i,
 				u32 node, u32 dtype)
@@ -327,8 +330,13 @@ static struct sk_buff *tipc_named_dequeue(struct sk_buff_head *namedq,
 	struct tipc_msg *hdr;
 	u16 seqno;
 
+	spin_lock_bh(&namedq->lock);
 	skb_queue_walk_safe(namedq, skb, tmp) {
-		skb_linearize(skb);
+		if (unlikely(skb_linearize(skb))) {
+			__skb_unlink(skb, namedq);
+			kfree_skb(skb);
+			continue;
+		}
 		hdr = buf_msg(skb);
 		seqno = msg_named_seqno(hdr);
 		if (msg_is_last_bulk(hdr)) {
@@ -338,12 +346,14 @@ static struct sk_buff *tipc_named_dequeue(struct sk_buff_head *namedq,
 
 		if (msg_is_bulk(hdr) || msg_is_legacy(hdr)) {
 			__skb_unlink(skb, namedq);
+			spin_unlock_bh(&namedq->lock);
 			return skb;
 		}
 
 		if (*open && (*rcv_nxt == seqno)) {
 			(*rcv_nxt)++;
 			__skb_unlink(skb, namedq);
+			spin_unlock_bh(&namedq->lock);
 			return skb;
 		}
 
@@ -353,11 +363,16 @@ static struct sk_buff *tipc_named_dequeue(struct sk_buff_head *namedq,
 			continue;
 		}
 	}
+	spin_unlock_bh(&namedq->lock);
 	return NULL;
 }
 
 /**
  * tipc_named_rcv - process name table update messages sent by another node
+ * @net: the associated network namespace
+ * @namedq: queue to receive from
+ * @rcv_nxt: store last received seqno here
+ * @open: last bulk msg was received (FIXME)
  */
 void tipc_named_rcv(struct net *net, struct sk_buff_head *namedq,
 		    u16 *rcv_nxt, bool *open)
@@ -385,6 +400,7 @@ void tipc_named_rcv(struct net *net, struct sk_buff_head *namedq,
 
 /**
  * tipc_named_reinit - re-initialize local publications
+ * @net: the associated network namespace
  *
  * This routine is called whenever TIPC networking is enabled.
  * All name table entries published by this node are updated to reflect
diff --git a/net/tipc/name_distr.h b/net/tipc/name_distr.h
index 092323158f06..e231e6964d61 100644
--- a/net/tipc/name_distr.h
+++ b/net/tipc/name_distr.h
@@ -46,7 +46,7 @@
  * @type: name sequence type
  * @lower: name sequence lower bound
  * @upper: name sequence upper bound
- * @ref: publishing port reference
+ * @port: publishing port reference
  * @key: publication key
  *
  * ===> All fields are stored in network byte order. <===
diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index 2ac33d32edc2..ee5ac40ea2b6 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2000-2006, 2014-2018, Ericsson AB
  * Copyright (c) 2004-2008, 2010-2014, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -103,7 +104,8 @@ RB_DECLARE_CALLBACKS_MAX(static, sr_callbacks,
  *                               range match
  * @sr: the service range pointer as a loop cursor
  * @sc: the pointer to tipc service which holds the service range rbtree
- * @start, end: the range (end >= start) for matching
+ * @start: beginning of the search range (end >= start) for matching
+ * @end: end of the search range (end >= start) for matching
  */
 #define service_range_foreach_match(sr, sc, start, end)			\
 	for (sr = service_range_match_first((sc)->ranges.rb_node,	\
@@ -117,7 +119,8 @@ RB_DECLARE_CALLBACKS_MAX(static, sr_callbacks,
 /**
  * service_range_match_first - find first service range matching a range
  * @n: the root node of service range rbtree for searching
- * @start, end: the range (end >= start) for matching
+ * @start: beginning of the search range (end >= start) for matching
+ * @end: end of the search range (end >= start) for matching
  *
  * Return: the leftmost service range node in the rbtree that overlaps the
  * specific range if any. Otherwise, returns NULL.
@@ -166,7 +169,8 @@ static struct service_range *service_range_match_first(struct rb_node *n,
 /**
  * service_range_match_next - find next service range matching a range
  * @n: a node in service range rbtree from which the searching starts
- * @start, end: the range (end >= start) for matching
+ * @start: beginning of the search range (end >= start) for matching
+ * @end: end of the search range (end >= start) for matching
  *
  * Return: the next service range node to the given node in the rbtree that
  * overlaps the specific range if any. Otherwise, returns NULL.
@@ -218,6 +222,13 @@ static int hash(int x)
 
 /**
  * tipc_publ_create - create a publication structure
+ * @type: name sequence type
+ * @lower: name sequence lower bound
+ * @upper: name sequence upper bound
+ * @scope: publication scope
+ * @node: network address of publishing socket
+ * @port: publishing port
+ * @key: publication key
  */
 static struct publication *tipc_publ_create(u32 type, u32 lower, u32 upper,
 					    u32 scope, u32 node, u32 port,
@@ -245,6 +256,8 @@ static struct publication *tipc_publ_create(u32 type, u32 lower, u32 upper,
 
 /**
  * tipc_service_create - create a service structure for the specified 'type'
+ * @type: service type
+ * @hd: name_table services list
  *
  * Allocates a single range structure and sets it to all 0's.
  */
@@ -361,6 +374,9 @@ err:
 
 /**
  * tipc_service_remove_publ - remove a publication from a service
+ * @sr: service_range to remove publication from
+ * @node: target node
+ * @key: target publication key
  */
 static struct publication *tipc_service_remove_publ(struct service_range *sr,
 						    u32 node, u32 key)
@@ -377,7 +393,7 @@ static struct publication *tipc_service_remove_publ(struct service_range *sr,
 	return NULL;
 }
 
-/**
+/*
  * Code reused: time_after32() for the same purpose
  */
 #define publication_after(pa, pb) time_after32((pa)->id, (pb)->id)
@@ -395,6 +411,8 @@ static int tipc_publ_sort(void *priv, struct list_head *a,
  * tipc_service_subscribe - attach a subscription, and optionally
  * issue the prescribed number of events if there is any service
  * range overlapping with the requested range
+ * @service: the tipc_service to attach the @sub to
+ * @sub: the subscription to attach
  */
 static void tipc_service_subscribe(struct tipc_service *service,
 				   struct tipc_subscription *sub)
@@ -403,12 +421,12 @@ static void tipc_service_subscribe(struct tipc_service *service,
 	struct publication *p, *first, *tmp;
 	struct list_head publ_list;
 	struct service_range *sr;
-	struct tipc_name_seq ns;
+	struct tipc_service_range r;
 	u32 filter;
 
-	ns.type = tipc_sub_read(sb, seq.type);
-	ns.lower = tipc_sub_read(sb, seq.lower);
-	ns.upper = tipc_sub_read(sb, seq.upper);
+	r.type = tipc_sub_read(sb, seq.type);
+	r.lower = tipc_sub_read(sb, seq.lower);
+	r.upper = tipc_sub_read(sb, seq.upper);
 	filter = tipc_sub_read(sb, filter);
 
 	tipc_sub_get(sub);
@@ -418,7 +436,7 @@ static void tipc_service_subscribe(struct tipc_service *service,
 		return;
 
 	INIT_LIST_HEAD(&publ_list);
-	service_range_foreach_match(sr, service, ns.lower, ns.upper) {
+	service_range_foreach_match(sr, service, r.lower, r.upper) {
 		first = NULL;
 		list_for_each_entry(p, &sr->all_publ, all_publ) {
 			if (filter & TIPC_SUB_PORTS)
@@ -528,14 +546,16 @@ exit:
 
 /**
  * tipc_nametbl_translate - perform service instance to socket translation
- *
- * On entry, 'dnode' is the search domain used during translation.
+ * @net: network namespace
+ * @type: message type
+ * @instance: message instance
+ * @dnode: the search domain used during translation
  *
  * On exit:
  * - if translation is deferred to another node, leave 'dnode' unchanged and
- *   return 0
+ * return 0
  * - if translation is attempted and succeeds, set 'dnode' to the publishing
- *   node and return the published (non-zero) port number
+ * node and return the published (non-zero) port number
  * - if translation is attempted and fails, set 'dnode' to 0 and return 0
  *
  * Note that for legacy users (node configured with Z.C.N address format) the
@@ -756,6 +776,11 @@ exit:
 
 /**
  * tipc_nametbl_withdraw - withdraw a service binding
+ * @net: network namespace
+ * @type: service type
+ * @lower: service range lower bound
+ * @upper: service range upper bound
+ * @key: target publication key
  */
 int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower,
 			  u32 upper, u32 key)
@@ -791,6 +816,7 @@ int tipc_nametbl_withdraw(struct net *net, u32 type, u32 lower,
 
 /**
  * tipc_nametbl_subscribe - add a subscription object to the name table
+ * @sub: subscription to add
  */
 bool tipc_nametbl_subscribe(struct tipc_subscription *sub)
 {
@@ -821,6 +847,7 @@ bool tipc_nametbl_subscribe(struct tipc_subscription *sub)
 
 /**
  * tipc_nametbl_unsubscribe - remove a subscription object from name table
+ * @sub: subscription to remove
  */
 void tipc_nametbl_unsubscribe(struct tipc_subscription *sub)
 {
@@ -870,7 +897,9 @@ int tipc_nametbl_init(struct net *net)
 }
 
 /**
- *  tipc_service_delete - purge all publications for a service and delete it
+ * tipc_service_delete - purge all publications for a service and delete it
+ * @net: the associated network namespace
+ * @sc: tipc_service to delete
  */
 static void tipc_service_delete(struct net *net, struct tipc_service *sc)
 {
diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h
index 8064e1986e2c..5a82a01369d6 100644
--- a/net/tipc/name_table.h
+++ b/net/tipc/name_table.h
@@ -60,8 +60,8 @@ struct tipc_group;
  * @key: publication key, unique across the cluster
  * @id: publication id
  * @binding_node: all publications from the same node which bound this one
- * - Remote publications: in node->publ_list
- *   Used by node/name distr to withdraw publications when node is lost
+ * - Remote publications: in node->publ_list;
+ * Used by node/name distr to withdraw publications when node is lost
  * - Local/node scope publications: in name_table->node_scope list
  * - Local/cluster scope publications: in name_table->cluster_scope list
  * @binding_sock: all publications from the same socket which bound this one
@@ -92,13 +92,16 @@ struct publication {
 
 /**
  * struct name_table - table containing all existing port name publications
- * @seq_hlist: name sequence hash lists
+ * @services: name sequence hash lists
  * @node_scope: all local publications with node scope
  *               - used by name_distr during re-init of name table
  * @cluster_scope: all local publications with cluster scope
  *               - used by name_distr to send bulk updates to new nodes
  *               - used by name_distr during re-init of name table
+ * @cluster_scope_lock: lock for accessing @cluster_scope
  * @local_publ_count: number of publications issued by this node
+ * @rc_dests: destination node counter
+ * @snd_nxt: next sequence number to be used
  */
 struct name_table {
 	struct hlist_head services[TIPC_NAMETBL_SIZE];
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 85400e4242de..a129f661bee3 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -105,12 +105,6 @@
  *     - A local spin_lock protecting the queue of subscriber events.
 */
 
-struct tipc_net_work {
-	struct work_struct work;
-	struct net *net;
-	u32 addr;
-};
-
 static void tipc_net_finalize(struct net *net, u32 addr);
 
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
@@ -138,29 +132,25 @@ static void tipc_net_finalize(struct net *net, u32 addr)
 	tipc_named_reinit(net);
 	tipc_sk_reinit(net);
 	tipc_mon_reinit_self(net);
-	tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
+	tipc_nametbl_publish(net, TIPC_NODE_STATE, addr, addr,
 			     TIPC_CLUSTER_SCOPE, 0, addr);
 }
 
-static void tipc_net_finalize_work(struct work_struct *work)
+void tipc_net_finalize_work(struct work_struct *work)
 {
 	struct tipc_net_work *fwork;
 
 	fwork = container_of(work, struct tipc_net_work, work);
 	tipc_net_finalize(fwork->net, fwork->addr);
-	kfree(fwork);
 }
 
 void tipc_sched_net_finalize(struct net *net, u32 addr)
 {
-	struct tipc_net_work *fwork = kzalloc(sizeof(*fwork), GFP_ATOMIC);
+	struct tipc_net *tn = tipc_net(net);
 
-	if (!fwork)
-		return;
-	INIT_WORK(&fwork->work, tipc_net_finalize_work);
-	fwork->net = net;
-	fwork->addr = addr;
-	schedule_work(&fwork->work);
+	tn->final_work.net = net;
+	tn->final_work.addr = addr;
+	schedule_work(&tn->final_work.work);
 }
 
 void tipc_net_stop(struct net *net)
diff --git a/net/tipc/net.h b/net/tipc/net.h
index 6740d97c706e..d0c91d2df20a 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -42,6 +42,7 @@
 extern const struct nla_policy tipc_nl_net_policy[];
 
 int tipc_net_init(struct net *net, u8 *node_id, u32 addr);
+void tipc_net_finalize_work(struct work_struct *work);
 void tipc_sched_net_finalize(struct net *net, u32 addr);
 void tipc_net_stop(struct net *net);
 int tipc_nl_net_dump(struct sk_buff *skb, struct netlink_callback *cb);
diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c
index c4aee6247d55..c447cb5f879e 100644
--- a/net/tipc/netlink.c
+++ b/net/tipc/netlink.c
@@ -108,6 +108,8 @@ const struct nla_policy tipc_nl_node_policy[TIPC_NLA_NODE_MAX + 1] = {
 					    .len = TIPC_NODEID_LEN},
 	[TIPC_NLA_NODE_KEY]		= { .type = NLA_BINARY,
 					    .len = TIPC_AEAD_KEY_SIZE_MAX},
+	[TIPC_NLA_NODE_KEY_MASTER]	= { .type = NLA_FLAG },
+	[TIPC_NLA_NODE_REKEYING]	= { .type = NLA_U32 },
 };
 
 /* Properties valid for media, bearer and link */
diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c
index 90e3c70a91ad..5a1ce64039f7 100644
--- a/net/tipc/netlink_compat.c
+++ b/net/tipc/netlink_compat.c
@@ -118,7 +118,8 @@ static void tipc_tlv_init(struct sk_buff *skb, u16 type)
 	skb_put(skb, sizeof(struct tlv_desc));
 }
 
-static int tipc_tlv_sprintf(struct sk_buff *skb, const char *fmt, ...)
+static __printf(2, 3) int tipc_tlv_sprintf(struct sk_buff *skb,
+					   const char *fmt, ...)
 {
 	int n;
 	u16 len;
@@ -212,12 +213,14 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd,
 	}
 
 	info.attrs = attrbuf;
-	err = nlmsg_parse_deprecated(cb.nlh, GENL_HDRLEN, attrbuf,
-				     tipc_genl_family.maxattr,
-				     tipc_genl_family.policy, NULL);
-	if (err)
-		goto err_out;
 
+	if (nlmsg_len(cb.nlh) > 0) {
+		err = nlmsg_parse_deprecated(cb.nlh, GENL_HDRLEN, attrbuf,
+					     tipc_genl_family.maxattr,
+					     tipc_genl_family.policy, NULL);
+		if (err)
+			goto err_out;
+	}
 	do {
 		int rem;
 
@@ -588,7 +591,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg,
 		return 0;
 
 	tipc_tlv_sprintf(msg->rep, "\nLink <%s>\n",
-			 nla_data(link[TIPC_NLA_LINK_NAME]));
+			 (char *)nla_data(link[TIPC_NLA_LINK_NAME]));
 
 	if (link[TIPC_NLA_LINK_BROADCAST]) {
 		__fill_bc_link_stat(msg, prop, stats);
@@ -695,7 +698,7 @@ static int tipc_nl_compat_link_dump(struct tipc_nl_compat_msg *msg,
 
 	link_info.dest = nla_get_flag(link[TIPC_NLA_LINK_DEST]);
 	link_info.up = htonl(nla_get_flag(link[TIPC_NLA_LINK_UP]));
-	nla_strlcpy(link_info.str, link[TIPC_NLA_LINK_NAME],
+	nla_strscpy(link_info.str, link[TIPC_NLA_LINK_NAME],
 		    TIPC_MAX_LINK_NAME);
 
 	return tipc_add_tlv(msg->rep, TIPC_TLV_LINK_INFO,
@@ -1337,7 +1340,7 @@ send:
 	return err;
 }
 
-static const struct genl_ops tipc_genl_compat_ops[] = {
+static const struct genl_small_ops tipc_genl_compat_ops[] = {
 	{
 		.cmd		= TIPC_GENL_CMD,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -1352,8 +1355,8 @@ static struct genl_family tipc_genl_compat_family __ro_after_init = {
 	.maxattr	= 0,
 	.netnsok	= true,
 	.module		= THIS_MODULE,
-	.ops		= tipc_genl_compat_ops,
-	.n_ops		= ARRAY_SIZE(tipc_genl_compat_ops),
+	.small_ops	= tipc_genl_compat_ops,
+	.n_small_ops	= ARRAY_SIZE(tipc_genl_compat_ops),
 };
 
 int __init tipc_netlink_compat_start(void)
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 4edcee3088da..008670d1f43e 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -82,7 +82,7 @@ struct tipc_bclink_entry {
 /**
  * struct tipc_node - TIPC node structure
  * @addr: network address of node
- * @ref: reference counter to node object
+ * @kref: reference counter to node object
  * @lock: rwlock governing access to structure
  * @net: the applicable net namespace
  * @hash: links to adjacent nodes in unsorted hash chain
@@ -90,9 +90,11 @@ struct tipc_bclink_entry {
  * @namedq: pointer to name table input queue with name table messages
  * @active_links: bearer ids of active links, used as index into links[] array
  * @links: array containing references to all links to node
+ * @bc_entry: broadcast link entry
  * @action_flags: bit mask of different types of node actions
  * @state: connectivity state vs peer node
  * @preliminary: a preliminary node or not
+ * @failover_sent: failover sent or not
  * @sync_point: sequence number where synch/failover is finished
  * @list: links to adjacent nodes in sorted list of cluster's nodes
  * @working_links: number of working links to node (both active and standby)
@@ -100,9 +102,16 @@ struct tipc_bclink_entry {
  * @capabilities: bitmap, indicating peer node's functional capabilities
  * @signature: node instance identifier
  * @link_id: local and remote bearer ids of changing link, if any
+ * @peer_id: 128-bit ID of peer
+ * @peer_id_string: ID string of peer
  * @publ_list: list of publications
+ * @conn_sks: list of connections (FIXME)
+ * @timer: node's keepalive timer
+ * @keepalive_intv: keepalive interval in milliseconds
  * @rcu: rcu struct for tipc_node
  * @delete_at: indicates the time for deleting a down node
+ * @peer_net: peer's net namespace
+ * @peer_hash_mix: hash for this peer (FIXME)
  * @crypto_rx: RX crypto handler
  */
 struct tipc_node {
@@ -267,6 +276,7 @@ char *tipc_node_get_id_str(struct tipc_node *node)
 #ifdef CONFIG_TIPC_CRYPTO
 /**
  * tipc_node_crypto_rx - Retrieve crypto RX handle from node
+ * @__n: target tipc_node
  * Note: node ref counter must be held first!
  */
 struct tipc_crypto *tipc_node_crypto_rx(struct tipc_node *__n)
@@ -278,6 +288,14 @@ struct tipc_crypto *tipc_node_crypto_rx_by_list(struct list_head *pos)
 {
 	return container_of(pos, struct tipc_node, list)->crypto_rx;
 }
+
+struct tipc_crypto *tipc_node_crypto_rx_by_addr(struct net *net, u32 addr)
+{
+	struct tipc_node *n;
+
+	n = tipc_node_find(net, addr);
+	return (n) ? n->crypto_rx : NULL;
+}
 #endif
 
 static void tipc_node_free(struct rcu_head *rp)
@@ -303,7 +321,7 @@ void tipc_node_put(struct tipc_node *node)
 	kref_put(&node->kref, tipc_node_kref_release);
 }
 
-static void tipc_node_get(struct tipc_node *node)
+void tipc_node_get(struct tipc_node *node)
 {
 	kref_get(&node->kref);
 }
@@ -584,6 +602,9 @@ static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l)
 
 static void tipc_node_delete_from_list(struct tipc_node *node)
 {
+#ifdef CONFIG_TIPC_CRYPTO
+	tipc_crypto_key_flush(node->crypto_rx);
+#endif
 	list_del_rcu(&node->list);
 	hlist_del_rcu(&node->hash);
 	tipc_node_put(node);
@@ -803,6 +824,9 @@ static void tipc_node_timeout(struct timer_list *t)
 
 /**
  * __tipc_node_link_up - handle addition of link
+ * @n: target tipc_node
+ * @bearer_id: id of the bearer
+ * @xmitq: queue for messages to be xmited on
  * Node lock must be held by caller
  * Link becomes active (alone or shared) or standby, depending on its priority.
  */
@@ -869,6 +893,9 @@ static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
 
 /**
  * tipc_node_link_up - handle addition of link
+ * @n: target tipc_node
+ * @bearer_id: id of the bearer
+ * @xmitq: queue for messages to be xmited on
  *
  * Link becomes active (alone or shared) or standby, depending on its priority.
  */
@@ -889,10 +916,11 @@ static void tipc_node_link_up(struct tipc_node *n, int bearer_id,
  *
  * This function is only called in a very special situation where link
  * failover can be already started on peer node but not on this node.
- * This can happen when e.g.
+ * This can happen when e.g.::
+ *
  *	1. Both links <1A-2A>, <1B-2B> down
  *	2. Link endpoint 2A up, but 1A still down (e.g. due to network
- *	   disturbance, wrong session, etc.)
+ *	disturbance, wrong session, etc.)
  *	3. Link <1B-2B> up
  *	4. Link endpoint 2A down (e.g. due to link tolerance timeout)
  *	5. Node 2 starts failover onto link <1B-2B>
@@ -929,6 +957,10 @@ static void tipc_node_link_failover(struct tipc_node *n, struct tipc_link *l,
 
 /**
  * __tipc_node_link_down - handle loss of link
+ * @n: target tipc_node
+ * @bearer_id: id of the bearer
+ * @xmitq: queue for messages to be xmited on
+ * @maddr: output media address of the bearer
  */
 static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
 				  struct sk_buff_head *xmitq,
@@ -1485,7 +1517,7 @@ static void node_lost_contact(struct tipc_node *n,
 
 	/* Clean up broadcast state */
 	tipc_bcast_remove_peer(n->net, n->bc_entry.link);
-	__skb_queue_purge(&n->bc_entry.namedq);
+	skb_queue_purge(&n->bc_entry.namedq);
 
 	/* Abort any ongoing link failover */
 	for (i = 0; i < MAX_BEARERS; i++) {
@@ -1514,11 +1546,13 @@ static void node_lost_contact(struct tipc_node *n,
 /**
  * tipc_node_get_linkname - get the name of a link
  *
+ * @net: the applicable net namespace
  * @bearer_id: id of the bearer
  * @addr: peer node address
  * @linkname: link name output buffer
+ * @len: size of @linkname output buffer
  *
- * Returns 0 on success
+ * Return: 0 on success
  */
 int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 addr,
 			   char *linkname, size_t len)
@@ -1627,17 +1661,17 @@ static void tipc_lxc_xmit(struct net *peer_net, struct sk_buff_head *list)
 		return;
 	default:
 		return;
-	};
+	}
 }
 
 /**
- * tipc_node_xmit() is the general link level function for message sending
+ * tipc_node_xmit() - general link level function for message sending
  * @net: the applicable net namespace
  * @list: chain of buffers containing message
  * @dnode: address of destination node
  * @selector: a number used for deterministic link selection
  * Consumes the buffer chain.
- * Returns 0 if success, otherwise: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE,-ENOBUF
+ * Return: 0 if success, otherwise: -ELINKCONG,-EHOSTUNREACH,-EMSGSIZE,-ENOBUF
  */
 int tipc_node_xmit(struct net *net, struct sk_buff_head *list,
 		   u32 dnode, int selector)
@@ -1870,9 +1904,11 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id
 
 /**
  * tipc_node_check_state - check and if necessary update node state
+ * @n: target tipc_node
  * @skb: TIPC packet
  * @bearer_id: identity of bearer delivering the packet
- * Returns true if state and msg are ok, otherwise false
+ * @xmitq: queue for messages to be xmited on
+ * Return: true if state and msg are ok, otherwise false
  */
 static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
 				  int bearer_id, struct sk_buff_head *xmitq)
@@ -2170,7 +2206,11 @@ void tipc_node_apply_property(struct net *net, struct tipc_bearer *b,
 							&xmitq);
 			else if (prop == TIPC_NLA_PROP_MTU)
 				tipc_link_set_mtu(e->link, b->mtu);
+
+			/* Update MTU for node link entry */
+			e->mtu = tipc_link_mss(e->link);
 		}
+
 		tipc_node_write_unlock(n);
 		tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr, NULL);
 	}
@@ -2184,6 +2224,9 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct nlattr *attrs[TIPC_NLA_NET_MAX + 1];
 	struct tipc_node *peer, *temp_node;
+	u8 node_id[NODE_ID_LEN];
+	u64 *w0 = (u64 *)&node_id[0];
+	u64 *w1 = (u64 *)&node_id[8];
 	u32 addr;
 	int err;
 
@@ -2197,10 +2240,22 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
-	if (!attrs[TIPC_NLA_NET_ADDR])
-		return -EINVAL;
+	/* attrs[TIPC_NLA_NET_NODEID] and attrs[TIPC_NLA_NET_ADDR] are
+	 * mutually exclusive cases
+	 */
+	if (attrs[TIPC_NLA_NET_ADDR]) {
+		addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]);
+		if (!addr)
+			return -EINVAL;
+	}
 
-	addr = nla_get_u32(attrs[TIPC_NLA_NET_ADDR]);
+	if (attrs[TIPC_NLA_NET_NODEID]) {
+		if (!attrs[TIPC_NLA_NET_NODEID_W1])
+			return -EINVAL;
+		*w0 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID]);
+		*w1 = nla_get_u64(attrs[TIPC_NLA_NET_NODEID_W1]);
+		addr = hash128to32(node_id);
+	}
 
 	if (in_own_node(net, addr))
 		return -ENOTSUPP;
@@ -2868,15 +2923,27 @@ static int tipc_nl_retrieve_nodeid(struct nlattr **attrs, u8 **node_id)
 	return 0;
 }
 
+static int tipc_nl_retrieve_rekeying(struct nlattr **attrs, u32 *intv)
+{
+	struct nlattr *attr = attrs[TIPC_NLA_NODE_REKEYING];
+
+	if (!attr)
+		return -ENODATA;
+
+	*intv = nla_get_u32(attr);
+	return 0;
+}
+
 static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *attrs[TIPC_NLA_NODE_MAX + 1];
 	struct net *net = sock_net(skb->sk);
-	struct tipc_net *tn = tipc_net(net);
+	struct tipc_crypto *tx = tipc_net(net)->crypto_tx, *c = tx;
 	struct tipc_node *n = NULL;
 	struct tipc_aead_key *ukey;
-	struct tipc_crypto *c;
-	u8 *id, *own_id;
+	bool rekeying = true, master_key = false;
+	u8 *id, *own_id, mode;
+	u32 intv = 0;
 	int rc = 0;
 
 	if (!info->attrs[TIPC_NLA_NODE])
@@ -2886,52 +2953,66 @@ static int __tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
 			      info->attrs[TIPC_NLA_NODE],
 			      tipc_nl_node_policy, info->extack);
 	if (rc)
-		goto exit;
+		return rc;
 
 	own_id = tipc_own_id(net);
 	if (!own_id) {
-		rc = -EPERM;
-		goto exit;
+		GENL_SET_ERR_MSG(info, "not found own node identity (set id?)");
+		return -EPERM;
 	}
 
+	rc = tipc_nl_retrieve_rekeying(attrs, &intv);
+	if (rc == -ENODATA)
+		rekeying = false;
+
 	rc = tipc_nl_retrieve_key(attrs, &ukey);
-	if (rc)
-		goto exit;
+	if (rc == -ENODATA && rekeying)
+		goto rekeying;
+	else if (rc)
+		return rc;
 
-	rc = tipc_aead_key_validate(ukey);
+	rc = tipc_aead_key_validate(ukey, info);
 	if (rc)
-		goto exit;
+		return rc;
 
 	rc = tipc_nl_retrieve_nodeid(attrs, &id);
 	switch (rc) {
 	case -ENODATA:
-		/* Cluster key mode */
-		rc = tipc_crypto_key_init(tn->crypto_tx, ukey, CLUSTER_KEY);
+		mode = CLUSTER_KEY;
+		master_key = !!(attrs[TIPC_NLA_NODE_KEY_MASTER]);
 		break;
 	case 0:
-		/* Per-node key mode */
-		if (!memcmp(id, own_id, NODE_ID_LEN)) {
-			c = tn->crypto_tx;
-		} else {
+		mode = PER_NODE_KEY;
+		if (memcmp(id, own_id, NODE_ID_LEN)) {
 			n = tipc_node_find_by_id(net, id) ?:
 				tipc_node_create(net, 0, id, 0xffffu, 0, true);
-			if (unlikely(!n)) {
-				rc = -ENOMEM;
-				break;
-			}
+			if (unlikely(!n))
+				return -ENOMEM;
 			c = n->crypto_rx;
 		}
-
-		rc = tipc_crypto_key_init(c, ukey, PER_NODE_KEY);
-		if (n)
-			tipc_node_put(n);
 		break;
 	default:
-		break;
+		return rc;
 	}
 
-exit:
-	return (rc < 0) ? rc : 0;
+	/* Initiate the TX/RX key */
+	rc = tipc_crypto_key_init(c, ukey, mode, master_key);
+	if (n)
+		tipc_node_put(n);
+
+	if (unlikely(rc < 0)) {
+		GENL_SET_ERR_MSG(info, "unable to initiate or attach new key");
+		return rc;
+	} else if (c == tx) {
+		/* Distribute TX key but not master one */
+		if (!master_key && tipc_crypto_key_distr(tx, rc, NULL))
+			GENL_SET_ERR_MSG(info, "failed to replicate new key");
+rekeying:
+		/* Schedule TX rekeying if needed */
+		tipc_crypto_rekeying_sched(tx, rekeying, intv);
+	}
+
+	return 0;
 }
 
 int tipc_nl_node_set_key(struct sk_buff *skb, struct genl_info *info)
@@ -2958,7 +3039,6 @@ static int __tipc_nl_node_flush_key(struct sk_buff *skb,
 		tipc_crypto_key_flush(n->crypto_rx);
 	rcu_read_unlock();
 
-	pr_info("All keys are flushed!\n");
 	return 0;
 }
 
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 9f6f13f1604f..154a5bbb0d29 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -79,12 +79,14 @@ bool tipc_node_get_id(struct net *net, u32 addr, u8 *id);
 u32 tipc_node_get_addr(struct tipc_node *node);
 char *tipc_node_get_id_str(struct tipc_node *node);
 void tipc_node_put(struct tipc_node *node);
+void tipc_node_get(struct tipc_node *node);
 struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
 				   u16 capabilities, u32 hash_mixes,
 				   bool preliminary);
 #ifdef CONFIG_TIPC_CRYPTO
 struct tipc_crypto *tipc_node_crypto_rx(struct tipc_node *__n);
 struct tipc_crypto *tipc_node_crypto_rx_by_list(struct list_head *pos);
+struct tipc_crypto *tipc_node_crypto_rx_by_addr(struct net *net, u32 addr);
 #endif
 u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr);
 void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128,
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 11b27ddc75ba..cebcc104dc70 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1,8 +1,9 @@
 /*
  * net/tipc/socket.c: TIPC socket API
  *
- * Copyright (c) 2001-2007, 2012-2017, Ericsson AB
+ * Copyright (c) 2001-2007, 2012-2019, Ericsson AB
  * Copyright (c) 2004-2008, 2010-2013, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -52,10 +53,9 @@
 #define NAGLE_START_MAX		1024
 #define CONN_TIMEOUT_DEFAULT    8000    /* default connect timeout = 8s */
 #define CONN_PROBING_INTV	msecs_to_jiffies(3600000)  /* [ms] => 1 h */
-#define TIPC_FWD_MSG		1
 #define TIPC_MAX_PORT		0xffffffff
 #define TIPC_MIN_PORT		1
-#define TIPC_ACK_RATE		4       /* ACK at 1/4 of of rcv window size */
+#define TIPC_ACK_RATE		4       /* ACK at 1/4 of rcv window size */
 
 enum {
 	TIPC_LISTEN = TCP_LISTEN,
@@ -80,19 +80,32 @@ struct sockaddr_pair {
  * @maxnagle: maximum size of msg which can be subject to nagle
  * @portid: unique port identity in TIPC socket hash table
  * @phdr: preformatted message header used when sending messages
- * #cong_links: list of congested links
+ * @cong_links: list of congested links
  * @publications: list of publications for port
  * @blocking_link: address of the congested link we are currently sleeping on
  * @pub_count: total # of publications port has made during its lifetime
  * @conn_timeout: the time we can wait for an unresponded setup request
+ * @probe_unacked: probe has not received ack yet
  * @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
  * @cong_link_cnt: number of congested links
  * @snt_unacked: # messages sent by socket, and not yet acked by peer
+ * @snd_win: send window size
+ * @peer_caps: peer capabilities mask
  * @rcv_unacked: # messages read by user, but not yet acked back to peer
+ * @rcv_win: receive window size
  * @peer: 'connected' peer for dgram/rdm
  * @node: hash table node
  * @mc_method: cookie for use between socket and broadcast layer
  * @rcu: rcu struct for tipc_sock
+ * @group: TIPC communications group
+ * @oneway: message count in one direction (FIXME)
+ * @nagle_start: current nagle value
+ * @snd_backlog: send backlog count
+ * @msg_acc: messages accepted; used in managing backlog and nagle
+ * @pkt_cnt: TIPC socket packet count
+ * @expect_ack: whether this TIPC socket is expecting an ack
+ * @nodelay: setsockopt() TIPC_NODELAY setting
+ * @group_is_open: TIPC socket group is fully open (FIXME)
  */
 struct tipc_sock {
 	struct sock sk;
@@ -139,9 +152,9 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
 		       bool kern);
 static void tipc_sk_timeout(struct timer_list *t);
 static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
-			   struct tipc_name_seq const *seq);
+			   struct tipc_service_range const *seq);
 static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
-			    struct tipc_name_seq const *seq);
+			    struct tipc_service_range const *seq);
 static int tipc_sk_leave(struct tipc_sock *tsk);
 static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid);
 static int tipc_sk_insert(struct tipc_sock *tsk);
@@ -261,6 +274,7 @@ static void tsk_set_nagle(struct tipc_sock *tsk)
 
 /**
  * tsk_advance_rx_queue - discard first buffer in socket receive queue
+ * @sk: network socket
  *
  * Caller must hold socket lock
  */
@@ -289,6 +303,8 @@ static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err)
 
 /**
  * tsk_rej_rx_queue - reject all buffers in socket receive queue
+ * @sk: network socket
+ * @error: response error code
  *
  * Caller must hold socket lock
  */
@@ -442,7 +458,7 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout)
  * This routine creates additional data structures used by the TIPC socket,
  * initializes them, and links them together.
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  */
 static int tipc_sk_create(struct net *net, struct socket *sock,
 			  int protocol, int kern)
@@ -607,7 +623,7 @@ static void __tipc_shutdown(struct socket *sock, int error)
  * are returned or discarded according to the "destination droppable" setting
  * specified for the message by the sender.
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  */
 static int tipc_release(struct socket *sock)
 {
@@ -645,75 +661,77 @@ static int tipc_release(struct socket *sock)
 }
 
 /**
- * tipc_bind - associate or disassocate TIPC name(s) with a socket
+ * __tipc_bind - associate or disassocate TIPC name(s) with a socket
  * @sock: socket structure
- * @uaddr: socket address describing name(s) and desired operation
- * @uaddr_len: size of socket address data structure
+ * @skaddr: socket address describing name(s) and desired operation
+ * @alen: size of socket address data structure
  *
  * Name and name sequence binding is indicated using a positive scope value;
  * a negative scope value unbinds the specified name.  Specifying no name
  * (i.e. a socket address length of 0) unbinds all names from the socket.
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  *
  * NOTE: This routine doesn't need to take the socket lock since it doesn't
  *       access any non-constant socket information.
  */
-static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
-		     int uaddr_len)
+static int __tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen)
 {
-	struct sock *sk = sock->sk;
-	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
-	struct tipc_sock *tsk = tipc_sk(sk);
-	int res = -EINVAL;
+	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)skaddr;
+	struct tipc_sock *tsk = tipc_sk(sock->sk);
 
-	lock_sock(sk);
-	if (unlikely(!uaddr_len)) {
-		res = tipc_sk_withdraw(tsk, 0, NULL);
-		goto exit;
-	}
-	if (tsk->group) {
-		res = -EACCES;
-		goto exit;
-	}
-	if (uaddr_len < sizeof(struct sockaddr_tipc)) {
-		res = -EINVAL;
-		goto exit;
-	}
-	if (addr->family != AF_TIPC) {
-		res = -EAFNOSUPPORT;
-		goto exit;
-	}
+	if (unlikely(!alen))
+		return tipc_sk_withdraw(tsk, 0, NULL);
 
-	if (addr->addrtype == TIPC_ADDR_NAME)
+	if (addr->addrtype == TIPC_SERVICE_ADDR)
 		addr->addr.nameseq.upper = addr->addr.nameseq.lower;
-	else if (addr->addrtype != TIPC_ADDR_NAMESEQ) {
-		res = -EAFNOSUPPORT;
-		goto exit;
-	}
 
-	if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&
-	    (addr->addr.nameseq.type != TIPC_TOP_SRV) &&
-	    (addr->addr.nameseq.type != TIPC_CFG_SRV)) {
-		res = -EACCES;
-		goto exit;
-	}
+	if (tsk->group)
+		return -EACCES;
 
-	res = (addr->scope >= 0) ?
-		tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq) :
-		tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq);
-exit:
-	release_sock(sk);
+	if (addr->scope >= 0)
+		return tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq);
+	else
+		return tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq);
+}
+
+int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen)
+{
+	int res;
+
+	lock_sock(sock->sk);
+	res = __tipc_bind(sock, skaddr, alen);
+	release_sock(sock->sk);
 	return res;
 }
 
+static int tipc_bind(struct socket *sock, struct sockaddr *skaddr, int alen)
+{
+	struct sockaddr_tipc *addr = (struct sockaddr_tipc *)skaddr;
+
+	if (alen) {
+		if (alen < sizeof(struct sockaddr_tipc))
+			return -EINVAL;
+		if (addr->family != AF_TIPC)
+			return -EAFNOSUPPORT;
+		if (addr->addrtype > TIPC_SERVICE_ADDR)
+			return -EAFNOSUPPORT;
+		if (addr->addr.nameseq.type < TIPC_RESERVED_TYPES) {
+			pr_warn_once("Can't bind to reserved service type %u\n",
+				     addr->addr.nameseq.type);
+			return -EACCES;
+		}
+	}
+	return tipc_sk_bind(sock, skaddr, alen);
+}
+
 /**
  * tipc_getname - get port ID of socket or peer socket
  * @sock: socket structure
  * @uaddr: area for returned socket address
  * @peer: 0 = own ID, 1 = current peer ID, 2 = current/former peer ID
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  *
  * NOTE: This routine doesn't need to take the socket lock since it only
  *       accesses socket information that is unchanging (or which changes in
@@ -738,7 +756,7 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
 		addr->addr.id.node = tipc_own_addr(sock_net(sk));
 	}
 
-	addr->addrtype = TIPC_ADDR_ID;
+	addr->addrtype = TIPC_SOCKET_ADDR;
 	addr->family = AF_TIPC;
 	addr->scope = 0;
 	addr->addr.name.domain = 0;
@@ -752,7 +770,7 @@ static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
  * @sock: socket for which to calculate the poll bits
  * @wait: ???
  *
- * Returns pollmask value
+ * Return: pollmask value
  *
  * COMMENTARY:
  * It appears that the usual socket locking mechanisms are not useful here
@@ -814,9 +832,9 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
  * @timeout: timeout to wait for wakeup
  *
  * Called from function tipc_sendmsg(), which has done all sanity checks
- * Returns the number of bytes sent on success, or errno
+ * Return: the number of bytes sent on success, or errno
  */
-static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
+static int tipc_sendmcast(struct  socket *sock, struct tipc_service_range *seq,
 			  struct msghdr *msg, size_t dlen, long timeout)
 {
 	struct sock *sk = sock->sk;
@@ -874,6 +892,7 @@ static int tipc_sendmcast(struct  socket *sock, struct tipc_name_seq *seq,
 /**
  * tipc_send_group_msg - send a message to a member in the group
  * @net: network namespace
+ * @tsk: tipc socket
  * @m: message to send
  * @mb: group member
  * @dnode: destination node
@@ -929,7 +948,7 @@ static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk,
  * @timeout: timeout to wait for wakeup
  *
  * Called from function tipc_sendmsg(), which has done all sanity checks
- * Returns the number of bytes sent on success, or errno
+ * Return: the number of bytes sent on success, or errno
  */
 static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m,
 				   int dlen, long timeout)
@@ -973,7 +992,7 @@ static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m,
  * @timeout: timeout to wait for wakeup
  *
  * Called from function tipc_sendmsg(), which has done all sanity checks
- * Returns the number of bytes sent on success, or errno
+ * Return: the number of bytes sent on success, or errno
  */
 static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
 				   int dlen, long timeout)
@@ -1058,7 +1077,7 @@ static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
  * @timeout: timeout to wait for wakeup
  *
  * Called from function tipc_sendmsg(), which has done all sanity checks
- * Returns the number of bytes sent on success, or errno
+ * Return: the number of bytes sent on success, or errno
  */
 static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
 				 int dlen, long timeout)
@@ -1132,7 +1151,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m,
  * @timeout: timeout to wait for wakeup
  *
  * Called from function tipc_sendmsg(), which has done all sanity checks
- * Returns the number of bytes sent on success, or errno
+ * Return: the number of bytes sent on success, or errno
  */
 static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m,
 				 int dlen, long timeout)
@@ -1169,6 +1188,7 @@ static int tipc_send_group_mcast(struct socket *sock, struct msghdr *m,
 
 /**
  * tipc_sk_mcast_rcv - Deliver multicast messages to all destination sockets
+ * @net: the associated network namespace
  * @arrvq: queue with arriving messages, to be cloned after destination lookup
  * @inputq: queue with cloned messages, delivered to socket after dest lookup
  *
@@ -1308,6 +1328,8 @@ static void tipc_sk_push_backlog(struct tipc_sock *tsk, bool nagle_ack)
  * tipc_sk_conn_proto_rcv - receive a connection mng protocol message
  * @tsk: receiving socket
  * @skb: pointer to message buffer.
+ * @inputq: buffer list containing the buffers
+ * @xmitq: output message area
  */
 static void tipc_sk_conn_proto_rcv(struct tipc_sock *tsk, struct sk_buff *skb,
 				   struct sk_buff_head *inputq,
@@ -1375,7 +1397,7 @@ exit:
  * and for 'SYN' messages on SOCK_SEQPACKET and SOCK_STREAM connections.
  * (Note: 'SYN+' is prohibited on SOCK_STREAM.)
  *
- * Returns the number of bytes sent on success, or errno otherwise
+ * Return: the number of bytes sent on success, or errno otherwise
  */
 static int tipc_sendmsg(struct socket *sock,
 			struct msghdr *m, size_t dsz)
@@ -1401,7 +1423,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	bool syn = !tipc_sk_type_connectionless(sk);
 	struct tipc_group *grp = tsk->group;
 	struct tipc_msg *hdr = &tsk->phdr;
-	struct tipc_name_seq *seq;
+	struct tipc_service_range *seq;
 	struct sk_buff_head pkts;
 	u32 dport = 0, dnode = 0;
 	u32 type = 0, inst = 0;
@@ -1420,9 +1442,9 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	if (grp) {
 		if (!dest)
 			return tipc_send_group_bcast(sock, m, dlen, timeout);
-		if (dest->addrtype == TIPC_ADDR_NAME)
+		if (dest->addrtype == TIPC_SERVICE_ADDR)
 			return tipc_send_group_anycast(sock, m, dlen, timeout);
-		if (dest->addrtype == TIPC_ADDR_ID)
+		if (dest->addrtype == TIPC_SOCKET_ADDR)
 			return tipc_send_group_unicast(sock, m, dlen, timeout);
 		if (dest->addrtype == TIPC_ADDR_MCAST)
 			return tipc_send_group_mcast(sock, m, dlen, timeout);
@@ -1442,7 +1464,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 			return -EISCONN;
 		if (tsk->published)
 			return -EOPNOTSUPP;
-		if (dest->addrtype == TIPC_ADDR_NAME) {
+		if (dest->addrtype == TIPC_SERVICE_ADDR) {
 			tsk->conn_type = dest->addr.name.name.type;
 			tsk->conn_instance = dest->addr.name.name.instance;
 		}
@@ -1453,14 +1475,14 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	if (dest->addrtype == TIPC_ADDR_MCAST)
 		return tipc_sendmcast(sock, seq, m, dlen, timeout);
 
-	if (dest->addrtype == TIPC_ADDR_NAME) {
+	if (dest->addrtype == TIPC_SERVICE_ADDR) {
 		type = dest->addr.name.name.type;
 		inst = dest->addr.name.name.instance;
 		dnode = dest->addr.name.domain;
 		dport = tipc_nametbl_translate(net, type, inst, &dnode);
 		if (unlikely(!dport && !dnode))
 			return -EHOSTUNREACH;
-	} else if (dest->addrtype == TIPC_ADDR_ID) {
+	} else if (dest->addrtype == TIPC_SOCKET_ADDR) {
 		dnode = dest->addr.id.node;
 	} else {
 		return -EINVAL;
@@ -1472,7 +1494,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 	if (unlikely(rc))
 		return rc;
 
-	if (dest->addrtype == TIPC_ADDR_NAME) {
+	if (dest->addrtype == TIPC_SERVICE_ADDR) {
 		msg_set_type(hdr, TIPC_NAMED_MSG);
 		msg_set_hdr_sz(hdr, NAMED_H_SIZE);
 		msg_set_nametype(hdr, type);
@@ -1480,7 +1502,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
 		msg_set_lookup_scope(hdr, tipc_node2scope(dnode));
 		msg_set_destnode(hdr, dnode);
 		msg_set_destport(hdr, dport);
-	} else { /* TIPC_ADDR_ID */
+	} else { /* TIPC_SOCKET_ADDR */
 		msg_set_type(hdr, TIPC_DIRECT_MSG);
 		msg_set_lookup_scope(hdr, 0);
 		msg_set_destnode(hdr, dnode);
@@ -1520,7 +1542,7 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen)
  *
  * Used for SOCK_STREAM data.
  *
- * Returns the number of bytes sent on success (or partial success),
+ * Return: the number of bytes sent on success (or partial success),
  * or errno if no data sent
  */
 static int tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz)
@@ -1628,7 +1650,7 @@ static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dlen)
  *
  * Used for SOCK_SEQPACKET messages.
  *
- * Returns the number of bytes sent on success, or errno otherwise
+ * Return: the number of bytes sent on success, or errno otherwise
  */
 static int tipc_send_packet(struct socket *sock, struct msghdr *m, size_t dsz)
 {
@@ -1685,7 +1707,7 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 		return;
 
 	srcaddr->sock.family = AF_TIPC;
-	srcaddr->sock.addrtype = TIPC_ADDR_ID;
+	srcaddr->sock.addrtype = TIPC_SOCKET_ADDR;
 	srcaddr->sock.scope = 0;
 	srcaddr->sock.addr.id.ref = msg_origport(hdr);
 	srcaddr->sock.addr.id.node = msg_orignode(hdr);
@@ -1697,7 +1719,7 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 
 	/* Group message users may also want to know sending member's id */
 	srcaddr->member.family = AF_TIPC;
-	srcaddr->member.addrtype = TIPC_ADDR_NAME;
+	srcaddr->member.addrtype = TIPC_SERVICE_ADDR;
 	srcaddr->member.scope = 0;
 	srcaddr->member.addr.name.name.type = msg_nametype(hdr);
 	srcaddr->member.addr.name.name.instance = TIPC_SKB_CB(skb)->orig_member;
@@ -1713,7 +1735,7 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
  *
  * Note: Ancillary data is not captured if not requested by receiver.
  *
- * Returns 0 if successful, otherwise errno
+ * Return: 0 if successful, otherwise errno
  */
 static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
 				 struct tipc_sock *tsk)
@@ -1863,6 +1885,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
 
 /**
  * tipc_recvmsg - receive packet-oriented message
+ * @sock: network socket
  * @m: descriptor for message info
  * @buflen: length of user buffer area
  * @flags: receive flags
@@ -1870,7 +1893,7 @@ static int tipc_wait_for_rcvmsg(struct socket *sock, long *timeop)
  * Used for SOCK_DGRAM, SOCK_RDM, and SOCK_SEQPACKET messages.
  * If the complete message doesn't fit in user area, truncate it.
  *
- * Returns size of returned message data, errno otherwise
+ * Return: size of returned message data, errno otherwise
  */
 static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 			size_t buflen,	int flags)
@@ -1971,6 +1994,7 @@ exit:
 
 /**
  * tipc_recvstream - receive stream-oriented data
+ * @sock: network socket
  * @m: descriptor for message info
  * @buflen: total size of user buffer area
  * @flags: receive flags
@@ -1978,7 +2002,7 @@ exit:
  * Used for SOCK_STREAM messages only.  If not enough data is available
  * will optionally wait for more; never truncates data.
  *
- * Returns size of returned message data, errno otherwise
+ * Return: size of returned message data, errno otherwise
  */
 static int tipc_recvstream(struct socket *sock, struct msghdr *m,
 			   size_t buflen, int flags)
@@ -2156,7 +2180,7 @@ static void tipc_sk_proto_rcv(struct sock *sk,
  * @tsk: TIPC socket
  * @skb: pointer to message buffer.
  * @xmitq: for Nagle ACK if any
- * Returns true if message should be added to receive queue, false otherwise
+ * Return: true if message should be added to receive queue, false otherwise
  */
 static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb,
 				   struct sk_buff_head *xmitq)
@@ -2270,7 +2294,7 @@ static bool tipc_sk_filter_connect(struct tipc_sock *tsk, struct sk_buff *skb,
  * TIPC_HIGH_IMPORTANCE      (8 MB)
  * TIPC_CRITICAL_IMPORTANCE  (16 MB)
  *
- * Returns overload limit according to corresponding message importance
+ * Return: overload limit according to corresponding message importance
  */
 static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
 {
@@ -2293,12 +2317,12 @@ static unsigned int rcvbuf_limit(struct sock *sk, struct sk_buff *skb)
  * tipc_sk_filter_rcv - validate incoming message
  * @sk: socket
  * @skb: pointer to message.
+ * @xmitq: output message area (FIXME)
  *
  * Enqueues message on receive queue if acceptable; optionally handles
  * disconnect indication for a connected socket.
  *
  * Called with socket lock already taken
- *
  */
 static void tipc_sk_filter_rcv(struct sock *sk, struct sk_buff *skb,
 			       struct sk_buff_head *xmitq)
@@ -2388,6 +2412,7 @@ static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
  * @inputq: list of incoming buffers with potentially different destinations
  * @sk: socket where the buffers should be enqueued
  * @dport: port number for the socket
+ * @xmitq: output queue
  *
  * Caller must hold socket lock
  */
@@ -2440,6 +2465,7 @@ static void tipc_sk_enqueue(struct sk_buff_head *inputq, struct sock *sk,
 
 /**
  * tipc_sk_rcv - handle a chain of incoming buffers
+ * @net: the associated network namespace
  * @inputq: buffer list containing the buffers
  * Consumes all buffers in list until inputq is empty
  * Note: may be called in multiple threads referring to the same queue
@@ -2532,7 +2558,7 @@ static bool tipc_sockaddr_is_sane(struct sockaddr_tipc *addr)
  * @destlen: size of socket address data structure
  * @flags: file-related flags associated with socket
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  */
 static int tipc_connect(struct socket *sock, struct sockaddr *dest,
 			int destlen, int flags)
@@ -2625,7 +2651,7 @@ exit:
  * @sock: socket structure
  * @len: (unused)
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  */
 static int tipc_listen(struct socket *sock, int len)
 {
@@ -2677,8 +2703,9 @@ static int tipc_wait_for_accept(struct socket *sock, long timeo)
  * @sock: listening socket
  * @new_sock: new socket that is to be connected
  * @flags: file-related flags associated with socket
+ * @kern: caused by kernel or by userspace?
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  */
 static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
 		       bool kern)
@@ -2757,7 +2784,7 @@ exit:
  *
  * Terminates connection (if necessary), then purges socket's receive queue.
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  */
 static int tipc_shutdown(struct socket *sock, int how)
 {
@@ -2865,7 +2892,7 @@ static void tipc_sk_timeout(struct timer_list *t)
 }
 
 static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
-			   struct tipc_name_seq const *seq)
+			   struct tipc_service_range const *seq)
 {
 	struct sock *sk = &tsk->sk;
 	struct net *net = sock_net(sk);
@@ -2893,7 +2920,7 @@ static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
 }
 
 static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
-			    struct tipc_name_seq const *seq)
+			    struct tipc_service_range const *seq)
 {
 	struct net *net = sock_net(&tsk->sk);
 	struct publication *publ;
@@ -3040,7 +3067,7 @@ static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq)
 	struct net *net = sock_net(&tsk->sk);
 	struct tipc_group *grp = tsk->group;
 	struct tipc_msg *hdr = &tsk->phdr;
-	struct tipc_name_seq seq;
+	struct tipc_service_range seq;
 	int rc;
 
 	if (mreq->type < TIPC_RESERVED_TYPES)
@@ -3077,7 +3104,7 @@ static int tipc_sk_leave(struct tipc_sock *tsk)
 {
 	struct net *net = sock_net(&tsk->sk);
 	struct tipc_group *grp = tsk->group;
-	struct tipc_name_seq seq;
+	struct tipc_service_range seq;
 	int scope;
 
 	if (!grp)
@@ -3100,7 +3127,7 @@ static int tipc_sk_leave(struct tipc_sock *tsk)
  * For stream sockets only, accepts and ignores all IPPROTO_TCP options
  * (to ease compatibility).
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  */
 static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
 			   sockptr_t ov, unsigned int ol)
@@ -3194,14 +3221,14 @@ static int tipc_setsockopt(struct socket *sock, int lvl, int opt,
  * For stream sockets only, returns 0 length result for all IPPROTO_TCP options
  * (to ease compatibility).
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  */
 static int tipc_getsockopt(struct socket *sock, int lvl, int opt,
 			   char __user *ov, int __user *ol)
 {
 	struct sock *sk = sock->sk;
 	struct tipc_sock *tsk = tipc_sk(sk);
-	struct tipc_name_seq seq;
+	struct tipc_service_range seq;
 	int len, scope;
 	u32 value;
 	int res;
@@ -3302,12 +3329,12 @@ static int tipc_socketpair(struct socket *sock1, struct socket *sock2)
 	u32 onode = tipc_own_addr(sock_net(sock1->sk));
 
 	tsk1->peer.family = AF_TIPC;
-	tsk1->peer.addrtype = TIPC_ADDR_ID;
+	tsk1->peer.addrtype = TIPC_SOCKET_ADDR;
 	tsk1->peer.scope = TIPC_NODE_SCOPE;
 	tsk1->peer.addr.id.ref = tsk2->portid;
 	tsk1->peer.addr.id.node = onode;
 	tsk2->peer.family = AF_TIPC;
-	tsk2->peer.addrtype = TIPC_ADDR_ID;
+	tsk2->peer.addrtype = TIPC_SOCKET_ADDR;
 	tsk2->peer.scope = TIPC_NODE_SCOPE;
 	tsk2->peer.addr.id.ref = tsk1->portid;
 	tsk2->peer.addr.id.node = onode;
@@ -3398,7 +3425,7 @@ static struct proto tipc_proto = {
 /**
  * tipc_socket_init - initialize TIPC socket interface
  *
- * Returns 0 on success, errno otherwise
+ * Return: 0 on success, errno otherwise
  */
 int tipc_socket_init(void)
 {
@@ -3797,10 +3824,11 @@ int tipc_nl_publ_dump(struct sk_buff *skb, struct netlink_callback *cb)
 /**
  * tipc_sk_filtering - check if a socket should be traced
  * @sk: the socket to be examined
- * @sysctl_tipc_sk_filter[]: the socket tuple for filtering,
- *  (portid, sock type, name type, name lower, name upper)
  *
- * Returns true if the socket meets the socket tuple data
+ * @sysctl_tipc_sk_filter is used as the socket tuple for filtering:
+ * (portid, sock type, name type, name lower, name upper)
+ *
+ * Return: true if the socket meets the socket tuple data
  * (value 0 = 'any') or when there is no tuple set (all = 0),
  * otherwise false
  */
@@ -3865,7 +3893,7 @@ u32 tipc_sock_get_portid(struct sock *sk)
  * @sk: tipc sk to be checked
  * @skb: tipc msg to be checked
  *
- * Returns true if the socket rx queue allocation is > 90%, otherwise false
+ * Return: true if the socket rx queue allocation is > 90%, otherwise false
  */
 
 bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb)
@@ -3883,7 +3911,7 @@ bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb)
  * @sk: tipc sk to be checked
  * @skb: tipc msg to be checked
  *
- * Returns true if the socket rx queue allocation is > 90%, otherwise false
+ * Return: true if the socket rx queue allocation is > 90%, otherwise false
  */
 
 bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb)
diff --git a/net/tipc/socket.h b/net/tipc/socket.h
index b11575afc66f..02cdf166807d 100644
--- a/net/tipc/socket.h
+++ b/net/tipc/socket.h
@@ -74,7 +74,7 @@ int tipc_dump_done(struct netlink_callback *cb);
 u32 tipc_sock_get_portid(struct sock *sk);
 bool tipc_sk_overlimit1(struct sock *sk, struct sk_buff *skb);
 bool tipc_sk_overlimit2(struct sock *sk, struct sk_buff *skb);
-
+int tipc_sk_bind(struct socket *sock, struct sockaddr *skaddr, int alen);
 int tsk_set_importance(struct sock *sk, int imp);
 
 #endif
diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c
index f340e53da625..f6ad0005218c 100644
--- a/net/tipc/subscr.c
+++ b/net/tipc/subscr.c
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2000-2017, Ericsson AB
  * Copyright (c) 2005-2007, 2010-2013, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -55,12 +56,14 @@ static void tipc_sub_send_event(struct tipc_subscription *sub,
 }
 
 /**
- * tipc_sub_check_overlap - test for subscription overlap with the
- * given values
+ * tipc_sub_check_overlap - test for subscription overlap with the given values
+ * @seq: tipc_name_seq to check
+ * @found_lower: lower value to test
+ * @found_upper: upper value to test
  *
- * Returns 1 if there is overlap, otherwise 0.
+ * Return: 1 if there is overlap, otherwise 0.
  */
-int tipc_sub_check_overlap(struct tipc_name_seq *seq, u32 found_lower,
+int tipc_sub_check_overlap(struct tipc_service_range *seq, u32 found_lower,
 			   u32 found_upper)
 {
 	if (found_lower < seq->lower)
@@ -79,7 +82,7 @@ void tipc_sub_report_overlap(struct tipc_subscription *sub,
 {
 	struct tipc_subscr *s = &sub->evt.s;
 	u32 filter = tipc_sub_read(s, filter);
-	struct tipc_name_seq seq;
+	struct tipc_service_range seq;
 
 	seq.type = tipc_sub_read(s, seq.type);
 	seq.lower = tipc_sub_read(s, seq.lower);
diff --git a/net/tipc/subscr.h b/net/tipc/subscr.h
index 6ebbec1bedd1..3ded27391d54 100644
--- a/net/tipc/subscr.h
+++ b/net/tipc/subscr.h
@@ -3,6 +3,7 @@
  *
  * Copyright (c) 2003-2017, Ericsson AB
  * Copyright (c) 2005-2007, 2012-2013, Wind River Systems
+ * Copyright (c) 2020, Red Hat Inc
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -47,12 +48,15 @@ struct tipc_conn;
 
 /**
  * struct tipc_subscription - TIPC network topology subscription object
- * @subscriber: pointer to its subscriber
- * @seq: name sequence associated with subscription
+ * @kref: reference count for this subscription
+ * @net: network namespace associated with subscription
  * @timer: timer governing subscription duration (optional)
- * @nameseq_list: adjacent subscriptions in name sequence's subscription list
+ * @service_list: adjacent subscriptions in name sequence's subscription list
  * @sub_list: adjacent subscriptions in subscriber's subscription list
  * @evt: template for events generated by subscription
+ * @conid: connection identifier of topology server
+ * @inactive: true if this subscription is inactive
+ * @lock: serialize up/down and timer events
  */
 struct tipc_subscription {
 	struct kref kref;
@@ -63,7 +67,7 @@ struct tipc_subscription {
 	struct tipc_event evt;
 	int conid;
 	bool inactive;
-	spinlock_t lock; /* serialize up/down and timer events */
+	spinlock_t lock;
 };
 
 struct tipc_subscription *tipc_sub_subscribe(struct net *net,
@@ -71,8 +75,8 @@ struct tipc_subscription *tipc_sub_subscribe(struct net *net,
 					     int conid);
 void tipc_sub_unsubscribe(struct tipc_subscription *sub);
 
-int tipc_sub_check_overlap(struct tipc_name_seq *seq, u32 found_lower,
-			   u32 found_upper);
+int tipc_sub_check_overlap(struct tipc_service_range *seq,
+			   u32 found_lower, u32 found_upper);
 void tipc_sub_report_overlap(struct tipc_subscription *sub,
 			     u32 found_lower, u32 found_upper,
 			     u32 event, u32 port, u32 node,
diff --git a/net/tipc/sysctl.c b/net/tipc/sysctl.c
index 97a6264a2993..9fb65c988f7f 100644
--- a/net/tipc/sysctl.c
+++ b/net/tipc/sysctl.c
@@ -74,6 +74,15 @@ static struct ctl_table tipc_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1         = SYSCTL_ONE,
 	},
+	{
+		.procname	= "key_exchange_enabled",
+		.data		= &sysctl_tipc_key_exchange_enabled,
+		.maxlen		= sizeof(sysctl_tipc_key_exchange_enabled),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
 #endif
 	{
 		.procname	= "bc_retruni",
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 1489cfb941d8..5522865deae9 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -48,7 +48,6 @@
 #define MAX_SEND_MSG_COUNT	25
 #define MAX_RECV_MSG_COUNT	25
 #define CF_CONNECTED		1
-#define CF_SERVER		2
 
 #define TIPC_SERVER_NAME_LEN	32
 
@@ -520,13 +519,13 @@ static int tipc_topsrv_create_listener(struct tipc_topsrv *srv)
 		goto err;
 
 	saddr.family	                = AF_TIPC;
-	saddr.addrtype		        = TIPC_ADDR_NAMESEQ;
-	saddr.addr.nameseq.type	        = TIPC_TOP_SRV;
+	saddr.addrtype		        = TIPC_SERVICE_RANGE;
+	saddr.addr.nameseq.type	= TIPC_TOP_SRV;
 	saddr.addr.nameseq.lower	= TIPC_TOP_SRV;
 	saddr.addr.nameseq.upper	= TIPC_TOP_SRV;
 	saddr.scope			= TIPC_NODE_SCOPE;
 
-	rc = kernel_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr));
+	rc = tipc_sk_bind(lsock, (struct sockaddr *)&saddr, sizeof(saddr));
 	if (rc < 0)
 		goto err;
 	rc = kernel_listen(lsock, 0);
@@ -665,12 +664,18 @@ static int tipc_topsrv_start(struct net *net)
 
 	ret = tipc_topsrv_work_start(srv);
 	if (ret < 0)
-		return ret;
+		goto err_start;
 
 	ret = tipc_topsrv_create_listener(srv);
 	if (ret < 0)
-		tipc_topsrv_work_stop(srv);
+		goto err_create;
 
+	return 0;
+
+err_create:
+	tipc_topsrv_work_stop(srv);
+err_start:
+	kfree(srv);
 	return ret;
 }
 
diff --git a/net/tipc/trace.c b/net/tipc/trace.c
index 265f6a26aa3d..7d2931521e0e 100644
--- a/net/tipc/trace.c
+++ b/net/tipc/trace.c
@@ -36,7 +36,7 @@
 #define CREATE_TRACE_POINTS
 #include "trace.h"
 
-/**
+/*
  * socket tuples for filtering in socket traces:
  * (portid, sock type, name type, name lower, name upper)
  */
diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
index 911d13cd2e67..21e75e28e86a 100644
--- a/net/tipc/udp_media.c
+++ b/net/tipc/udp_media.c
@@ -52,6 +52,7 @@
 #include "bearer.h"
 #include "netlink.h"
 #include "msg.h"
+#include "udp_media.h"
 
 /* IANA assigned UDP port */
 #define UDP_PORT_DEFAULT	6118
@@ -63,6 +64,11 @@
  *
  * This is the bearer level originating address used in neighbor discovery
  * messages, and all fields should be in network byte order
+ *
+ * @proto: Ethernet protocol in use
+ * @port: port being used
+ * @ipv4: IPv4 address of neighbor
+ * @ipv6: IPv6 address of neighbor
  */
 struct udp_media_addr {
 	__be16	proto;
@@ -87,6 +93,7 @@ struct udp_replicast {
  * @ubsock:	bearer associated socket
  * @ifindex:	local address scope
  * @work:	used to schedule deferred work on a bearer
+ * @rcast:	associated udp_replicast container
  */
 struct udp_bearer {
 	struct tipc_bearer __rcu *bearer;
@@ -771,7 +778,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b,
 	if (err)
 		goto free;
 
-	/**
+	/*
 	 * The bcast media address port is used for all peers and the ip
 	 * is used if it's a multicast address.
 	 */
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index b74e2741f74f..f7fb7d2c1de1 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -327,7 +327,7 @@ static int tls_device_record_close(struct sock *sk,
 	/* fill prepend */
 	tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]),
 			 record->len - prot->overhead_size,
-			 record_type, prot->version);
+			 record_type);
 	return ret;
 }
 
@@ -418,14 +418,14 @@ static int tls_push_data(struct sock *sk,
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_prot_info *prot = &tls_ctx->prot_info;
 	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
-	int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE);
 	struct tls_record_info *record = ctx->open_record;
 	int tls_push_record_flags;
 	struct page_frag *pfrag;
 	size_t orig_size = size;
 	u32 max_open_record_len;
-	int copy, rc = 0;
+	bool more = false;
 	bool done = false;
+	int copy, rc = 0;
 	long timeo;
 
 	if (flags &
@@ -492,9 +492,8 @@ handle_error:
 		if (!size) {
 last_record:
 			tls_push_record_flags = flags;
-			if (more) {
-				tls_ctx->pending_open_record_frags =
-						!!record->num_frags;
+			if (flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE)) {
+				more = true;
 				break;
 			}
 
@@ -526,6 +525,8 @@ last_record:
 		}
 	} while (!done);
 
+	tls_ctx->pending_open_record_frags = more;
+
 	if (orig_size - size > 0)
 		rc = orig_size - size;
 
@@ -693,36 +694,51 @@ static void tls_device_resync_rx(struct tls_context *tls_ctx,
 
 static bool
 tls_device_rx_resync_async(struct tls_offload_resync_async *resync_async,
-			   s64 resync_req, u32 *seq)
+			   s64 resync_req, u32 *seq, u16 *rcd_delta)
 {
 	u32 is_async = resync_req & RESYNC_REQ_ASYNC;
 	u32 req_seq = resync_req >> 32;
 	u32 req_end = req_seq + ((resync_req >> 16) & 0xffff);
+	u16 i;
+
+	*rcd_delta = 0;
 
 	if (is_async) {
+		/* shouldn't get to wraparound:
+		 * too long in async stage, something bad happened
+		 */
+		if (WARN_ON_ONCE(resync_async->rcd_delta == USHRT_MAX))
+			return false;
+
 		/* asynchronous stage: log all headers seq such that
 		 * req_seq <= seq <= end_seq, and wait for real resync request
 		 */
-		if (between(*seq, req_seq, req_end) &&
+		if (before(*seq, req_seq))
+			return false;
+		if (!after(*seq, req_end) &&
 		    resync_async->loglen < TLS_DEVICE_RESYNC_ASYNC_LOGMAX)
 			resync_async->log[resync_async->loglen++] = *seq;
 
+		resync_async->rcd_delta++;
+
 		return false;
 	}
 
 	/* synchronous stage: check against the logged entries and
 	 * proceed to check the next entries if no match was found
 	 */
-	while (resync_async->loglen) {
-		if (req_seq == resync_async->log[resync_async->loglen - 1] &&
-		    atomic64_try_cmpxchg(&resync_async->req,
-					 &resync_req, 0)) {
-			resync_async->loglen = 0;
+	for (i = 0; i < resync_async->loglen; i++)
+		if (req_seq == resync_async->log[i] &&
+		    atomic64_try_cmpxchg(&resync_async->req, &resync_req, 0)) {
+			*rcd_delta = resync_async->rcd_delta - i;
 			*seq = req_seq;
+			resync_async->loglen = 0;
+			resync_async->rcd_delta = 0;
 			return true;
 		}
-		resync_async->loglen--;
-	}
+
+	resync_async->loglen = 0;
+	resync_async->rcd_delta = 0;
 
 	if (req_seq == *seq &&
 	    atomic64_try_cmpxchg(&resync_async->req,
@@ -740,6 +756,7 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq)
 	u32 sock_data, is_req_pending;
 	struct tls_prot_info *prot;
 	s64 resync_req;
+	u16 rcd_delta;
 	u32 req_seq;
 
 	if (tls_ctx->rx_conf != TLS_HW)
@@ -785,8 +802,9 @@ void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq)
 			return;
 
 		if (!tls_device_rx_resync_async(rx_ctx->resync_async,
-						resync_req, &seq))
+						resync_req, &seq, &rcd_delta))
 			return;
+		tls_bigint_subtract(rcd_sn, rcd_delta);
 		break;
 	}
 
@@ -980,7 +998,7 @@ static void tls_device_attach(struct tls_context *ctx, struct sock *sk,
 
 int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 {
-	u16 nonce_size, tag_size, iv_size, rec_seq_size;
+	u16 nonce_size, tag_size, iv_size, rec_seq_size, salt_size;
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_prot_info *prot = &tls_ctx->prot_info;
 	struct tls_record_info *start_marker_record;
@@ -1021,6 +1039,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 		iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
 		iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv;
 		rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE;
+		salt_size = TLS_CIPHER_AES_GCM_128_SALT_SIZE;
 		rec_seq =
 		 ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq;
 		break;
@@ -1041,6 +1060,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	prot->tag_size = tag_size;
 	prot->overhead_size = prot->prepend_size + prot->tag_size;
 	prot->iv_size = iv_size;
+	prot->salt_size = salt_size;
 	ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
 			     GFP_KERNEL);
 	if (!ctx->tx.iv) {
@@ -1244,6 +1264,8 @@ void tls_device_offload_cleanup_rx(struct sock *sk)
 	if (tls_ctx->tx_conf != TLS_HW) {
 		dev_put(netdev);
 		tls_ctx->netdev = NULL;
+	} else {
+		set_bit(TLS_RX_DEV_CLOSED, &tls_ctx->flags);
 	}
 out:
 	up_read(&device_offload_lock);
@@ -1273,7 +1295,8 @@ static int tls_device_down(struct net_device *netdev)
 		if (ctx->tx_conf == TLS_HW)
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_TX);
-		if (ctx->rx_conf == TLS_HW)
+		if (ctx->rx_conf == TLS_HW &&
+		    !test_bit(TLS_RX_DEV_CLOSED, &ctx->flags))
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_RX);
 		WRITE_ONCE(ctx->netdev, NULL);
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 28895333701e..d946817ed065 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -49,7 +49,8 @@ static int tls_enc_record(struct aead_request *aead_req,
 			  struct crypto_aead *aead, char *aad,
 			  char *iv, __be64 rcd_sn,
 			  struct scatter_walk *in,
-			  struct scatter_walk *out, int *in_len)
+			  struct scatter_walk *out, int *in_len,
+			  struct tls_prot_info *prot)
 {
 	unsigned char buf[TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE];
 	struct scatterlist sg_in[3];
@@ -73,8 +74,7 @@ static int tls_enc_record(struct aead_request *aead_req,
 	len -= TLS_CIPHER_AES_GCM_128_IV_SIZE;
 
 	tls_make_aad(aad, len - TLS_CIPHER_AES_GCM_128_TAG_SIZE,
-		(char *)&rcd_sn, sizeof(rcd_sn), buf[0],
-		TLS_1_2_VERSION);
+		(char *)&rcd_sn, buf[0], prot);
 
 	memcpy(iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, buf + TLS_HEADER_SIZE,
 	       TLS_CIPHER_AES_GCM_128_IV_SIZE);
@@ -140,7 +140,7 @@ static struct aead_request *tls_alloc_aead_request(struct crypto_aead *aead,
 static int tls_enc_records(struct aead_request *aead_req,
 			   struct crypto_aead *aead, struct scatterlist *sg_in,
 			   struct scatterlist *sg_out, char *aad, char *iv,
-			   u64 rcd_sn, int len)
+			   u64 rcd_sn, int len, struct tls_prot_info *prot)
 {
 	struct scatter_walk out, in;
 	int rc;
@@ -150,7 +150,7 @@ static int tls_enc_records(struct aead_request *aead_req,
 
 	do {
 		rc = tls_enc_record(aead_req, aead, aad, iv,
-				    cpu_to_be64(rcd_sn), &in, &out, &len);
+				    cpu_to_be64(rcd_sn), &in, &out, &len, prot);
 		rcd_sn++;
 
 	} while (rc == 0 && len);
@@ -348,7 +348,8 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
 		    payload_len, sync_size, dummy_buf);
 
 	if (tls_enc_records(aead_req, ctx->aead_send, sg_in, sg_out, aad, iv,
-			    rcd_sn, sync_size + payload_len) < 0)
+			    rcd_sn, sync_size + payload_len,
+			    &tls_ctx->prot_info) < 0)
 		goto free_nskb;
 
 	complete_skb(nskb, skb, tcp_payload_offset);
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index bbc52b088d29..47b7c5334c34 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -330,12 +330,13 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 		tls_ctx_free(sk, ctx);
 }
 
-static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
-				int __user *optlen)
+static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval,
+				  int __user *optlen, int tx)
 {
 	int rc = 0;
 	struct tls_context *ctx = tls_get_ctx(sk);
 	struct tls_crypto_info *crypto_info;
+	struct cipher_context *cctx;
 	int len;
 
 	if (get_user(len, optlen))
@@ -352,7 +353,13 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
 	}
 
 	/* get user crypto info */
-	crypto_info = &ctx->crypto_send.info;
+	if (tx) {
+		crypto_info = &ctx->crypto_send.info;
+		cctx = &ctx->tx;
+	} else {
+		crypto_info = &ctx->crypto_recv.info;
+		cctx = &ctx->rx;
+	}
 
 	if (!TLS_CRYPTO_INFO_READY(crypto_info)) {
 		rc = -EBUSY;
@@ -379,9 +386,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
 		}
 		lock_sock(sk);
 		memcpy(crypto_info_aes_gcm_128->iv,
-		       ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+		       cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
 		       TLS_CIPHER_AES_GCM_128_IV_SIZE);
-		memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->tx.rec_seq,
+		memcpy(crypto_info_aes_gcm_128->rec_seq, cctx->rec_seq,
 		       TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE);
 		release_sock(sk);
 		if (copy_to_user(optval,
@@ -403,9 +410,9 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval,
 		}
 		lock_sock(sk);
 		memcpy(crypto_info_aes_gcm_256->iv,
-		       ctx->tx.iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE,
+		       cctx->iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE,
 		       TLS_CIPHER_AES_GCM_256_IV_SIZE);
-		memcpy(crypto_info_aes_gcm_256->rec_seq, ctx->tx.rec_seq,
+		memcpy(crypto_info_aes_gcm_256->rec_seq, cctx->rec_seq,
 		       TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE);
 		release_sock(sk);
 		if (copy_to_user(optval,
@@ -429,7 +436,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname,
 
 	switch (optname) {
 	case TLS_TX:
-		rc = do_tls_getsockopt_tx(sk, optval, optlen);
+	case TLS_RX:
+		rc = do_tls_getsockopt_conf(sk, optval, optlen,
+					    optname == TLS_TX);
 		break;
 	default:
 		rc = -ENOPROTOOPT;
@@ -512,6 +521,9 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval,
 	case TLS_CIPHER_AES_CCM_128:
 		optsize = sizeof(struct tls12_crypto_info_aes_ccm_128);
 		break;
+	case TLS_CIPHER_CHACHA20_POLY1305:
+		optsize = sizeof(struct tls12_crypto_info_chacha20_poly1305);
+		break;
 	default:
 		rc = -EINVAL;
 		goto err_crypto_info;
@@ -860,7 +872,7 @@ static int __init tls_register(void)
 
 	tls_sw_proto_ops = inet_stream_ops;
 	tls_sw_proto_ops.splice_read = tls_sw_splice_read;
-	tls_sw_proto_ops.sendpage_locked   = tls_sw_sendpage_locked,
+	tls_sw_proto_ops.sendpage_locked   = tls_sw_sendpage_locked;
 
 	tls_device_init();
 	tcp_register_ulp(&tcp_tls_ulp_ops);
diff --git a/net/tls/tls_proc.c b/net/tls/tls_proc.c
index 3a5dd1e07233..feeceb0e4cb4 100644
--- a/net/tls/tls_proc.c
+++ b/net/tls/tls_proc.c
@@ -37,9 +37,12 @@ static int tls_statistics_seq_show(struct seq_file *seq, void *v)
 
 int __net_init tls_proc_init(struct net *net)
 {
+#ifdef CONFIG_PROC_FS
 	if (!proc_create_net_single("tls_stat", 0444, net->proc_net,
 				    tls_statistics_seq_show, NULL))
 		return -ENOMEM;
+#endif /* CONFIG_PROC_FS */
+
 	return 0;
 }
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 95ab5545a931..01d933ae5f16 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -505,7 +505,7 @@ static int tls_do_encryption(struct sock *sk,
 	memcpy(&rec->iv_data[iv_offset], tls_ctx->tx.iv,
 	       prot->iv_size + prot->salt_size);
 
-	xor_iv_with_seq(prot->version, rec->iv_data, tls_ctx->tx.rec_seq);
+	xor_iv_with_seq(prot, rec->iv_data, tls_ctx->tx.rec_seq);
 
 	sge->offset += prot->prepend_size;
 	sge->length -= prot->prepend_size;
@@ -748,14 +748,13 @@ static int tls_push_record(struct sock *sk, int flags,
 	sg_chain(rec->sg_aead_out, 2, &msg_en->sg.data[i]);
 
 	tls_make_aad(rec->aad_space, msg_pl->sg.size + prot->tail_size,
-		     tls_ctx->tx.rec_seq, prot->rec_seq_size,
-		     record_type, prot->version);
+		     tls_ctx->tx.rec_seq, record_type, prot);
 
 	tls_fill_prepend(tls_ctx,
 			 page_address(sg_page(&msg_en->sg.data[i])) +
 			 msg_en->sg.data[i].offset,
 			 msg_pl->sg.size + prot->tail_size,
-			 record_type, prot->version);
+			 record_type);
 
 	tls_ctx->pending_open_record_frags = false;
 
@@ -1295,6 +1294,12 @@ static struct sk_buff *tls_wait_data(struct sock *sk, struct sk_psock *psock,
 			return NULL;
 		}
 
+		if (!skb_queue_empty(&sk->sk_receive_queue)) {
+			__strp_unpause(&ctx->strp);
+			if (ctx->recv_pkt)
+				return ctx->recv_pkt;
+		}
+
 		if (sk->sk_shutdown & RCV_SHUTDOWN)
 			return NULL;
 
@@ -1465,19 +1470,19 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
 		kfree(mem);
 		return err;
 	}
-	if (prot->version == TLS_1_3_VERSION)
+	if (prot->version == TLS_1_3_VERSION ||
+	    prot->cipher_type == TLS_CIPHER_CHACHA20_POLY1305)
 		memcpy(iv + iv_offset, tls_ctx->rx.iv,
 		       crypto_aead_ivsize(ctx->aead_recv));
 	else
 		memcpy(iv + iv_offset, tls_ctx->rx.iv, prot->salt_size);
 
-	xor_iv_with_seq(prot->version, iv, tls_ctx->rx.rec_seq);
+	xor_iv_with_seq(prot, iv, tls_ctx->rx.rec_seq);
 
 	/* Prepare AAD */
 	tls_make_aad(aad, rxm->full_len - prot->overhead_size +
 		     prot->tail_size,
-		     tls_ctx->rx.rec_seq, prot->rec_seq_size,
-		     ctx->control, prot->version);
+		     tls_ctx->rx.rec_seq, ctx->control, prot);
 
 	/* Prepare sgin */
 	sg_init_table(sgin, n_sgin);
@@ -1913,7 +1918,7 @@ pick_next_record:
 			 * another message type
 			 */
 			msg->msg_flags |= MSG_EOR;
-			if (ctx->control != TLS_RECORD_TYPE_DATA)
+			if (control != TLS_RECORD_TYPE_DATA)
 				goto recv_end;
 		} else {
 			break;
@@ -2070,7 +2075,8 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
 	data_len = ((header[4] & 0xFF) | (header[3] << 8));
 
 	cipher_overhead = prot->tag_size;
-	if (prot->version != TLS_1_3_VERSION)
+	if (prot->version != TLS_1_3_VERSION &&
+	    prot->cipher_type != TLS_CIPHER_CHACHA20_POLY1305)
 		cipher_overhead += prot->iv_size;
 
 	if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead +
@@ -2290,6 +2296,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	struct tls12_crypto_info_aes_gcm_128 *gcm_128_info;
 	struct tls12_crypto_info_aes_gcm_256 *gcm_256_info;
 	struct tls12_crypto_info_aes_ccm_128 *ccm_128_info;
+	struct tls12_crypto_info_chacha20_poly1305 *chacha20_poly1305_info;
 	struct tls_sw_context_tx *sw_ctx_tx = NULL;
 	struct tls_sw_context_rx *sw_ctx_rx = NULL;
 	struct cipher_context *cctx;
@@ -2402,6 +2409,21 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 		cipher_name = "ccm(aes)";
 		break;
 	}
+	case TLS_CIPHER_CHACHA20_POLY1305: {
+		chacha20_poly1305_info = (void *)crypto_info;
+		nonce_size = 0;
+		tag_size = TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE;
+		iv_size = TLS_CIPHER_CHACHA20_POLY1305_IV_SIZE;
+		iv = chacha20_poly1305_info->iv;
+		rec_seq_size = TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE;
+		rec_seq = chacha20_poly1305_info->rec_seq;
+		keysize = TLS_CIPHER_CHACHA20_POLY1305_KEY_SIZE;
+		key = chacha20_poly1305_info->key;
+		salt = chacha20_poly1305_info->salt;
+		salt_size = TLS_CIPHER_CHACHA20_POLY1305_SALT_SIZE;
+		cipher_name = "rfc7539(chacha20,poly1305)";
+		break;
+	}
 	default:
 		rc = -EINVAL;
 		goto free_priv;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 92784e51ee7d..41c3303c3357 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -613,7 +613,6 @@ static int unix_listen(struct socket *sock, int backlog)
 	int err;
 	struct sock *sk = sock->sk;
 	struct unix_sock *u = unix_sk(sk);
-	struct pid *old_pid = NULL;
 
 	err = -EOPNOTSUPP;
 	if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
@@ -634,7 +633,6 @@ static int unix_listen(struct socket *sock, int backlog)
 
 out_unlock:
 	unix_state_unlock(sk);
-	put_pid(old_pid);
 out:
 	return err;
 }
@@ -878,7 +876,6 @@ static int unix_autobind(struct socket *sock)
 	if (err)
 		return err;
 
-	err = 0;
 	if (u->addr)
 		goto out;
 
diff --git a/net/unix/scm.c b/net/unix/scm.c
index 8c40f2b32392..052ae709ce28 100644
--- a/net/unix/scm.c
+++ b/net/unix/scm.c
@@ -8,6 +8,7 @@
 #include <net/af_unix.h>
 #include <net/scm.h>
 #include <linux/init.h>
+#include <linux/io_uring.h>
 
 #include "scm.h"
 
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 9e93bc201cc0..5546710d8ac1 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -421,7 +421,8 @@ static void vsock_deassign_transport(struct vsock_sock *vsk)
  * The vsk->remote_addr is used to decide which transport to use:
  *  - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if
  *    g2h is not loaded, will use local transport;
- *  - remote CID <= VMADDR_CID_HOST will use guest->host transport;
+ *  - remote CID <= VMADDR_CID_HOST or h2g is not loaded or remote flags field
+ *    includes VMADDR_FLAG_TO_HOST flag value, will use guest->host transport;
  *  - remote CID > VMADDR_CID_HOST will use host->guest transport;
  */
 int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
@@ -429,8 +430,23 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 	const struct vsock_transport *new_transport;
 	struct sock *sk = sk_vsock(vsk);
 	unsigned int remote_cid = vsk->remote_addr.svm_cid;
+	__u8 remote_flags;
 	int ret;
 
+	/* If the packet is coming with the source and destination CIDs higher
+	 * than VMADDR_CID_HOST, then a vsock channel where all the packets are
+	 * forwarded to the host should be established. Then the host will
+	 * need to forward the packets to the guest.
+	 *
+	 * The flag is set on the (listen) receive path (psk is not NULL). On
+	 * the connect path the flag can be set by the user space application.
+	 */
+	if (psk && vsk->local_addr.svm_cid > VMADDR_CID_HOST &&
+	    vsk->remote_addr.svm_cid > VMADDR_CID_HOST)
+		vsk->remote_addr.svm_flags |= VMADDR_FLAG_TO_HOST;
+
+	remote_flags = vsk->remote_addr.svm_flags;
+
 	switch (sk->sk_type) {
 	case SOCK_DGRAM:
 		new_transport = transport_dgram;
@@ -438,7 +454,8 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 	case SOCK_STREAM:
 		if (vsock_use_local_transport(remote_cid))
 			new_transport = transport_local;
-		else if (remote_cid <= VMADDR_CID_HOST)
+		else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g ||
+			 (remote_flags & VMADDR_FLAG_TO_HOST))
 			new_transport = transport_g2h;
 		else
 			new_transport = transport_h2g;
@@ -739,7 +756,7 @@ static struct sock *__vsock_create(struct net *net,
 		vsk->buffer_min_size = psk->buffer_min_size;
 		vsk->buffer_max_size = psk->buffer_max_size;
 	} else {
-		vsk->trusted = capable(CAP_NET_ADMIN);
+		vsk->trusted = ns_capable_noaudit(&init_user_ns, CAP_NET_ADMIN);
 		vsk->owner = get_current_cred();
 		vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT;
 		vsk->buffer_size = VSOCK_DEFAULT_BUFFER_SIZE;
@@ -926,10 +943,12 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	 */
 
 	sk = sock->sk;
+
+	lock_sock(sk);
 	if (sock->state == SS_UNCONNECTED) {
 		err = -ENOTCONN;
 		if (sk->sk_type == SOCK_STREAM)
-			return err;
+			goto out;
 	} else {
 		sock->state = SS_DISCONNECTING;
 		err = 0;
@@ -938,10 +957,8 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	/* Receive and send shutdowns are treated alike. */
 	mode = mode & (RCV_SHUTDOWN | SEND_SHUTDOWN);
 	if (mode) {
-		lock_sock(sk);
 		sk->sk_shutdown |= mode;
 		sk->sk_state_change(sk);
-		release_sock(sk);
 
 		if (sk->sk_type == SOCK_STREAM) {
 			sock_reset_flag(sk, SOCK_DONE);
@@ -949,6 +966,8 @@ static int vsock_shutdown(struct socket *sock, int mode)
 		}
 	}
 
+out:
+	release_sock(sk);
 	return err;
 }
 
@@ -997,9 +1016,12 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock,
 			mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
 
 	} else if (sock->type == SOCK_STREAM) {
-		const struct vsock_transport *transport = vsk->transport;
+		const struct vsock_transport *transport;
+
 		lock_sock(sk);
 
+		transport = vsk->transport;
+
 		/* Listening sockets that have connections in their accept
 		 * queue can be read.
 		 */
@@ -1082,10 +1104,11 @@ static int vsock_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	err = 0;
 	sk = sock->sk;
 	vsk = vsock_sk(sk);
-	transport = vsk->transport;
 
 	lock_sock(sk);
 
+	transport = vsk->transport;
+
 	err = vsock_auto_bind(vsk);
 	if (err)
 		goto out;
@@ -1212,7 +1235,7 @@ static int vsock_transport_cancel_pkt(struct vsock_sock *vsk)
 {
 	const struct vsock_transport *transport = vsk->transport;
 
-	if (!transport->cancel_pkt)
+	if (!transport || !transport->cancel_pkt)
 		return -EOPNOTSUPP;
 
 	return transport->cancel_pkt(vsk);
@@ -1222,7 +1245,6 @@ static void vsock_connect_timeout(struct work_struct *work)
 {
 	struct sock *sk;
 	struct vsock_sock *vsk;
-	int cancel = 0;
 
 	vsk = container_of(work, struct vsock_sock, connect_work.work);
 	sk = sk_vsock(vsk);
@@ -1233,11 +1255,9 @@ static void vsock_connect_timeout(struct work_struct *work)
 		sk->sk_state = TCP_CLOSE;
 		sk->sk_err = ETIMEDOUT;
 		sk->sk_error_report(sk);
-		cancel = 1;
+		vsock_transport_cancel_pkt(vsk);
 	}
 	release_sock(sk);
-	if (cancel)
-		vsock_transport_cancel_pkt(vsk);
 
 	sock_put(sk);
 }
@@ -1544,10 +1564,11 @@ static int vsock_stream_setsockopt(struct socket *sock,
 	err = 0;
 	sk = sock->sk;
 	vsk = vsock_sk(sk);
-	transport = vsk->transport;
 
 	lock_sock(sk);
 
+	transport = vsk->transport;
+
 	switch (optname) {
 	case SO_VM_SOCKETS_BUFFER_SIZE:
 		COPY_IN(val);
@@ -1680,7 +1701,6 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	sk = sock->sk;
 	vsk = vsock_sk(sk);
-	transport = vsk->transport;
 	total_written = 0;
 	err = 0;
 
@@ -1689,6 +1709,8 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	lock_sock(sk);
 
+	transport = vsk->transport;
+
 	/* Callers should not provide a destination with stream sockets. */
 	if (msg->msg_namelen) {
 		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
@@ -1823,11 +1845,12 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 	sk = sock->sk;
 	vsk = vsock_sk(sk);
-	transport = vsk->transport;
 	err = 0;
 
 	lock_sock(sk);
 
+	transport = vsk->transport;
+
 	if (!transport || sk->sk_state != TCP_ESTABLISHED) {
 		/* Recvmsg is supposed to return 0 if a peer performs an
 		 * orderly shutdown. Differentiate between that case and when a
@@ -2072,8 +2095,7 @@ static long vsock_dev_do_ioctl(struct file *filp,
 		break;
 
 	default:
-		pr_err("Unknown ioctl %d\n", cmd);
-		retval = -EINVAL;
+		retval = -ENOIOCTLCMD;
 	}
 
 	return retval;
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 630b851f8150..cc3bae2659e7 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -474,14 +474,10 @@ static void hvs_shutdown_lock_held(struct hvsock *hvs, int mode)
 
 static int hvs_shutdown(struct vsock_sock *vsk, int mode)
 {
-	struct sock *sk = sk_vsock(vsk);
-
 	if (!(mode & SEND_SHUTDOWN))
 		return 0;
 
-	lock_sock(sk);
 	hvs_shutdown_lock_held(vsk->trans, mode);
-	release_sock(sk);
 	return 0;
 }
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 0edda1edf988..e4370b1b7494 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -841,8 +841,10 @@ void virtio_transport_release(struct vsock_sock *vsk)
 		virtio_transport_free_pkt(pkt);
 	}
 
-	if (remove_sock)
+	if (remove_sock) {
+		sock_set_flag(sk, SOCK_DONE);
 		vsock_remove_sock(vsk);
+	}
 }
 EXPORT_SYMBOL_GPL(virtio_transport_release);
 
@@ -1128,18 +1130,18 @@ void virtio_transport_recv_pkt(struct virtio_transport *t,
 
 	vsk = vsock_sk(sk);
 
-	space_available = virtio_transport_space_update(sk, pkt);
-
 	lock_sock(sk);
 
-	/* Check if sk has been released before lock_sock */
-	if (sk->sk_shutdown == SHUTDOWN_MASK) {
+	/* Check if sk has been closed before lock_sock */
+	if (sock_flag(sk, SOCK_DONE)) {
 		(void)virtio_transport_reset_no_sock(t, pkt);
 		release_sock(sk);
 		sock_put(sk);
 		goto free_pkt;
 	}
 
+	space_available = virtio_transport_space_update(sk, pkt);
+
 	/* Update CID in case it has changed after a transport reset event */
 	vsk->local_addr.svm_cid = dst.svm_cid;
 
diff --git a/net/vmw_vsock/vsock_addr.c b/net/vmw_vsock/vsock_addr.c
index 909de26cb0e7..223b9660a759 100644
--- a/net/vmw_vsock/vsock_addr.c
+++ b/net/vmw_vsock/vsock_addr.c
@@ -22,13 +22,15 @@ EXPORT_SYMBOL_GPL(vsock_addr_init);
 
 int vsock_addr_validate(const struct sockaddr_vm *addr)
 {
+	__u8 svm_valid_flags = VMADDR_FLAG_TO_HOST;
+
 	if (!addr)
 		return -EFAULT;
 
 	if (addr->svm_family != AF_VSOCK)
 		return -EAFNOSUPPORT;
 
-	if (addr->svm_zero[0] != 0)
+	if (addr->svm_flags & ~svm_valid_flags)
 		return -EINVAL;
 
 	return 0;
diff --git a/net/wimax/Kconfig b/net/wimax/Kconfig
deleted file mode 100644
index d13762bc4abc..000000000000
--- a/net/wimax/Kconfig
+++ /dev/null
@@ -1,40 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-#
-# WiMAX LAN device configuration
-#
-
-menuconfig WIMAX
-	tristate "WiMAX Wireless Broadband support"
-	depends on RFKILL || !RFKILL
-	help
-
-	  Select to configure support for devices that provide
-	  wireless broadband connectivity using the WiMAX protocol
-	  (IEEE 802.16).
-
-	  Please note that most of these devices require signing up
-	  for a service plan with a provider.
-
-	  The different WiMAX drivers can be enabled in the menu entry
-
-	  Device Drivers > Network device support > WiMAX Wireless
-	  Broadband devices
-
-	  If unsure, it is safe to select M (module).
-
-config WIMAX_DEBUG_LEVEL
-	int "WiMAX debug level"
-	depends on WIMAX
-	default 8
-	help
-
-	  Select the maximum debug verbosity level to be compiled into
-	  the WiMAX stack code.
-
-	  By default, debug messages are disabled at runtime and can
-	  be selectively enabled for different parts of the code using
-	  the sysfs debug-levels file.
-
-	  If set at zero, this will compile out all the debug code.
-
-	  It is recommended that it is left at 8.
diff --git a/net/wimax/Makefile b/net/wimax/Makefile
deleted file mode 100644
index c2a71ae487ac..000000000000
--- a/net/wimax/Makefile
+++ /dev/null
@@ -1,13 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-obj-$(CONFIG_WIMAX)		+= wimax.o
-
-wimax-y :=		\
-	id-table.o	\
-	op-msg.o	\
-	op-reset.o	\
-	op-rfkill.o	\
-	op-state-get.o	\
-	stack.o
-
-wimax-$(CONFIG_DEBUG_FS) += debugfs.o
diff --git a/net/wimax/debug-levels.h b/net/wimax/debug-levels.h
deleted file mode 100644
index ebc287cde336..000000000000
--- a/net/wimax/debug-levels.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX Stack
- * Debug levels control file for the wimax module
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#ifndef __debug_levels__h__
-#define __debug_levels__h__
-
-/* Maximum compile and run time debug level for all submodules */
-#define D_MODULENAME wimax
-#define D_MASTER CONFIG_WIMAX_DEBUG_LEVEL
-
-#include <linux/wimax/debug.h>
-
-/* List of all the enabled modules */
-enum d_module {
-	D_SUBMODULE_DECLARE(debugfs),
-	D_SUBMODULE_DECLARE(id_table),
-	D_SUBMODULE_DECLARE(op_msg),
-	D_SUBMODULE_DECLARE(op_reset),
-	D_SUBMODULE_DECLARE(op_rfkill),
-	D_SUBMODULE_DECLARE(op_state_get),
-	D_SUBMODULE_DECLARE(stack),
-};
-
-#endif /* #ifndef __debug_levels__h__ */
diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c
deleted file mode 100644
index 3c54bb6b925a..000000000000
--- a/net/wimax/debugfs.c
+++ /dev/null
@@ -1,38 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Debugfs support
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-#include <linux/debugfs.h>
-#include <linux/wimax.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE debugfs
-#include "debug-levels.h"
-
-void wimax_debugfs_add(struct wimax_dev *wimax_dev)
-{
-	struct net_device *net_dev = wimax_dev->net_dev;
-	struct dentry *dentry;
-	char buf[128];
-
-	snprintf(buf, sizeof(buf), "wimax:%s", net_dev->name);
-	dentry = debugfs_create_dir(buf, NULL);
-	wimax_dev->debugfs_dentry = dentry;
-
-	d_level_register_debugfs("wimax_dl_", debugfs, dentry);
-	d_level_register_debugfs("wimax_dl_", id_table, dentry);
-	d_level_register_debugfs("wimax_dl_", op_msg, dentry);
-	d_level_register_debugfs("wimax_dl_", op_reset, dentry);
-	d_level_register_debugfs("wimax_dl_", op_rfkill, dentry);
-	d_level_register_debugfs("wimax_dl_", op_state_get, dentry);
-	d_level_register_debugfs("wimax_dl_", stack, dentry);
-}
-
-void wimax_debugfs_rm(struct wimax_dev *wimax_dev)
-{
-	debugfs_remove_recursive(wimax_dev->debugfs_dentry);
-}
diff --git a/net/wimax/id-table.c b/net/wimax/id-table.c
deleted file mode 100644
index 02eee37b7e31..000000000000
--- a/net/wimax/id-table.c
+++ /dev/null
@@ -1,130 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Mappping of generic netlink family IDs to net devices
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * We assign a single generic netlink family ID to each device (to
- * simplify lookup).
- *
- * We need a way to map family ID to a wimax_dev pointer.
- *
- * The idea is to use a very simple lookup. Using a netlink attribute
- * with (for example) the interface name implies a heavier search over
- * all the network devices; seemed kind of a waste given that we know
- * we are looking for a WiMAX device and that most systems will have
- * just a single WiMAX adapter.
- *
- * We put all the WiMAX devices in the system in a linked list and
- * match the generic link family ID against the list.
- *
- * By using a linked list, the case of a single adapter in the system
- * becomes (almost) no overhead, while still working for many more. If
- * it ever goes beyond two, I'll be surprised.
- */
-#include <linux/device.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/list.h>
-#include <linux/wimax.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE id_table
-#include "debug-levels.h"
-
-
-static DEFINE_SPINLOCK(wimax_id_table_lock);
-static struct list_head wimax_id_table = LIST_HEAD_INIT(wimax_id_table);
-
-
-/*
- * wimax_id_table_add - add a gennetlink familiy ID / wimax_dev mapping
- *
- * @wimax_dev: WiMAX device descriptor to associate to the Generic
- *     Netlink family ID.
- *
- * Look for an empty spot in the ID table; if none found, double the
- * table's size and get the first spot.
- */
-void wimax_id_table_add(struct wimax_dev *wimax_dev)
-{
-	d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-	spin_lock(&wimax_id_table_lock);
-	list_add(&wimax_dev->id_table_node, &wimax_id_table);
-	spin_unlock(&wimax_id_table_lock);
-	d_fnend(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-}
-
-
-/*
- * wimax_get_netdev_by_info - lookup a wimax_dev from the gennetlink info
- *
- * The generic netlink family ID has been filled out in the
- * nlmsghdr->nlmsg_type field, so we pull it from there, look it up in
- * the mapping table and reference the wimax_dev.
- *
- * When done, the reference should be dropped with
- * 'dev_put(wimax_dev->net_dev)'.
- */
-struct wimax_dev *wimax_dev_get_by_genl_info(
-	struct genl_info *info, int ifindex)
-{
-	struct wimax_dev *wimax_dev = NULL;
-
-	d_fnstart(3, NULL, "(info %p ifindex %d)\n", info, ifindex);
-	spin_lock(&wimax_id_table_lock);
-	list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
-		if (wimax_dev->net_dev->ifindex == ifindex) {
-			dev_hold(wimax_dev->net_dev);
-			goto found;
-		}
-	}
-	wimax_dev = NULL;
-	d_printf(1, NULL, "wimax: no devices found with ifindex %d\n",
-		 ifindex);
-found:
-	spin_unlock(&wimax_id_table_lock);
-	d_fnend(3, NULL, "(info %p ifindex %d) = %p\n",
-		info, ifindex, wimax_dev);
-	return wimax_dev;
-}
-
-
-/*
- * wimax_id_table_rm - Remove a gennetlink familiy ID / wimax_dev mapping
- *
- * @id: family ID to remove from the table
- */
-void wimax_id_table_rm(struct wimax_dev *wimax_dev)
-{
-	spin_lock(&wimax_id_table_lock);
-	list_del_init(&wimax_dev->id_table_node);
-	spin_unlock(&wimax_id_table_lock);
-}
-
-
-/*
- * Release the gennetlink family id / mapping table
- *
- * On debug, verify that the table is empty upon removal. We want the
- * code always compiled, to ensure it doesn't bit rot. It will be
- * compiled out if CONFIG_BUG is disabled.
- */
-void wimax_id_table_release(void)
-{
-	struct wimax_dev *wimax_dev;
-
-#ifndef CONFIG_BUG
-	return;
-#endif
-	spin_lock(&wimax_id_table_lock);
-	list_for_each_entry(wimax_dev, &wimax_id_table, id_table_node) {
-		pr_err("BUG: %s wimax_dev %p ifindex %d not cleared\n",
-		       __func__, wimax_dev, wimax_dev->net_dev->ifindex);
-		WARN_ON(1);
-	}
-	spin_unlock(&wimax_id_table_lock);
-}
diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c
deleted file mode 100644
index 6460b5785758..000000000000
--- a/net/wimax/op-msg.c
+++ /dev/null
@@ -1,391 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Generic messaging interface between userspace and driver/device
- *
- * Copyright (C) 2007-2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements a direct communication channel between user space and
- * the driver/device, by which free form messages can be sent back and
- * forth.
- *
- * This is intended for device-specific features, vendor quirks, etc.
- *
- * See include/net/wimax.h
- *
- * GENERIC NETLINK ENCODING AND CAPACITY
- *
- * A destination "pipe name" is added to each message; it is up to the
- * drivers to assign or use those names (if using them at all).
- *
- * Messages are encoded as a binary netlink attribute using nla_put()
- * using type NLA_UNSPEC (as some versions of libnl still in
- * deployment don't yet understand NLA_BINARY).
- *
- * The maximum capacity of this transport is PAGESIZE per message (so
- * the actual payload will be bit smaller depending on the
- * netlink/generic netlink attributes and headers).
- *
- * RECEPTION OF MESSAGES
- *
- * When a message is received from user space, it is passed verbatim
- * to the driver calling wimax_dev->op_msg_from_user(). The return
- * value from this function is passed back to user space as an ack
- * over the generic netlink protocol.
- *
- * The stack doesn't do any processing or interpretation of these
- * messages.
- *
- * SENDING MESSAGES
- *
- * Messages can be sent with wimax_msg().
- *
- * If the message delivery needs to happen on a different context to
- * that of its creation, wimax_msg_alloc() can be used to get a
- * pointer to the message that can be delivered later on with
- * wimax_msg_send().
- *
- * ROADMAP
- *
- * wimax_gnl_doit_msg_from_user()    Process a message from user space
- *   wimax_dev_get_by_genl_info()
- *   wimax_dev->op_msg_from_user()   Delivery of message to the driver
- *
- * wimax_msg()                       Send a message to user space
- *   wimax_msg_alloc()
- *   wimax_msg_send()
- */
-#include <linux/device.h>
-#include <linux/slab.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE op_msg
-#include "debug-levels.h"
-
-
-/**
- * wimax_msg_alloc - Create a new skb for sending a message to userspace
- *
- * @wimax_dev: WiMAX device descriptor
- * @pipe_name: "named pipe" the message will be sent to
- * @msg: pointer to the message data to send
- * @size: size of the message to send (in bytes), including the header.
- * @gfp_flags: flags for memory allocation.
- *
- * Returns: %0 if ok, negative errno code on error
- *
- * Description:
- *
- * Allocates an skb that will contain the message to send to user
- * space over the messaging pipe and initializes it, copying the
- * payload.
- *
- * Once this call is done, you can deliver it with
- * wimax_msg_send().
- *
- * IMPORTANT:
- *
- * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
- * wimax_msg_send() depends on skb->data being placed at the
- * beginning of the user message.
- *
- * Unlike other WiMAX stack calls, this call can be used way early,
- * even before wimax_dev_add() is called, as long as the
- * wimax_dev->net_dev pointer is set to point to a proper
- * net_dev. This is so that drivers can use it early in case they need
- * to send stuff around or communicate with user space.
- */
-struct sk_buff *wimax_msg_alloc(struct wimax_dev *wimax_dev,
-				const char *pipe_name,
-				const void *msg, size_t size,
-				gfp_t gfp_flags)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	size_t msg_size;
-	void *genl_msg;
-	struct sk_buff *skb;
-
-	msg_size = nla_total_size(size)
-		+ nla_total_size(sizeof(u32))
-		+ (pipe_name ? nla_total_size(strlen(pipe_name)) : 0);
-	result = -ENOMEM;
-	skb = genlmsg_new(msg_size, gfp_flags);
-	if (skb == NULL)
-		goto error_new;
-	genl_msg = genlmsg_put(skb, 0, 0, &wimax_gnl_family,
-			       0, WIMAX_GNL_OP_MSG_TO_USER);
-	if (genl_msg == NULL) {
-		dev_err(dev, "no memory to create generic netlink message\n");
-		goto error_genlmsg_put;
-	}
-	result = nla_put_u32(skb, WIMAX_GNL_MSG_IFIDX,
-			     wimax_dev->net_dev->ifindex);
-	if (result < 0) {
-		dev_err(dev, "no memory to add ifindex attribute\n");
-		goto error_nla_put;
-	}
-	if (pipe_name) {
-		result = nla_put_string(skb, WIMAX_GNL_MSG_PIPE_NAME,
-					pipe_name);
-		if (result < 0) {
-			dev_err(dev, "no memory to add pipe_name attribute\n");
-			goto error_nla_put;
-		}
-	}
-	result = nla_put(skb, WIMAX_GNL_MSG_DATA, size, msg);
-	if (result < 0) {
-		dev_err(dev, "no memory to add payload (msg %p size %zu) in "
-			"attribute: %d\n", msg, size, result);
-		goto error_nla_put;
-	}
-	genlmsg_end(skb, genl_msg);
-	return skb;
-
-error_nla_put:
-error_genlmsg_put:
-error_new:
-	nlmsg_free(skb);
-	return ERR_PTR(result);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_alloc);
-
-
-/**
- * wimax_msg_data_len - Return a pointer and size of a message's payload
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- * @size: Pointer to where to store the message's size
- *
- * Returns the pointer to the message data.
- */
-const void *wimax_msg_data_len(struct sk_buff *msg, size_t *size)
-{
-	struct nlmsghdr *nlh = (void *) msg->head;
-	struct nlattr *nla;
-
-	nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
-			      WIMAX_GNL_MSG_DATA);
-	if (nla == NULL) {
-		pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
-		return NULL;
-	}
-	*size = nla_len(nla);
-	return nla_data(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_data_len);
-
-
-/**
- * wimax_msg_data - Return a pointer to a message's payload
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- */
-const void *wimax_msg_data(struct sk_buff *msg)
-{
-	struct nlmsghdr *nlh = (void *) msg->head;
-	struct nlattr *nla;
-
-	nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
-			      WIMAX_GNL_MSG_DATA);
-	if (nla == NULL) {
-		pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
-		return NULL;
-	}
-	return nla_data(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_data);
-
-
-/**
- * wimax_msg_len - Return a message's payload length
- *
- * @msg: Pointer to a message created with wimax_msg_alloc()
- */
-ssize_t wimax_msg_len(struct sk_buff *msg)
-{
-	struct nlmsghdr *nlh = (void *) msg->head;
-	struct nlattr *nla;
-
-	nla = nlmsg_find_attr(nlh, sizeof(struct genlmsghdr),
-			      WIMAX_GNL_MSG_DATA);
-	if (nla == NULL) {
-		pr_err("Cannot find attribute WIMAX_GNL_MSG_DATA\n");
-		return -EINVAL;
-	}
-	return nla_len(nla);
-}
-EXPORT_SYMBOL_GPL(wimax_msg_len);
-
-
-/**
- * wimax_msg_send - Send a pre-allocated message to user space
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @skb: &struct sk_buff returned by wimax_msg_alloc(). Note the
- *     ownership of @skb is transferred to this function.
- *
- * Returns: 0 if ok, < 0 errno code on error
- *
- * Description:
- *
- * Sends a free-form message that was preallocated with
- * wimax_msg_alloc() and filled up.
- *
- * Assumes that once you pass an skb to this function for sending, it
- * owns it and will release it when done (on success).
- *
- * IMPORTANT:
- *
- * Don't use skb_push()/skb_pull()/skb_reserve() on the skb, as
- * wimax_msg_send() depends on skb->data being placed at the
- * beginning of the user message.
- *
- * Unlike other WiMAX stack calls, this call can be used way early,
- * even before wimax_dev_add() is called, as long as the
- * wimax_dev->net_dev pointer is set to point to a proper
- * net_dev. This is so that drivers can use it early in case they need
- * to send stuff around or communicate with user space.
- */
-int wimax_msg_send(struct wimax_dev *wimax_dev, struct sk_buff *skb)
-{
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	void *msg = skb->data;
-	size_t size = skb->len;
-	might_sleep();
-
-	d_printf(1, dev, "CTX: wimax msg, %zu bytes\n", size);
-	d_dump(2, dev, msg, size);
-	genlmsg_multicast(&wimax_gnl_family, skb, 0, 0, GFP_KERNEL);
-	d_printf(1, dev, "CTX: genl multicast done\n");
-	return 0;
-}
-EXPORT_SYMBOL_GPL(wimax_msg_send);
-
-
-/**
- * wimax_msg - Send a message to user space
- *
- * @wimax_dev: WiMAX device descriptor (properly referenced)
- * @pipe_name: "named pipe" the message will be sent to
- * @buf: pointer to the message to send.
- * @size: size of the buffer pointed to by @buf (in bytes).
- * @gfp_flags: flags for memory allocation.
- *
- * Returns: %0 if ok, negative errno code on error.
- *
- * Description:
- *
- * Sends a free-form message to user space on the device @wimax_dev.
- *
- * NOTES:
- *
- * Once the @skb is given to this function, who will own it and will
- * release it when done (unless it returns error).
- */
-int wimax_msg(struct wimax_dev *wimax_dev, const char *pipe_name,
-	      const void *buf, size_t size, gfp_t gfp_flags)
-{
-	int result = -ENOMEM;
-	struct sk_buff *skb;
-
-	skb = wimax_msg_alloc(wimax_dev, pipe_name, buf, size, gfp_flags);
-	if (IS_ERR(skb))
-		result = PTR_ERR(skb);
-	else
-		result = wimax_msg_send(wimax_dev, skb);
-	return result;
-}
-EXPORT_SYMBOL_GPL(wimax_msg);
-
-/*
- * Relays a message from user space to the driver
- *
- * The skb is passed to the driver-specific function with the netlink
- * and generic netlink headers already stripped.
- *
- * This call will block while handling/relaying the message.
- */
-int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info)
-{
-	int result, ifindex;
-	struct wimax_dev *wimax_dev;
-	struct device *dev;
-	struct nlmsghdr *nlh = info->nlhdr;
-	char *pipe_name;
-	void *msg_buf;
-	size_t msg_len;
-
-	might_sleep();
-	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
-	result = -ENODEV;
-	if (info->attrs[WIMAX_GNL_MSG_IFIDX] == NULL) {
-		pr_err("WIMAX_GNL_MSG_FROM_USER: can't find IFIDX attribute\n");
-		goto error_no_wimax_dev;
-	}
-	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_MSG_IFIDX]);
-	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
-	if (wimax_dev == NULL)
-		goto error_no_wimax_dev;
-	dev = wimax_dev_to_dev(wimax_dev);
-
-	/* Unpack arguments */
-	result = -EINVAL;
-	if (info->attrs[WIMAX_GNL_MSG_DATA] == NULL) {
-		dev_err(dev, "WIMAX_GNL_MSG_FROM_USER: can't find MSG_DATA "
-			"attribute\n");
-		goto error_no_data;
-	}
-	msg_buf = nla_data(info->attrs[WIMAX_GNL_MSG_DATA]);
-	msg_len = nla_len(info->attrs[WIMAX_GNL_MSG_DATA]);
-
-	if (info->attrs[WIMAX_GNL_MSG_PIPE_NAME] == NULL)
-		pipe_name = NULL;
-	else {
-		struct nlattr *attr = info->attrs[WIMAX_GNL_MSG_PIPE_NAME];
-		size_t attr_len = nla_len(attr);
-		/* libnl-1.1 does not yet support NLA_NUL_STRING */
-		result = -ENOMEM;
-		pipe_name = kstrndup(nla_data(attr), attr_len + 1, GFP_KERNEL);
-		if (pipe_name == NULL)
-			goto error_alloc;
-		pipe_name[attr_len] = 0;
-	}
-	mutex_lock(&wimax_dev->mutex);
-	result = wimax_dev_is_ready(wimax_dev);
-	if (result == -ENOMEDIUM)
-		result = 0;
-	if (result < 0)
-		goto error_not_ready;
-	result = -ENOSYS;
-	if (wimax_dev->op_msg_from_user == NULL)
-		goto error_noop;
-
-	d_printf(1, dev,
-		 "CRX: nlmsghdr len %u type %u flags 0x%04x seq 0x%x pid %u\n",
-		 nlh->nlmsg_len, nlh->nlmsg_type, nlh->nlmsg_flags,
-		 nlh->nlmsg_seq, nlh->nlmsg_pid);
-	d_printf(1, dev, "CRX: wimax message %zu bytes\n", msg_len);
-	d_dump(2, dev, msg_buf, msg_len);
-
-	result = wimax_dev->op_msg_from_user(wimax_dev, pipe_name,
-					     msg_buf, msg_len, info);
-error_noop:
-error_not_ready:
-	mutex_unlock(&wimax_dev->mutex);
-error_alloc:
-	kfree(pipe_name);
-error_no_data:
-	dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
-	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
-	return result;
-}
diff --git a/net/wimax/op-reset.c b/net/wimax/op-reset.c
deleted file mode 100644
index 9899b2e56721..000000000000
--- a/net/wimax/op-reset.c
+++ /dev/null
@@ -1,108 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Implement and export a method for resetting a WiMAX device
- *
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements a simple synchronous call to reset a WiMAX device.
- *
- * Resets aim at being warm, keeping the device handles active;
- * however, when that fails, it falls back to a cold reset (that will
- * disconnect and reconnect the device).
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_reset
-#include "debug-levels.h"
-
-
-/**
- * wimax_reset - Reset a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Returns:
- *
- * %0 if ok and a warm reset was done (the device still exists in
- * the system).
- *
- * -%ENODEV if a cold/bus reset had to be done (device has
- * disconnected and reconnected, so current handle is not valid
- * any more).
- *
- * -%EINVAL if the device is not even registered.
- *
- * Any other negative error code shall be considered as
- * non-recoverable.
- *
- * Description:
- *
- * Called when wanting to reset the device for any reason. Device is
- * taken back to power on status.
- *
- * This call blocks; on successful return, the device has completed the
- * reset process and is ready to operate.
- */
-int wimax_reset(struct wimax_dev *wimax_dev)
-{
-	int result = -EINVAL;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st state;
-
-	might_sleep();
-	d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
-	mutex_lock(&wimax_dev->mutex);
-	dev_hold(wimax_dev->net_dev);
-	state = wimax_dev->state;
-	mutex_unlock(&wimax_dev->mutex);
-
-	if (state >= WIMAX_ST_DOWN) {
-		mutex_lock(&wimax_dev->mutex_reset);
-		result = wimax_dev->op_reset(wimax_dev);
-		mutex_unlock(&wimax_dev->mutex_reset);
-	}
-	dev_put(wimax_dev->net_dev);
-
-	d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
-	return result;
-}
-EXPORT_SYMBOL(wimax_reset);
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the reset command from user space, return error code.
- *
- * No attributes.
- */
-int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info)
-{
-	int result, ifindex;
-	struct wimax_dev *wimax_dev;
-
-	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
-	result = -ENODEV;
-	if (info->attrs[WIMAX_GNL_RESET_IFIDX] == NULL) {
-		pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
-		goto error_no_wimax_dev;
-	}
-	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RESET_IFIDX]);
-	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
-	if (wimax_dev == NULL)
-		goto error_no_wimax_dev;
-	/* Execute the operation and send the result back to user space */
-	result = wimax_reset(wimax_dev);
-	dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
-	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
-	return result;
-}
diff --git a/net/wimax/op-rfkill.c b/net/wimax/op-rfkill.c
deleted file mode 100644
index 248d10b60b05..000000000000
--- a/net/wimax/op-rfkill.c
+++ /dev/null
@@ -1,431 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * RF-kill framework integration
- *
- * Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This integrates into the Linux Kernel rfkill susbystem so that the
- * drivers just have to do the bare minimal work, which is providing a
- * method to set the software RF-Kill switch and to report changes in
- * the software and hardware switch status.
- *
- * A non-polled generic rfkill device is embedded into the WiMAX
- * subsystem's representation of a device.
- *
- * FIXME: Need polled support? Let drivers provide a poll routine
- *	  and hand it to rfkill ops then?
- *
- * All device drivers have to do is after wimax_dev_init(), call
- * wimax_report_rfkill_hw() and wimax_report_rfkill_sw() to update
- * initial state and then every time it changes. See wimax.h:struct
- * wimax_dev for more information.
- *
- * ROADMAP
- *
- * wimax_gnl_doit_rfkill()      User space calling wimax_rfkill()
- *   wimax_rfkill()             Kernel calling wimax_rfkill()
- *     __wimax_rf_toggle_radio()
- *
- * wimax_rfkill_set_radio_block()  RF-Kill subsystem calling
- *   __wimax_rf_toggle_radio()
- *
- * __wimax_rf_toggle_radio()
- *   wimax_dev->op_rfkill_sw_toggle() Driver backend
- *   __wimax_state_change()
- *
- * wimax_report_rfkill_sw()     Driver reports state change
- *   __wimax_state_change()
- *
- * wimax_report_rfkill_hw()     Driver reports state change
- *   __wimax_state_change()
- *
- * wimax_rfkill_add()           Initialize/shutdown rfkill support
- * wimax_rfkill_rm()            [called by wimax_dev_add/rm()]
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include <linux/rfkill.h>
-#include <linux/export.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_rfkill
-#include "debug-levels.h"
-
-/**
- * wimax_report_rfkill_hw - Reports changes in the hardware RF switch
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New state of the RF Kill switch. %WIMAX_RF_ON radio on,
- *     %WIMAX_RF_OFF radio off.
- *
- * When the device detects a change in the state of thehardware RF
- * switch, it must call this function to let the WiMAX kernel stack
- * know that the state has changed so it can be properly propagated.
- *
- * The WiMAX stack caches the state (the driver doesn't need to). As
- * well, as the change is propagated it will come back as a request to
- * change the software state to mirror the hardware state.
- *
- * If the device doesn't have a hardware kill switch, just report
- * it on initialization as always on (%WIMAX_RF_ON, radio on).
- */
-void wimax_report_rfkill_hw(struct wimax_dev *wimax_dev,
-			    enum wimax_rf_state state)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st wimax_state;
-
-	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
-	BUG_ON(state == WIMAX_RF_QUERY);
-	BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
-
-	mutex_lock(&wimax_dev->mutex);
-	result = wimax_dev_is_ready(wimax_dev);
-	if (result < 0)
-		goto error_not_ready;
-
-	if (state != wimax_dev->rf_hw) {
-		wimax_dev->rf_hw = state;
-		if (wimax_dev->rf_hw == WIMAX_RF_ON &&
-		    wimax_dev->rf_sw == WIMAX_RF_ON)
-			wimax_state = WIMAX_ST_READY;
-		else
-			wimax_state = WIMAX_ST_RADIO_OFF;
-
-		result = rfkill_set_hw_state(wimax_dev->rfkill,
-					     state == WIMAX_RF_OFF);
-
-		__wimax_state_change(wimax_dev, wimax_state);
-	}
-error_not_ready:
-	mutex_unlock(&wimax_dev->mutex);
-	d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
-		wimax_dev, state, result);
-}
-EXPORT_SYMBOL_GPL(wimax_report_rfkill_hw);
-
-
-/**
- * wimax_report_rfkill_sw - Reports changes in the software RF switch
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New state of the RF kill switch. %WIMAX_RF_ON radio on,
- *     %WIMAX_RF_OFF radio off.
- *
- * Reports changes in the software RF switch state to the WiMAX stack.
- *
- * The main use is during initialization, so the driver can query the
- * device for its current software radio kill switch state and feed it
- * to the system.
- *
- * On the side, the device does not change the software state by
- * itself. In practice, this can happen, as the device might decide to
- * switch (in software) the radio off for different reasons.
- */
-void wimax_report_rfkill_sw(struct wimax_dev *wimax_dev,
-			    enum wimax_rf_state state)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st wimax_state;
-
-	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
-	BUG_ON(state == WIMAX_RF_QUERY);
-	BUG_ON(state != WIMAX_RF_ON && state != WIMAX_RF_OFF);
-
-	mutex_lock(&wimax_dev->mutex);
-	result = wimax_dev_is_ready(wimax_dev);
-	if (result < 0)
-		goto error_not_ready;
-
-	if (state != wimax_dev->rf_sw) {
-		wimax_dev->rf_sw = state;
-		if (wimax_dev->rf_hw == WIMAX_RF_ON &&
-		    wimax_dev->rf_sw == WIMAX_RF_ON)
-			wimax_state = WIMAX_ST_READY;
-		else
-			wimax_state = WIMAX_ST_RADIO_OFF;
-		__wimax_state_change(wimax_dev, wimax_state);
-		rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
-	}
-error_not_ready:
-	mutex_unlock(&wimax_dev->mutex);
-	d_fnend(3, dev, "(wimax_dev %p state %u) = void [%d]\n",
-		wimax_dev, state, result);
-}
-EXPORT_SYMBOL_GPL(wimax_report_rfkill_sw);
-
-
-/*
- * Callback for the RF Kill toggle operation
- *
- * This function is called by:
- *
- * - The rfkill subsystem when the RF-Kill key is pressed in the
- *   hardware and the driver notifies through
- *   wimax_report_rfkill_hw(). The rfkill subsystem ends up calling back
- *   here so the software RF Kill switch state is changed to reflect
- *   the hardware switch state.
- *
- * - When the user sets the state through sysfs' rfkill/state file
- *
- * - When the user calls wimax_rfkill().
- *
- * This call blocks!
- *
- * WARNING! When we call rfkill_unregister(), this will be called with
- * state 0!
- *
- * WARNING: wimax_dev must be locked
- */
-static
-int __wimax_rf_toggle_radio(struct wimax_dev *wimax_dev,
-			    enum wimax_rf_state state)
-{
-	int result = 0;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st wimax_state;
-
-	might_sleep();
-	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
-	if (wimax_dev->rf_sw == state)
-		goto out_no_change;
-	if (wimax_dev->op_rfkill_sw_toggle != NULL)
-		result = wimax_dev->op_rfkill_sw_toggle(wimax_dev, state);
-	else if (state == WIMAX_RF_OFF)	/* No op? can't turn off */
-		result = -ENXIO;
-	else				/* No op? can turn on */
-		result = 0;		/* should never happen tho */
-	if (result >= 0) {
-		result = 0;
-		wimax_dev->rf_sw = state;
-		wimax_state = state == WIMAX_RF_ON ?
-			WIMAX_ST_READY : WIMAX_ST_RADIO_OFF;
-		__wimax_state_change(wimax_dev, wimax_state);
-	}
-out_no_change:
-	d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
-		wimax_dev, state, result);
-	return result;
-}
-
-
-/*
- * Translate from rfkill state to wimax state
- *
- * NOTE: Special state handling rules here
- *
- *     Just pretend the call didn't happen if we are in a state where
- *     we know for sure it cannot be handled (WIMAX_ST_DOWN or
- *     __WIMAX_ST_QUIESCING). rfkill() needs it to register and
- *     unregister, as it will run this path.
- *
- * NOTE: This call will block until the operation is completed.
- */
-static int wimax_rfkill_set_radio_block(void *data, bool blocked)
-{
-	int result;
-	struct wimax_dev *wimax_dev = data;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_rf_state rf_state;
-
-	d_fnstart(3, dev, "(wimax_dev %p blocked %u)\n", wimax_dev, blocked);
-	rf_state = WIMAX_RF_ON;
-	if (blocked)
-		rf_state = WIMAX_RF_OFF;
-	mutex_lock(&wimax_dev->mutex);
-	if (wimax_dev->state <= __WIMAX_ST_QUIESCING)
-		result = 0;
-	else
-		result = __wimax_rf_toggle_radio(wimax_dev, rf_state);
-	mutex_unlock(&wimax_dev->mutex);
-	d_fnend(3, dev, "(wimax_dev %p blocked %u) = %d\n",
-		wimax_dev, blocked, result);
-	return result;
-}
-
-static const struct rfkill_ops wimax_rfkill_ops = {
-	.set_block = wimax_rfkill_set_radio_block,
-};
-
-/**
- * wimax_rfkill - Set the software RF switch state for a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * @state: New RF state.
- *
- * Returns:
- *
- * >= 0 toggle state if ok, < 0 errno code on error. The toggle state
- * is returned as a bitmap, bit 0 being the hardware RF state, bit 1
- * the software RF state.
- *
- * 0 means disabled (%WIMAX_RF_ON, radio on), 1 means enabled radio
- * off (%WIMAX_RF_OFF).
- *
- * Description:
- *
- * Called by the user when he wants to request the WiMAX radio to be
- * switched on (%WIMAX_RF_ON) or off (%WIMAX_RF_OFF). With
- * %WIMAX_RF_QUERY, just the current state is returned.
- *
- * NOTE:
- *
- * This call will block until the operation is complete.
- */
-int wimax_rfkill(struct wimax_dev *wimax_dev, enum wimax_rf_state state)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-
-	d_fnstart(3, dev, "(wimax_dev %p state %u)\n", wimax_dev, state);
-	mutex_lock(&wimax_dev->mutex);
-	result = wimax_dev_is_ready(wimax_dev);
-	if (result < 0) {
-		/* While initializing, < 1.4.3 wimax-tools versions use
-		 * this call to check if the device is a valid WiMAX
-		 * device; so we allow it to proceed always,
-		 * considering the radios are all off. */
-		if (result == -ENOMEDIUM && state == WIMAX_RF_QUERY)
-			result = WIMAX_RF_OFF << 1 | WIMAX_RF_OFF;
-		goto error_not_ready;
-	}
-	switch (state) {
-	case WIMAX_RF_ON:
-	case WIMAX_RF_OFF:
-		result = __wimax_rf_toggle_radio(wimax_dev, state);
-		if (result < 0)
-			goto error;
-		rfkill_set_sw_state(wimax_dev->rfkill, state == WIMAX_RF_OFF);
-		break;
-	case WIMAX_RF_QUERY:
-		break;
-	default:
-		result = -EINVAL;
-		goto error;
-	}
-	result = wimax_dev->rf_sw << 1 | wimax_dev->rf_hw;
-error:
-error_not_ready:
-	mutex_unlock(&wimax_dev->mutex);
-	d_fnend(3, dev, "(wimax_dev %p state %u) = %d\n",
-		wimax_dev, state, result);
-	return result;
-}
-EXPORT_SYMBOL(wimax_rfkill);
-
-
-/*
- * Register a new WiMAX device's RF Kill support
- *
- * WARNING: wimax_dev->mutex must be unlocked
- */
-int wimax_rfkill_add(struct wimax_dev *wimax_dev)
-{
-	int result;
-	struct rfkill *rfkill;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-
-	d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
-	/* Initialize RF Kill */
-	result = -ENOMEM;
-	rfkill = rfkill_alloc(wimax_dev->name, dev, RFKILL_TYPE_WIMAX,
-			      &wimax_rfkill_ops, wimax_dev);
-	if (rfkill == NULL)
-		goto error_rfkill_allocate;
-
-	d_printf(1, dev, "rfkill %p\n", rfkill);
-
-	wimax_dev->rfkill = rfkill;
-
-	rfkill_init_sw_state(rfkill, 1);
-	result = rfkill_register(wimax_dev->rfkill);
-	if (result < 0)
-		goto error_rfkill_register;
-
-	/* If there is no SW toggle op, SW RFKill is always on */
-	if (wimax_dev->op_rfkill_sw_toggle == NULL)
-		wimax_dev->rf_sw = WIMAX_RF_ON;
-
-	d_fnend(3, dev, "(wimax_dev %p) = 0\n", wimax_dev);
-	return 0;
-
-error_rfkill_register:
-	rfkill_destroy(wimax_dev->rfkill);
-error_rfkill_allocate:
-	d_fnend(3, dev, "(wimax_dev %p) = %d\n", wimax_dev, result);
-	return result;
-}
-
-
-/*
- * Deregister a WiMAX device's RF Kill support
- *
- * Ick, we can't call rfkill_free() after rfkill_unregister()...oh
- * well.
- *
- * WARNING: wimax_dev->mutex must be unlocked
- */
-void wimax_rfkill_rm(struct wimax_dev *wimax_dev)
-{
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	d_fnstart(3, dev, "(wimax_dev %p)\n", wimax_dev);
-	rfkill_unregister(wimax_dev->rfkill);
-	rfkill_destroy(wimax_dev->rfkill);
-	d_fnend(3, dev, "(wimax_dev %p)\n", wimax_dev);
-}
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the rfkill command from user space, return a combination
- * value that describe the states of the different toggles.
- *
- * Only one attribute: the new state requested (on, off or no change,
- * just query).
- */
-
-int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info)
-{
-	int result, ifindex;
-	struct wimax_dev *wimax_dev;
-	struct device *dev;
-	enum wimax_rf_state new_state;
-
-	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
-	result = -ENODEV;
-	if (info->attrs[WIMAX_GNL_RFKILL_IFIDX] == NULL) {
-		pr_err("WIMAX_GNL_OP_RFKILL: can't find IFIDX attribute\n");
-		goto error_no_wimax_dev;
-	}
-	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_IFIDX]);
-	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
-	if (wimax_dev == NULL)
-		goto error_no_wimax_dev;
-	dev = wimax_dev_to_dev(wimax_dev);
-	result = -EINVAL;
-	if (info->attrs[WIMAX_GNL_RFKILL_STATE] == NULL) {
-		dev_err(dev, "WIMAX_GNL_RFKILL: can't find RFKILL_STATE "
-			"attribute\n");
-		goto error_no_pid;
-	}
-	new_state = nla_get_u32(info->attrs[WIMAX_GNL_RFKILL_STATE]);
-
-	/* Execute the operation and send the result back to user space */
-	result = wimax_rfkill(wimax_dev, new_state);
-error_no_pid:
-	dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
-	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
-	return result;
-}
diff --git a/net/wimax/op-state-get.c b/net/wimax/op-state-get.c
deleted file mode 100644
index 5bc712de1563..000000000000
--- a/net/wimax/op-state-get.c
+++ /dev/null
@@ -1,52 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Implement and export a method for getting a WiMAX device current state
- *
- * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt>
- *
- * Based on previous WiMAX core work by:
- *  Copyright (C) 2008 Intel Corporation <linux-wimax@intel.com>
- *  Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- */
-
-#include <net/wimax.h>
-#include <net/genetlink.h>
-#include <linux/wimax.h>
-#include <linux/security.h>
-#include "wimax-internal.h"
-
-#define D_SUBMODULE op_state_get
-#include "debug-levels.h"
-
-
-/*
- * Exporting to user space over generic netlink
- *
- * Parse the state get command from user space, return a combination
- * value that describe the current state.
- *
- * No attributes.
- */
-int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info)
-{
-	int result, ifindex;
-	struct wimax_dev *wimax_dev;
-
-	d_fnstart(3, NULL, "(skb %p info %p)\n", skb, info);
-	result = -ENODEV;
-	if (info->attrs[WIMAX_GNL_STGET_IFIDX] == NULL) {
-		pr_err("WIMAX_GNL_OP_STATE_GET: can't find IFIDX attribute\n");
-		goto error_no_wimax_dev;
-	}
-	ifindex = nla_get_u32(info->attrs[WIMAX_GNL_STGET_IFIDX]);
-	wimax_dev = wimax_dev_get_by_genl_info(info, ifindex);
-	if (wimax_dev == NULL)
-		goto error_no_wimax_dev;
-	/* Execute the operation and send the result back to user space */
-	result = wimax_state_get(wimax_dev);
-	dev_put(wimax_dev->net_dev);
-error_no_wimax_dev:
-	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
-	return result;
-}
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
deleted file mode 100644
index 4b9b1c5e8f3a..000000000000
--- a/net/wimax/stack.c
+++ /dev/null
@@ -1,609 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Linux WiMAX
- * Initialization, addition and removal of wimax devices
- *
- * Copyright (C) 2005-2006 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This implements:
- *
- *   - basic life cycle of 'struct wimax_dev' [wimax_dev_*()]; on
- *     addition/registration initialize all subfields and allocate
- *     generic netlink resources for user space communication. On
- *     removal/unregistration, undo all that.
- *
- *   - device state machine [wimax_state_change()] and support to send
- *     reports to user space when the state changes
- *     [wimax_gnl_re_state_change*()].
- *
- * See include/net/wimax.h for rationales and design.
- *
- * ROADMAP
- *
- * [__]wimax_state_change()     Called by drivers to update device's state
- *   wimax_gnl_re_state_change_alloc()
- *   wimax_gnl_re_state_change_send()
- *
- * wimax_dev_init()	        Init a device
- * wimax_dev_add()              Register
- *   wimax_rfkill_add()
- *   wimax_gnl_add()            Register all the generic netlink resources.
- *   wimax_id_table_add()
- * wimax_dev_rm()               Unregister
- *   wimax_id_table_rm()
- *   wimax_gnl_rm()
- *   wimax_rfkill_rm()
- */
-#include <linux/device.h>
-#include <linux/gfp.h>
-#include <net/genetlink.h>
-#include <linux/netdevice.h>
-#include <linux/wimax.h>
-#include <linux/module.h>
-#include "wimax-internal.h"
-
-
-#define D_SUBMODULE stack
-#include "debug-levels.h"
-
-static char wimax_debug_params[128];
-module_param_string(debug, wimax_debug_params, sizeof(wimax_debug_params),
-		    0644);
-MODULE_PARM_DESC(debug,
-		 "String of space-separated NAME:VALUE pairs, where NAMEs "
-		 "are the different debug submodules and VALUE are the "
-		 "initial debug value to set.");
-
-/*
- * Authoritative source for the RE_STATE_CHANGE attribute policy
- *
- * We don't really use it here, but /me likes to keep the definition
- * close to where the data is generated.
- */
-/*
-static const struct nla_policy wimax_gnl_re_status_change[WIMAX_GNL_ATTR_MAX + 1] = {
-	[WIMAX_GNL_STCH_STATE_OLD] = { .type = NLA_U8 },
-	[WIMAX_GNL_STCH_STATE_NEW] = { .type = NLA_U8 },
-};
-*/
-
-
-/*
- * Allocate a Report State Change message
- *
- * @header: save it, you need it for _send()
- *
- * Creates and fills a basic state change message; different code
- * paths can then add more attributes to the message as needed.
- *
- * Use wimax_gnl_re_state_change_send() to send the returned skb.
- *
- * Returns: skb with the genl message if ok, IS_ERR() ptr on error
- *     with an errno code.
- */
-static
-struct sk_buff *wimax_gnl_re_state_change_alloc(
-	struct wimax_dev *wimax_dev,
-	enum wimax_st new_state, enum wimax_st old_state,
-	void **header)
-{
-	int result;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	void *data;
-	struct sk_buff *report_skb;
-
-	d_fnstart(3, dev, "(wimax_dev %p new_state %u old_state %u)\n",
-		  wimax_dev, new_state, old_state);
-	result = -ENOMEM;
-	report_skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (report_skb == NULL) {
-		dev_err(dev, "RE_STCH: can't create message\n");
-		goto error_new;
-	}
-	/* FIXME: sending a group ID as the seq is wrong */
-	data = genlmsg_put(report_skb, 0, wimax_gnl_family.mcgrp_offset,
-			   &wimax_gnl_family, 0, WIMAX_GNL_RE_STATE_CHANGE);
-	if (data == NULL) {
-		dev_err(dev, "RE_STCH: can't put data into message\n");
-		goto error_put;
-	}
-	*header = data;
-
-	result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_OLD, old_state);
-	if (result < 0) {
-		dev_err(dev, "RE_STCH: Error adding OLD attr: %d\n", result);
-		goto error_put;
-	}
-	result = nla_put_u8(report_skb, WIMAX_GNL_STCH_STATE_NEW, new_state);
-	if (result < 0) {
-		dev_err(dev, "RE_STCH: Error adding NEW attr: %d\n", result);
-		goto error_put;
-	}
-	result = nla_put_u32(report_skb, WIMAX_GNL_STCH_IFIDX,
-			     wimax_dev->net_dev->ifindex);
-	if (result < 0) {
-		dev_err(dev, "RE_STCH: Error adding IFINDEX attribute\n");
-		goto error_put;
-	}
-	d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %p\n",
-		wimax_dev, new_state, old_state, report_skb);
-	return report_skb;
-
-error_put:
-	nlmsg_free(report_skb);
-error_new:
-	d_fnend(3, dev, "(wimax_dev %p new_state %u old_state %u) = %d\n",
-		wimax_dev, new_state, old_state, result);
-	return ERR_PTR(result);
-}
-
-
-/*
- * Send a Report State Change message (as created with _alloc).
- *
- * @report_skb: as returned by wimax_gnl_re_state_change_alloc()
- * @header: as returned by wimax_gnl_re_state_change_alloc()
- *
- * Returns: 0 if ok, < 0 errno code on error.
- *
- * If the message is  NULL, pretend it didn't happen.
- */
-static
-int wimax_gnl_re_state_change_send(
-	struct wimax_dev *wimax_dev, struct sk_buff *report_skb,
-	void *header)
-{
-	int result = 0;
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	d_fnstart(3, dev, "(wimax_dev %p report_skb %p)\n",
-		  wimax_dev, report_skb);
-	if (report_skb == NULL) {
-		result = -ENOMEM;
-		goto out;
-	}
-	genlmsg_end(report_skb, header);
-	genlmsg_multicast(&wimax_gnl_family, report_skb, 0, 0, GFP_KERNEL);
-out:
-	d_fnend(3, dev, "(wimax_dev %p report_skb %p) = %d\n",
-		wimax_dev, report_skb, result);
-	return result;
-}
-
-
-static
-void __check_new_state(enum wimax_st old_state, enum wimax_st new_state,
-		       unsigned int allowed_states_bm)
-{
-	if (WARN_ON(((1 << new_state) & allowed_states_bm) == 0)) {
-		pr_err("SW BUG! Forbidden state change %u -> %u\n",
-		       old_state, new_state);
-	}
-}
-
-
-/*
- * Set the current state of a WiMAX device [unlocking version of
- * wimax_state_change().
- */
-void __wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
-{
-	struct device *dev = wimax_dev_to_dev(wimax_dev);
-	enum wimax_st old_state = wimax_dev->state;
-	struct sk_buff *stch_skb;
-	void *header;
-
-	d_fnstart(3, dev, "(wimax_dev %p new_state %u [old %u])\n",
-		  wimax_dev, new_state, old_state);
-
-	if (WARN_ON(new_state >= __WIMAX_ST_INVALID)) {
-		dev_err(dev, "SW BUG: requesting invalid state %u\n",
-			new_state);
-		goto out;
-	}
-	if (old_state == new_state)
-		goto out;
-	header = NULL;	/* gcc complains? can't grok why */
-	stch_skb = wimax_gnl_re_state_change_alloc(
-		wimax_dev, new_state, old_state, &header);
-
-	/* Verify the state transition and do exit-from-state actions */
-	switch (old_state) {
-	case __WIMAX_ST_NULL:
-		__check_new_state(old_state, new_state,
-				  1 << WIMAX_ST_DOWN);
-		break;
-	case WIMAX_ST_DOWN:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_UNINITIALIZED
-				  | 1 << WIMAX_ST_RADIO_OFF);
-		break;
-	case __WIMAX_ST_QUIESCING:
-		__check_new_state(old_state, new_state, 1 << WIMAX_ST_DOWN);
-		break;
-	case WIMAX_ST_UNINITIALIZED:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF);
-		break;
-	case WIMAX_ST_RADIO_OFF:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_READY);
-		break;
-	case WIMAX_ST_READY:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF
-				  | 1 << WIMAX_ST_SCANNING
-				  | 1 << WIMAX_ST_CONNECTING
-				  | 1 << WIMAX_ST_CONNECTED);
-		break;
-	case WIMAX_ST_SCANNING:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF
-				  | 1 << WIMAX_ST_READY
-				  | 1 << WIMAX_ST_CONNECTING
-				  | 1 << WIMAX_ST_CONNECTED);
-		break;
-	case WIMAX_ST_CONNECTING:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF
-				  | 1 << WIMAX_ST_READY
-				  | 1 << WIMAX_ST_SCANNING
-				  | 1 << WIMAX_ST_CONNECTED);
-		break;
-	case WIMAX_ST_CONNECTED:
-		__check_new_state(old_state, new_state,
-				  1 << __WIMAX_ST_QUIESCING
-				  | 1 << WIMAX_ST_RADIO_OFF
-				  | 1 << WIMAX_ST_READY);
-		netif_tx_disable(wimax_dev->net_dev);
-		netif_carrier_off(wimax_dev->net_dev);
-		break;
-	case __WIMAX_ST_INVALID:
-	default:
-		dev_err(dev, "SW BUG: wimax_dev %p is in unknown state %u\n",
-			wimax_dev, wimax_dev->state);
-		WARN_ON(1);
-		goto out;
-	}
-
-	/* Execute the actions of entry to the new state */
-	switch (new_state) {
-	case __WIMAX_ST_NULL:
-		dev_err(dev, "SW BUG: wimax_dev %p entering NULL state "
-			"from %u\n", wimax_dev, wimax_dev->state);
-		WARN_ON(1);		/* Nobody can enter this state */
-		break;
-	case WIMAX_ST_DOWN:
-		break;
-	case __WIMAX_ST_QUIESCING:
-		break;
-	case WIMAX_ST_UNINITIALIZED:
-		break;
-	case WIMAX_ST_RADIO_OFF:
-		break;
-	case WIMAX_ST_READY:
-		break;
-	case WIMAX_ST_SCANNING:
-		break;
-	case WIMAX_ST_CONNECTING:
-		break;
-	case WIMAX_ST_CONNECTED:
-		netif_carrier_on(wimax_dev->net_dev);
-		netif_wake_queue(wimax_dev->net_dev);
-		break;
-	case __WIMAX_ST_INVALID:
-	default:
-		BUG();
-	}
-	__wimax_state_set(wimax_dev, new_state);
-	if (!IS_ERR(stch_skb))
-		wimax_gnl_re_state_change_send(wimax_dev, stch_skb, header);
-out:
-	d_fnend(3, dev, "(wimax_dev %p new_state %u [old %u]) = void\n",
-		wimax_dev, new_state, old_state);
-}
-
-
-/**
- * wimax_state_change - Set the current state of a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor (properly referenced)
- * @new_state: New state to switch to
- *
- * This implements the state changes for the wimax devices. It will
- *
- * - verify that the state transition is legal (for now it'll just
- *   print a warning if not) according to the table in
- *   linux/wimax.h's documentation for 'enum wimax_st'.
- *
- * - perform the actions needed for leaving the current state and
- *   whichever are needed for entering the new state.
- *
- * - issue a report to user space indicating the new state (and an
- *   optional payload with information about the new state).
- *
- * NOTE: @wimax_dev must be locked
- */
-void wimax_state_change(struct wimax_dev *wimax_dev, enum wimax_st new_state)
-{
-	/*
-	 * A driver cannot take the wimax_dev out of the
-	 * __WIMAX_ST_NULL state unless by calling wimax_dev_add(). If
-	 * the wimax_dev's state is still NULL, we ignore any request
-	 * to change its state because it means it hasn't been yet
-	 * registered.
-	 *
-	 * There is no need to complain about it, as routines that
-	 * call this might be shared from different code paths that
-	 * are called before or after wimax_dev_add() has done its
-	 * job.
-	 */
-	mutex_lock(&wimax_dev->mutex);
-	if (wimax_dev->state > __WIMAX_ST_NULL)
-		__wimax_state_change(wimax_dev, new_state);
-	mutex_unlock(&wimax_dev->mutex);
-}
-EXPORT_SYMBOL_GPL(wimax_state_change);
-
-
-/**
- * wimax_state_get() - Return the current state of a WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Returns: Current state of the device according to its driver.
- */
-enum wimax_st wimax_state_get(struct wimax_dev *wimax_dev)
-{
-	enum wimax_st state;
-	mutex_lock(&wimax_dev->mutex);
-	state = wimax_dev->state;
-	mutex_unlock(&wimax_dev->mutex);
-	return state;
-}
-EXPORT_SYMBOL_GPL(wimax_state_get);
-
-
-/**
- * wimax_dev_init - initialize a newly allocated instance
- *
- * @wimax_dev: WiMAX device descriptor to initialize.
- *
- * Initializes fields of a freshly allocated @wimax_dev instance. This
- * function assumes that after allocation, the memory occupied by
- * @wimax_dev was zeroed.
- */
-void wimax_dev_init(struct wimax_dev *wimax_dev)
-{
-	INIT_LIST_HEAD(&wimax_dev->id_table_node);
-	__wimax_state_set(wimax_dev, __WIMAX_ST_NULL);
-	mutex_init(&wimax_dev->mutex);
-	mutex_init(&wimax_dev->mutex_reset);
-}
-EXPORT_SYMBOL_GPL(wimax_dev_init);
-
-static const struct nla_policy wimax_gnl_policy[WIMAX_GNL_ATTR_MAX + 1] = {
-	[WIMAX_GNL_RESET_IFIDX] = { .type = NLA_U32, },
-	[WIMAX_GNL_RFKILL_IFIDX] = { .type = NLA_U32, },
-	[WIMAX_GNL_RFKILL_STATE] = {
-		.type = NLA_U32		/* enum wimax_rf_state */
-	},
-	[WIMAX_GNL_STGET_IFIDX] = { .type = NLA_U32, },
-	[WIMAX_GNL_MSG_IFIDX] = { .type = NLA_U32, },
-	[WIMAX_GNL_MSG_DATA] = {
-		.type = NLA_UNSPEC,	/* libnl doesn't grok BINARY yet */
-	},
-};
-
-static const struct genl_ops wimax_gnl_ops[] = {
-	{
-		.cmd = WIMAX_GNL_OP_MSG_FROM_USER,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM,
-		.doit = wimax_gnl_doit_msg_from_user,
-	},
-	{
-		.cmd = WIMAX_GNL_OP_RESET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM,
-		.doit = wimax_gnl_doit_reset,
-	},
-	{
-		.cmd = WIMAX_GNL_OP_RFKILL,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM,
-		.doit = wimax_gnl_doit_rfkill,
-	},
-	{
-		.cmd = WIMAX_GNL_OP_STATE_GET,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.flags = GENL_ADMIN_PERM,
-		.doit = wimax_gnl_doit_state_get,
-	},
-};
-
-
-static
-size_t wimax_addr_scnprint(char *addr_str, size_t addr_str_size,
-			   unsigned char *addr, size_t addr_len)
-{
-	unsigned int cnt, total;
-
-	for (total = cnt = 0; cnt < addr_len; cnt++)
-		total += scnprintf(addr_str + total, addr_str_size - total,
-				   "%02x%c", addr[cnt],
-				   cnt == addr_len - 1 ? '\0' : ':');
-	return total;
-}
-
-
-/**
- * wimax_dev_add - Register a new WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor (as embedded in your @net_dev's
- *     priv data). You must have called wimax_dev_init() on it before.
- *
- * @net_dev: net device the @wimax_dev is associated with. The
- *     function expects SET_NETDEV_DEV() and register_netdev() were
- *     already called on it.
- *
- * Registers the new WiMAX device, sets up the user-kernel control
- * interface (generic netlink) and common WiMAX infrastructure.
- *
- * Note that the parts that will allow interaction with user space are
- * setup at the very end, when the rest is in place, as once that
- * happens, the driver might get user space control requests via
- * netlink or from debugfs that might translate into calls into
- * wimax_dev->op_*().
- */
-int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev)
-{
-	int result;
-	struct device *dev = net_dev->dev.parent;
-	char addr_str[32];
-
-	d_fnstart(3, dev, "(wimax_dev %p net_dev %p)\n", wimax_dev, net_dev);
-
-	/* Do the RFKILL setup before locking, as RFKILL will call
-	 * into our functions.
-	 */
-	wimax_dev->net_dev = net_dev;
-	result = wimax_rfkill_add(wimax_dev);
-	if (result < 0)
-		goto error_rfkill_add;
-
-	/* Set up user-space interaction */
-	mutex_lock(&wimax_dev->mutex);
-	wimax_id_table_add(wimax_dev);
-	wimax_debugfs_add(wimax_dev);
-
-	__wimax_state_set(wimax_dev, WIMAX_ST_DOWN);
-	mutex_unlock(&wimax_dev->mutex);
-
-	wimax_addr_scnprint(addr_str, sizeof(addr_str),
-			    net_dev->dev_addr, net_dev->addr_len);
-	dev_err(dev, "WiMAX interface %s (%s) ready\n",
-		net_dev->name, addr_str);
-	d_fnend(3, dev, "(wimax_dev %p net_dev %p) = 0\n", wimax_dev, net_dev);
-	return 0;
-
-error_rfkill_add:
-	d_fnend(3, dev, "(wimax_dev %p net_dev %p) = %d\n",
-		wimax_dev, net_dev, result);
-	return result;
-}
-EXPORT_SYMBOL_GPL(wimax_dev_add);
-
-
-/**
- * wimax_dev_rm - Unregister an existing WiMAX device
- *
- * @wimax_dev: WiMAX device descriptor
- *
- * Unregisters a WiMAX device previously registered for use with
- * wimax_add_rm().
- *
- * IMPORTANT! Must call before calling unregister_netdev().
- *
- * After this function returns, you will not get any more user space
- * control requests (via netlink or debugfs) and thus to wimax_dev->ops.
- *
- * Reentrancy control is ensured by setting the state to
- * %__WIMAX_ST_QUIESCING. rfkill operations coming through
- * wimax_*rfkill*() will be stopped by the quiescing state; ops coming
- * from the rfkill subsystem will be stopped by the support being
- * removed by wimax_rfkill_rm().
- */
-void wimax_dev_rm(struct wimax_dev *wimax_dev)
-{
-	d_fnstart(3, NULL, "(wimax_dev %p)\n", wimax_dev);
-
-	mutex_lock(&wimax_dev->mutex);
-	__wimax_state_change(wimax_dev, __WIMAX_ST_QUIESCING);
-	wimax_debugfs_rm(wimax_dev);
-	wimax_id_table_rm(wimax_dev);
-	__wimax_state_change(wimax_dev, WIMAX_ST_DOWN);
-	mutex_unlock(&wimax_dev->mutex);
-	wimax_rfkill_rm(wimax_dev);
-	d_fnend(3, NULL, "(wimax_dev %p) = void\n", wimax_dev);
-}
-EXPORT_SYMBOL_GPL(wimax_dev_rm);
-
-
-/* Debug framework control of debug levels */
-struct d_level D_LEVEL[] = {
-	D_SUBMODULE_DEFINE(debugfs),
-	D_SUBMODULE_DEFINE(id_table),
-	D_SUBMODULE_DEFINE(op_msg),
-	D_SUBMODULE_DEFINE(op_reset),
-	D_SUBMODULE_DEFINE(op_rfkill),
-	D_SUBMODULE_DEFINE(op_state_get),
-	D_SUBMODULE_DEFINE(stack),
-};
-size_t D_LEVEL_SIZE = ARRAY_SIZE(D_LEVEL);
-
-
-static const struct genl_multicast_group wimax_gnl_mcgrps[] = {
-	{ .name = "msg", },
-};
-
-struct genl_family wimax_gnl_family __ro_after_init = {
-	.name = "WiMAX",
-	.version = WIMAX_GNL_VERSION,
-	.hdrsize = 0,
-	.maxattr = WIMAX_GNL_ATTR_MAX,
-	.policy = wimax_gnl_policy,
-	.module = THIS_MODULE,
-	.ops = wimax_gnl_ops,
-	.n_ops = ARRAY_SIZE(wimax_gnl_ops),
-	.mcgrps = wimax_gnl_mcgrps,
-	.n_mcgrps = ARRAY_SIZE(wimax_gnl_mcgrps),
-};
-
-
-
-/* Shutdown the wimax stack */
-static
-int __init wimax_subsys_init(void)
-{
-	int result;
-
-	d_fnstart(4, NULL, "()\n");
-	d_parse_params(D_LEVEL, D_LEVEL_SIZE, wimax_debug_params,
-		       "wimax.debug");
-
-	result = genl_register_family(&wimax_gnl_family);
-	if (unlikely(result < 0)) {
-		pr_err("cannot register generic netlink family: %d\n", result);
-		goto error_register_family;
-	}
-
-	d_fnend(4, NULL, "() = 0\n");
-	return 0;
-
-error_register_family:
-	d_fnend(4, NULL, "() = %d\n", result);
-	return result;
-
-}
-module_init(wimax_subsys_init);
-
-
-/* Shutdown the wimax stack */
-static
-void __exit wimax_subsys_exit(void)
-{
-	wimax_id_table_release();
-	genl_unregister_family(&wimax_gnl_family);
-}
-module_exit(wimax_subsys_exit);
-
-MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
-MODULE_DESCRIPTION("Linux WiMAX stack");
-MODULE_LICENSE("GPL");
diff --git a/net/wimax/wimax-internal.h b/net/wimax/wimax-internal.h
deleted file mode 100644
index 40751207296c..000000000000
--- a/net/wimax/wimax-internal.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Linux WiMAX
- * Internal API for kernel space WiMAX stack
- *
- * Copyright (C) 2007 Intel Corporation <linux-wimax@intel.com>
- * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
- *
- * This header file is for declarations and definitions internal to
- * the WiMAX stack. For public APIs and documentation, see
- * include/net/wimax.h and include/linux/wimax.h.
- */
-
-#ifndef __WIMAX_INTERNAL_H__
-#define __WIMAX_INTERNAL_H__
-#ifdef __KERNEL__
-
-#ifdef pr_fmt
-#undef pr_fmt
-#endif
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/device.h>
-#include <net/wimax.h>
-
-
-/*
- * Decide if a (locked) device is ready for use
- *
- * Before using the device structure, it must be locked
- * (wimax_dev->mutex). As well, most operations need to call this
- * function to check if the state is the right one.
- *
- * An error value will be returned if the state is not the right
- * one. In that case, the caller should not attempt to use the device
- * and just unlock it.
- */
-static inline __must_check
-int wimax_dev_is_ready(struct wimax_dev *wimax_dev)
-{
-	if (wimax_dev->state == __WIMAX_ST_NULL)
-		return -EINVAL;	/* Device is not even registered! */
-	if (wimax_dev->state == WIMAX_ST_DOWN)
-		return -ENOMEDIUM;
-	if (wimax_dev->state == __WIMAX_ST_QUIESCING)
-		return -ESHUTDOWN;
-	return 0;
-}
-
-
-static inline
-void __wimax_state_set(struct wimax_dev *wimax_dev, enum wimax_st state)
-{
-	wimax_dev->state = state;
-}
-void __wimax_state_change(struct wimax_dev *, enum wimax_st);
-
-#ifdef CONFIG_DEBUG_FS
-void wimax_debugfs_add(struct wimax_dev *);
-void wimax_debugfs_rm(struct wimax_dev *);
-#else
-static inline void wimax_debugfs_add(struct wimax_dev *wimax_dev) {}
-static inline void wimax_debugfs_rm(struct wimax_dev *wimax_dev) {}
-#endif
-
-void wimax_id_table_add(struct wimax_dev *);
-struct wimax_dev *wimax_dev_get_by_genl_info(struct genl_info *, int);
-void wimax_id_table_rm(struct wimax_dev *);
-void wimax_id_table_release(void);
-
-int wimax_rfkill_add(struct wimax_dev *);
-void wimax_rfkill_rm(struct wimax_dev *);
-
-/* generic netlink */
-extern struct genl_family wimax_gnl_family;
-
-/* ops */
-int wimax_gnl_doit_msg_from_user(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_reset(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_rfkill(struct sk_buff *skb, struct genl_info *info);
-int wimax_gnl_doit_state_get(struct sk_buff *skb, struct genl_info *info);
-
-#endif /* #ifdef __KERNEL__ */
-#endif /* #ifndef __WIMAX_INTERNAL_H__ */
diff --git a/net/wireless/Kconfig b/net/wireless/Kconfig
index 27026f587fa6..f620acd2a0f5 100644
--- a/net/wireless/Kconfig
+++ b/net/wireless/Kconfig
@@ -21,6 +21,7 @@ config CFG80211
 	tristate "cfg80211 - wireless configuration API"
 	depends on RFKILL || !RFKILL
 	select FW_LOADER
+	select CRC32
 	# may need to update this when certificates are changed and are
 	# using a different algorithm, though right now they shouldn't
 	# (this is here rather than below to allow it to be a module)
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 6a6f2f214c10..e4030f1fbc60 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -141,9 +141,62 @@ static bool cfg80211_edmg_chandef_valid(const struct cfg80211_chan_def *chandef)
 	return true;
 }
 
+static int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width)
+{
+	int mhz;
+
+	switch (chan_width) {
+	case NL80211_CHAN_WIDTH_1:
+		mhz = 1;
+		break;
+	case NL80211_CHAN_WIDTH_2:
+		mhz = 2;
+		break;
+	case NL80211_CHAN_WIDTH_4:
+		mhz = 4;
+		break;
+	case NL80211_CHAN_WIDTH_8:
+		mhz = 8;
+		break;
+	case NL80211_CHAN_WIDTH_16:
+		mhz = 16;
+		break;
+	case NL80211_CHAN_WIDTH_5:
+		mhz = 5;
+		break;
+	case NL80211_CHAN_WIDTH_10:
+		mhz = 10;
+		break;
+	case NL80211_CHAN_WIDTH_20:
+	case NL80211_CHAN_WIDTH_20_NOHT:
+		mhz = 20;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		mhz = 40;
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+	case NL80211_CHAN_WIDTH_80:
+		mhz = 80;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		mhz = 160;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+	return mhz;
+}
+
+static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c)
+{
+	return nl80211_chan_width_to_mhz(c->width);
+}
+
 bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef)
 {
-	u32 control_freq;
+	u32 control_freq, oper_freq;
+	int oper_width, control_width;
 
 	if (!chandef->chan)
 		return false;
@@ -154,11 +207,6 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef)
 	control_freq = chandef->chan->center_freq;
 
 	switch (chandef->width) {
-	case NL80211_CHAN_WIDTH_1:
-	case NL80211_CHAN_WIDTH_2:
-	case NL80211_CHAN_WIDTH_4:
-	case NL80211_CHAN_WIDTH_8:
-	case NL80211_CHAN_WIDTH_16:
 	case NL80211_CHAN_WIDTH_5:
 	case NL80211_CHAN_WIDTH_10:
 	case NL80211_CHAN_WIDTH_20:
@@ -169,6 +217,34 @@ bool cfg80211_chandef_valid(const struct cfg80211_chan_def *chandef)
 		if (chandef->center_freq2)
 			return false;
 		break;
+	case NL80211_CHAN_WIDTH_1:
+	case NL80211_CHAN_WIDTH_2:
+	case NL80211_CHAN_WIDTH_4:
+	case NL80211_CHAN_WIDTH_8:
+	case NL80211_CHAN_WIDTH_16:
+		if (chandef->chan->band != NL80211_BAND_S1GHZ)
+			return false;
+
+		control_freq = ieee80211_channel_to_khz(chandef->chan);
+		oper_freq = ieee80211_chandef_to_khz(chandef);
+		control_width = nl80211_chan_width_to_mhz(
+					ieee80211_s1g_channel_width(
+								chandef->chan));
+		oper_width = cfg80211_chandef_get_width(chandef);
+
+		if (oper_width < 0 || control_width < 0)
+			return false;
+		if (chandef->center_freq2)
+			return false;
+
+		if (control_freq + MHZ_TO_KHZ(control_width) / 2 >
+		    oper_freq + MHZ_TO_KHZ(oper_width) / 2)
+			return false;
+
+		if (control_freq - MHZ_TO_KHZ(control_width) / 2 <
+		    oper_freq - MHZ_TO_KHZ(oper_width) / 2)
+			return false;
+		break;
 	case NL80211_CHAN_WIDTH_40:
 		if (chandef->center_freq1 != control_freq + 10 &&
 		    chandef->center_freq1 != control_freq - 10)
@@ -264,53 +340,6 @@ static void chandef_primary_freqs(const struct cfg80211_chan_def *c,
 	}
 }
 
-static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c)
-{
-	int width;
-
-	switch (c->width) {
-	case NL80211_CHAN_WIDTH_1:
-		width = 1;
-		break;
-	case NL80211_CHAN_WIDTH_2:
-		width = 2;
-		break;
-	case NL80211_CHAN_WIDTH_4:
-		width = 4;
-		break;
-	case NL80211_CHAN_WIDTH_8:
-		width = 8;
-		break;
-	case NL80211_CHAN_WIDTH_16:
-		width = 16;
-		break;
-	case NL80211_CHAN_WIDTH_5:
-		width = 5;
-		break;
-	case NL80211_CHAN_WIDTH_10:
-		width = 10;
-		break;
-	case NL80211_CHAN_WIDTH_20:
-	case NL80211_CHAN_WIDTH_20_NOHT:
-		width = 20;
-		break;
-	case NL80211_CHAN_WIDTH_40:
-		width = 40;
-		break;
-	case NL80211_CHAN_WIDTH_80P80:
-	case NL80211_CHAN_WIDTH_80:
-		width = 80;
-		break;
-	case NL80211_CHAN_WIDTH_160:
-		width = 160;
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return -1;
-	}
-	return width;
-}
-
 const struct cfg80211_chan_def *
 cfg80211_chandef_compatible(const struct cfg80211_chan_def *c1,
 			    const struct cfg80211_chan_def *c2)
@@ -501,10 +530,10 @@ int cfg80211_chandef_dfs_required(struct wiphy *wiphy,
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_AP_VLAN:
-	case NL80211_IFTYPE_WDS:
 	case NL80211_IFTYPE_P2P_DEVICE:
 	case NL80211_IFTYPE_NAN:
 		break;
+	case NL80211_IFTYPE_WDS:
 	case NL80211_IFTYPE_UNSPECIFIED:
 	case NUM_NL80211_IFTYPES:
 		WARN_ON(1);
@@ -648,12 +677,12 @@ bool cfg80211_beaconing_iface_active(struct wireless_dev *wdev)
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_AP_VLAN:
-	case NL80211_IFTYPE_WDS:
 	case NL80211_IFTYPE_P2P_DEVICE:
 	/* Can NAN type be considered as beaconing interface? */
 	case NL80211_IFTYPE_NAN:
 		break;
 	case NL80211_IFTYPE_UNSPECIFIED:
+	case NL80211_IFTYPE_WDS:
 	case NUM_NL80211_IFTYPES:
 		WARN_ON(1);
 	}
@@ -1295,12 +1324,12 @@ cfg80211_get_chan_state(struct wireless_dev *wdev,
 		break;
 	case NL80211_IFTYPE_MONITOR:
 	case NL80211_IFTYPE_AP_VLAN:
-	case NL80211_IFTYPE_WDS:
 	case NL80211_IFTYPE_P2P_DEVICE:
 	case NL80211_IFTYPE_NAN:
 		/* these interface types don't really have a channel */
 		return;
 	case NL80211_IFTYPE_UNSPECIFIED:
+	case NL80211_IFTYPE_WDS:
 	case NUM_NL80211_IFTYPES:
 		WARN_ON(1);
 	}
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 354b0ccbdc24..4b1f35e976e7 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -236,7 +236,9 @@ void cfg80211_stop_p2p_device(struct cfg80211_registered_device *rdev,
 	rdev->opencount--;
 
 	if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
-		if (WARN_ON(!rdev->scan_req->notified))
+		if (WARN_ON(!rdev->scan_req->notified &&
+			    (!rdev->int_scan_req ||
+			     !rdev->int_scan_req->notified)))
 			rdev->scan_req->info.aborted = true;
 		___cfg80211_scan_done(rdev, false);
 	}
@@ -629,10 +631,8 @@ static int wiphy_verify_combinations(struct wiphy *wiphy)
 				return -EINVAL;
 		}
 
-#ifndef CONFIG_WIRELESS_WDS
 		if (WARN_ON(all_iftypes & BIT(NL80211_IFTYPE_WDS)))
 			return -EINVAL;
-#endif
 
 		/* You can't even choose that many! */
 		if (WARN_ON(cnt < c->max_interfaces))
@@ -673,10 +673,8 @@ int wiphy_register(struct wiphy *wiphy)
 		     !(wiphy->nan_supported_bands & BIT(NL80211_BAND_2GHZ)))))
 		return -EINVAL;
 
-#ifndef CONFIG_WIRELESS_WDS
 	if (WARN_ON(wiphy->interface_modes & BIT(NL80211_IFTYPE_WDS)))
 		return -EINVAL;
-#endif
 
 	if (WARN_ON(wiphy->pmsr_capa && !wiphy->pmsr_capa->ftm.supported))
 		return -EINVAL;
@@ -1200,9 +1198,6 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 	case NL80211_IFTYPE_OCB:
 		__cfg80211_leave_ocb(rdev, dev);
 		break;
-	case NL80211_IFTYPE_WDS:
-		/* must be handled by mac80211/driver, has no APIs */
-		break;
 	case NL80211_IFTYPE_P2P_DEVICE:
 	case NL80211_IFTYPE_NAN:
 		/* cannot happen, has no netdev */
@@ -1212,6 +1207,7 @@ void __cfg80211_leave(struct cfg80211_registered_device *rdev,
 		/* nothing to do */
 		break;
 	case NL80211_IFTYPE_UNSPECIFIED:
+	case NL80211_IFTYPE_WDS:
 	case NUM_NL80211_IFTYPES:
 		/* invalid */
 		break;
@@ -1248,8 +1244,7 @@ void cfg80211_stop_iface(struct wiphy *wiphy, struct wireless_dev *wdev,
 }
 EXPORT_SYMBOL(cfg80211_stop_iface);
 
-void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
-			struct wireless_dev *wdev)
+void cfg80211_init_wdev(struct wireless_dev *wdev)
 {
 	mutex_init(&wdev->mtx);
 	INIT_LIST_HEAD(&wdev->event_list);
@@ -1260,6 +1255,30 @@ void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
 	spin_lock_init(&wdev->pmsr_lock);
 	INIT_WORK(&wdev->pmsr_free_wk, cfg80211_pmsr_free_wk);
 
+#ifdef CONFIG_CFG80211_WEXT
+	wdev->wext.default_key = -1;
+	wdev->wext.default_mgmt_key = -1;
+	wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
+#endif
+
+	if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT)
+		wdev->ps = true;
+	else
+		wdev->ps = false;
+	/* allow mac80211 to determine the timeout */
+	wdev->ps_timeout = -1;
+
+	if ((wdev->iftype == NL80211_IFTYPE_STATION ||
+	     wdev->iftype == NL80211_IFTYPE_P2P_CLIENT ||
+	     wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr)
+		wdev->netdev->priv_flags |= IFF_DONT_BRIDGE;
+
+	INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk);
+}
+
+void cfg80211_register_wdev(struct cfg80211_registered_device *rdev,
+			    struct wireless_dev *wdev)
+{
 	/*
 	 * We get here also when the interface changes network namespaces,
 	 * as it's registered into the new one, but we don't want it to
@@ -1293,6 +1312,11 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 	switch (state) {
 	case NETDEV_POST_INIT:
 		SET_NETDEV_DEVTYPE(dev, &wiphy_type);
+		wdev->netdev = dev;
+		/* can only change netns with wiphy */
+		dev->features |= NETIF_F_NETNS_LOCAL;
+
+		cfg80211_init_wdev(wdev);
 		break;
 	case NETDEV_REGISTER:
 		/*
@@ -1300,35 +1324,12 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		 * called within code protected by it when interfaces
 		 * are added with nl80211.
 		 */
-		/* can only change netns with wiphy */
-		dev->features |= NETIF_F_NETNS_LOCAL;
-
 		if (sysfs_create_link(&dev->dev.kobj, &rdev->wiphy.dev.kobj,
 				      "phy80211")) {
 			pr_err("failed to add phy80211 symlink to netdev!\n");
 		}
-		wdev->netdev = dev;
-#ifdef CONFIG_CFG80211_WEXT
-		wdev->wext.default_key = -1;
-		wdev->wext.default_mgmt_key = -1;
-		wdev->wext.connect.auth_type = NL80211_AUTHTYPE_AUTOMATIC;
-#endif
-
-		if (wdev->wiphy->flags & WIPHY_FLAG_PS_ON_BY_DEFAULT)
-			wdev->ps = true;
-		else
-			wdev->ps = false;
-		/* allow mac80211 to determine the timeout */
-		wdev->ps_timeout = -1;
-
-		if ((wdev->iftype == NL80211_IFTYPE_STATION ||
-		     wdev->iftype == NL80211_IFTYPE_P2P_CLIENT ||
-		     wdev->iftype == NL80211_IFTYPE_ADHOC) && !wdev->use_4addr)
-			dev->priv_flags |= IFF_DONT_BRIDGE;
-
-		INIT_WORK(&wdev->disconnect_wk, cfg80211_autodisconnect_wk);
 
-		cfg80211_init_wdev(rdev, wdev);
+		cfg80211_register_wdev(rdev, wdev);
 		break;
 	case NETDEV_GOING_DOWN:
 		cfg80211_leave(rdev, wdev);
@@ -1336,7 +1337,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 	case NETDEV_DOWN:
 		cfg80211_update_iface_num(rdev, wdev->iftype, -1);
 		if (rdev->scan_req && rdev->scan_req->wdev == wdev) {
-			if (WARN_ON(!rdev->scan_req->notified))
+			if (WARN_ON(!rdev->scan_req->notified &&
+				    (!rdev->int_scan_req ||
+				     !rdev->int_scan_req->notified)))
 				rdev->scan_req->info.aborted = true;
 			___cfg80211_scan_done(rdev, false);
 		}
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 67b0389fca4d..7df91f940212 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -3,7 +3,7 @@
  * Wireless configuration interface internals.
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 #ifndef __NET_WIRELESS_CORE_H
 #define __NET_WIRELESS_CORE_H
@@ -72,6 +72,7 @@ struct cfg80211_registered_device {
 	u32 bss_generation;
 	u32 bss_entries;
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
+	struct cfg80211_scan_request *int_scan_req;
 	struct sk_buff *scan_msg;
 	struct list_head sched_scan_req_list;
 	time64_t suspend_at;
@@ -208,8 +209,9 @@ struct wiphy *wiphy_idx_to_wiphy(int wiphy_idx);
 int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 			  struct net *net);
 
-void cfg80211_init_wdev(struct cfg80211_registered_device *rdev,
-			struct wireless_dev *wdev);
+void cfg80211_init_wdev(struct wireless_dev *wdev);
+void cfg80211_register_wdev(struct cfg80211_registered_device *rdev,
+			    struct wireless_dev *wdev);
 
 static inline void wdev_lock(struct wireless_dev *wdev)
 	__acquires(wdev)
@@ -431,6 +433,8 @@ void cfg80211_sme_abandon_assoc(struct wireless_dev *wdev);
 
 /* internal helpers */
 bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher);
+bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev,
+			    int key_idx, bool pairwise);
 int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 				   struct key_params *params, int key_idx,
 				   bool pairwise, const u8 *mac_addr);
@@ -457,6 +461,8 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev);
 bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range,
 				u32 center_freq_khz, u32 bw_khz);
 
+int cfg80211_scan(struct cfg80211_registered_device *rdev);
+
 extern struct work_struct cfg80211_disconnect_work;
 
 /**
@@ -466,8 +472,8 @@ extern struct work_struct cfg80211_disconnect_work;
  *
  * Checks if chandef is usable and we can/need start CAC on such channel.
  *
- * Return: Return true if all channels available and at least
- *	   one channel require CAC (NL80211_DFS_USABLE)
+ * Return: true if all channels available and at least
+ *	   one channel requires CAC (NL80211_DFS_USABLE)
  */
 bool cfg80211_chandef_dfs_usable(struct wiphy *wiphy,
 				 const struct cfg80211_chan_def *chandef);
diff --git a/net/wireless/lib80211.c b/net/wireless/lib80211.c
index cc7b9fd5c166..d66a913027e0 100644
--- a/net/wireless/lib80211.c
+++ b/net/wireless/lib80211.c
@@ -26,8 +26,6 @@
 
 #include <net/lib80211.h>
 
-#define DRV_NAME        "lib80211"
-
 #define DRV_DESCRIPTION	"common routines for IEEE802.11 drivers"
 
 MODULE_DESCRIPTION(DRV_DESCRIPTION);
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index db7333e20dd7..e1e90761dc00 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -4,7 +4,7 @@
  *
  * Copyright (c) 2009, Jouni Malinen <j@w1.fi>
  * Copyright (c) 2015		Intel Deutschland GmbH
- * Copyright (C) 2019 Intel Corporation
+ * Copyright (C) 2019-2020 Intel Corporation
  */
 
 #include <linux/kernel.h>
@@ -30,6 +30,15 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
 	struct cfg80211_connect_resp_params cr;
+	const u8 *resp_ie = mgmt->u.assoc_resp.variable;
+	size_t resp_ie_len = len - offsetof(struct ieee80211_mgmt,
+					    u.assoc_resp.variable);
+
+	if (bss->channel->band == NL80211_BAND_S1GHZ) {
+		resp_ie = (u8 *)&mgmt->u.s1g_assoc_resp.variable;
+		resp_ie_len = len - offsetof(struct ieee80211_mgmt,
+					     u.s1g_assoc_resp.variable);
+	}
 
 	memset(&cr, 0, sizeof(cr));
 	cr.status = (int)le16_to_cpu(mgmt->u.assoc_resp.status_code);
@@ -37,9 +46,8 @@ void cfg80211_rx_assoc_resp(struct net_device *dev, struct cfg80211_bss *bss,
 	cr.bss = bss;
 	cr.req_ie = req_ies;
 	cr.req_ie_len = req_ies_len;
-	cr.resp_ie = mgmt->u.assoc_resp.variable;
-	cr.resp_ie_len =
-		len - offsetof(struct ieee80211_mgmt, u.assoc_resp.variable);
+	cr.resp_ie = resp_ie;
+	cr.resp_ie_len = resp_ie_len;
 	cr.timeout_reason = NL80211_TIMEOUT_UNSPECIFIED;
 
 	trace_cfg80211_send_rx_assoc(dev, bss);
@@ -73,7 +81,8 @@ static void cfg80211_process_auth(struct wireless_dev *wdev,
 }
 
 static void cfg80211_process_deauth(struct wireless_dev *wdev,
-				    const u8 *buf, size_t len)
+				    const u8 *buf, size_t len,
+				    bool reconnect)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
@@ -81,7 +90,7 @@ static void cfg80211_process_deauth(struct wireless_dev *wdev,
 	u16 reason_code = le16_to_cpu(mgmt->u.deauth.reason_code);
 	bool from_ap = !ether_addr_equal(mgmt->sa, wdev->netdev->dev_addr);
 
-	nl80211_send_deauth(rdev, wdev->netdev, buf, len, GFP_KERNEL);
+	nl80211_send_deauth(rdev, wdev->netdev, buf, len, reconnect, GFP_KERNEL);
 
 	if (!wdev->current_bss ||
 	    !ether_addr_equal(wdev->current_bss->pub.bssid, bssid))
@@ -92,7 +101,8 @@ static void cfg80211_process_deauth(struct wireless_dev *wdev,
 }
 
 static void cfg80211_process_disassoc(struct wireless_dev *wdev,
-				      const u8 *buf, size_t len)
+				      const u8 *buf, size_t len,
+				      bool reconnect)
 {
 	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)buf;
@@ -100,7 +110,8 @@ static void cfg80211_process_disassoc(struct wireless_dev *wdev,
 	u16 reason_code = le16_to_cpu(mgmt->u.disassoc.reason_code);
 	bool from_ap = !ether_addr_equal(mgmt->sa, wdev->netdev->dev_addr);
 
-	nl80211_send_disassoc(rdev, wdev->netdev, buf, len, GFP_KERNEL);
+	nl80211_send_disassoc(rdev, wdev->netdev, buf, len, reconnect,
+			      GFP_KERNEL);
 
 	if (WARN_ON(!wdev->current_bss ||
 		    !ether_addr_equal(wdev->current_bss->pub.bssid, bssid)))
@@ -125,9 +136,9 @@ void cfg80211_rx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len)
 	if (ieee80211_is_auth(mgmt->frame_control))
 		cfg80211_process_auth(wdev, buf, len);
 	else if (ieee80211_is_deauth(mgmt->frame_control))
-		cfg80211_process_deauth(wdev, buf, len);
+		cfg80211_process_deauth(wdev, buf, len, false);
 	else if (ieee80211_is_disassoc(mgmt->frame_control))
-		cfg80211_process_disassoc(wdev, buf, len);
+		cfg80211_process_disassoc(wdev, buf, len, false);
 }
 EXPORT_SYMBOL(cfg80211_rx_mlme_mgmt);
 
@@ -172,22 +183,23 @@ void cfg80211_abandon_assoc(struct net_device *dev, struct cfg80211_bss *bss)
 }
 EXPORT_SYMBOL(cfg80211_abandon_assoc);
 
-void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len)
+void cfg80211_tx_mlme_mgmt(struct net_device *dev, const u8 *buf, size_t len,
+			   bool reconnect)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct ieee80211_mgmt *mgmt = (void *)buf;
 
 	ASSERT_WDEV_LOCK(wdev);
 
-	trace_cfg80211_tx_mlme_mgmt(dev, buf, len);
+	trace_cfg80211_tx_mlme_mgmt(dev, buf, len, reconnect);
 
 	if (WARN_ON(len < 2))
 		return;
 
 	if (ieee80211_is_deauth(mgmt->frame_control))
-		cfg80211_process_deauth(wdev, buf, len);
+		cfg80211_process_deauth(wdev, buf, len, reconnect);
 	else
-		cfg80211_process_disassoc(wdev, buf, len);
+		cfg80211_process_disassoc(wdev, buf, len, reconnect);
 }
 EXPORT_SYMBOL(cfg80211_tx_mlme_mgmt);
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 7fd45f6ddb05..775d0c4d86c3 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -209,14 +209,23 @@ static int validate_beacon_head(const struct nlattr *attr,
 	unsigned int len = nla_len(attr);
 	const struct element *elem;
 	const struct ieee80211_mgmt *mgmt = (void *)data;
-	unsigned int fixedlen = offsetof(struct ieee80211_mgmt,
-					 u.beacon.variable);
+	bool s1g_bcn = ieee80211_is_s1g_beacon(mgmt->frame_control);
+	unsigned int fixedlen, hdrlen;
+
+	if (s1g_bcn) {
+		fixedlen = offsetof(struct ieee80211_ext,
+				    u.s1g_beacon.variable);
+		hdrlen = offsetof(struct ieee80211_ext, u.s1g_beacon);
+	} else {
+		fixedlen = offsetof(struct ieee80211_mgmt,
+				    u.beacon.variable);
+		hdrlen = offsetof(struct ieee80211_mgmt, u.beacon);
+	}
 
 	if (len < fixedlen)
 		goto err;
 
-	if (ieee80211_hdrlen(mgmt->frame_control) !=
-	    offsetof(struct ieee80211_mgmt, u.beacon))
+	if (ieee80211_hdrlen(mgmt->frame_control) != hdrlen)
 		goto err;
 
 	data += fixedlen;
@@ -320,6 +329,13 @@ he_obss_pd_policy[NL80211_HE_OBSS_PD_ATTR_MAX + 1] = {
 		NLA_POLICY_RANGE(NLA_U8, 1, 20),
 	[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET] =
 		NLA_POLICY_RANGE(NLA_U8, 1, 20),
+	[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET] =
+		NLA_POLICY_RANGE(NLA_U8, 1, 20),
+	[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP] =
+		NLA_POLICY_EXACT_LEN(8),
+	[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP] =
+		NLA_POLICY_EXACT_LEN(8),
+	[NL80211_HE_OBSS_PD_ATTR_SR_CTRL] = { .type = NLA_U8 },
 };
 
 static const struct nla_policy
@@ -336,6 +352,13 @@ static const struct nla_policy nl80211_txattr_policy[NL80211_TXRATE_MAX + 1] = {
 				.len = NL80211_MAX_SUPP_HT_RATES },
 	[NL80211_TXRATE_VHT] = NLA_POLICY_EXACT_LEN_WARN(sizeof(struct nl80211_txrate_vht)),
 	[NL80211_TXRATE_GI] = { .type = NLA_U8 },
+	[NL80211_TXRATE_HE] = NLA_POLICY_EXACT_LEN(sizeof(struct nl80211_txrate_he)),
+	[NL80211_TXRATE_HE_GI] =  NLA_POLICY_RANGE(NLA_U8,
+						   NL80211_RATE_INFO_HE_GI_0_8,
+						   NL80211_RATE_INFO_HE_GI_3_2),
+	[NL80211_TXRATE_HE_LTF] = NLA_POLICY_RANGE(NLA_U8,
+						   NL80211_RATE_INFO_HE_1XLTF,
+						   NL80211_RATE_INFO_HE_4XLTF),
 };
 
 static const struct nla_policy
@@ -360,6 +383,34 @@ nl80211_tid_config_attr_policy[NL80211_TID_CONFIG_ATTR_MAX + 1] = {
 			NLA_POLICY_NESTED(nl80211_txattr_policy),
 };
 
+static const struct nla_policy
+nl80211_fils_discovery_policy[NL80211_FILS_DISCOVERY_ATTR_MAX + 1] = {
+	[NL80211_FILS_DISCOVERY_ATTR_INT_MIN] = NLA_POLICY_MAX(NLA_U32, 10000),
+	[NL80211_FILS_DISCOVERY_ATTR_INT_MAX] = NLA_POLICY_MAX(NLA_U32, 10000),
+	NLA_POLICY_RANGE(NLA_BINARY,
+			 NL80211_FILS_DISCOVERY_TMPL_MIN_LEN,
+			 IEEE80211_MAX_DATA_LEN),
+};
+
+static const struct nla_policy
+nl80211_unsol_bcast_probe_resp_policy[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX + 1] = {
+	[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT] = NLA_POLICY_MAX(NLA_U32, 20),
+	[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL] = { .type = NLA_BINARY,
+						       .len = IEEE80211_MAX_DATA_LEN }
+};
+
+static const struct nla_policy
+sar_specs_policy[NL80211_SAR_ATTR_SPECS_MAX + 1] = {
+	[NL80211_SAR_ATTR_SPECS_POWER] = { .type = NLA_S32 },
+	[NL80211_SAR_ATTR_SPECS_RANGE_INDEX] = {.type = NLA_U32 },
+};
+
+static const struct nla_policy
+sar_policy[NL80211_SAR_ATTR_MAX + 1] = {
+	[NL80211_SAR_ATTR_TYPE] = NLA_POLICY_MAX(NLA_U32, NUM_NL80211_SAR_TYPE),
+	[NL80211_SAR_ATTR_SPECS] = NLA_POLICY_NESTED_ARRAY(sar_specs_policy),
+};
+
 static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD },
 	[NL80211_ATTR_WIPHY] = { .type = NLA_U32 },
@@ -539,7 +590,10 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_BG_SCAN_PERIOD] = { .type = NLA_U16 },
 	[NL80211_ATTR_WDEV] = { .type = NLA_U64 },
 	[NL80211_ATTR_USER_REG_HINT_TYPE] = { .type = NLA_U32 },
-	[NL80211_ATTR_AUTH_DATA] = { .type = NLA_BINARY, },
+
+	/* need to include at least Auth Transaction and Status Code */
+	[NL80211_ATTR_AUTH_DATA] = NLA_POLICY_MIN_LEN(4),
+
 	[NL80211_ATTR_VHT_CAPABILITY] = NLA_POLICY_EXACT_LEN_WARN(NL80211_VHT_CAPABILITY_LEN),
 	[NL80211_ATTR_SCAN_FLAGS] = { .type = NLA_U32 },
 	[NL80211_ATTR_P2P_CTWINDOW] = NLA_POLICY_MAX(NLA_U8, 127),
@@ -561,23 +615,30 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY,
 				  .len = IEEE80211_MAX_DATA_LEN },
 	[NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 },
-	[NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 },
+	[NL80211_ATTR_MAX_CRIT_PROT_DURATION] =
+		NLA_POLICY_MAX(NLA_U16, NL80211_CRIT_PROTO_MAX_DURATION),
 	[NL80211_ATTR_PEER_AID] =
 		NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID),
 	[NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 },
 	[NL80211_ATTR_CH_SWITCH_BLOCK_TX] = { .type = NLA_FLAG },
 	[NL80211_ATTR_CSA_IES] = { .type = NLA_NESTED },
-	[NL80211_ATTR_CSA_C_OFF_BEACON] = { .type = NLA_BINARY },
-	[NL80211_ATTR_CSA_C_OFF_PRESP] = { .type = NLA_BINARY },
-	[NL80211_ATTR_STA_SUPPORTED_CHANNELS] = { .type = NLA_BINARY },
-	[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] = { .type = NLA_BINARY },
+	[NL80211_ATTR_CNTDWN_OFFS_BEACON] = { .type = NLA_BINARY },
+	[NL80211_ATTR_CNTDWN_OFFS_PRESP] = { .type = NLA_BINARY },
+	[NL80211_ATTR_STA_SUPPORTED_CHANNELS] = NLA_POLICY_MIN_LEN(2),
+	/*
+	 * The value of the Length field of the Supported Operating
+	 * Classes element is between 2 and 253.
+	 */
+	[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES] =
+		NLA_POLICY_RANGE(NLA_BINARY, 2, 253),
 	[NL80211_ATTR_HANDLE_DFS] = { .type = NLA_FLAG },
 	[NL80211_ATTR_OPMODE_NOTIF] = { .type = NLA_U8 },
 	[NL80211_ATTR_VENDOR_ID] = { .type = NLA_U32 },
 	[NL80211_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 },
 	[NL80211_ATTR_VENDOR_DATA] = { .type = NLA_BINARY },
-	[NL80211_ATTR_QOS_MAP] = { .type = NLA_BINARY,
-				   .len = IEEE80211_QOS_MAP_LEN_MAX },
+	[NL80211_ATTR_QOS_MAP] = NLA_POLICY_RANGE(NLA_BINARY,
+						  IEEE80211_QOS_MAP_LEN_MIN,
+						  IEEE80211_QOS_MAP_LEN_MAX),
 	[NL80211_ATTR_MAC_HINT] = NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN),
 	[NL80211_ATTR_WIPHY_FREQ_HINT] = { .type = NLA_U32 },
 	[NL80211_ATTR_TDLS_PEER_CAPABILITY] = { .type = NLA_U32 },
@@ -625,15 +686,17 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 					.len = FILS_ERP_MAX_RRK_LEN },
 	[NL80211_ATTR_FILS_CACHE_ID] = NLA_POLICY_EXACT_LEN_WARN(2),
 	[NL80211_ATTR_PMK] = { .type = NLA_BINARY, .len = PMK_MAX_LEN },
+	[NL80211_ATTR_PMKR0_NAME] = NLA_POLICY_EXACT_LEN(WLAN_PMK_NAME_LEN),
 	[NL80211_ATTR_SCHED_SCAN_MULTI] = { .type = NLA_FLAG },
 	[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT] = { .type = NLA_FLAG },
 
 	[NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 },
 	[NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 },
 	[NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 },
-	[NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY,
-					 .len = NL80211_HE_MAX_CAPABILITY_LEN },
-
+	[NL80211_ATTR_HE_CAPABILITY] =
+		NLA_POLICY_RANGE(NLA_BINARY,
+				 NL80211_HE_MIN_CAPABILITY_LEN,
+				 NL80211_HE_MAX_CAPABILITY_LEN),
 	[NL80211_ATTR_FTM_RESPONDER] =
 		NLA_POLICY_NESTED(nl80211_ftm_responder_policy),
 	[NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1),
@@ -654,10 +717,21 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_RECEIVE_MULTICAST] = { .type = NLA_FLAG },
 	[NL80211_ATTR_WIPHY_FREQ_OFFSET] = NLA_POLICY_RANGE(NLA_U32, 0, 999),
 	[NL80211_ATTR_SCAN_FREQ_KHZ] = { .type = NLA_NESTED },
-	[NL80211_ATTR_HE_6GHZ_CAPABILITY] = {
-		.type = NLA_EXACT_LEN,
-		.len = sizeof(struct ieee80211_he_6ghz_capa),
-	},
+	[NL80211_ATTR_HE_6GHZ_CAPABILITY] =
+		NLA_POLICY_EXACT_LEN(sizeof(struct ieee80211_he_6ghz_capa)),
+	[NL80211_ATTR_FILS_DISCOVERY] =
+		NLA_POLICY_NESTED(nl80211_fils_discovery_policy),
+	[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP] =
+		NLA_POLICY_NESTED(nl80211_unsol_bcast_probe_resp_policy),
+	[NL80211_ATTR_S1G_CAPABILITY] =
+		NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
+	[NL80211_ATTR_S1G_CAPABILITY_MASK] =
+		NLA_POLICY_EXACT_LEN(IEEE80211_S1G_CAPABILITY_LEN),
+	[NL80211_ATTR_SAE_PWE] =
+		NLA_POLICY_RANGE(NLA_U8, NL80211_SAE_PWE_HUNT_AND_PECK,
+				 NL80211_SAE_PWE_BOTH),
+	[NL80211_ATTR_RECONNECT_REQUESTED] = { .type = NLA_REJECT },
+	[NL80211_ATTR_SAR_SPEC] = NLA_POLICY_NESTED(sar_policy),
 };
 
 /* policy for the key attributes */
@@ -703,7 +777,7 @@ nl80211_wowlan_tcp_policy[NUM_NL80211_WOWLAN_TCP] = {
 	[NL80211_WOWLAN_TCP_DST_MAC] = NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN),
 	[NL80211_WOWLAN_TCP_SRC_PORT] = { .type = NLA_U16 },
 	[NL80211_WOWLAN_TCP_DST_PORT] = { .type = NLA_U16 },
-	[NL80211_WOWLAN_TCP_DATA_PAYLOAD] = { .type = NLA_MIN_LEN, .len = 1 },
+	[NL80211_WOWLAN_TCP_DATA_PAYLOAD] = NLA_POLICY_MIN_LEN(1),
 	[NL80211_WOWLAN_TCP_DATA_PAYLOAD_SEQ] = {
 		.len = sizeof(struct nl80211_wowlan_tcp_data_seq)
 	},
@@ -711,8 +785,8 @@ nl80211_wowlan_tcp_policy[NUM_NL80211_WOWLAN_TCP] = {
 		.len = sizeof(struct nl80211_wowlan_tcp_data_token)
 	},
 	[NL80211_WOWLAN_TCP_DATA_INTERVAL] = { .type = NLA_U32 },
-	[NL80211_WOWLAN_TCP_WAKE_PAYLOAD] = { .type = NLA_MIN_LEN, .len = 1 },
-	[NL80211_WOWLAN_TCP_WAKE_MASK] = { .type = NLA_MIN_LEN, .len = 1 },
+	[NL80211_WOWLAN_TCP_WAKE_PAYLOAD] = NLA_POLICY_MIN_LEN(1),
+	[NL80211_WOWLAN_TCP_WAKE_MASK] = NLA_POLICY_MIN_LEN(1),
 };
 #endif /* CONFIG_PM */
 
@@ -738,7 +812,7 @@ nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = {
 		.type = NLA_BINARY,
 		.len = NL80211_KCK_EXT_LEN
 	},
-	[NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN_WARN(NL80211_REPLAY_CTR_LEN),
+	[NL80211_REKEY_DATA_REPLAY_CTR] = NLA_POLICY_EXACT_LEN(NL80211_REPLAY_CTR_LEN),
 	[NL80211_REKEY_DATA_AKM] = { .type = NLA_U32 },
 };
 
@@ -778,7 +852,8 @@ nl80211_bss_select_policy[NL80211_BSS_SELECT_ATTR_MAX + 1] = {
 /* policy for NAN function attributes */
 static const struct nla_policy
 nl80211_nan_func_policy[NL80211_NAN_FUNC_ATTR_MAX + 1] = {
-	[NL80211_NAN_FUNC_TYPE] = { .type = NLA_U8 },
+	[NL80211_NAN_FUNC_TYPE] =
+		NLA_POLICY_MAX(NLA_U8, NL80211_NAN_FUNC_MAX_TYPE),
 	[NL80211_NAN_FUNC_SERVICE_ID] = {
 				    .len = NL80211_NAN_FUNC_SERVICE_ID_LEN },
 	[NL80211_NAN_FUNC_PUBLISH_TYPE] = { .type = NLA_U8 },
@@ -926,6 +1001,8 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy,
 	if (!large && chan->flags &
 	    (IEEE80211_CHAN_NO_10MHZ | IEEE80211_CHAN_NO_20MHZ))
 		return 0;
+	if (!large && chan->freq_offset)
+		return 0;
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_FREQ,
 			chan->center_freq))
@@ -992,6 +1069,21 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy,
 		if ((chan->flags & IEEE80211_CHAN_NO_HE) &&
 		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_HE))
 			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_1MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_1MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_2MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_2MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_4MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_4MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_8MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_8MHZ))
+			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_16MHZ) &&
+		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_16MHZ))
+			goto nla_put_failure;
 	}
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
@@ -1603,7 +1695,8 @@ nl80211_send_iftype_data(struct sk_buff *msg,
 }
 
 static int nl80211_send_band_rateinfo(struct sk_buff *msg,
-				      struct ieee80211_supported_band *sband)
+				      struct ieee80211_supported_band *sband,
+				      bool large)
 {
 	struct nlattr *nl_rates, *nl_rate;
 	struct ieee80211_rate *rate;
@@ -1631,7 +1724,7 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg,
 			 sband->vht_cap.cap)))
 		return -ENOBUFS;
 
-	if (sband->n_iftype_data) {
+	if (large && sband->n_iftype_data) {
 		struct nlattr *nl_iftype_data =
 			nla_nest_start_noflag(msg,
 					      NL80211_BAND_ATTR_IFTYPE_DATA);
@@ -1659,7 +1752,7 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg,
 	}
 
 	/* add EDMG info */
-	if (sband->edmg_cap.channels &&
+	if (large && sband->edmg_cap.channels &&
 	    (nla_put_u8(msg, NL80211_BAND_ATTR_EDMG_CHANNELS,
 		       sband->edmg_cap.channels) ||
 	    nla_put_u8(msg, NL80211_BAND_ATTR_EDMG_BW_CONFIG,
@@ -1806,7 +1899,6 @@ static int nl80211_add_commands_unsplit(struct cfg80211_registered_device *rdev,
 		if (nla_put_u32(msg, i, NL80211_CMD_SET_CHANNEL))
 			goto nla_put_failure;
 	}
-	CMD(set_wds_peer, SET_WDS_PEER);
 	if (rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_TDLS) {
 		CMD(tdls_mgmt, TDLS_MGMT);
 		CMD(tdls_oper, TDLS_OPER);
@@ -2016,6 +2108,56 @@ fail:
 	return -ENOBUFS;
 }
 
+static int
+nl80211_put_sar_specs(struct cfg80211_registered_device *rdev,
+		      struct sk_buff *msg)
+{
+	struct nlattr *sar_capa, *specs, *sub_freq_range;
+	u8 num_freq_ranges;
+	int i;
+
+	if (!rdev->wiphy.sar_capa)
+		return 0;
+
+	num_freq_ranges = rdev->wiphy.sar_capa->num_freq_ranges;
+
+	sar_capa = nla_nest_start(msg, NL80211_ATTR_SAR_SPEC);
+	if (!sar_capa)
+		return -ENOSPC;
+
+	if (nla_put_u32(msg, NL80211_SAR_ATTR_TYPE, rdev->wiphy.sar_capa->type))
+		goto fail;
+
+	specs = nla_nest_start(msg, NL80211_SAR_ATTR_SPECS);
+	if (!specs)
+		goto fail;
+
+	/* report supported freq_ranges */
+	for (i = 0; i < num_freq_ranges; i++) {
+		sub_freq_range = nla_nest_start(msg, i + 1);
+		if (!sub_freq_range)
+			goto fail;
+
+		if (nla_put_u32(msg, NL80211_SAR_ATTR_SPECS_START_FREQ,
+				rdev->wiphy.sar_capa->freq_ranges[i].start_freq))
+			goto fail;
+
+		if (nla_put_u32(msg, NL80211_SAR_ATTR_SPECS_END_FREQ,
+				rdev->wiphy.sar_capa->freq_ranges[i].end_freq))
+			goto fail;
+
+		nla_nest_end(msg, sub_freq_range);
+	}
+
+	nla_nest_end(msg, specs);
+	nla_nest_end(msg, sar_capa);
+
+	return 0;
+fail:
+	nla_nest_cancel(msg, sar_capa);
+	return -ENOBUFS;
+}
+
 struct nl80211_dump_wiphy_state {
 	s64 filter_wiphy;
 	long start;
@@ -2077,13 +2219,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		    nla_put_u16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN,
 				rdev->wiphy.max_sched_scan_ie_len) ||
 		    nla_put_u8(msg, NL80211_ATTR_MAX_MATCH_SETS,
-			       rdev->wiphy.max_match_sets) ||
-		    nla_put_u32(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS,
-				rdev->wiphy.max_sched_scan_plans) ||
-		    nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL,
-				rdev->wiphy.max_sched_scan_plan_interval) ||
-		    nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS,
-				rdev->wiphy.max_sched_scan_plan_iterations))
+			       rdev->wiphy.max_match_sets))
 			goto nla_put_failure;
 
 		if ((rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) &&
@@ -2173,6 +2309,10 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		     band < NUM_NL80211_BANDS; band++) {
 			struct ieee80211_supported_band *sband;
 
+			/* omit higher bands for ancient software */
+			if (band > NL80211_BAND_5GHZ && !state->split)
+				break;
+
 			sband = rdev->wiphy.bands[band];
 
 			if (!sband)
@@ -2184,7 +2324,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 
 			switch (state->chan_start) {
 			case 0:
-				if (nl80211_send_band_rateinfo(msg, sband))
+				if (nl80211_send_band_rateinfo(msg, sband,
+							       state->split))
 					goto nla_put_failure;
 				state->chan_start++;
 				if (state->split)
@@ -2266,6 +2407,8 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			CMD(set_multicast_to_unicast, SET_MULTICAST_TO_UNICAST);
 			CMD(update_connect_params, UPDATE_CONNECT_PARAMS);
 			CMD(update_ft_ies, UPDATE_FT_IES);
+			if (rdev->wiphy.sar_capa)
+				CMD(set_sar_specs, SET_SAR_SPECS);
 		}
 #undef CMD
 
@@ -2286,8 +2429,6 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		    nla_put_flag(msg, NL80211_ATTR_OFFCHANNEL_TX_OK))
 			goto nla_put_failure;
 
-		if (nl80211_send_mgmt_stypes(msg, mgmt_stypes))
-			goto nla_put_failure;
 		state->split_start++;
 		if (state->split)
 			break;
@@ -2355,9 +2496,23 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 		 * case we'll continue with more data in the next round,
 		 * but break unconditionally so unsplit data stops here.
 		 */
-		state->split_start++;
+		if (state->split)
+			state->split_start++;
+		else
+			state->split_start = 0;
 		break;
 	case 9:
+		if (nl80211_send_mgmt_stypes(msg, mgmt_stypes))
+			goto nla_put_failure;
+
+		if (nla_put_u32(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS,
+				rdev->wiphy.max_sched_scan_plans) ||
+		    nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL,
+				rdev->wiphy.max_sched_scan_plan_interval) ||
+		    nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS,
+				rdev->wiphy.max_sched_scan_plan_iterations))
+			goto nla_put_failure;
+
 		if (rdev->wiphy.extended_capabilities &&
 		    (nla_put(msg, NL80211_ATTR_EXT_CAPA,
 			     rdev->wiphy.extended_capabilities_len,
@@ -2579,6 +2734,11 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 
 		if (nl80211_put_tid_config_support(rdev, msg))
 			goto nla_put_failure;
+		state->split_start++;
+		break;
+	case 16:
+		if (nl80211_put_sar_specs(rdev, msg))
+			goto nla_put_failure;
 
 		/* done */
 		state->split_start = 0;
@@ -2773,8 +2933,8 @@ static int parse_txq_params(struct nlattr *tb[],
 static bool nl80211_can_set_dev_channel(struct wireless_dev *wdev)
 {
 	/*
-	 * You can only set the channel explicitly for WDS interfaces,
-	 * all others have their channel managed via their respective
+	 * You can only set the channel explicitly for some interfaces,
+	 * most have their channel managed via their respective
 	 * "establish a connection" command (connect, join, ...)
 	 *
 	 * For AP/GO and mesh mode, the channel can be set with the
@@ -2979,29 +3139,6 @@ static int nl80211_set_channel(struct sk_buff *skb, struct genl_info *info)
 	return __nl80211_set_channel(rdev, netdev, info);
 }
 
-static int nl80211_set_wds_peer(struct sk_buff *skb, struct genl_info *info)
-{
-	struct cfg80211_registered_device *rdev = info->user_ptr[0];
-	struct net_device *dev = info->user_ptr[1];
-	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	const u8 *bssid;
-
-	if (!info->attrs[NL80211_ATTR_MAC])
-		return -EINVAL;
-
-	if (netif_running(dev))
-		return -EBUSY;
-
-	if (!rdev->ops->set_wds_peer)
-		return -EOPNOTSUPP;
-
-	if (wdev->iftype != NL80211_IFTYPE_WDS)
-		return -EOPNOTSUPP;
-
-	bssid = nla_data(info->attrs[NL80211_ATTR_MAC]);
-	return rdev_set_wds_peer(rdev, dev, bssid);
-}
-
 static int nl80211_set_wiphy(struct sk_buff *skb, struct genl_info *info)
 {
 	struct cfg80211_registered_device *rdev;
@@ -3798,7 +3935,8 @@ static int nl80211_new_interface(struct sk_buff *skb, struct genl_info *info)
 		 * P2P Device and NAN do not have a netdev, so don't go
 		 * through the netdev notifier and must be added here
 		 */
-		cfg80211_init_wdev(rdev, wdev);
+		cfg80211_init_wdev(wdev);
+		cfg80211_register_wdev(rdev, wdev);
 		break;
 	default:
 		break;
@@ -4172,9 +4310,6 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
-	if (key.idx < 0)
-		return -EINVAL;
-
 	if (info->attrs[NL80211_ATTR_MAC])
 		mac_addr = nla_data(info->attrs[NL80211_ATTR_MAC]);
 
@@ -4190,6 +4325,10 @@ static int nl80211_del_key(struct sk_buff *skb, struct genl_info *info)
 	    key.type != NL80211_KEYTYPE_GROUP)
 		return -EINVAL;
 
+	if (!cfg80211_valid_key_idx(rdev, key.idx,
+				    key.type == NL80211_KEYTYPE_PAIRWISE))
+		return -EINVAL;
+
 	if (!rdev->ops->del_key)
 		return -EOPNOTSUPP;
 
@@ -4422,21 +4561,110 @@ static bool vht_set_mcs_mask(struct ieee80211_supported_band *sband,
 	return true;
 }
 
+static u16 he_mcs_map_to_mcs_mask(u8 he_mcs_map)
+{
+	switch (he_mcs_map) {
+	case IEEE80211_HE_MCS_NOT_SUPPORTED:
+		return 0;
+	case IEEE80211_HE_MCS_SUPPORT_0_7:
+		return 0x00FF;
+	case IEEE80211_HE_MCS_SUPPORT_0_9:
+		return 0x03FF;
+	case IEEE80211_HE_MCS_SUPPORT_0_11:
+		return 0xFFF;
+	default:
+		break;
+	}
+	return 0;
+}
+
+static void he_build_mcs_mask(u16 he_mcs_map,
+			      u16 he_mcs_mask[NL80211_HE_NSS_MAX])
+{
+	u8 nss;
+
+	for (nss = 0; nss < NL80211_HE_NSS_MAX; nss++) {
+		he_mcs_mask[nss] = he_mcs_map_to_mcs_mask(he_mcs_map & 0x03);
+		he_mcs_map >>= 2;
+	}
+}
+
+static u16 he_get_txmcsmap(struct genl_info *info,
+			   const struct ieee80211_sta_he_cap *he_cap)
+{
+	struct net_device *dev = info->user_ptr[1];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
+	__le16	tx_mcs;
+
+	switch (wdev->chandef.width) {
+	case NL80211_CHAN_WIDTH_80P80:
+		tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80p80;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_160;
+		break;
+	default:
+		tx_mcs = he_cap->he_mcs_nss_supp.tx_mcs_80;
+		break;
+	}
+	return le16_to_cpu(tx_mcs);
+}
+
+static bool he_set_mcs_mask(struct genl_info *info,
+			    struct wireless_dev *wdev,
+			    struct ieee80211_supported_band *sband,
+			    struct nl80211_txrate_he *txrate,
+			    u16 mcs[NL80211_HE_NSS_MAX])
+{
+	const struct ieee80211_sta_he_cap *he_cap;
+	u16 tx_mcs_mask[NL80211_HE_NSS_MAX] = {};
+	u16 tx_mcs_map = 0;
+	u8 i;
+
+	he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype);
+	if (!he_cap)
+		return false;
+
+	memset(mcs, 0, sizeof(u16) * NL80211_HE_NSS_MAX);
+
+	tx_mcs_map = he_get_txmcsmap(info, he_cap);
+
+	/* Build he_mcs_mask from HE capabilities */
+	he_build_mcs_mask(tx_mcs_map, tx_mcs_mask);
+
+	for (i = 0; i < NL80211_HE_NSS_MAX; i++) {
+		if ((tx_mcs_mask[i] & txrate->mcs[i]) == txrate->mcs[i])
+			mcs[i] = txrate->mcs[i];
+		else
+			return false;
+	}
+
+	return true;
+}
+
 static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 					 struct nlattr *attrs[],
 					 enum nl80211_attrs attr,
-					 struct cfg80211_bitrate_mask *mask)
+					 struct cfg80211_bitrate_mask *mask,
+					 struct net_device *dev,
+					 bool default_all_enabled)
 {
 	struct nlattr *tb[NL80211_TXRATE_MAX + 1];
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	int rem, i;
 	struct nlattr *tx_rates;
 	struct ieee80211_supported_band *sband;
-	u16 vht_tx_mcs_map;
+	u16 vht_tx_mcs_map, he_tx_mcs_map;
 
 	memset(mask, 0, sizeof(*mask));
 	/* Default to all rates enabled */
 	for (i = 0; i < NUM_NL80211_BANDS; i++) {
+		const struct ieee80211_sta_he_cap *he_cap;
+
+		if (!default_all_enabled)
+			break;
+
 		sband = rdev->wiphy.bands[i];
 
 		if (!sband)
@@ -4452,6 +4680,16 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 
 		vht_tx_mcs_map = le16_to_cpu(sband->vht_cap.vht_mcs.tx_mcs_map);
 		vht_build_mcs_mask(vht_tx_mcs_map, mask->control[i].vht_mcs);
+
+		he_cap = ieee80211_get_he_iftype_cap(sband, wdev->iftype);
+		if (!he_cap)
+			continue;
+
+		he_tx_mcs_map = he_get_txmcsmap(info, he_cap);
+		he_build_mcs_mask(he_tx_mcs_map, mask->control[i].he_mcs);
+
+		mask->control[i].he_gi = 0xFF;
+		mask->control[i].he_ltf = 0xFF;
 	}
 
 	/* if no rates are given set it back to the defaults */
@@ -4494,6 +4732,7 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 					mask->control[band].ht_mcs))
 				return -EINVAL;
 		}
+
 		if (tb[NL80211_TXRATE_VHT]) {
 			if (!vht_set_mcs_mask(
 					sband,
@@ -4501,19 +4740,33 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 					mask->control[band].vht_mcs))
 				return -EINVAL;
 		}
+
 		if (tb[NL80211_TXRATE_GI]) {
 			mask->control[band].gi =
 				nla_get_u8(tb[NL80211_TXRATE_GI]);
 			if (mask->control[band].gi > NL80211_TXRATE_FORCE_LGI)
 				return -EINVAL;
 		}
+		if (tb[NL80211_TXRATE_HE] &&
+		    !he_set_mcs_mask(info, wdev, sband,
+				     nla_data(tb[NL80211_TXRATE_HE]),
+				     mask->control[band].he_mcs))
+			return -EINVAL;
+
+		if (tb[NL80211_TXRATE_HE_GI])
+			mask->control[band].he_gi =
+				nla_get_u8(tb[NL80211_TXRATE_HE_GI]);
+		if (tb[NL80211_TXRATE_HE_LTF])
+			mask->control[band].he_ltf =
+				nla_get_u8(tb[NL80211_TXRATE_HE_LTF]);
 
 		if (mask->control[band].legacy == 0) {
-			/* don't allow empty legacy rates if HT or VHT
+			/* don't allow empty legacy rates if HT, VHT or HE
 			 * are not even supported.
 			 */
 			if (!(rdev->wiphy.bands[band]->ht_cap.ht_supported ||
-			      rdev->wiphy.bands[band]->vht_cap.vht_supported))
+			      rdev->wiphy.bands[band]->vht_cap.vht_supported ||
+			      ieee80211_get_he_iftype_cap(sband, wdev->iftype)))
 				return -EINVAL;
 
 			for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++)
@@ -4524,6 +4777,10 @@ static int nl80211_parse_tx_bitrate_mask(struct genl_info *info,
 				if (mask->control[band].vht_mcs[i])
 					goto out;
 
+			for (i = 0; i < NL80211_HE_NSS_MAX; i++)
+				if (mask->control[band].he_mcs[i])
+					goto out;
+
 			/* legacy and mcs rates may not be both empty */
 			return -EINVAL;
 		}
@@ -4537,7 +4794,7 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev,
 				   enum nl80211_band band,
 				   struct cfg80211_bitrate_mask *beacon_rate)
 {
-	u32 count_ht, count_vht, i;
+	u32 count_ht, count_vht, count_he, i;
 	u32 rate = beacon_rate->control[band].legacy;
 
 	/* Allow only one rate */
@@ -4570,7 +4827,21 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev,
 			return -EINVAL;
 	}
 
-	if ((count_ht && count_vht) || (!rate && !count_ht && !count_vht))
+	count_he = 0;
+	for (i = 0; i < NL80211_HE_NSS_MAX; i++) {
+		if (hweight16(beacon_rate->control[band].he_mcs[i]) > 1) {
+			return -EINVAL;
+		} else if (beacon_rate->control[band].he_mcs[i]) {
+			count_he++;
+			if (count_he > 1)
+				return -EINVAL;
+		}
+		if (count_he && rate)
+			return -EINVAL;
+	}
+
+	if ((count_ht && count_vht && count_he) ||
+	    (!rate && !count_ht && !count_vht && !count_he))
 		return -EINVAL;
 
 	if (rate &&
@@ -4585,6 +4856,10 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev,
 	    !wiphy_ext_feature_isset(&rdev->wiphy,
 				     NL80211_EXT_FEATURE_BEACON_RATE_VHT))
 		return -EINVAL;
+	if (count_he &&
+	    !wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_BEACON_RATE_HE))
+		return -EINVAL;
 
 	return 0;
 }
@@ -4683,18 +4958,34 @@ static int nl80211_parse_he_obss_pd(struct nlattr *attrs,
 	if (err)
 		return err;
 
-	if (!tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET] ||
-	    !tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET])
+	if (!tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL])
 		return -EINVAL;
 
-	he_obss_pd->min_offset =
-		nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]);
-	he_obss_pd->max_offset =
-		nla_get_u32(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]);
+	he_obss_pd->sr_ctrl = nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_SR_CTRL]);
+
+	if (tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET])
+		he_obss_pd->min_offset =
+			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MIN_OFFSET]);
+	if (tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET])
+		he_obss_pd->max_offset =
+			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_MAX_OFFSET]);
+	if (tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET])
+		he_obss_pd->non_srg_max_offset =
+			nla_get_u8(tb[NL80211_HE_OBSS_PD_ATTR_NON_SRG_MAX_OFFSET]);
 
-	if (he_obss_pd->min_offset >= he_obss_pd->max_offset)
+	if (he_obss_pd->min_offset > he_obss_pd->max_offset)
 		return -EINVAL;
 
+	if (tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP])
+		memcpy(he_obss_pd->bss_color_bitmap,
+		       nla_data(tb[NL80211_HE_OBSS_PD_ATTR_BSS_COLOR_BITMAP]),
+		       sizeof(he_obss_pd->bss_color_bitmap));
+
+	if (tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP])
+		memcpy(he_obss_pd->partial_bssid_bitmap,
+		       nla_data(tb[NL80211_HE_OBSS_PD_ATTR_PARTIAL_BSSID_BITMAP]),
+		       sizeof(he_obss_pd->partial_bssid_bitmap));
+
 	he_obss_pd->enable = true;
 
 	return 0;
@@ -4724,6 +5015,65 @@ static int nl80211_parse_he_bss_color(struct nlattr *attrs,
 	return 0;
 }
 
+static int nl80211_parse_fils_discovery(struct cfg80211_registered_device *rdev,
+					struct nlattr *attrs,
+					struct cfg80211_ap_settings *params)
+{
+	struct nlattr *tb[NL80211_FILS_DISCOVERY_ATTR_MAX + 1];
+	int ret;
+	struct cfg80211_fils_discovery *fd = &params->fils_discovery;
+
+	if (!wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_FILS_DISCOVERY))
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, NL80211_FILS_DISCOVERY_ATTR_MAX, attrs,
+			       NULL, NULL);
+	if (ret)
+		return ret;
+
+	if (!tb[NL80211_FILS_DISCOVERY_ATTR_INT_MIN] ||
+	    !tb[NL80211_FILS_DISCOVERY_ATTR_INT_MAX] ||
+	    !tb[NL80211_FILS_DISCOVERY_ATTR_TMPL])
+		return -EINVAL;
+
+	fd->tmpl_len = nla_len(tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]);
+	fd->tmpl = nla_data(tb[NL80211_FILS_DISCOVERY_ATTR_TMPL]);
+	fd->min_interval = nla_get_u32(tb[NL80211_FILS_DISCOVERY_ATTR_INT_MIN]);
+	fd->max_interval = nla_get_u32(tb[NL80211_FILS_DISCOVERY_ATTR_INT_MAX]);
+
+	return 0;
+}
+
+static int
+nl80211_parse_unsol_bcast_probe_resp(struct cfg80211_registered_device *rdev,
+				     struct nlattr *attrs,
+				     struct cfg80211_ap_settings *params)
+{
+	struct nlattr *tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX + 1];
+	int ret;
+	struct cfg80211_unsol_bcast_probe_resp *presp =
+					&params->unsol_bcast_probe_resp;
+
+	if (!wiphy_ext_feature_isset(&rdev->wiphy,
+				     NL80211_EXT_FEATURE_UNSOL_BCAST_PROBE_RESP))
+		return -EINVAL;
+
+	ret = nla_parse_nested(tb, NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_MAX,
+			       attrs, NULL, NULL);
+	if (ret)
+		return ret;
+
+	if (!tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT] ||
+	    !tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL])
+		return -EINVAL;
+
+	presp->tmpl = nla_data(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]);
+	presp->tmpl_len = nla_len(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_TMPL]);
+	presp->interval = nla_get_u32(tb[NL80211_UNSOL_BCAST_PROBE_RESP_ATTR_INT]);
+	return 0;
+}
+
 static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params,
 					    const u8 *rates)
 {
@@ -4739,6 +5089,8 @@ static void nl80211_check_ap_rate_selectors(struct cfg80211_ap_settings *params,
 			params->vht_required = true;
 		if (rates[2 + i] == BSS_MEMBERSHIP_SELECTOR_HE_PHY)
 			params->he_required = true;
+		if (rates[2 + i] == BSS_MEMBERSHIP_SELECTOR_SAE_H2E)
+			params->sae_h2e_required = true;
 	}
 }
 
@@ -4834,8 +5186,9 @@ static bool nl80211_valid_auth_type(struct cfg80211_registered_device *rdev,
 			return false;
 		return true;
 	case NL80211_CMD_START_AP:
-		/* SAE not supported yet */
-		if (auth_type == NL80211_AUTHTYPE_SAE)
+		if (!wiphy_ext_feature_isset(&rdev->wiphy,
+					     NL80211_EXT_FEATURE_SAE_OFFLOAD_AP) &&
+		    auth_type == NL80211_AUTHTYPE_SAE)
 			return false;
 		/* FILS not supported yet */
 		if (auth_type == NL80211_AUTHTYPE_FILS_SK ||
@@ -4899,8 +5252,7 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 		params.ssid = nla_data(info->attrs[NL80211_ATTR_SSID]);
 		params.ssid_len =
 			nla_len(info->attrs[NL80211_ATTR_SSID]);
-		if (params.ssid_len == 0 ||
-		    params.ssid_len > IEEE80211_MAX_SSID_LEN)
+		if (params.ssid_len == 0)
 			return -EINVAL;
 	}
 
@@ -4969,7 +5321,8 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_TX_RATES]) {
 		err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
 						    NL80211_ATTR_TX_RATES,
-						    &params.beacon_rate);
+						    &params.beacon_rate,
+						    dev, false);
 		if (err)
 			return err;
 
@@ -5031,6 +5384,22 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
 			goto out;
 	}
 
+	if (info->attrs[NL80211_ATTR_FILS_DISCOVERY]) {
+		err = nl80211_parse_fils_discovery(rdev,
+						   info->attrs[NL80211_ATTR_FILS_DISCOVERY],
+						   &params);
+		if (err)
+			goto out;
+	}
+
+	if (info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP]) {
+		err = nl80211_parse_unsol_bcast_probe_resp(
+			rdev, info->attrs[NL80211_ATTR_UNSOL_BCAST_PROBE_RESP],
+			&params);
+		if (err)
+			return err;
+	}
+
 	nl80211_calculate_ap_params(&params);
 
 	if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT])
@@ -5840,11 +6209,9 @@ static int nl80211_parse_sta_channel_info(struct genl_info *info,
 		     nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_CHANNELS]);
 		/*
 		 * Need to include at least one (first channel, number of
-		 * channels) tuple for each subband, and must have proper
-		 * tuples for the rest of the data as well.
+		 * channels) tuple for each subband (checked in policy),
+		 * and must have proper tuples for the rest of the data as well.
 		 */
-		if (params->supported_channels_len < 2)
-			return -EINVAL;
 		if (params->supported_channels_len % 2)
 			return -EINVAL;
 	}
@@ -5854,13 +6221,6 @@ static int nl80211_parse_sta_channel_info(struct genl_info *info,
 		 nla_data(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]);
 		params->supported_oper_classes_len =
 		  nla_len(info->attrs[NL80211_ATTR_STA_SUPPORTED_OPER_CLASSES]);
-		/*
-		 * The value of the Length field of the Supported Operating
-		 * Classes element is between 2 and 253.
-		 */
-		if (params->supported_oper_classes_len < 2 ||
-		    params->supported_oper_classes_len > 253)
-			return -EINVAL;
 	}
 	return 0;
 }
@@ -5883,9 +6243,6 @@ static int nl80211_set_station_tdls(struct genl_info *info,
 			nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
 		params->he_capa_len =
 			nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
-
-		if (params->he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN)
-			return -EINVAL;
 	}
 
 	err = nl80211_parse_sta_channel_info(info, params);
@@ -6144,10 +6501,6 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 			nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
 		params.he_capa_len =
 			nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
-
-		/* max len is validated in nla policy */
-		if (params.he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN)
-			return -EINVAL;
 	}
 
 	if (info->attrs[NL80211_ATTR_HE_6GHZ_CAPABILITY])
@@ -7962,12 +8315,6 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	if (info->attrs[NL80211_ATTR_MEASUREMENT_DURATION]) {
-		if (!wiphy_ext_feature_isset(wiphy,
-					NL80211_EXT_FEATURE_SET_SCAN_DWELL)) {
-			err = -EOPNOTSUPP;
-			goto out_free;
-		}
-
 		request->duration =
 			nla_get_u16(info->attrs[NL80211_ATTR_MEASUREMENT_DURATION]);
 		request->duration_mandatory =
@@ -8006,7 +8353,7 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
 	request->scan_start = jiffies;
 
 	rdev->scan_req = request;
-	err = rdev_scan(rdev, request);
+	err = cfg80211_scan(rdev);
 
 	if (err)
 		goto out_free;
@@ -8419,23 +8766,14 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
 			}
 
 			if (ssid) {
-				if (nla_len(ssid) > IEEE80211_MAX_SSID_LEN) {
-					err = -EINVAL;
-					goto out_free;
-				}
 				memcpy(request->match_sets[i].ssid.ssid,
 				       nla_data(ssid), nla_len(ssid));
 				request->match_sets[i].ssid.ssid_len =
 					nla_len(ssid);
 			}
-			if (bssid) {
-				if (nla_len(bssid) != ETH_ALEN) {
-					err = -EINVAL;
-					goto out_free;
-				}
+			if (bssid)
 				memcpy(request->match_sets[i].bssid,
 				       nla_data(bssid), ETH_ALEN);
-			}
 
 			/* special attribute - old implementation w/a */
 			request->match_sets[i].rssi_thold = default_match_rssi;
@@ -8790,10 +9128,10 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		return err;
 
-	if (!csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON])
+	if (!csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON])
 		return -EINVAL;
 
-	len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
+	len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]);
 	if (!len || (len % sizeof(u16)))
 		return -EINVAL;
 
@@ -8804,7 +9142,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 
 	params.counter_offsets_beacon =
-		nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_BEACON]);
+		nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_BEACON]);
 
 	/* sanity checks - counters should fit and be the same */
 	for (i = 0; i < params.n_counter_offsets_beacon; i++) {
@@ -8817,8 +9155,8 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 			return -EINVAL;
 	}
 
-	if (csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]) {
-		len = nla_len(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
+	if (csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]) {
+		len = nla_len(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]);
 		if (!len || (len % sizeof(u16)))
 			return -EINVAL;
 
@@ -8829,7 +9167,7 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info)
 			return -EINVAL;
 
 		params.counter_offsets_presp =
-			nla_data(csa_attrs[NL80211_ATTR_CSA_C_OFF_PRESP]);
+			nla_data(csa_attrs[NL80211_ATTR_CNTDWN_OFFS_PRESP]);
 
 		/* sanity checks - counters should fit and be the same */
 		for (i = 0; i < params.n_counter_offsets_presp; i++) {
@@ -9094,6 +9432,11 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 portid, u32 seq,
 			survey->channel->center_freq))
 		goto nla_put_failure;
 
+	if (survey->channel && survey->channel->freq_offset &&
+	    nla_put_u32(msg, NL80211_SURVEY_INFO_FREQUENCY_OFFSET,
+			survey->channel->freq_offset))
+		goto nla_put_failure;
+
 	if ((survey->filled & SURVEY_INFO_NOISE_DBM) &&
 	    nla_put_u8(msg, NL80211_SURVEY_INFO_NOISE, survey->noise))
 		goto nla_put_failure;
@@ -9312,9 +9655,6 @@ static int nl80211_authenticate(struct sk_buff *skb, struct genl_info *info)
 			return -EINVAL;
 		auth_data = nla_data(info->attrs[NL80211_ATTR_AUTH_DATA]);
 		auth_data_len = nla_len(info->attrs[NL80211_ATTR_AUTH_DATA]);
-		/* need to include at least Auth Transaction and Status Code */
-		if (auth_data_len < 4)
-			return -EINVAL;
 	}
 
 	local_state_change = !!info->attrs[NL80211_ATTR_LOCAL_STATE_CHANGE];
@@ -9454,7 +9794,9 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 
 	if (info->attrs[NL80211_ATTR_SAE_PASSWORD]) {
 		if (!wiphy_ext_feature_isset(&rdev->wiphy,
-					     NL80211_EXT_FEATURE_SAE_OFFLOAD))
+					     NL80211_EXT_FEATURE_SAE_OFFLOAD) &&
+		    !wiphy_ext_feature_isset(&rdev->wiphy,
+					     NL80211_EXT_FEATURE_SAE_OFFLOAD_AP))
 			return -EINVAL;
 		settings->sae_pwd =
 			nla_data(info->attrs[NL80211_ATTR_SAE_PASSWORD]);
@@ -9462,6 +9804,12 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 			nla_len(info->attrs[NL80211_ATTR_SAE_PASSWORD]);
 	}
 
+	if (info->attrs[NL80211_ATTR_SAE_PWE])
+		settings->sae_pwe =
+			nla_get_u8(info->attrs[NL80211_ATTR_SAE_PWE]);
+	else
+		settings->sae_pwe = NL80211_SAE_PWE_UNSPECIFIED;
+
 	return 0;
 }
 
@@ -9572,6 +9920,22 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 			nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]);
 	}
 
+	if (info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]) {
+		if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY])
+			return -EINVAL;
+		memcpy(&req.s1g_capa_mask,
+		       nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK]),
+		       sizeof(req.s1g_capa_mask));
+	}
+
+	if (info->attrs[NL80211_ATTR_S1G_CAPABILITY]) {
+		if (!info->attrs[NL80211_ATTR_S1G_CAPABILITY_MASK])
+			return -EINVAL;
+		memcpy(&req.s1g_capa,
+		       nla_data(info->attrs[NL80211_ATTR_S1G_CAPABILITY]),
+		       sizeof(req.s1g_capa));
+	}
+
 	err = nl80211_crypto_settings(rdev, info, &req.crypto, 1);
 	if (!err) {
 		wdev_lock(dev->ieee80211_ptr);
@@ -10801,7 +11165,8 @@ static int nl80211_set_tx_bitrate_mask(struct sk_buff *skb,
 		return -EOPNOTSUPP;
 
 	err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
-					    NL80211_ATTR_TX_RATES, &mask);
+					    NL80211_ATTR_TX_RATES, &mask,
+					    dev, true);
 	if (err)
 		return err;
 
@@ -10878,6 +11243,7 @@ static int nl80211_tx_mgmt(struct sk_buff *skb, struct genl_info *info)
 	case NL80211_IFTYPE_P2P_DEVICE:
 		if (!info->attrs[NL80211_ATTR_WIPHY_FREQ])
 			return -EINVAL;
+		break;
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_ADHOC:
 	case NL80211_IFTYPE_P2P_CLIENT:
@@ -11409,7 +11775,8 @@ static int nl80211_join_mesh(struct sk_buff *skb, struct genl_info *info)
 	if (info->attrs[NL80211_ATTR_TX_RATES]) {
 		err = nl80211_parse_tx_bitrate_mask(info, info->attrs,
 						    NL80211_ATTR_TX_RATES,
-						    &setup.beacon_rate);
+						    &setup.beacon_rate,
+						    dev, false);
 		if (err)
 			return err;
 
@@ -12346,7 +12713,7 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info)
 	struct net_device *dev = info->user_ptr[1];
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct nlattr *tb[NUM_NL80211_REKEY_DATA];
-	struct cfg80211_gtk_rekey_data rekey_data;
+	struct cfg80211_gtk_rekey_data rekey_data = {};
 	int err;
 
 	if (!info->attrs[NL80211_ATTR_REKEY_DATA])
@@ -12361,8 +12728,6 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info)
 	if (!tb[NL80211_REKEY_DATA_REPLAY_CTR] || !tb[NL80211_REKEY_DATA_KEK] ||
 	    !tb[NL80211_REKEY_DATA_KCK])
 		return -EINVAL;
-	if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN)
-		return -ERANGE;
 	if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN &&
 	    !(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK &&
 	      nla_len(tb[NL80211_REKEY_DATA_KEK]) == NL80211_KEK_EXT_LEN))
@@ -12687,8 +13052,7 @@ static int nl80211_nan_add_func(struct sk_buff *skb,
 
 	func->cookie = cfg80211_assign_cookie(rdev);
 
-	if (!tb[NL80211_NAN_FUNC_TYPE] ||
-	    nla_get_u8(tb[NL80211_NAN_FUNC_TYPE]) > NL80211_NAN_FUNC_MAX_TYPE) {
+	if (!tb[NL80211_NAN_FUNC_TYPE]) {
 		err = -EINVAL;
 		goto out;
 	}
@@ -13178,9 +13542,6 @@ static int nl80211_crit_protocol_start(struct sk_buff *skb,
 	duration =
 		nla_get_u16(info->attrs[NL80211_ATTR_MAX_CRIT_PROT_DURATION]);
 
-	if (duration > NL80211_CRIT_PROTO_MAX_DURATION)
-		return -ERANGE;
-
 	ret = rdev_crit_proto_start(rdev, wdev, proto, duration);
 	if (!ret)
 		rdev->crit_proto_nlportid = info->snd_portid;
@@ -13565,8 +13926,7 @@ static int nl80211_set_qos_map(struct sk_buff *skb,
 		pos = nla_data(info->attrs[NL80211_ATTR_QOS_MAP]);
 		len = nla_len(info->attrs[NL80211_ATTR_QOS_MAP]);
 
-		if (len % 2 || len < IEEE80211_QOS_MAP_LEN_MIN ||
-		    len > IEEE80211_QOS_MAP_LEN_MAX)
+		if (len % 2)
 			return -EINVAL;
 
 		qos_map = kzalloc(sizeof(struct cfg80211_qos_map), GFP_KERNEL);
@@ -13834,17 +14194,9 @@ static int nl80211_set_pmk(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	}
 
-	if (info->attrs[NL80211_ATTR_PMKR0_NAME]) {
-		int r0_name_len = nla_len(info->attrs[NL80211_ATTR_PMKR0_NAME]);
-
-		if (r0_name_len != WLAN_PMK_NAME_LEN) {
-			ret = -EINVAL;
-			goto out;
-		}
-
+	if (info->attrs[NL80211_ATTR_PMKR0_NAME])
 		pmk_conf.pmk_r0_name =
 			nla_data(info->attrs[NL80211_ATTR_PMKR0_NAME]);
-	}
 
 	ret = rdev_set_pmk(rdev, dev, &pmk_conf);
 out:
@@ -13903,8 +14255,7 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info)
 
 	if (info->attrs[NL80211_ATTR_SSID]) {
 		params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]);
-		if (params.ssid.ssid_len == 0 ||
-		    params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN)
+		if (params.ssid.ssid_len == 0)
 			return -EINVAL;
 		memcpy(params.ssid.ssid,
 		       nla_data(info->attrs[NL80211_ATTR_SSID]),
@@ -14205,7 +14556,8 @@ static int parse_tid_conf(struct cfg80211_registered_device *rdev,
 		if (tid_conf->txrate_type != NL80211_TX_RATE_AUTOMATIC) {
 			attr = NL80211_TID_CONFIG_ATTR_TX_RATE;
 			err = nl80211_parse_tx_bitrate_mask(info, attrs, attr,
-						    &tid_conf->txrate_mask);
+						    &tid_conf->txrate_mask, dev,
+						    true);
 			if (err)
 				return err;
 
@@ -14386,6 +14738,111 @@ static void nl80211_post_doit(const struct genl_ops *ops, struct sk_buff *skb,
 	}
 }
 
+static int nl80211_set_sar_sub_specs(struct cfg80211_registered_device *rdev,
+				     struct cfg80211_sar_specs *sar_specs,
+				     struct nlattr *spec[], int index)
+{
+	u32 range_index, i;
+
+	if (!sar_specs || !spec)
+		return -EINVAL;
+
+	if (!spec[NL80211_SAR_ATTR_SPECS_POWER] ||
+	    !spec[NL80211_SAR_ATTR_SPECS_RANGE_INDEX])
+		return -EINVAL;
+
+	range_index = nla_get_u32(spec[NL80211_SAR_ATTR_SPECS_RANGE_INDEX]);
+
+	/* check if range_index exceeds num_freq_ranges */
+	if (range_index >= rdev->wiphy.sar_capa->num_freq_ranges)
+		return -EINVAL;
+
+	/* check if range_index duplicates */
+	for (i = 0; i < index; i++) {
+		if (sar_specs->sub_specs[i].freq_range_index == range_index)
+			return -EINVAL;
+	}
+
+	sar_specs->sub_specs[index].power =
+		nla_get_s32(spec[NL80211_SAR_ATTR_SPECS_POWER]);
+
+	sar_specs->sub_specs[index].freq_range_index = range_index;
+
+	return 0;
+}
+
+static int nl80211_set_sar_specs(struct sk_buff *skb, struct genl_info *info)
+{
+	struct cfg80211_registered_device *rdev = info->user_ptr[0];
+	struct nlattr *spec[NL80211_SAR_ATTR_SPECS_MAX + 1];
+	struct nlattr *tb[NL80211_SAR_ATTR_MAX + 1];
+	struct cfg80211_sar_specs *sar_spec;
+	enum nl80211_sar_type type;
+	struct nlattr *spec_list;
+	u32 specs;
+	int rem, err;
+
+	if (!rdev->wiphy.sar_capa || !rdev->ops->set_sar_specs)
+		return -EOPNOTSUPP;
+
+	if (!info->attrs[NL80211_ATTR_SAR_SPEC])
+		return -EINVAL;
+
+	nla_parse_nested(tb, NL80211_SAR_ATTR_MAX,
+			 info->attrs[NL80211_ATTR_SAR_SPEC],
+			 NULL, NULL);
+
+	if (!tb[NL80211_SAR_ATTR_TYPE] || !tb[NL80211_SAR_ATTR_SPECS])
+		return -EINVAL;
+
+	type = nla_get_u32(tb[NL80211_SAR_ATTR_TYPE]);
+	if (type != rdev->wiphy.sar_capa->type)
+		return -EINVAL;
+
+	specs = 0;
+	nla_for_each_nested(spec_list, tb[NL80211_SAR_ATTR_SPECS], rem)
+		specs++;
+
+	if (specs > rdev->wiphy.sar_capa->num_freq_ranges)
+		return -EINVAL;
+
+	sar_spec = kzalloc(sizeof(*sar_spec) +
+			   specs * sizeof(struct cfg80211_sar_sub_specs),
+			   GFP_KERNEL);
+	if (!sar_spec)
+		return -ENOMEM;
+
+	sar_spec->type = type;
+	specs = 0;
+	nla_for_each_nested(spec_list, tb[NL80211_SAR_ATTR_SPECS], rem) {
+		nla_parse_nested(spec, NL80211_SAR_ATTR_SPECS_MAX,
+				 spec_list, NULL, NULL);
+
+		switch (type) {
+		case NL80211_SAR_TYPE_POWER:
+			if (nl80211_set_sar_sub_specs(rdev, sar_spec,
+						      spec, specs)) {
+				err = -EINVAL;
+				goto error;
+			}
+			break;
+		default:
+			err = -EINVAL;
+			goto error;
+		}
+		specs++;
+	}
+
+	sar_spec->num_sub_specs = specs;
+
+	rdev->cur_cmd_info = info;
+	err = rdev_set_sar_specs(rdev, sar_spec);
+	rdev->cur_cmd_info = NULL;
+error:
+	kfree(sar_spec);
+	return err;
+}
+
 static const struct genl_ops nl80211_ops[] = {
 	{
 		.cmd = NL80211_CMD_GET_WIPHY,
@@ -14397,6 +14854,9 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_WIPHY |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+};
+
+static const struct genl_small_ops nl80211_small_ops[] = {
 	{
 		.cmd = NL80211_CMD_SET_WIPHY,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -14865,14 +15325,6 @@ static const struct genl_ops nl80211_ops[] = {
 				  NL80211_FLAG_NEED_RTNL,
 	},
 	{
-		.cmd = NL80211_CMD_SET_WDS_PEER,
-		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
-		.doit = nl80211_set_wds_peer,
-		.flags = GENL_UNS_ADMIN_PERM,
-		.internal_flags = NL80211_FLAG_NEED_NETDEV |
-				  NL80211_FLAG_NEED_RTNL,
-	},
-	{
 		.cmd = NL80211_CMD_JOIN_MESH,
 		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
 		.doit = nl80211_join_mesh,
@@ -15244,6 +15696,14 @@ static const struct genl_ops nl80211_ops[] = {
 		.internal_flags = NL80211_FLAG_NEED_NETDEV |
 				  NL80211_FLAG_NEED_RTNL,
 	},
+	{
+		.cmd = NL80211_CMD_SET_SAR_SPECS,
+		.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
+		.doit = nl80211_set_sar_specs,
+		.flags = GENL_UNS_ADMIN_PERM,
+		.internal_flags = NL80211_FLAG_NEED_WIPHY |
+				  NL80211_FLAG_NEED_RTNL,
+	},
 };
 
 static struct genl_family nl80211_fam __ro_after_init = {
@@ -15258,6 +15718,8 @@ static struct genl_family nl80211_fam __ro_after_init = {
 	.module = THIS_MODULE,
 	.ops = nl80211_ops,
 	.n_ops = ARRAY_SIZE(nl80211_ops),
+	.small_ops = nl80211_small_ops,
+	.n_small_ops = ARRAY_SIZE(nl80211_small_ops),
 	.mcgrps = nl80211_mcgrps,
 	.n_mcgrps = ARRAY_SIZE(nl80211_mcgrps),
 	.parallel_ops = true,
@@ -15312,6 +15774,7 @@ static int nl80211_add_scan_req(struct sk_buff *msg,
 	struct cfg80211_scan_request *req = rdev->scan_req;
 	struct nlattr *nest;
 	int i;
+	struct cfg80211_scan_info *info;
 
 	if (WARN_ON(!req))
 		return 0;
@@ -15355,11 +15818,13 @@ static int nl80211_add_scan_req(struct sk_buff *msg,
 	    nla_put_u32(msg, NL80211_ATTR_SCAN_FLAGS, req->flags))
 		goto nla_put_failure;
 
-	if (req->info.scan_start_tsf &&
+	info = rdev->int_scan_req ? &rdev->int_scan_req->info :
+		&rdev->scan_req->info;
+	if (info->scan_start_tsf &&
 	    (nla_put_u64_64bit(msg, NL80211_ATTR_SCAN_START_TIME_TSF,
-			       req->info.scan_start_tsf, NL80211_BSS_PAD) ||
+			       info->scan_start_tsf, NL80211_BSS_PAD) ||
 	     nla_put(msg, NL80211_ATTR_SCAN_START_TIME_TSF_BSSID, ETH_ALEN,
-		     req->info.tsf_bssid)))
+		     info->tsf_bssid)))
 		goto nla_put_failure;
 
 	return 0;
@@ -15574,7 +16039,7 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev,
 				    const u8 *buf, size_t len,
 				    enum nl80211_commands cmd, gfp_t gfp,
 				    int uapsd_queues, const u8 *req_ies,
-				    size_t req_ies_len)
+				    size_t req_ies_len, bool reconnect)
 {
 	struct sk_buff *msg;
 	void *hdr;
@@ -15596,6 +16061,9 @@ static void nl80211_send_mlme_event(struct cfg80211_registered_device *rdev,
 	     nla_put(msg, NL80211_ATTR_REQ_IE, req_ies_len, req_ies)))
 		goto nla_put_failure;
 
+	if (reconnect && nla_put_flag(msg, NL80211_ATTR_RECONNECT_REQUESTED))
+		goto nla_put_failure;
+
 	if (uapsd_queues >= 0) {
 		struct nlattr *nla_wmm =
 			nla_nest_start_noflag(msg, NL80211_ATTR_STA_WME);
@@ -15624,7 +16092,8 @@ void nl80211_send_rx_auth(struct cfg80211_registered_device *rdev,
 			  size_t len, gfp_t gfp)
 {
 	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_AUTHENTICATE, gfp, -1, NULL, 0);
+				NL80211_CMD_AUTHENTICATE, gfp, -1, NULL, 0,
+				false);
 }
 
 void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev,
@@ -15634,23 +16103,25 @@ void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev,
 {
 	nl80211_send_mlme_event(rdev, netdev, buf, len,
 				NL80211_CMD_ASSOCIATE, gfp, uapsd_queues,
-				req_ies, req_ies_len);
+				req_ies, req_ies_len, false);
 }
 
 void nl80211_send_deauth(struct cfg80211_registered_device *rdev,
 			 struct net_device *netdev, const u8 *buf,
-			 size_t len, gfp_t gfp)
+			 size_t len, bool reconnect, gfp_t gfp)
 {
 	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_DEAUTHENTICATE, gfp, -1, NULL, 0);
+				NL80211_CMD_DEAUTHENTICATE, gfp, -1, NULL, 0,
+				reconnect);
 }
 
 void nl80211_send_disassoc(struct cfg80211_registered_device *rdev,
 			   struct net_device *netdev, const u8 *buf,
-			   size_t len, gfp_t gfp)
+			   size_t len, bool reconnect, gfp_t gfp)
 {
 	nl80211_send_mlme_event(rdev, netdev, buf, len,
-				NL80211_CMD_DISASSOCIATE, gfp, -1, NULL, 0);
+				NL80211_CMD_DISASSOCIATE, gfp, -1, NULL, 0,
+				reconnect);
 }
 
 void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf,
@@ -15681,7 +16152,7 @@ void cfg80211_rx_unprot_mlme_mgmt(struct net_device *dev, const u8 *buf,
 
 	trace_cfg80211_rx_unprot_mlme_mgmt(dev, buf, len);
 	nl80211_send_mlme_event(rdev, dev, buf, len, cmd, GFP_ATOMIC, -1,
-				NULL, 0);
+				NULL, 0, false);
 }
 EXPORT_SYMBOL(cfg80211_rx_unprot_mlme_mgmt);
 
@@ -16782,7 +17253,7 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 				     struct cfg80211_chan_def *chandef,
 				     gfp_t gfp,
 				     enum nl80211_commands notif,
-				     u8 count)
+				     u8 count, bool quiet)
 {
 	struct sk_buff *msg;
 	void *hdr;
@@ -16803,9 +17274,13 @@ static void nl80211_ch_switch_notify(struct cfg80211_registered_device *rdev,
 	if (nl80211_send_chandef(msg, chandef))
 		goto nla_put_failure;
 
-	if ((notif == NL80211_CMD_CH_SWITCH_STARTED_NOTIFY) &&
-	    (nla_put_u32(msg, NL80211_ATTR_CH_SWITCH_COUNT, count)))
+	if (notif == NL80211_CMD_CH_SWITCH_STARTED_NOTIFY) {
+		if (nla_put_u32(msg, NL80211_ATTR_CH_SWITCH_COUNT, count))
 			goto nla_put_failure;
+		if (quiet &&
+		    nla_put_flag(msg, NL80211_ATTR_CH_SWITCH_BLOCK_TX))
+			goto nla_put_failure;
+	}
 
 	genlmsg_end(msg, hdr);
 
@@ -16838,13 +17313,13 @@ void cfg80211_ch_switch_notify(struct net_device *dev,
 	cfg80211_sched_dfs_chan_update(rdev);
 
 	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL,
-				 NL80211_CMD_CH_SWITCH_NOTIFY, 0);
+				 NL80211_CMD_CH_SWITCH_NOTIFY, 0, false);
 }
 EXPORT_SYMBOL(cfg80211_ch_switch_notify);
 
 void cfg80211_ch_switch_started_notify(struct net_device *dev,
 				       struct cfg80211_chan_def *chandef,
-				       u8 count)
+				       u8 count, bool quiet)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	struct wiphy *wiphy = wdev->wiphy;
@@ -16853,7 +17328,8 @@ void cfg80211_ch_switch_started_notify(struct net_device *dev,
 	trace_cfg80211_ch_switch_started_notify(dev, chandef);
 
 	nl80211_ch_switch_notify(rdev, dev, chandef, GFP_KERNEL,
-				 NL80211_CMD_CH_SWITCH_STARTED_NOTIFY, count);
+				 NL80211_CMD_CH_SWITCH_STARTED_NOTIFY,
+				 count, quiet);
 }
 EXPORT_SYMBOL(cfg80211_ch_switch_started_notify);
 
diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h
index d3e8e426c486..a3f387770f1b 100644
--- a/net/wireless/nl80211.h
+++ b/net/wireless/nl80211.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Portions of this file
- * Copyright (C) 2018 Intel Corporation
+ * Copyright (C) 2018, 2020 Intel Corporation
  */
 #ifndef __NET_WIRELESS_NL80211_H
 #define __NET_WIRELESS_NL80211_H
@@ -69,10 +69,12 @@ void nl80211_send_rx_assoc(struct cfg80211_registered_device *rdev,
 			   const u8 *req_ies, size_t req_ies_len);
 void nl80211_send_deauth(struct cfg80211_registered_device *rdev,
 			 struct net_device *netdev,
-			 const u8 *buf, size_t len, gfp_t gfp);
+			 const u8 *buf, size_t len,
+			 bool reconnect, gfp_t gfp);
 void nl80211_send_disassoc(struct cfg80211_registered_device *rdev,
 			   struct net_device *netdev,
-			   const u8 *buf, size_t len, gfp_t gfp);
+			   const u8 *buf, size_t len,
+			   bool reconnect, gfp_t gfp);
 void nl80211_send_auth_timeout(struct cfg80211_registered_device *rdev,
 			       struct net_device *netdev,
 			       const u8 *addr, gfp_t gfp);
diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index d5e28239e030..36f1b59a78bf 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -59,6 +59,7 @@ static const struct ieee80211_radiotap_namespace radiotap_ns = {
  * @iterator: radiotap_iterator to initialize
  * @radiotap_header: radiotap header to parse
  * @max_length: total length we can parse into (eg, whole packet length)
+ * @vns: vendor namespaces to parse
  *
  * Returns: 0 or a negative error code if there is a problem.
  *
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 950d57494168..8b1358d04ca2 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -582,16 +582,6 @@ static inline int rdev_get_tx_power(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
-static inline int rdev_set_wds_peer(struct cfg80211_registered_device *rdev,
-				    struct net_device *dev, const u8 *addr)
-{
-	int ret;
-	trace_rdev_set_wds_peer(&rdev->wiphy, dev, addr);
-	ret = rdev->ops->set_wds_peer(&rdev->wiphy, dev, addr);
-	trace_rdev_return_int(&rdev->wiphy, ret);
-	return ret;
-}
-
 static inline int
 rdev_set_multicast_to_unicast(struct cfg80211_registered_device *rdev,
 			      struct net_device *dev,
@@ -1356,4 +1346,16 @@ static inline int rdev_reset_tid_config(struct cfg80211_registered_device *rdev,
 	return ret;
 }
 
+static inline int rdev_set_sar_specs(struct cfg80211_registered_device *rdev,
+				     struct cfg80211_sar_specs *sar)
+{
+	int ret;
+
+	trace_rdev_set_sar_specs(&rdev->wiphy, sar);
+	ret = rdev->ops->set_sar_specs(&rdev->wiphy, sar);
+	trace_rdev_return_int(&rdev->wiphy, ret);
+
+	return ret;
+}
+
 #endif /* __CFG80211_RDEV_OPS */
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index d8a90d397423..8114bba8556c 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -5,7 +5,7 @@
  * Copyright 2008-2011	Luis R. Rodriguez <mcgrof@qca.qualcomm.com>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright      2017  Intel Deutschland GmbH
- * Copyright (C) 2018 - 2019 Intel Corporation
+ * Copyright (C) 2018 - 2021 Intel Corporation
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -139,6 +139,11 @@ static const struct ieee80211_regdomain *get_cfg80211_regdom(void)
 	return rcu_dereference_rtnl(cfg80211_regdomain);
 }
 
+/*
+ * Returns the regulatory domain associated with the wiphy.
+ *
+ * Requires either RTNL or RCU protection
+ */
 const struct ieee80211_regdomain *get_wiphy_regdom(struct wiphy *wiphy)
 {
 	return rcu_dereference_rtnl(wiphy->regd);
@@ -1594,7 +1599,7 @@ freq_reg_info_regd(u32 center_freq,
 
 		/*
 		 * We only need to know if one frequency rule was
-		 * was in center_freq's band, that's enough, so lets
+		 * in center_freq's band, that's enough, so let's
 		 * not overwrite it once found
 		 */
 		if (!band_rule_found)
@@ -1616,10 +1621,12 @@ static const struct ieee80211_reg_rule *
 __freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 min_bw)
 {
 	const struct ieee80211_regdomain *regd = reg_get_regdomain(wiphy);
-	const struct ieee80211_reg_rule *reg_rule = NULL;
+	static const u32 bws[] = {0, 1, 2, 4, 5, 8, 10, 16, 20};
+	const struct ieee80211_reg_rule *reg_rule;
+	int i = ARRAY_SIZE(bws) - 1;
 	u32 bw;
 
-	for (bw = MHZ_TO_KHZ(20); bw >= min_bw; bw = bw / 2) {
+	for (bw = MHZ_TO_KHZ(bws[i]); bw >= min_bw; bw = MHZ_TO_KHZ(bws[i--])) {
 		reg_rule = freq_reg_info_regd(center_freq, regd, bw);
 		if (!IS_ERR(reg_rule))
 			return reg_rule;
@@ -1631,7 +1638,9 @@ __freq_reg_info(struct wiphy *wiphy, u32 center_freq, u32 min_bw)
 const struct ieee80211_reg_rule *freq_reg_info(struct wiphy *wiphy,
 					       u32 center_freq)
 {
-	return __freq_reg_info(wiphy, center_freq, MHZ_TO_KHZ(20));
+	u32 min_bw = center_freq < MHZ_TO_KHZ(1000) ? 1 : 20;
+
+	return __freq_reg_info(wiphy, center_freq, MHZ_TO_KHZ(min_bw));
 }
 EXPORT_SYMBOL(freq_reg_info);
 
@@ -1659,6 +1668,7 @@ static uint32_t reg_rule_to_chan_bw_flags(const struct ieee80211_regdomain *regd
 {
 	const struct ieee80211_freq_range *freq_range = NULL;
 	u32 max_bandwidth_khz, center_freq_khz, bw_flags = 0;
+	bool is_s1g = chan->band == NL80211_BAND_S1GHZ;
 
 	freq_range = &reg_rule->freq_range;
 
@@ -1678,70 +1688,72 @@ static uint32_t reg_rule_to_chan_bw_flags(const struct ieee80211_regdomain *regd
 					MHZ_TO_KHZ(20)))
 		bw_flags |= IEEE80211_CHAN_NO_20MHZ;
 
-	if (max_bandwidth_khz < MHZ_TO_KHZ(10))
-		bw_flags |= IEEE80211_CHAN_NO_10MHZ;
-	if (max_bandwidth_khz < MHZ_TO_KHZ(20))
-		bw_flags |= IEEE80211_CHAN_NO_20MHZ;
-	if (max_bandwidth_khz < MHZ_TO_KHZ(40))
-		bw_flags |= IEEE80211_CHAN_NO_HT40;
-	if (max_bandwidth_khz < MHZ_TO_KHZ(80))
-		bw_flags |= IEEE80211_CHAN_NO_80MHZ;
-	if (max_bandwidth_khz < MHZ_TO_KHZ(160))
-		bw_flags |= IEEE80211_CHAN_NO_160MHZ;
+	if (is_s1g) {
+		/* S1G is strict about non overlapping channels. We can
+		 * calculate which bandwidth is allowed per channel by finding
+		 * the largest bandwidth which cleanly divides the freq_range.
+		 */
+		int edge_offset;
+		int ch_bw = max_bandwidth_khz;
+
+		while (ch_bw) {
+			edge_offset = (center_freq_khz - ch_bw / 2) -
+				      freq_range->start_freq_khz;
+			if (edge_offset % ch_bw == 0) {
+				switch (KHZ_TO_MHZ(ch_bw)) {
+				case 1:
+					bw_flags |= IEEE80211_CHAN_1MHZ;
+					break;
+				case 2:
+					bw_flags |= IEEE80211_CHAN_2MHZ;
+					break;
+				case 4:
+					bw_flags |= IEEE80211_CHAN_4MHZ;
+					break;
+				case 8:
+					bw_flags |= IEEE80211_CHAN_8MHZ;
+					break;
+				case 16:
+					bw_flags |= IEEE80211_CHAN_16MHZ;
+					break;
+				default:
+					/* If we got here, no bandwidths fit on
+					 * this frequency, ie. band edge.
+					 */
+					bw_flags |= IEEE80211_CHAN_DISABLED;
+					break;
+				}
+				break;
+			}
+			ch_bw /= 2;
+		}
+	} else {
+		if (max_bandwidth_khz < MHZ_TO_KHZ(10))
+			bw_flags |= IEEE80211_CHAN_NO_10MHZ;
+		if (max_bandwidth_khz < MHZ_TO_KHZ(20))
+			bw_flags |= IEEE80211_CHAN_NO_20MHZ;
+		if (max_bandwidth_khz < MHZ_TO_KHZ(40))
+			bw_flags |= IEEE80211_CHAN_NO_HT40;
+		if (max_bandwidth_khz < MHZ_TO_KHZ(80))
+			bw_flags |= IEEE80211_CHAN_NO_80MHZ;
+		if (max_bandwidth_khz < MHZ_TO_KHZ(160))
+			bw_flags |= IEEE80211_CHAN_NO_160MHZ;
+	}
 	return bw_flags;
 }
 
-/*
- * Note that right now we assume the desired channel bandwidth
- * is always 20 MHz for each individual channel (HT40 uses 20 MHz
- * per channel, the primary and the extension channel).
- */
-static void handle_channel(struct wiphy *wiphy,
-			   enum nl80211_reg_initiator initiator,
-			   struct ieee80211_channel *chan)
+static void handle_channel_single_rule(struct wiphy *wiphy,
+				       enum nl80211_reg_initiator initiator,
+				       struct ieee80211_channel *chan,
+				       u32 flags,
+				       struct regulatory_request *lr,
+				       struct wiphy *request_wiphy,
+				       const struct ieee80211_reg_rule *reg_rule)
 {
-	u32 flags, bw_flags = 0;
-	const struct ieee80211_reg_rule *reg_rule = NULL;
+	u32 bw_flags = 0;
 	const struct ieee80211_power_rule *power_rule = NULL;
-	struct wiphy *request_wiphy = NULL;
-	struct regulatory_request *lr = get_last_request();
 	const struct ieee80211_regdomain *regd;
 
-	request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx);
-
-	flags = chan->orig_flags;
-
-	reg_rule = freq_reg_info(wiphy, ieee80211_channel_to_khz(chan));
-	if (IS_ERR(reg_rule)) {
-		/*
-		 * We will disable all channels that do not match our
-		 * received regulatory rule unless the hint is coming
-		 * from a Country IE and the Country IE had no information
-		 * about a band. The IEEE 802.11 spec allows for an AP
-		 * to send only a subset of the regulatory rules allowed,
-		 * so an AP in the US that only supports 2.4 GHz may only send
-		 * a country IE with information for the 2.4 GHz band
-		 * while 5 GHz is still supported.
-		 */
-		if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE &&
-		    PTR_ERR(reg_rule) == -ERANGE)
-			return;
-
-		if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER &&
-		    request_wiphy && request_wiphy == wiphy &&
-		    request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) {
-			pr_debug("Disabling freq %d.%03d MHz for good\n",
-				 chan->center_freq, chan->freq_offset);
-			chan->orig_flags |= IEEE80211_CHAN_DISABLED;
-			chan->flags = chan->orig_flags;
-		} else {
-			pr_debug("Disabling freq %d.%03d MHz\n",
-				 chan->center_freq, chan->freq_offset);
-			chan->flags |= IEEE80211_CHAN_DISABLED;
-		}
-		return;
-	}
-
 	regd = reg_get_regdomain(wiphy);
 
 	power_rule = &reg_rule->power_rule;
@@ -1803,6 +1815,204 @@ static void handle_channel(struct wiphy *wiphy,
 		chan->max_power = chan->max_reg_power;
 }
 
+static void handle_channel_adjacent_rules(struct wiphy *wiphy,
+					  enum nl80211_reg_initiator initiator,
+					  struct ieee80211_channel *chan,
+					  u32 flags,
+					  struct regulatory_request *lr,
+					  struct wiphy *request_wiphy,
+					  const struct ieee80211_reg_rule *rrule1,
+					  const struct ieee80211_reg_rule *rrule2,
+					  struct ieee80211_freq_range *comb_range)
+{
+	u32 bw_flags1 = 0;
+	u32 bw_flags2 = 0;
+	const struct ieee80211_power_rule *power_rule1 = NULL;
+	const struct ieee80211_power_rule *power_rule2 = NULL;
+	const struct ieee80211_regdomain *regd;
+
+	regd = reg_get_regdomain(wiphy);
+
+	power_rule1 = &rrule1->power_rule;
+	power_rule2 = &rrule2->power_rule;
+	bw_flags1 = reg_rule_to_chan_bw_flags(regd, rrule1, chan);
+	bw_flags2 = reg_rule_to_chan_bw_flags(regd, rrule2, chan);
+
+	if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER &&
+	    request_wiphy && request_wiphy == wiphy &&
+	    request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) {
+		/* This guarantees the driver's requested regulatory domain
+		 * will always be used as a base for further regulatory
+		 * settings
+		 */
+		chan->flags =
+			map_regdom_flags(rrule1->flags) |
+			map_regdom_flags(rrule2->flags) |
+			bw_flags1 |
+			bw_flags2;
+		chan->orig_flags = chan->flags;
+		chan->max_antenna_gain =
+			min_t(int, MBI_TO_DBI(power_rule1->max_antenna_gain),
+			      MBI_TO_DBI(power_rule2->max_antenna_gain));
+		chan->orig_mag = chan->max_antenna_gain;
+		chan->max_reg_power =
+			min_t(int, MBM_TO_DBM(power_rule1->max_eirp),
+			      MBM_TO_DBM(power_rule2->max_eirp));
+		chan->max_power = chan->max_reg_power;
+		chan->orig_mpwr = chan->max_reg_power;
+
+		if (chan->flags & IEEE80211_CHAN_RADAR) {
+			chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS;
+			if (rrule1->dfs_cac_ms || rrule2->dfs_cac_ms)
+				chan->dfs_cac_ms = max_t(unsigned int,
+							 rrule1->dfs_cac_ms,
+							 rrule2->dfs_cac_ms);
+		}
+
+		return;
+	}
+
+	chan->dfs_state = NL80211_DFS_USABLE;
+	chan->dfs_state_entered = jiffies;
+
+	chan->beacon_found = false;
+	chan->flags = flags | bw_flags1 | bw_flags2 |
+		      map_regdom_flags(rrule1->flags) |
+		      map_regdom_flags(rrule2->flags);
+
+	/* reg_rule_to_chan_bw_flags may forbids 10 and forbids 20 MHz
+	 * (otherwise no adj. rule case), recheck therefore
+	 */
+	if (cfg80211_does_bw_fit_range(comb_range,
+				       ieee80211_channel_to_khz(chan),
+				       MHZ_TO_KHZ(10)))
+		chan->flags &= ~IEEE80211_CHAN_NO_10MHZ;
+	if (cfg80211_does_bw_fit_range(comb_range,
+				       ieee80211_channel_to_khz(chan),
+				       MHZ_TO_KHZ(20)))
+		chan->flags &= ~IEEE80211_CHAN_NO_20MHZ;
+
+	chan->max_antenna_gain =
+		min_t(int, chan->orig_mag,
+		      min_t(int,
+			    MBI_TO_DBI(power_rule1->max_antenna_gain),
+			    MBI_TO_DBI(power_rule2->max_antenna_gain)));
+	chan->max_reg_power = min_t(int,
+				    MBM_TO_DBM(power_rule1->max_eirp),
+				    MBM_TO_DBM(power_rule2->max_eirp));
+
+	if (chan->flags & IEEE80211_CHAN_RADAR) {
+		if (rrule1->dfs_cac_ms || rrule2->dfs_cac_ms)
+			chan->dfs_cac_ms = max_t(unsigned int,
+						 rrule1->dfs_cac_ms,
+						 rrule2->dfs_cac_ms);
+		else
+			chan->dfs_cac_ms = IEEE80211_DFS_MIN_CAC_TIME_MS;
+	}
+
+	if (chan->orig_mpwr) {
+		/* Devices that use REGULATORY_COUNTRY_IE_FOLLOW_POWER
+		 * will always follow the passed country IE power settings.
+		 */
+		if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE &&
+		    wiphy->regulatory_flags & REGULATORY_COUNTRY_IE_FOLLOW_POWER)
+			chan->max_power = chan->max_reg_power;
+		else
+			chan->max_power = min(chan->orig_mpwr,
+					      chan->max_reg_power);
+	} else {
+		chan->max_power = chan->max_reg_power;
+	}
+}
+
+/* Note that right now we assume the desired channel bandwidth
+ * is always 20 MHz for each individual channel (HT40 uses 20 MHz
+ * per channel, the primary and the extension channel).
+ */
+static void handle_channel(struct wiphy *wiphy,
+			   enum nl80211_reg_initiator initiator,
+			   struct ieee80211_channel *chan)
+{
+	const u32 orig_chan_freq = ieee80211_channel_to_khz(chan);
+	struct regulatory_request *lr = get_last_request();
+	struct wiphy *request_wiphy = wiphy_idx_to_wiphy(lr->wiphy_idx);
+	const struct ieee80211_reg_rule *rrule = NULL;
+	const struct ieee80211_reg_rule *rrule1 = NULL;
+	const struct ieee80211_reg_rule *rrule2 = NULL;
+
+	u32 flags = chan->orig_flags;
+
+	rrule = freq_reg_info(wiphy, orig_chan_freq);
+	if (IS_ERR(rrule)) {
+		/* check for adjacent match, therefore get rules for
+		 * chan - 20 MHz and chan + 20 MHz and test
+		 * if reg rules are adjacent
+		 */
+		rrule1 = freq_reg_info(wiphy,
+				       orig_chan_freq - MHZ_TO_KHZ(20));
+		rrule2 = freq_reg_info(wiphy,
+				       orig_chan_freq + MHZ_TO_KHZ(20));
+		if (!IS_ERR(rrule1) && !IS_ERR(rrule2)) {
+			struct ieee80211_freq_range comb_range;
+
+			if (rrule1->freq_range.end_freq_khz !=
+			    rrule2->freq_range.start_freq_khz)
+				goto disable_chan;
+
+			comb_range.start_freq_khz =
+				rrule1->freq_range.start_freq_khz;
+			comb_range.end_freq_khz =
+				rrule2->freq_range.end_freq_khz;
+			comb_range.max_bandwidth_khz =
+				min_t(u32,
+				      rrule1->freq_range.max_bandwidth_khz,
+				      rrule2->freq_range.max_bandwidth_khz);
+
+			if (!cfg80211_does_bw_fit_range(&comb_range,
+							orig_chan_freq,
+							MHZ_TO_KHZ(20)))
+				goto disable_chan;
+
+			handle_channel_adjacent_rules(wiphy, initiator, chan,
+						      flags, lr, request_wiphy,
+						      rrule1, rrule2,
+						      &comb_range);
+			return;
+		}
+
+disable_chan:
+		/* We will disable all channels that do not match our
+		 * received regulatory rule unless the hint is coming
+		 * from a Country IE and the Country IE had no information
+		 * about a band. The IEEE 802.11 spec allows for an AP
+		 * to send only a subset of the regulatory rules allowed,
+		 * so an AP in the US that only supports 2.4 GHz may only send
+		 * a country IE with information for the 2.4 GHz band
+		 * while 5 GHz is still supported.
+		 */
+		if (initiator == NL80211_REGDOM_SET_BY_COUNTRY_IE &&
+		    PTR_ERR(rrule) == -ERANGE)
+			return;
+
+		if (lr->initiator == NL80211_REGDOM_SET_BY_DRIVER &&
+		    request_wiphy && request_wiphy == wiphy &&
+		    request_wiphy->regulatory_flags & REGULATORY_STRICT_REG) {
+			pr_debug("Disabling freq %d.%03d MHz for good\n",
+				 chan->center_freq, chan->freq_offset);
+			chan->orig_flags |= IEEE80211_CHAN_DISABLED;
+			chan->flags = chan->orig_flags;
+		} else {
+			pr_debug("Disabling freq %d.%03d MHz\n",
+				 chan->center_freq, chan->freq_offset);
+			chan->flags |= IEEE80211_CHAN_DISABLED;
+		}
+		return;
+	}
+
+	handle_channel_single_rule(wiphy, initiator, chan, flags, lr,
+				   request_wiphy, rrule);
+}
+
 static void handle_band(struct wiphy *wiphy,
 			enum nl80211_reg_initiator initiator,
 			struct ieee80211_supported_band *sband)
@@ -2342,6 +2552,7 @@ static void handle_band_custom(struct wiphy *wiphy,
 void wiphy_apply_custom_regulatory(struct wiphy *wiphy,
 				   const struct ieee80211_regdomain *regd)
 {
+	const struct ieee80211_regdomain *new_regd, *tmp;
 	enum nl80211_band band;
 	unsigned int bands_set = 0;
 
@@ -2361,6 +2572,17 @@ void wiphy_apply_custom_regulatory(struct wiphy *wiphy,
 	 * on your device's supported bands.
 	 */
 	WARN_ON(!bands_set);
+	new_regd = reg_copy_regd(regd);
+	if (IS_ERR(new_regd))
+		return;
+
+	rtnl_lock();
+
+	tmp = get_wiphy_regdom(wiphy);
+	rcu_assign_pointer(wiphy->regd, new_regd);
+	rcu_free_regdom(tmp);
+
+	rtnl_unlock();
 }
 EXPORT_SYMBOL(wiphy_apply_custom_regulatory);
 
@@ -3170,7 +3392,7 @@ static void restore_custom_reg_settings(struct wiphy *wiphy)
  *   - send a user regulatory hint if applicable
  *
  * Device drivers that send a regulatory hint for a specific country
- * keep their own regulatory domain on wiphy->regd so that does does
+ * keep their own regulatory domain on wiphy->regd so that does
  * not need to be remembered.
  */
 static void restore_regulatory_settings(bool reset_user, bool cached)
@@ -3411,7 +3633,7 @@ static void print_rd_rules(const struct ieee80211_regdomain *rd)
 		power_rule = &reg_rule->power_rule;
 
 		if (reg_rule->flags & NL80211_RRF_AUTO_BW)
-			snprintf(bw, sizeof(bw), "%d KHz, %d KHz AUTO",
+			snprintf(bw, sizeof(bw), "%d KHz, %u KHz AUTO",
 				 freq_range->max_bandwidth_khz,
 				 reg_get_max_bandwidth(rd, reg_rule));
 		else
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 04f2d198c215..1b7fec3b53cd 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -5,7 +5,7 @@
  * Copyright 2008 Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2016	Intel Deutschland GmbH
- * Copyright (C) 2018-2019 Intel Corporation
+ * Copyright (C) 2018-2020 Intel Corporation
  */
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -14,6 +14,8 @@
 #include <linux/wireless.h>
 #include <linux/nl80211.h>
 #include <linux/etherdevice.h>
+#include <linux/crc32.h>
+#include <linux/bitfield.h>
 #include <net/arp.h>
 #include <net/cfg80211.h>
 #include <net/cfg80211-wext.h>
@@ -55,7 +57,7 @@
  *
  * Also note that the hidden_beacon_bss pointer is only relevant
  * if the driver uses something other than the IEs, e.g. private
- * data stored stored in the BSS struct, since the beacon IEs are
+ * data stored in the BSS struct, since the beacon IEs are
  * also linked into the probe response struct.
  */
 
@@ -74,6 +76,43 @@ MODULE_PARM_DESC(bss_entries_limit,
 
 #define IEEE80211_SCAN_RESULT_EXPIRE	(30 * HZ)
 
+/**
+ * struct cfg80211_colocated_ap - colocated AP information
+ *
+ * @list: linked list to all colocated aPS
+ * @bssid: BSSID of the reported AP
+ * @ssid: SSID of the reported AP
+ * @ssid_len: length of the ssid
+ * @center_freq: frequency the reported AP is on
+ * @unsolicited_probe: the reported AP is part of an ESS, where all the APs
+ *	that operate in the same channel as the reported AP and that might be
+ *	detected by a STA receiving this frame, are transmitting unsolicited
+ *	Probe Response frames every 20 TUs
+ * @oct_recommended: OCT is recommended to exchange MMPDUs with the reported AP
+ * @same_ssid: the reported AP has the same SSID as the reporting AP
+ * @multi_bss: the reported AP is part of a multiple BSSID set
+ * @transmitted_bssid: the reported AP is the transmitting BSSID
+ * @colocated_ess: all the APs that share the same ESS as the reported AP are
+ *	colocated and can be discovered via legacy bands.
+ * @short_ssid_valid: short_ssid is valid and can be used
+ * @short_ssid: the short SSID for this SSID
+ */
+struct cfg80211_colocated_ap {
+	struct list_head list;
+	u8 bssid[ETH_ALEN];
+	u8 ssid[IEEE80211_MAX_SSID_LEN];
+	size_t ssid_len;
+	u32 short_ssid;
+	u32 center_freq;
+	u8 unsolicited_probe:1,
+	   oct_recommended:1,
+	   same_ssid:1,
+	   multi_bss:1,
+	   transmitted_bssid:1,
+	   colocated_ess:1,
+	   short_ssid_valid:1;
+};
+
 static void bss_free(struct cfg80211_internal_bss *bss)
 {
 	struct cfg80211_bss_ies *ies;
@@ -448,10 +487,431 @@ static bool cfg80211_bss_expire_oldest(struct cfg80211_registered_device *rdev)
 	return ret;
 }
 
+static u8 cfg80211_parse_bss_param(u8 data,
+				   struct cfg80211_colocated_ap *coloc_ap)
+{
+	coloc_ap->oct_recommended =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED);
+	coloc_ap->same_ssid =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_SAME_SSID);
+	coloc_ap->multi_bss =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_MULTI_BSSID);
+	coloc_ap->transmitted_bssid =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_TRANSMITTED_BSSID);
+	coloc_ap->unsolicited_probe =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_PROBE_ACTIVE);
+	coloc_ap->colocated_ess =
+		u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_COLOC_ESS);
+
+	return u8_get_bits(data, IEEE80211_RNR_TBTT_PARAMS_COLOC_AP);
+}
+
+static int cfg80211_calc_short_ssid(const struct cfg80211_bss_ies *ies,
+				    const struct element **elem, u32 *s_ssid)
+{
+
+	*elem = cfg80211_find_elem(WLAN_EID_SSID, ies->data, ies->len);
+	if (!*elem || (*elem)->datalen > IEEE80211_MAX_SSID_LEN)
+		return -EINVAL;
+
+	*s_ssid = ~crc32_le(~0, (*elem)->data, (*elem)->datalen);
+	return 0;
+}
+
+static void cfg80211_free_coloc_ap_list(struct list_head *coloc_ap_list)
+{
+	struct cfg80211_colocated_ap *ap, *tmp_ap;
+
+	list_for_each_entry_safe(ap, tmp_ap, coloc_ap_list, list) {
+		list_del(&ap->list);
+		kfree(ap);
+	}
+}
+
+static int cfg80211_parse_ap_info(struct cfg80211_colocated_ap *entry,
+				  const u8 *pos, u8 length,
+				  const struct element *ssid_elem,
+				  int s_ssid_tmp)
+{
+	/* skip the TBTT offset */
+	pos++;
+
+	memcpy(entry->bssid, pos, ETH_ALEN);
+	pos += ETH_ALEN;
+
+	if (length == IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM) {
+		memcpy(&entry->short_ssid, pos,
+		       sizeof(entry->short_ssid));
+		entry->short_ssid_valid = true;
+		pos += 4;
+	}
+
+	/* skip non colocated APs */
+	if (!cfg80211_parse_bss_param(*pos, entry))
+		return -EINVAL;
+	pos++;
+
+	if (length == IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM) {
+		/*
+		 * no information about the short ssid. Consider the entry valid
+		 * for now. It would later be dropped in case there are explicit
+		 * SSIDs that need to be matched
+		 */
+		if (!entry->same_ssid)
+			return 0;
+	}
+
+	if (entry->same_ssid) {
+		entry->short_ssid = s_ssid_tmp;
+		entry->short_ssid_valid = true;
+
+		/*
+		 * This is safe because we validate datalen in
+		 * cfg80211_parse_colocated_ap(), before calling this
+		 * function.
+		 */
+		memcpy(&entry->ssid, &ssid_elem->data,
+		       ssid_elem->datalen);
+		entry->ssid_len = ssid_elem->datalen;
+	}
+	return 0;
+}
+
+static int cfg80211_parse_colocated_ap(const struct cfg80211_bss_ies *ies,
+				       struct list_head *list)
+{
+	struct ieee80211_neighbor_ap_info *ap_info;
+	const struct element *elem, *ssid_elem;
+	const u8 *pos, *end;
+	u32 s_ssid_tmp;
+	int n_coloc = 0, ret;
+	LIST_HEAD(ap_list);
+
+	elem = cfg80211_find_elem(WLAN_EID_REDUCED_NEIGHBOR_REPORT, ies->data,
+				  ies->len);
+	if (!elem || elem->datalen > IEEE80211_MAX_SSID_LEN)
+		return 0;
+
+	pos = elem->data;
+	end = pos + elem->datalen;
+
+	ret = cfg80211_calc_short_ssid(ies, &ssid_elem, &s_ssid_tmp);
+	if (ret)
+		return ret;
+
+	/* RNR IE may contain more than one NEIGHBOR_AP_INFO */
+	while (pos + sizeof(*ap_info) <= end) {
+		enum nl80211_band band;
+		int freq;
+		u8 length, i, count;
+
+		ap_info = (void *)pos;
+		count = u8_get_bits(ap_info->tbtt_info_hdr,
+				    IEEE80211_AP_INFO_TBTT_HDR_COUNT) + 1;
+		length = ap_info->tbtt_info_len;
+
+		pos += sizeof(*ap_info);
+
+		if (!ieee80211_operating_class_to_band(ap_info->op_class,
+						       &band))
+			break;
+
+		freq = ieee80211_channel_to_frequency(ap_info->channel, band);
+
+		if (end - pos < count * ap_info->tbtt_info_len)
+			break;
+
+		/*
+		 * TBTT info must include bss param + BSSID +
+		 * (short SSID or same_ssid bit to be set).
+		 * ignore other options, and move to the
+		 * next AP info
+		 */
+		if (band != NL80211_BAND_6GHZ ||
+		    (length != IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM &&
+		     length < IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM)) {
+			pos += count * ap_info->tbtt_info_len;
+			continue;
+		}
+
+		for (i = 0; i < count; i++) {
+			struct cfg80211_colocated_ap *entry;
+
+			entry = kzalloc(sizeof(*entry) + IEEE80211_MAX_SSID_LEN,
+					GFP_ATOMIC);
+
+			if (!entry)
+				break;
+
+			entry->center_freq = freq;
+
+			if (!cfg80211_parse_ap_info(entry, pos, length,
+						    ssid_elem, s_ssid_tmp)) {
+				n_coloc++;
+				list_add_tail(&entry->list, &ap_list);
+			} else {
+				kfree(entry);
+			}
+
+			pos += ap_info->tbtt_info_len;
+		}
+	}
+
+	if (pos != end) {
+		cfg80211_free_coloc_ap_list(&ap_list);
+		return 0;
+	}
+
+	list_splice_tail(&ap_list, list);
+	return n_coloc;
+}
+
+static  void cfg80211_scan_req_add_chan(struct cfg80211_scan_request *request,
+					struct ieee80211_channel *chan,
+					bool add_to_6ghz)
+{
+	int i;
+	u32 n_channels = request->n_channels;
+	struct cfg80211_scan_6ghz_params *params =
+		&request->scan_6ghz_params[request->n_6ghz_params];
+
+	for (i = 0; i < n_channels; i++) {
+		if (request->channels[i] == chan) {
+			if (add_to_6ghz)
+				params->channel_idx = i;
+			return;
+		}
+	}
+
+	request->channels[n_channels] = chan;
+	if (add_to_6ghz)
+		request->scan_6ghz_params[request->n_6ghz_params].channel_idx =
+			n_channels;
+
+	request->n_channels++;
+}
+
+static bool cfg80211_find_ssid_match(struct cfg80211_colocated_ap *ap,
+				     struct cfg80211_scan_request *request)
+{
+	int i;
+	u32 s_ssid;
+
+	for (i = 0; i < request->n_ssids; i++) {
+		/* wildcard ssid in the scan request */
+		if (!request->ssids[i].ssid_len)
+			return true;
+
+		if (ap->ssid_len &&
+		    ap->ssid_len == request->ssids[i].ssid_len) {
+			if (!memcmp(request->ssids[i].ssid, ap->ssid,
+				    ap->ssid_len))
+				return true;
+		} else if (ap->short_ssid_valid) {
+			s_ssid = ~crc32_le(~0, request->ssids[i].ssid,
+					   request->ssids[i].ssid_len);
+
+			if (ap->short_ssid == s_ssid)
+				return true;
+		}
+	}
+
+	return false;
+}
+
+static int cfg80211_scan_6ghz(struct cfg80211_registered_device *rdev)
+{
+	u8 i;
+	struct cfg80211_colocated_ap *ap;
+	int n_channels, count = 0, err;
+	struct cfg80211_scan_request *request, *rdev_req = rdev->scan_req;
+	LIST_HEAD(coloc_ap_list);
+	bool need_scan_psc = true;
+	const struct ieee80211_sband_iftype_data *iftd;
+
+	rdev_req->scan_6ghz = true;
+
+	if (!rdev->wiphy.bands[NL80211_BAND_6GHZ])
+		return -EOPNOTSUPP;
+
+	iftd = ieee80211_get_sband_iftype_data(rdev->wiphy.bands[NL80211_BAND_6GHZ],
+					       rdev_req->wdev->iftype);
+	if (!iftd || !iftd->he_cap.has_he)
+		return -EOPNOTSUPP;
+
+	n_channels = rdev->wiphy.bands[NL80211_BAND_6GHZ]->n_channels;
+
+	if (rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ) {
+		struct cfg80211_internal_bss *intbss;
+
+		spin_lock_bh(&rdev->bss_lock);
+		list_for_each_entry(intbss, &rdev->bss_list, list) {
+			struct cfg80211_bss *res = &intbss->pub;
+			const struct cfg80211_bss_ies *ies;
+
+			ies = rcu_access_pointer(res->ies);
+			count += cfg80211_parse_colocated_ap(ies,
+							     &coloc_ap_list);
+		}
+		spin_unlock_bh(&rdev->bss_lock);
+	}
+
+	request = kzalloc(struct_size(request, channels, n_channels) +
+			  sizeof(*request->scan_6ghz_params) * count,
+			  GFP_KERNEL);
+	if (!request) {
+		cfg80211_free_coloc_ap_list(&coloc_ap_list);
+		return -ENOMEM;
+	}
+
+	*request = *rdev_req;
+	request->n_channels = 0;
+	request->scan_6ghz_params =
+		(void *)&request->channels[n_channels];
+
+	/*
+	 * PSC channels should not be scanned in case of direct scan with 1 SSID
+	 * and at least one of the reported co-located APs with same SSID
+	 * indicating that all APs in the same ESS are co-located
+	 */
+	if (count && request->n_ssids == 1 && request->ssids[0].ssid_len) {
+		list_for_each_entry(ap, &coloc_ap_list, list) {
+			if (ap->colocated_ess &&
+			    cfg80211_find_ssid_match(ap, request)) {
+				need_scan_psc = false;
+				break;
+			}
+		}
+	}
+
+	/*
+	 * add to the scan request the channels that need to be scanned
+	 * regardless of the collocated APs (PSC channels or all channels
+	 * in case that NL80211_SCAN_FLAG_COLOCATED_6GHZ is not set)
+	 */
+	for (i = 0; i < rdev_req->n_channels; i++) {
+		if (rdev_req->channels[i]->band == NL80211_BAND_6GHZ &&
+		    ((need_scan_psc &&
+		      cfg80211_channel_is_psc(rdev_req->channels[i])) ||
+		     !(rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ))) {
+			cfg80211_scan_req_add_chan(request,
+						   rdev_req->channels[i],
+						   false);
+		}
+	}
+
+	if (!(rdev_req->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ))
+		goto skip;
+
+	list_for_each_entry(ap, &coloc_ap_list, list) {
+		bool found = false;
+		struct cfg80211_scan_6ghz_params *scan_6ghz_params =
+			&request->scan_6ghz_params[request->n_6ghz_params];
+		struct ieee80211_channel *chan =
+			ieee80211_get_channel(&rdev->wiphy, ap->center_freq);
+
+		if (!chan || chan->flags & IEEE80211_CHAN_DISABLED)
+			continue;
+
+		for (i = 0; i < rdev_req->n_channels; i++) {
+			if (rdev_req->channels[i] == chan)
+				found = true;
+		}
+
+		if (!found)
+			continue;
+
+		if (request->n_ssids > 0 &&
+		    !cfg80211_find_ssid_match(ap, request))
+			continue;
+
+		cfg80211_scan_req_add_chan(request, chan, true);
+		memcpy(scan_6ghz_params->bssid, ap->bssid, ETH_ALEN);
+		scan_6ghz_params->short_ssid = ap->short_ssid;
+		scan_6ghz_params->short_ssid_valid = ap->short_ssid_valid;
+		scan_6ghz_params->unsolicited_probe = ap->unsolicited_probe;
+
+		/*
+		 * If a PSC channel is added to the scan and 'need_scan_psc' is
+		 * set to false, then all the APs that the scan logic is
+		 * interested with on the channel are collocated and thus there
+		 * is no need to perform the initial PSC channel listen.
+		 */
+		if (cfg80211_channel_is_psc(chan) && !need_scan_psc)
+			scan_6ghz_params->psc_no_listen = true;
+
+		request->n_6ghz_params++;
+	}
+
+skip:
+	cfg80211_free_coloc_ap_list(&coloc_ap_list);
+
+	if (request->n_channels) {
+		struct cfg80211_scan_request *old = rdev->int_scan_req;
+
+		rdev->int_scan_req = request;
+
+		/*
+		 * If this scan follows a previous scan, save the scan start
+		 * info from the first part of the scan
+		 */
+		if (old)
+			rdev->int_scan_req->info = old->info;
+
+		err = rdev_scan(rdev, request);
+		if (err) {
+			rdev->int_scan_req = old;
+			kfree(request);
+		} else {
+			kfree(old);
+		}
+
+		return err;
+	}
+
+	kfree(request);
+	return -EINVAL;
+}
+
+int cfg80211_scan(struct cfg80211_registered_device *rdev)
+{
+	struct cfg80211_scan_request *request;
+	struct cfg80211_scan_request *rdev_req = rdev->scan_req;
+	u32 n_channels = 0, idx, i;
+
+	if (!(rdev->wiphy.flags & WIPHY_FLAG_SPLIT_SCAN_6GHZ))
+		return rdev_scan(rdev, rdev_req);
+
+	for (i = 0; i < rdev_req->n_channels; i++) {
+		if (rdev_req->channels[i]->band != NL80211_BAND_6GHZ)
+			n_channels++;
+	}
+
+	if (!n_channels)
+		return cfg80211_scan_6ghz(rdev);
+
+	request = kzalloc(struct_size(request, channels, n_channels),
+			  GFP_KERNEL);
+	if (!request)
+		return -ENOMEM;
+
+	*request = *rdev_req;
+	request->n_channels = n_channels;
+
+	for (i = idx = 0; i < rdev_req->n_channels; i++) {
+		if (rdev_req->channels[i]->band != NL80211_BAND_6GHZ)
+			request->channels[idx++] = rdev_req->channels[i];
+	}
+
+	rdev_req->scan_6ghz = false;
+	rdev->int_scan_req = request;
+	return rdev_scan(rdev, request);
+}
+
 void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 			   bool send_message)
 {
-	struct cfg80211_scan_request *request;
+	struct cfg80211_scan_request *request, *rdev_req;
 	struct wireless_dev *wdev;
 	struct sk_buff *msg;
 #ifdef CONFIG_CFG80211_WEXT
@@ -466,11 +926,18 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 		return;
 	}
 
-	request = rdev->scan_req;
-	if (!request)
+	rdev_req = rdev->scan_req;
+	if (!rdev_req)
 		return;
 
-	wdev = request->wdev;
+	wdev = rdev_req->wdev;
+	request = rdev->int_scan_req ? rdev->int_scan_req : rdev_req;
+
+	if (wdev_running(wdev) &&
+	    (rdev->wiphy.flags & WIPHY_FLAG_SPLIT_SCAN_6GHZ) &&
+	    !rdev_req->scan_6ghz && !request->info.aborted &&
+	    !cfg80211_scan_6ghz(rdev))
+		return;
 
 	/*
 	 * This must be before sending the other events!
@@ -501,8 +968,11 @@ void ___cfg80211_scan_done(struct cfg80211_registered_device *rdev,
 	if (wdev->netdev)
 		dev_put(wdev->netdev);
 
+	kfree(rdev->int_scan_req);
+	rdev->int_scan_req = NULL;
+
+	kfree(rdev->scan_req);
 	rdev->scan_req = NULL;
-	kfree(request);
 
 	if (!send_message)
 		rdev->scan_msg = msg;
@@ -525,10 +995,25 @@ void __cfg80211_scan_done(struct work_struct *wk)
 void cfg80211_scan_done(struct cfg80211_scan_request *request,
 			struct cfg80211_scan_info *info)
 {
+	struct cfg80211_scan_info old_info = request->info;
+
 	trace_cfg80211_scan_done(request, info);
-	WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req);
+	WARN_ON(request != wiphy_to_rdev(request->wiphy)->scan_req &&
+		request != wiphy_to_rdev(request->wiphy)->int_scan_req);
 
 	request->info = *info;
+
+	/*
+	 * In case the scan is split, the scan_start_tsf and tsf_bssid should
+	 * be of the first part. In such a case old_info.scan_start_tsf should
+	 * be non zero.
+	 */
+	if (request->scan_6ghz && old_info.scan_start_tsf) {
+		request->info.scan_start_tsf = old_info.scan_start_tsf;
+		memcpy(request->info.tsf_bssid, old_info.tsf_bssid,
+		       sizeof(request->info.tsf_bssid));
+	}
+
 	request->notified = true;
 	queue_work(cfg80211_wq, &wiphy_to_rdev(request->wiphy)->scan_done_wk);
 }
@@ -1315,15 +1800,24 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen,
 	int channel_number = -1;
 	struct ieee80211_channel *alt_channel;
 
-	tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen);
-	if (tmp && tmp[1] == 1) {
-		channel_number = tmp[2];
+	if (channel->band == NL80211_BAND_S1GHZ) {
+		tmp = cfg80211_find_ie(WLAN_EID_S1G_OPERATION, ie, ielen);
+		if (tmp && tmp[1] >= sizeof(struct ieee80211_s1g_oper_ie)) {
+			struct ieee80211_s1g_oper_ie *s1gop = (void *)(tmp + 2);
+
+			channel_number = s1gop->primary_ch;
+		}
 	} else {
-		tmp = cfg80211_find_ie(WLAN_EID_HT_OPERATION, ie, ielen);
-		if (tmp && tmp[1] >= sizeof(struct ieee80211_ht_operation)) {
-			struct ieee80211_ht_operation *htop = (void *)(tmp + 2);
+		tmp = cfg80211_find_ie(WLAN_EID_DS_PARAMS, ie, ielen);
+		if (tmp && tmp[1] == 1) {
+			channel_number = tmp[2];
+		} else {
+			tmp = cfg80211_find_ie(WLAN_EID_HT_OPERATION, ie, ielen);
+			if (tmp && tmp[1] >= sizeof(struct ieee80211_ht_operation)) {
+				struct ieee80211_ht_operation *htop = (void *)(tmp + 2);
 
-			channel_number = htop->primary_chan;
+				channel_number = htop->primary_chan;
+			}
 		}
 	}
 
@@ -1405,6 +1899,9 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
 	tmp.pub.beacon_interval = beacon_interval;
 	tmp.pub.capability = capability;
 	tmp.ts_boottime = data->boottime_ns;
+	tmp.parent_tsf = data->parent_tsf;
+	ether_addr_copy(tmp.parent_bssid, data->parent_bssid);
+
 	if (non_tx_data) {
 		tmp.pub.transmitted_bss = non_tx_data->tx_bss;
 		ts = bss_from_pub(non_tx_data->tx_bss)->ts;
@@ -1488,7 +1985,7 @@ static const struct element
 					 ielen - (mbssid_end - ie));
 
 	/*
-	 * If is is not the last subelement in current MBSSID IE or there isn't
+	 * If it is not the last subelement in current MBSSID IE or there isn't
 	 * a next MBSSID IE - profile is complete.
 	*/
 	if ((sub_elem->data + sub_elem->datalen < mbssid_end - 1) ||
@@ -1807,8 +2304,11 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 	struct cfg80211_bss_ies *ies;
 	struct ieee80211_channel *channel;
 	bool signal_valid;
-	size_t ielen = len - offsetof(struct ieee80211_mgmt,
-				      u.probe_resp.variable);
+	struct ieee80211_ext *ext = NULL;
+	u8 *bssid, *variable;
+	u16 capability, beacon_int;
+	size_t ielen, min_hdr_len = offsetof(struct ieee80211_mgmt,
+					     u.probe_resp.variable);
 	int bss_type;
 
 	BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) !=
@@ -1826,21 +2326,57 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 		    (data->signal < 0 || data->signal > 100)))
 		return NULL;
 
-	if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable)))
+	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+		ext = (void *) mgmt;
+		min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon);
+		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+			min_hdr_len = offsetof(struct ieee80211_ext,
+					       u.s1g_short_beacon.variable);
+	}
+
+	if (WARN_ON(len < min_hdr_len))
 		return NULL;
 
-	channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable,
+	ielen = len - min_hdr_len;
+	variable = mgmt->u.probe_resp.variable;
+	if (ext) {
+		if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+			variable = ext->u.s1g_short_beacon.variable;
+		else
+			variable = ext->u.s1g_beacon.variable;
+	}
+
+	channel = cfg80211_get_bss_channel(wiphy, variable,
 					   ielen, data->chan, data->scan_width);
 	if (!channel)
 		return NULL;
 
+	if (ext) {
+		struct ieee80211_s1g_bcn_compat_ie *compat;
+		u8 *ie;
+
+		ie = (void *)cfg80211_find_ie(WLAN_EID_S1G_BCN_COMPAT,
+					      variable, ielen);
+		if (!ie)
+			return NULL;
+		compat = (void *)(ie + 2);
+		bssid = ext->u.s1g_beacon.sa;
+		capability = le16_to_cpu(compat->compat_info);
+		beacon_int = le16_to_cpu(compat->beacon_int);
+	} else {
+		bssid = mgmt->bssid;
+		beacon_int = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
+		capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
+	}
+
 	ies = kzalloc(sizeof(*ies) + ielen, gfp);
 	if (!ies)
 		return NULL;
 	ies->len = ielen;
 	ies->tsf = le64_to_cpu(mgmt->u.probe_resp.timestamp);
-	ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control);
-	memcpy(ies->data, mgmt->u.probe_resp.variable, ielen);
+	ies->from_beacon = ieee80211_is_beacon(mgmt->frame_control) ||
+			   ieee80211_is_s1g_beacon(mgmt->frame_control);
+	memcpy(ies->data, variable, ielen);
 
 	if (ieee80211_is_probe_resp(mgmt->frame_control))
 		rcu_assign_pointer(tmp.pub.proberesp_ies, ies);
@@ -1848,12 +2384,12 @@ cfg80211_inform_single_bss_frame_data(struct wiphy *wiphy,
 		rcu_assign_pointer(tmp.pub.beacon_ies, ies);
 	rcu_assign_pointer(tmp.pub.ies, ies);
 
-	memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN);
+	memcpy(tmp.pub.bssid, bssid, ETH_ALEN);
+	tmp.pub.beacon_interval = beacon_int;
+	tmp.pub.capability = capability;
 	tmp.pub.channel = channel;
 	tmp.pub.scan_width = data->scan_width;
 	tmp.pub.signal = data->signal;
-	tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int);
-	tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info);
 	tmp.ts_boottime = data->boottime_ns;
 	tmp.parent_tsf = data->parent_tsf;
 	tmp.pub.chains = data->chains;
diff --git a/net/wireless/sme.c b/net/wireless/sme.c
index 079ce320dc1e..38df713f2e2e 100644
--- a/net/wireless/sme.c
+++ b/net/wireless/sme.c
@@ -24,7 +24,7 @@
 
 /*
  * Software SME in cfg80211, using auth/assoc/deauth calls to the
- * driver. This is is for implementing nl80211's connect/disconnect
+ * driver. This is for implementing nl80211's connect/disconnect
  * and wireless extensions (if configured.)
  */
 
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 6e218a0acd4e..76b777d5903f 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -838,11 +838,6 @@ DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_del_mpath,
 	TP_ARGS(wiphy, netdev, mac)
 );
 
-DEFINE_EVENT(wiphy_netdev_mac_evt, rdev_set_wds_peer,
-	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, const u8 *mac),
-	TP_ARGS(wiphy, netdev, mac)
-);
-
 TRACE_EVENT(rdev_dump_station,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, int _idx,
 		 u8 *mac),
@@ -2684,19 +2679,23 @@ DEFINE_EVENT(netdev_frame_event, cfg80211_rx_mlme_mgmt,
 );
 
 TRACE_EVENT(cfg80211_tx_mlme_mgmt,
-	TP_PROTO(struct net_device *netdev, const u8 *buf, int len),
-	TP_ARGS(netdev, buf, len),
+	TP_PROTO(struct net_device *netdev, const u8 *buf, int len,
+		 bool reconnect),
+	TP_ARGS(netdev, buf, len, reconnect),
 	TP_STRUCT__entry(
 		NETDEV_ENTRY
 		__dynamic_array(u8, frame, len)
+		__field(int, reconnect)
 	),
 	TP_fast_assign(
 		NETDEV_ASSIGN;
 		memcpy(__get_dynamic_array(frame), buf, len);
+		__entry->reconnect = reconnect;
 	),
-	TP_printk(NETDEV_PR_FMT ", ftype:0x%.2x",
+	TP_printk(NETDEV_PR_FMT ", ftype:0x%.2x reconnect:%d",
 		  NETDEV_PR_ARG,
-		  le16_to_cpup((__le16 *)__get_dynamic_array(frame)))
+		  le16_to_cpup((__le16 *)__get_dynamic_array(frame)),
+		  __entry->reconnect)
 );
 
 DECLARE_EVENT_CLASS(netdev_mac_evt,
@@ -3547,6 +3546,25 @@ TRACE_EVENT(rdev_reset_tid_config,
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", peer: " MAC_PR_FMT ", tids: 0x%x",
 		  WIPHY_PR_ARG, NETDEV_PR_ARG, MAC_PR_ARG(peer), __entry->tids)
 );
+
+TRACE_EVENT(rdev_set_sar_specs,
+	TP_PROTO(struct wiphy *wiphy, struct cfg80211_sar_specs *sar),
+	TP_ARGS(wiphy, sar),
+	TP_STRUCT__entry(
+		WIPHY_ENTRY
+		__field(u16, type)
+		__field(u16, num)
+	),
+	TP_fast_assign(
+		WIPHY_ASSIGN;
+		__entry->type = sar->type;
+		__entry->num = sar->num_sub_specs;
+
+	),
+	TP_printk(WIPHY_PR_FMT ", Set type:%d, num_specs:%d",
+		  WIPHY_PR_ARG, __entry->type, __entry->num)
+);
+
 #endif /* !__RDEV_OPS_TRACE || TRACE_HEADER_MULTI_READ */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 6fa99df52f86..b4acc805114b 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -111,6 +111,33 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band)
 }
 EXPORT_SYMBOL(ieee80211_channel_to_freq_khz);
 
+enum nl80211_chan_width
+ieee80211_s1g_channel_width(const struct ieee80211_channel *chan)
+{
+	if (WARN_ON(!chan || chan->band != NL80211_BAND_S1GHZ))
+		return NL80211_CHAN_WIDTH_20_NOHT;
+
+	/*S1G defines a single allowed channel width per channel.
+	 * Extract that width here.
+	 */
+	if (chan->flags & IEEE80211_CHAN_1MHZ)
+		return NL80211_CHAN_WIDTH_1;
+	else if (chan->flags & IEEE80211_CHAN_2MHZ)
+		return NL80211_CHAN_WIDTH_2;
+	else if (chan->flags & IEEE80211_CHAN_4MHZ)
+		return NL80211_CHAN_WIDTH_4;
+	else if (chan->flags & IEEE80211_CHAN_8MHZ)
+		return NL80211_CHAN_WIDTH_8;
+	else if (chan->flags & IEEE80211_CHAN_16MHZ)
+		return NL80211_CHAN_WIDTH_16;
+
+	pr_err("unknown channel width for channel at %dKHz?\n",
+	       ieee80211_channel_to_khz(chan));
+
+	return NL80211_CHAN_WIDTH_1;
+}
+EXPORT_SYMBOL(ieee80211_s1g_channel_width);
+
 int ieee80211_freq_khz_to_channel(u32 freq)
 {
 	/* TODO: just handle MHz for now */
@@ -245,18 +272,53 @@ bool cfg80211_supported_cipher_suite(struct wiphy *wiphy, u32 cipher)
 	return false;
 }
 
-int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
-				   struct key_params *params, int key_idx,
-				   bool pairwise, const u8 *mac_addr)
+static bool
+cfg80211_igtk_cipher_supported(struct cfg80211_registered_device *rdev)
 {
-	int max_key_idx = 5;
+	struct wiphy *wiphy = &rdev->wiphy;
+	int i;
 
-	if (wiphy_ext_feature_isset(&rdev->wiphy,
-				    NL80211_EXT_FEATURE_BEACON_PROTECTION) ||
-	    wiphy_ext_feature_isset(&rdev->wiphy,
-				    NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT))
+	for (i = 0; i < wiphy->n_cipher_suites; i++) {
+		switch (wiphy->cipher_suites[i]) {
+		case WLAN_CIPHER_SUITE_AES_CMAC:
+		case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+			return true;
+		}
+	}
+
+	return false;
+}
+
+bool cfg80211_valid_key_idx(struct cfg80211_registered_device *rdev,
+			    int key_idx, bool pairwise)
+{
+	int max_key_idx;
+
+	if (pairwise)
+		max_key_idx = 3;
+	else if (wiphy_ext_feature_isset(&rdev->wiphy,
+					 NL80211_EXT_FEATURE_BEACON_PROTECTION) ||
+		 wiphy_ext_feature_isset(&rdev->wiphy,
+					 NL80211_EXT_FEATURE_BEACON_PROTECTION_CLIENT))
 		max_key_idx = 7;
+	else if (cfg80211_igtk_cipher_supported(rdev))
+		max_key_idx = 5;
+	else
+		max_key_idx = 3;
+
 	if (key_idx < 0 || key_idx > max_key_idx)
+		return false;
+
+	return true;
+}
+
+int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
+				   struct key_params *params, int key_idx,
+				   bool pairwise, const u8 *mac_addr)
+{
+	if (!cfg80211_valid_key_idx(rdev, key_idx, pairwise))
 		return -EINVAL;
 
 	if (!pairwise && mac_addr && !(rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN))
@@ -308,6 +370,7 @@ int cfg80211_validate_key_settings(struct cfg80211_registered_device *rdev,
 	case WLAN_CIPHER_SUITE_WEP104:
 		if (key_idx > 3)
 			return -EINVAL;
+		break;
 	default:
 		break;
 	}
@@ -399,6 +462,11 @@ unsigned int __attribute_const__ ieee80211_hdrlen(__le16 fc)
 {
 	unsigned int hdrlen = 24;
 
+	if (ieee80211_is_ext(fc)) {
+		hdrlen = 4;
+		goto out;
+	}
+
 	if (ieee80211_is_data(fc)) {
 		if (ieee80211_has_a4(fc))
 			hdrlen = 30;
@@ -518,8 +586,7 @@ int ieee80211_data_to_8023_exthdr(struct sk_buff *skb, struct ethhdr *ehdr,
 			return -1;
 		break;
 	case cpu_to_le16(IEEE80211_FCTL_TODS | IEEE80211_FCTL_FROMDS):
-		if (unlikely(iftype != NL80211_IFTYPE_WDS &&
-			     iftype != NL80211_IFTYPE_MESH_POINT &&
+		if (unlikely(iftype != NL80211_IFTYPE_MESH_POINT &&
 			     iftype != NL80211_IFTYPE_AP_VLAN &&
 			     iftype != NL80211_IFTYPE_STATION))
 			return -1;
@@ -1019,7 +1086,6 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 		case NL80211_IFTYPE_P2P_GO:
 		case NL80211_IFTYPE_AP:
 		case NL80211_IFTYPE_AP_VLAN:
-		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_MESH_POINT:
 			/* bridging OK */
 			break;
@@ -1031,6 +1097,7 @@ int cfg80211_change_iface(struct cfg80211_registered_device *rdev,
 			/* not happening */
 			break;
 		case NL80211_IFTYPE_P2P_DEVICE:
+		case NL80211_IFTYPE_WDS:
 		case NL80211_IFTYPE_NAN:
 			WARN_ON(1);
 			break;
@@ -1244,20 +1311,22 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate)
 
 static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
 {
-#define SCALE 2048
-	u16 mcs_divisors[12] = {
-		34133, /* 16.666666... */
-		17067, /*  8.333333... */
-		11378, /*  5.555555... */
-		 8533, /*  4.166666... */
-		 5689, /*  2.777777... */
-		 4267, /*  2.083333... */
-		 3923, /*  1.851851... */
-		 3413, /*  1.666666... */
-		 2844, /*  1.388888... */
-		 2560, /*  1.250000... */
-		 2276, /*  1.111111... */
-		 2048, /*  1.000000... */
+#define SCALE 6144
+	u32 mcs_divisors[14] = {
+		102399, /* 16.666666... */
+		 51201, /*  8.333333... */
+		 34134, /*  5.555555... */
+		 25599, /*  4.166666... */
+		 17067, /*  2.777777... */
+		 12801, /*  2.083333... */
+		 11769, /*  1.851851... */
+		 10239, /*  1.666666... */
+		  8532, /*  1.388888... */
+		  7680, /*  1.250000... */
+		  6828, /*  1.111111... */
+		  6144, /*  1.000000... */
+		  5690, /*  0.926106... */
+		  5120, /*  0.833333... */
 	};
 	u32 rates_160M[3] = { 960777777, 907400000, 816666666 };
 	u32 rates_969[3] =  { 480388888, 453700000, 408333333 };
@@ -1269,7 +1338,7 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
 	u64 tmp;
 	u32 result;
 
-	if (WARN_ON_ONCE(rate->mcs > 11))
+	if (WARN_ON_ONCE(rate->mcs > 13))
 		return 0;
 
 	if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2))
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 4d2160c989a3..fd9ad74972fb 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -49,9 +49,6 @@ int cfg80211_wext_siwmode(struct net_device *dev, struct iw_request_info *info,
 	case IW_MODE_ADHOC:
 		type = NL80211_IFTYPE_ADHOC;
 		break;
-	case IW_MODE_REPEAT:
-		type = NL80211_IFTYPE_WDS;
-		break;
 	case IW_MODE_MONITOR:
 		type = NL80211_IFTYPE_MONITOR;
 		break;
@@ -497,7 +494,7 @@ static int __cfg80211_set_encryption(struct cfg80211_registered_device *rdev,
 
 	/*
 	 * We only need to store WEP keys, since they're the only keys that
-	 * can be be set before a connection is established and persist after
+	 * can be set before a connection is established and persist after
 	 * disconnecting.
 	 */
 	if (!addr && (params->cipher == WLAN_CIPHER_SUITE_WEP40 ||
@@ -1150,50 +1147,6 @@ static int cfg80211_wext_giwpower(struct net_device *dev,
 	return 0;
 }
 
-static int cfg80211_wds_wext_siwap(struct net_device *dev,
-				   struct iw_request_info *info,
-				   struct sockaddr *addr, char *extra)
-{
-	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy);
-	int err;
-
-	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS))
-		return -EINVAL;
-
-	if (addr->sa_family != ARPHRD_ETHER)
-		return -EINVAL;
-
-	if (netif_running(dev))
-		return -EBUSY;
-
-	if (!rdev->ops->set_wds_peer)
-		return -EOPNOTSUPP;
-
-	err = rdev_set_wds_peer(rdev, dev, (u8 *)&addr->sa_data);
-	if (err)
-		return err;
-
-	memcpy(&wdev->wext.bssid, (u8 *) &addr->sa_data, ETH_ALEN);
-
-	return 0;
-}
-
-static int cfg80211_wds_wext_giwap(struct net_device *dev,
-				   struct iw_request_info *info,
-				   struct sockaddr *addr, char *extra)
-{
-	struct wireless_dev *wdev = dev->ieee80211_ptr;
-
-	if (WARN_ON(wdev->iftype != NL80211_IFTYPE_WDS))
-		return -EINVAL;
-
-	addr->sa_family = ARPHRD_ETHER;
-	memcpy(&addr->sa_data, wdev->wext.bssid, ETH_ALEN);
-
-	return 0;
-}
-
 static int cfg80211_wext_siwrate(struct net_device *dev,
 				 struct iw_request_info *info,
 				 struct iw_param *rate, char *extra)
@@ -1371,8 +1324,6 @@ static int cfg80211_wext_siwap(struct net_device *dev,
 		return cfg80211_ibss_wext_siwap(dev, info, ap_addr, extra);
 	case NL80211_IFTYPE_STATION:
 		return cfg80211_mgd_wext_siwap(dev, info, ap_addr, extra);
-	case NL80211_IFTYPE_WDS:
-		return cfg80211_wds_wext_siwap(dev, info, ap_addr, extra);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1389,8 +1340,6 @@ static int cfg80211_wext_giwap(struct net_device *dev,
 		return cfg80211_ibss_wext_giwap(dev, info, ap_addr, extra);
 	case NL80211_IFTYPE_STATION:
 		return cfg80211_mgd_wext_giwap(dev, info, ap_addr, extra);
-	case NL80211_IFTYPE_WDS:
-		return cfg80211_wds_wext_giwap(dev, info, ap_addr, extra);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1472,39 +1421,78 @@ static int cfg80211_wext_siwpmksa(struct net_device *dev,
 	}
 }
 
+#define DEFINE_WEXT_COMPAT_STUB(func, type)			\
+	static int __ ## func(struct net_device *dev,		\
+			      struct iw_request_info *info,	\
+			      union iwreq_data *wrqu,		\
+			      char *extra)			\
+	{							\
+		return func(dev, info, (type *)wrqu, extra);	\
+	}
+
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwname, char)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwfreq, struct iw_freq)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwfreq, struct iw_freq)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwmode, u32)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwmode, u32)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwrange, struct iw_point)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwap, struct sockaddr)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwap, struct sockaddr)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwmlme, struct iw_point)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwscan, struct iw_point)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwessid, struct iw_point)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwessid, struct iw_point)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwrate, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwrate, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwrts, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwrts, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwfrag, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwfrag, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwretry, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwretry, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwencode, struct iw_point)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwencode, struct iw_point)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwpower, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwpower, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwgenie, struct iw_point)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_giwauth, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwauth, struct iw_param)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwencodeext, struct iw_point)
+DEFINE_WEXT_COMPAT_STUB(cfg80211_wext_siwpmksa, struct iw_point)
+
 static const iw_handler cfg80211_handlers[] = {
-	[IW_IOCTL_IDX(SIOCGIWNAME)]	= (iw_handler) cfg80211_wext_giwname,
-	[IW_IOCTL_IDX(SIOCSIWFREQ)]	= (iw_handler) cfg80211_wext_siwfreq,
-	[IW_IOCTL_IDX(SIOCGIWFREQ)]	= (iw_handler) cfg80211_wext_giwfreq,
-	[IW_IOCTL_IDX(SIOCSIWMODE)]	= (iw_handler) cfg80211_wext_siwmode,
-	[IW_IOCTL_IDX(SIOCGIWMODE)]	= (iw_handler) cfg80211_wext_giwmode,
-	[IW_IOCTL_IDX(SIOCGIWRANGE)]	= (iw_handler) cfg80211_wext_giwrange,
-	[IW_IOCTL_IDX(SIOCSIWAP)]	= (iw_handler) cfg80211_wext_siwap,
-	[IW_IOCTL_IDX(SIOCGIWAP)]	= (iw_handler) cfg80211_wext_giwap,
-	[IW_IOCTL_IDX(SIOCSIWMLME)]	= (iw_handler) cfg80211_wext_siwmlme,
-	[IW_IOCTL_IDX(SIOCSIWSCAN)]	= (iw_handler) cfg80211_wext_siwscan,
-	[IW_IOCTL_IDX(SIOCGIWSCAN)]	= (iw_handler) cfg80211_wext_giwscan,
-	[IW_IOCTL_IDX(SIOCSIWESSID)]	= (iw_handler) cfg80211_wext_siwessid,
-	[IW_IOCTL_IDX(SIOCGIWESSID)]	= (iw_handler) cfg80211_wext_giwessid,
-	[IW_IOCTL_IDX(SIOCSIWRATE)]	= (iw_handler) cfg80211_wext_siwrate,
-	[IW_IOCTL_IDX(SIOCGIWRATE)]	= (iw_handler) cfg80211_wext_giwrate,
-	[IW_IOCTL_IDX(SIOCSIWRTS)]	= (iw_handler) cfg80211_wext_siwrts,
-	[IW_IOCTL_IDX(SIOCGIWRTS)]	= (iw_handler) cfg80211_wext_giwrts,
-	[IW_IOCTL_IDX(SIOCSIWFRAG)]	= (iw_handler) cfg80211_wext_siwfrag,
-	[IW_IOCTL_IDX(SIOCGIWFRAG)]	= (iw_handler) cfg80211_wext_giwfrag,
-	[IW_IOCTL_IDX(SIOCSIWTXPOW)]	= (iw_handler) cfg80211_wext_siwtxpower,
-	[IW_IOCTL_IDX(SIOCGIWTXPOW)]	= (iw_handler) cfg80211_wext_giwtxpower,
-	[IW_IOCTL_IDX(SIOCSIWRETRY)]	= (iw_handler) cfg80211_wext_siwretry,
-	[IW_IOCTL_IDX(SIOCGIWRETRY)]	= (iw_handler) cfg80211_wext_giwretry,
-	[IW_IOCTL_IDX(SIOCSIWENCODE)]	= (iw_handler) cfg80211_wext_siwencode,
-	[IW_IOCTL_IDX(SIOCGIWENCODE)]	= (iw_handler) cfg80211_wext_giwencode,
-	[IW_IOCTL_IDX(SIOCSIWPOWER)]	= (iw_handler) cfg80211_wext_siwpower,
-	[IW_IOCTL_IDX(SIOCGIWPOWER)]	= (iw_handler) cfg80211_wext_giwpower,
-	[IW_IOCTL_IDX(SIOCSIWGENIE)]	= (iw_handler) cfg80211_wext_siwgenie,
-	[IW_IOCTL_IDX(SIOCSIWAUTH)]	= (iw_handler) cfg80211_wext_siwauth,
-	[IW_IOCTL_IDX(SIOCGIWAUTH)]	= (iw_handler) cfg80211_wext_giwauth,
-	[IW_IOCTL_IDX(SIOCSIWENCODEEXT)]= (iw_handler) cfg80211_wext_siwencodeext,
-	[IW_IOCTL_IDX(SIOCSIWPMKSA)]	= (iw_handler) cfg80211_wext_siwpmksa,
+	[IW_IOCTL_IDX(SIOCGIWNAME)]	= __cfg80211_wext_giwname,
+	[IW_IOCTL_IDX(SIOCSIWFREQ)]	= __cfg80211_wext_siwfreq,
+	[IW_IOCTL_IDX(SIOCGIWFREQ)]	= __cfg80211_wext_giwfreq,
+	[IW_IOCTL_IDX(SIOCSIWMODE)]	= __cfg80211_wext_siwmode,
+	[IW_IOCTL_IDX(SIOCGIWMODE)]	= __cfg80211_wext_giwmode,
+	[IW_IOCTL_IDX(SIOCGIWRANGE)]	= __cfg80211_wext_giwrange,
+	[IW_IOCTL_IDX(SIOCSIWAP)]	= __cfg80211_wext_siwap,
+	[IW_IOCTL_IDX(SIOCGIWAP)]	= __cfg80211_wext_giwap,
+	[IW_IOCTL_IDX(SIOCSIWMLME)]	= __cfg80211_wext_siwmlme,
+	[IW_IOCTL_IDX(SIOCSIWSCAN)]	= cfg80211_wext_siwscan,
+	[IW_IOCTL_IDX(SIOCGIWSCAN)]	= __cfg80211_wext_giwscan,
+	[IW_IOCTL_IDX(SIOCSIWESSID)]	= __cfg80211_wext_siwessid,
+	[IW_IOCTL_IDX(SIOCGIWESSID)]	= __cfg80211_wext_giwessid,
+	[IW_IOCTL_IDX(SIOCSIWRATE)]	= __cfg80211_wext_siwrate,
+	[IW_IOCTL_IDX(SIOCGIWRATE)]	= __cfg80211_wext_giwrate,
+	[IW_IOCTL_IDX(SIOCSIWRTS)]	= __cfg80211_wext_siwrts,
+	[IW_IOCTL_IDX(SIOCGIWRTS)]	= __cfg80211_wext_giwrts,
+	[IW_IOCTL_IDX(SIOCSIWFRAG)]	= __cfg80211_wext_siwfrag,
+	[IW_IOCTL_IDX(SIOCGIWFRAG)]	= __cfg80211_wext_giwfrag,
+	[IW_IOCTL_IDX(SIOCSIWTXPOW)]	= cfg80211_wext_siwtxpower,
+	[IW_IOCTL_IDX(SIOCGIWTXPOW)]	= cfg80211_wext_giwtxpower,
+	[IW_IOCTL_IDX(SIOCSIWRETRY)]	= __cfg80211_wext_siwretry,
+	[IW_IOCTL_IDX(SIOCGIWRETRY)]	= __cfg80211_wext_giwretry,
+	[IW_IOCTL_IDX(SIOCSIWENCODE)]	= __cfg80211_wext_siwencode,
+	[IW_IOCTL_IDX(SIOCGIWENCODE)]	= __cfg80211_wext_giwencode,
+	[IW_IOCTL_IDX(SIOCSIWPOWER)]	= __cfg80211_wext_siwpower,
+	[IW_IOCTL_IDX(SIOCGIWPOWER)]	= __cfg80211_wext_giwpower,
+	[IW_IOCTL_IDX(SIOCSIWGENIE)]	= __cfg80211_wext_siwgenie,
+	[IW_IOCTL_IDX(SIOCSIWAUTH)]	= __cfg80211_wext_siwauth,
+	[IW_IOCTL_IDX(SIOCGIWAUTH)]	= __cfg80211_wext_giwauth,
+	[IW_IOCTL_IDX(SIOCSIWENCODEEXT)]= __cfg80211_wext_siwencodeext,
+	[IW_IOCTL_IDX(SIOCSIWPMKSA)]	= __cfg80211_wext_siwpmksa,
 };
 
 const struct iw_handler_def cfg80211_wext_handler = {
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index 69102fda9ebd..76a80a41615b 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -896,8 +896,9 @@ out:
 int call_commit_handler(struct net_device *dev)
 {
 #ifdef CONFIG_WIRELESS_EXT
-	if ((netif_running(dev)) &&
-	   (dev->wireless_handlers->standard[0] != NULL))
+	if (netif_running(dev) &&
+	    dev->wireless_handlers &&
+	    dev->wireless_handlers->standard[0])
 		/* Call the commit handler on the driver */
 		return dev->wireless_handlers->standard[0](dev, NULL,
 							   NULL, NULL);
diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c
index 0bbb283f23c9..ff687b97b2d9 100644
--- a/net/x25/af_x25.c
+++ b/net/x25/af_x25.c
@@ -200,22 +200,6 @@ static void x25_remove_socket(struct sock *sk)
 }
 
 /*
- *	Kill all bound sockets on a dropped device.
- */
-static void x25_kill_by_device(struct net_device *dev)
-{
-	struct sock *s;
-
-	write_lock_bh(&x25_list_lock);
-
-	sk_for_each(s, &x25_list)
-		if (x25_sk(s)->neighbour && x25_sk(s)->neighbour->dev == dev)
-			x25_disconnect(s, ENETUNREACH, 0, 0);
-
-	write_unlock_bh(&x25_list_lock);
-}
-
-/*
  *	Handle device status changes.
  */
 static int x25_device_event(struct notifier_block *this, unsigned long event,
@@ -227,27 +211,33 @@ static int x25_device_event(struct notifier_block *this, unsigned long event,
 	if (!net_eq(dev_net(dev), &init_net))
 		return NOTIFY_DONE;
 
-	if (dev->type == ARPHRD_X25
-#if IS_ENABLED(CONFIG_LLC)
-	 || dev->type == ARPHRD_ETHER
-#endif
-	 ) {
+	if (dev->type == ARPHRD_X25) {
 		switch (event) {
-		case NETDEV_UP:
+		case NETDEV_REGISTER:
+		case NETDEV_POST_TYPE_CHANGE:
 			x25_link_device_up(dev);
 			break;
-		case NETDEV_GOING_DOWN:
+		case NETDEV_DOWN:
 			nb = x25_get_neigh(dev);
 			if (nb) {
-				x25_terminate_link(nb);
+				x25_link_terminated(nb);
 				x25_neigh_put(nb);
 			}
-			break;
-		case NETDEV_DOWN:
-			x25_kill_by_device(dev);
 			x25_route_device_down(dev);
+			break;
+		case NETDEV_PRE_TYPE_CHANGE:
+		case NETDEV_UNREGISTER:
 			x25_link_device_down(dev);
 			break;
+		case NETDEV_CHANGE:
+			if (!netif_carrier_ok(dev)) {
+				nb = x25_get_neigh(dev);
+				if (nb) {
+					x25_link_terminated(nb);
+					x25_neigh_put(nb);
+				}
+			}
+			break;
 		}
 	}
 
@@ -681,7 +671,8 @@ static int x25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	int len, i, rc = 0;
 
 	if (addr_len != sizeof(struct sockaddr_x25) ||
-	    addr->sx25_family != AF_X25) {
+	    addr->sx25_family != AF_X25 ||
+	    strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN) {
 		rc = -EINVAL;
 		goto out;
 	}
@@ -775,7 +766,8 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
 
 	rc = -EINVAL;
 	if (addr_len != sizeof(struct sockaddr_x25) ||
-	    addr->sx25_family != AF_X25)
+	    addr->sx25_family != AF_X25 ||
+	    strnlen(addr->sx25_addr.x25_addr, X25_ADDR_LEN) == X25_ADDR_LEN)
 		goto out;
 
 	rc = -ENETUNREACH;
@@ -825,7 +817,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr,
 	sock->state = SS_CONNECTED;
 	rc = 0;
 out_put_neigh:
-	if (rc) {
+	if (rc && x25->neighbour) {
 		read_lock_bh(&x25_list_lock);
 		x25_neigh_put(x25->neighbour);
 		x25->neighbour = NULL;
@@ -1050,6 +1042,7 @@ int x25_rx_call_request(struct sk_buff *skb, struct x25_neigh *nb,
 	makex25->lci           = lci;
 	makex25->dest_addr     = dest_addr;
 	makex25->source_addr   = source_addr;
+	x25_neigh_hold(nb);
 	makex25->neighbour     = nb;
 	makex25->facilities    = facilities;
 	makex25->dte_facilities= dte_facilities;
diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c
index 25bf72ee6cad..5259ef8f5242 100644
--- a/net/x25/x25_dev.c
+++ b/net/x25/x25_dev.c
@@ -160,10 +160,6 @@ void x25_establish_link(struct x25_neigh *nb)
 		*ptr = X25_IFACE_CONNECT;
 		break;
 
-#if IS_ENABLED(CONFIG_LLC)
-	case ARPHRD_ETHER:
-		return;
-#endif
 	default:
 		return;
 	}
@@ -179,10 +175,6 @@ void x25_terminate_link(struct x25_neigh *nb)
 	struct sk_buff *skb;
 	unsigned char *ptr;
 
-#if IS_ENABLED(CONFIG_LLC)
-	if (nb->dev->type == ARPHRD_ETHER)
-		return;
-#endif
 	if (nb->dev->type != ARPHRD_X25)
 		return;
 
@@ -212,11 +204,6 @@ void x25_send_frame(struct sk_buff *skb, struct x25_neigh *nb)
 		*dptr = X25_IFACE_DATA;
 		break;
 
-#if IS_ENABLED(CONFIG_LLC)
-	case ARPHRD_ETHER:
-		kfree_skb(skb);
-		return;
-#endif
 	default:
 		kfree_skb(skb);
 		return;
diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c
index fdae054b7dc1..57a81100c5da 100644
--- a/net/x25/x25_link.c
+++ b/net/x25/x25_link.c
@@ -58,11 +58,6 @@ static inline void x25_stop_t20timer(struct x25_neigh *nb)
 	del_timer(&nb->t20timer);
 }
 
-static inline int x25_t20timer_pending(struct x25_neigh *nb)
-{
-	return timer_pending(&nb->t20timer);
-}
-
 /*
  *	This handles all restart and diagnostic frames.
  */
@@ -70,20 +65,45 @@ void x25_link_control(struct sk_buff *skb, struct x25_neigh *nb,
 		      unsigned short frametype)
 {
 	struct sk_buff *skbn;
-	int confirm;
 
 	switch (frametype) {
 	case X25_RESTART_REQUEST:
-		confirm = !x25_t20timer_pending(nb);
-		x25_stop_t20timer(nb);
-		nb->state = X25_LINK_STATE_3;
-		if (confirm)
+		switch (nb->state) {
+		case X25_LINK_STATE_0:
+			/* This can happen when the x25 module just gets loaded
+			 * and doesn't know layer 2 has already connected
+			 */
+			nb->state = X25_LINK_STATE_3;
 			x25_transmit_restart_confirmation(nb);
+			break;
+		case X25_LINK_STATE_2:
+			x25_stop_t20timer(nb);
+			nb->state = X25_LINK_STATE_3;
+			break;
+		case X25_LINK_STATE_3:
+			/* clear existing virtual calls */
+			x25_kill_by_neigh(nb);
+
+			x25_transmit_restart_confirmation(nb);
+			break;
+		}
 		break;
 
 	case X25_RESTART_CONFIRMATION:
-		x25_stop_t20timer(nb);
-		nb->state = X25_LINK_STATE_3;
+		switch (nb->state) {
+		case X25_LINK_STATE_2:
+			x25_stop_t20timer(nb);
+			nb->state = X25_LINK_STATE_3;
+			break;
+		case X25_LINK_STATE_3:
+			/* clear existing virtual calls */
+			x25_kill_by_neigh(nb);
+
+			x25_transmit_restart_request(nb);
+			nb->state = X25_LINK_STATE_2;
+			x25_start_t20timer(nb);
+			break;
+		}
 		break;
 
 	case X25_DIAGNOSTIC:
@@ -214,8 +234,6 @@ void x25_link_established(struct x25_neigh *nb)
 {
 	switch (nb->state) {
 	case X25_LINK_STATE_0:
-		nb->state = X25_LINK_STATE_2;
-		break;
 	case X25_LINK_STATE_1:
 		x25_transmit_restart_request(nb);
 		nb->state = X25_LINK_STATE_2;
@@ -232,6 +250,9 @@ void x25_link_established(struct x25_neigh *nb)
 void x25_link_terminated(struct x25_neigh *nb)
 {
 	nb->state = X25_LINK_STATE_0;
+	skb_queue_purge(&nb->queue);
+	x25_stop_t20timer(nb);
+
 	/* Out of order: clear existing virtual calls (X.25 03/93 4.6.3) */
 	x25_kill_by_neigh(nb);
 }
@@ -277,9 +298,6 @@ void x25_link_device_up(struct net_device *dev)
  */
 static void __x25_remove_neigh(struct x25_neigh *nb)
 {
-	skb_queue_purge(&nb->queue);
-	x25_stop_t20timer(nb);
-
 	if (nb->node.next) {
 		list_del(&nb->node);
 		x25_neigh_put(nb);
diff --git a/net/x25/x25_route.c b/net/x25/x25_route.c
index 00e46c9a5280..9fbe4bb38d94 100644
--- a/net/x25/x25_route.c
+++ b/net/x25/x25_route.c
@@ -115,9 +115,6 @@ void x25_route_device_down(struct net_device *dev)
 			__x25_remove_route(rt);
 	}
 	write_unlock_bh(&x25_route_list_lock);
-
-	/* Remove any related forwarding */
-	x25_clear_forward_by_dev(dev);
 }
 
 /*
@@ -127,12 +124,7 @@ struct net_device *x25_dev_get(char *devname)
 {
 	struct net_device *dev = dev_get_by_name(&init_net, devname);
 
-	if (dev &&
-	    (!(dev->flags & IFF_UP) || (dev->type != ARPHRD_X25
-#if IS_ENABLED(CONFIG_LLC)
-					&& dev->type != ARPHRD_ETHER
-#endif
-					))){
+	if (dev && (!(dev->flags & IFF_UP) || dev->type != ARPHRD_X25)) {
 		dev_put(dev);
 		dev = NULL;
 	}
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index b010bfde0149..56a28a686988 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -23,162 +23,6 @@
 
 static DEFINE_IDA(umem_ida);
 
-void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
-{
-	unsigned long flags;
-
-	if (!xs->tx)
-		return;
-
-	spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
-	list_add_rcu(&xs->list, &umem->xsk_tx_list);
-	spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
-}
-
-void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
-{
-	unsigned long flags;
-
-	if (!xs->tx)
-		return;
-
-	spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
-	list_del_rcu(&xs->list);
-	spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
-}
-
-/* The umem is stored both in the _rx struct and the _tx struct as we do
- * not know if the device has more tx queues than rx, or the opposite.
- * This might also change during run time.
- */
-static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem,
-			       u16 queue_id)
-{
-	if (queue_id >= max_t(unsigned int,
-			      dev->real_num_rx_queues,
-			      dev->real_num_tx_queues))
-		return -EINVAL;
-
-	if (queue_id < dev->real_num_rx_queues)
-		dev->_rx[queue_id].umem = umem;
-	if (queue_id < dev->real_num_tx_queues)
-		dev->_tx[queue_id].umem = umem;
-
-	return 0;
-}
-
-struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
-				       u16 queue_id)
-{
-	if (queue_id < dev->real_num_rx_queues)
-		return dev->_rx[queue_id].umem;
-	if (queue_id < dev->real_num_tx_queues)
-		return dev->_tx[queue_id].umem;
-
-	return NULL;
-}
-EXPORT_SYMBOL(xdp_get_umem_from_qid);
-
-static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id)
-{
-	if (queue_id < dev->real_num_rx_queues)
-		dev->_rx[queue_id].umem = NULL;
-	if (queue_id < dev->real_num_tx_queues)
-		dev->_tx[queue_id].umem = NULL;
-}
-
-int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
-			u16 queue_id, u16 flags)
-{
-	bool force_zc, force_copy;
-	struct netdev_bpf bpf;
-	int err = 0;
-
-	ASSERT_RTNL();
-
-	force_zc = flags & XDP_ZEROCOPY;
-	force_copy = flags & XDP_COPY;
-
-	if (force_zc && force_copy)
-		return -EINVAL;
-
-	if (xdp_get_umem_from_qid(dev, queue_id))
-		return -EBUSY;
-
-	err = xdp_reg_umem_at_qid(dev, umem, queue_id);
-	if (err)
-		return err;
-
-	umem->dev = dev;
-	umem->queue_id = queue_id;
-
-	if (flags & XDP_USE_NEED_WAKEUP) {
-		umem->flags |= XDP_UMEM_USES_NEED_WAKEUP;
-		/* Tx needs to be explicitly woken up the first time.
-		 * Also for supporting drivers that do not implement this
-		 * feature. They will always have to call sendto().
-		 */
-		xsk_set_tx_need_wakeup(umem);
-	}
-
-	dev_hold(dev);
-
-	if (force_copy)
-		/* For copy-mode, we are done. */
-		return 0;
-
-	if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) {
-		err = -EOPNOTSUPP;
-		goto err_unreg_umem;
-	}
-
-	bpf.command = XDP_SETUP_XSK_UMEM;
-	bpf.xsk.umem = umem;
-	bpf.xsk.queue_id = queue_id;
-
-	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
-	if (err)
-		goto err_unreg_umem;
-
-	umem->zc = true;
-	return 0;
-
-err_unreg_umem:
-	if (!force_zc)
-		err = 0; /* fallback to copy mode */
-	if (err)
-		xdp_clear_umem_at_qid(dev, queue_id);
-	return err;
-}
-
-void xdp_umem_clear_dev(struct xdp_umem *umem)
-{
-	struct netdev_bpf bpf;
-	int err;
-
-	ASSERT_RTNL();
-
-	if (!umem->dev)
-		return;
-
-	if (umem->zc) {
-		bpf.command = XDP_SETUP_XSK_UMEM;
-		bpf.xsk.umem = NULL;
-		bpf.xsk.queue_id = umem->queue_id;
-
-		err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf);
-
-		if (err)
-			WARN(1, "failed to disable umem!\n");
-	}
-
-	xdp_clear_umem_at_qid(umem->dev, umem->queue_id);
-
-	dev_put(umem->dev);
-	umem->dev = NULL;
-	umem->zc = false;
-}
-
 static void xdp_umem_unpin_pages(struct xdp_umem *umem)
 {
 	unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true);
@@ -195,25 +39,27 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem)
 	}
 }
 
-static void xdp_umem_release(struct xdp_umem *umem)
+static void xdp_umem_addr_unmap(struct xdp_umem *umem)
 {
-	rtnl_lock();
-	xdp_umem_clear_dev(umem);
-	rtnl_unlock();
-
-	ida_simple_remove(&umem_ida, umem->id);
+	vunmap(umem->addrs);
+	umem->addrs = NULL;
+}
 
-	if (umem->fq) {
-		xskq_destroy(umem->fq);
-		umem->fq = NULL;
-	}
+static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages,
+			     u32 nr_pages)
+{
+	umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!umem->addrs)
+		return -ENOMEM;
+	return 0;
+}
 
-	if (umem->cq) {
-		xskq_destroy(umem->cq);
-		umem->cq = NULL;
-	}
+static void xdp_umem_release(struct xdp_umem *umem)
+{
+	umem->zc = false;
+	ida_simple_remove(&umem_ida, umem->id);
 
-	xp_destroy(umem->pool);
+	xdp_umem_addr_unmap(umem);
 	xdp_umem_unpin_pages(umem);
 
 	xdp_umem_unaccount_pages(umem);
@@ -232,14 +78,18 @@ void xdp_get_umem(struct xdp_umem *umem)
 	refcount_inc(&umem->users);
 }
 
-void xdp_put_umem(struct xdp_umem *umem)
+void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup)
 {
 	if (!umem)
 		return;
 
 	if (refcount_dec_and_test(&umem->users)) {
-		INIT_WORK(&umem->work, xdp_umem_release_deferred);
-		schedule_work(&umem->work);
+		if (defer_cleanup) {
+			INIT_WORK(&umem->work, xdp_umem_release_deferred);
+			schedule_work(&umem->work);
+		} else {
+			xdp_umem_release(umem);
+		}
 	}
 }
 
@@ -319,8 +169,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 		return -EINVAL;
 	}
 
-	if (mr->flags & ~(XDP_UMEM_UNALIGNED_CHUNK_FLAG |
-			XDP_UMEM_USES_NEED_WAKEUP))
+	if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG)
 		return -EINVAL;
 
 	if (!unaligned_chunks && !is_power_of_2(chunk_size))
@@ -355,13 +204,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->size = size;
 	umem->headroom = headroom;
 	umem->chunk_size = chunk_size;
+	umem->chunks = chunks;
 	umem->npgs = (u32)npgs;
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
-	INIT_LIST_HEAD(&umem->xsk_tx_list);
-	spin_lock_init(&umem->xsk_tx_list_lock);
 
+	INIT_LIST_HEAD(&umem->xsk_dma_list);
 	refcount_set(&umem->users, 1);
 
 	err = xdp_umem_account_pages(umem);
@@ -372,15 +221,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (err)
 		goto out_account;
 
-	umem->pool = xp_create(umem->pgs, umem->npgs, chunks, chunk_size,
-			       headroom, size, unaligned_chunks);
-	if (!umem->pool) {
-		err = -ENOMEM;
-		goto out_pin;
-	}
+	err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs);
+	if (err)
+		goto out_unpin;
+
 	return 0;
 
-out_pin:
+out_unpin:
 	xdp_umem_unpin_pages(umem);
 out_account:
 	xdp_umem_unaccount_pages(umem);
@@ -412,8 +259,3 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr)
 
 	return umem;
 }
-
-bool xdp_umem_validate_queues(struct xdp_umem *umem)
-{
-	return umem->fq && umem->cq;
-}
diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h
index 32067fe98f65..aa9fe2780410 100644
--- a/net/xdp/xdp_umem.h
+++ b/net/xdp/xdp_umem.h
@@ -8,14 +8,8 @@
 
 #include <net/xdp_sock_drv.h>
 
-int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
-			u16 queue_id, u16 flags);
-void xdp_umem_clear_dev(struct xdp_umem *umem);
-bool xdp_umem_validate_queues(struct xdp_umem *umem);
 void xdp_get_umem(struct xdp_umem *umem);
-void xdp_put_umem(struct xdp_umem *umem);
-void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs);
-void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs);
+void xdp_put_umem(struct xdp_umem *umem, bool defer_cleanup);
 struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr);
 
 #endif /* XDP_UMEM_H_ */
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 6c5e09e7440a..4a83117507f5 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -23,6 +23,7 @@
 #include <linux/netdevice.h>
 #include <linux/rculist.h>
 #include <net/xdp_sock_drv.h>
+#include <net/busy_poll.h>
 #include <net/xdp.h>
 
 #include "xsk_queue.h"
@@ -33,71 +34,105 @@
 
 static DEFINE_PER_CPU(struct list_head, xskmap_flush_list);
 
-bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
+void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
-	return READ_ONCE(xs->rx) &&  READ_ONCE(xs->umem) &&
-		READ_ONCE(xs->umem->fq);
-}
-
-void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
-{
-	if (umem->need_wakeup & XDP_WAKEUP_RX)
+	if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
 		return;
 
-	umem->fq->ring->flags |= XDP_RING_NEED_WAKEUP;
-	umem->need_wakeup |= XDP_WAKEUP_RX;
+	pool->fq->ring->flags |= XDP_RING_NEED_WAKEUP;
+	pool->cached_need_wakeup |= XDP_WAKEUP_RX;
 }
 EXPORT_SYMBOL(xsk_set_rx_need_wakeup);
 
-void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+void xsk_set_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
 	struct xdp_sock *xs;
 
-	if (umem->need_wakeup & XDP_WAKEUP_TX)
+	if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP;
 	}
 	rcu_read_unlock();
 
-	umem->need_wakeup |= XDP_WAKEUP_TX;
+	pool->cached_need_wakeup |= XDP_WAKEUP_TX;
 }
 EXPORT_SYMBOL(xsk_set_tx_need_wakeup);
 
-void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+void xsk_clear_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
-	if (!(umem->need_wakeup & XDP_WAKEUP_RX))
+	if (!(pool->cached_need_wakeup & XDP_WAKEUP_RX))
 		return;
 
-	umem->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;
-	umem->need_wakeup &= ~XDP_WAKEUP_RX;
+	pool->fq->ring->flags &= ~XDP_RING_NEED_WAKEUP;
+	pool->cached_need_wakeup &= ~XDP_WAKEUP_RX;
 }
 EXPORT_SYMBOL(xsk_clear_rx_need_wakeup);
 
-void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+void xsk_clear_tx_need_wakeup(struct xsk_buff_pool *pool)
 {
 	struct xdp_sock *xs;
 
-	if (!(umem->need_wakeup & XDP_WAKEUP_TX))
+	if (!(pool->cached_need_wakeup & XDP_WAKEUP_TX))
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP;
 	}
 	rcu_read_unlock();
 
-	umem->need_wakeup &= ~XDP_WAKEUP_TX;
+	pool->cached_need_wakeup &= ~XDP_WAKEUP_TX;
 }
 EXPORT_SYMBOL(xsk_clear_tx_need_wakeup);
 
-bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+bool xsk_uses_need_wakeup(struct xsk_buff_pool *pool)
+{
+	return pool->uses_need_wakeup;
+}
+EXPORT_SYMBOL(xsk_uses_need_wakeup);
+
+struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev,
+					    u16 queue_id)
+{
+	if (queue_id < dev->real_num_rx_queues)
+		return dev->_rx[queue_id].pool;
+	if (queue_id < dev->real_num_tx_queues)
+		return dev->_tx[queue_id].pool;
+
+	return NULL;
+}
+EXPORT_SYMBOL(xsk_get_pool_from_qid);
+
+void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id)
+{
+	if (queue_id < dev->num_rx_queues)
+		dev->_rx[queue_id].pool = NULL;
+	if (queue_id < dev->num_tx_queues)
+		dev->_tx[queue_id].pool = NULL;
+}
+
+/* The buffer pool is stored both in the _rx struct and the _tx struct as we do
+ * not know if the device has more tx queues than rx, or the opposite.
+ * This might also change during run time.
+ */
+int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
+			u16 queue_id)
 {
-	return umem->flags & XDP_UMEM_USES_NEED_WAKEUP;
+	if (queue_id >= max_t(unsigned int,
+			      dev->real_num_rx_queues,
+			      dev->real_num_tx_queues))
+		return -EINVAL;
+
+	if (queue_id < dev->real_num_rx_queues)
+		dev->_rx[queue_id].pool = pool;
+	if (queue_id < dev->real_num_tx_queues)
+		dev->_tx[queue_id].pool = pool;
+
+	return 0;
 }
-EXPORT_SYMBOL(xsk_umem_uses_need_wakeup);
 
 void xp_release(struct xdp_buff_xsk *xskb)
 {
@@ -155,12 +190,12 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len,
 	struct xdp_buff *xsk_xdp;
 	int err;
 
-	if (len > xsk_umem_get_rx_frame_size(xs->umem)) {
+	if (len > xsk_pool_get_rx_frame_size(xs->pool)) {
 		xs->rx_dropped++;
 		return -ENOSPC;
 	}
 
-	xsk_xdp = xsk_buff_alloc(xs->umem);
+	xsk_xdp = xsk_buff_alloc(xs->pool);
 	if (!xsk_xdp) {
 		xs->rx_dropped++;
 		return -ENOSPC;
@@ -177,6 +212,14 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len,
 	return 0;
 }
 
+static bool xsk_tx_writeable(struct xdp_sock *xs)
+{
+	if (xskq_cons_present_entries(xs->tx) > xs->tx->nentries / 2)
+		return false;
+
+	return true;
+}
+
 static bool xsk_is_bound(struct xdp_sock *xs)
 {
 	if (READ_ONCE(xs->state) == XSK_BOUND) {
@@ -198,6 +241,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp,
 	if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index)
 		return -EINVAL;
 
+	sk_mark_napi_id_once_xdp(&xs->sk, xdp);
 	len = xdp->data_end - xdp->data;
 
 	return xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL ?
@@ -208,7 +252,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp,
 static void xsk_flush(struct xdp_sock *xs)
 {
 	xskq_prod_submit(xs->rx);
-	__xskq_cons_release(xs->umem->fq);
+	__xskq_cons_release(xs->pool->fq);
 	sock_def_readable(&xs->sk);
 }
 
@@ -249,32 +293,33 @@ void __xsk_map_flush(void)
 	}
 }
 
-void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
+void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries)
 {
-	xskq_prod_submit_n(umem->cq, nb_entries);
+	xskq_prod_submit_n(pool->cq, nb_entries);
 }
-EXPORT_SYMBOL(xsk_umem_complete_tx);
+EXPORT_SYMBOL(xsk_tx_completed);
 
-void xsk_umem_consume_tx_done(struct xdp_umem *umem)
+void xsk_tx_release(struct xsk_buff_pool *pool)
 {
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
 		__xskq_cons_release(xs->tx);
-		xs->sk.sk_write_space(&xs->sk);
+		if (xsk_tx_writeable(xs))
+			xs->sk.sk_write_space(&xs->sk);
 	}
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(xsk_umem_consume_tx_done);
+EXPORT_SYMBOL(xsk_tx_release);
 
-bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
+bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc)
 {
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
-		if (!xskq_cons_peek_desc(xs->tx, desc, umem)) {
+	list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) {
+		if (!xskq_cons_peek_desc(xs->tx, desc, pool)) {
 			xs->tx->queue_empty_descs++;
 			continue;
 		}
@@ -284,7 +329,7 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
-		if (xskq_prod_reserve_addr(umem->cq, desc->addr))
+		if (xskq_prod_reserve_addr(pool->cq, desc->addr))
 			goto out;
 
 		xskq_cons_release(xs->tx);
@@ -296,7 +341,64 @@ out:
 	rcu_read_unlock();
 	return false;
 }
-EXPORT_SYMBOL(xsk_umem_consume_tx);
+EXPORT_SYMBOL(xsk_tx_peek_desc);
+
+static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, struct xdp_desc *descs,
+					u32 max_entries)
+{
+	u32 nb_pkts = 0;
+
+	while (nb_pkts < max_entries && xsk_tx_peek_desc(pool, &descs[nb_pkts]))
+		nb_pkts++;
+
+	xsk_tx_release(pool);
+	return nb_pkts;
+}
+
+u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *descs,
+				   u32 max_entries)
+{
+	struct xdp_sock *xs;
+	u32 nb_pkts;
+
+	rcu_read_lock();
+	if (!list_is_singular(&pool->xsk_tx_list)) {
+		/* Fallback to the non-batched version */
+		rcu_read_unlock();
+		return xsk_tx_peek_release_fallback(pool, descs, max_entries);
+	}
+
+	xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list);
+	if (!xs) {
+		nb_pkts = 0;
+		goto out;
+	}
+
+	nb_pkts = xskq_cons_peek_desc_batch(xs->tx, descs, pool, max_entries);
+	if (!nb_pkts) {
+		xs->tx->queue_empty_descs++;
+		goto out;
+	}
+
+	/* This is the backpressure mechanism for the Tx path. Try to
+	 * reserve space in the completion queue for all packets, but
+	 * if there are fewer slots available, just process that many
+	 * packets. This avoids having to implement any buffering in
+	 * the Tx path.
+	 */
+	nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, descs, nb_pkts);
+	if (!nb_pkts)
+		goto out;
+
+	xskq_cons_release_n(xs->tx, nb_pkts);
+	__xskq_cons_release(xs->tx);
+	xs->sk.sk_write_space(&xs->sk);
+
+out:
+	rcu_read_unlock();
+	return nb_pkts;
+}
+EXPORT_SYMBOL(xsk_tx_peek_release_desc_batch);
 
 static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
 {
@@ -321,9 +423,9 @@ static void xsk_destruct_skb(struct sk_buff *skb)
 	struct xdp_sock *xs = xdp_sk(skb->sk);
 	unsigned long flags;
 
-	spin_lock_irqsave(&xs->tx_completion_lock, flags);
-	xskq_prod_submit_addr(xs->umem->cq, addr);
-	spin_unlock_irqrestore(&xs->tx_completion_lock, flags);
+	spin_lock_irqsave(&xs->pool->cq_lock, flags);
+	xskq_prod_submit_addr(xs->pool->cq, addr);
+	spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 
 	sock_wfree(skb);
 }
@@ -335,6 +437,7 @@ static int xsk_generic_xmit(struct sock *sk)
 	bool sent_frame = false;
 	struct xdp_desc desc;
 	struct sk_buff *skb;
+	unsigned long flags;
 	int err = 0;
 
 	mutex_lock(&xs->mutex);
@@ -342,7 +445,7 @@ static int xsk_generic_xmit(struct sock *sk)
 	if (xs->queue_id >= xs->dev->real_num_tx_queues)
 		goto out;
 
-	while (xskq_cons_peek_desc(xs->tx, &desc, xs->umem)) {
+	while (xskq_cons_peek_desc(xs->tx, &desc, xs->pool)) {
 		char *buffer;
 		u64 addr;
 		u32 len;
@@ -359,17 +462,20 @@ static int xsk_generic_xmit(struct sock *sk)
 
 		skb_put(skb, len);
 		addr = desc.addr;
-		buffer = xsk_buff_raw_get_data(xs->umem, addr);
+		buffer = xsk_buff_raw_get_data(xs->pool, addr);
 		err = skb_store_bits(skb, 0, buffer, len);
 		/* This is the backpressure mechanism for the Tx path.
 		 * Reserve space in the completion queue and only proceed
 		 * if there is space in it. This avoids having to implement
 		 * any buffering in the Tx path.
 		 */
-		if (unlikely(err) || xskq_prod_reserve(xs->umem->cq)) {
+		spin_lock_irqsave(&xs->pool->cq_lock, flags);
+		if (unlikely(err) || xskq_prod_reserve(xs->pool->cq)) {
+			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 			kfree_skb(skb);
 			goto out;
 		}
+		spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 
 		skb->dev = xs->dev;
 		skb->priority = sk->sk_priority;
@@ -377,14 +483,13 @@ static int xsk_generic_xmit(struct sock *sk)
 		skb_shinfo(skb)->destructor_arg = (void *)(long)desc.addr;
 		skb->destructor = xsk_destruct_skb;
 
-		/* Hinder dev_direct_xmit from freeing the packet and
-		 * therefore completing it in the destructor
-		 */
-		refcount_inc(&skb->users);
-		err = dev_direct_xmit(skb, xs->queue_id);
+		err = __dev_direct_xmit(skb, xs->queue_id);
 		if  (err == NETDEV_TX_BUSY) {
 			/* Tell user-space to retry the send */
 			skb->destructor = sock_wfree;
+			spin_lock_irqsave(&xs->pool->cq_lock, flags);
+			xskq_prod_cancel(xs->pool->cq);
+			spin_unlock_irqrestore(&xs->pool->cq_lock, flags);
 			/* Free skb without triggering the perf drop trace */
 			consume_skb(skb);
 			err = -EAGAIN;
@@ -395,12 +500,10 @@ static int xsk_generic_xmit(struct sock *sk)
 		/* Ignore NET_XMIT_CN as packet might have been sent */
 		if (err == NET_XMIT_DROP) {
 			/* SKB completed but not sent */
-			kfree_skb(skb);
 			err = -EBUSY;
 			goto out;
 		}
 
-		consume_skb(skb);
 		sent_frame = true;
 	}
 
@@ -408,7 +511,8 @@ static int xsk_generic_xmit(struct sock *sk)
 
 out:
 	if (sent_frame)
-		sk->sk_write_space(sk);
+		if (xsk_tx_writeable(xs))
+			sk->sk_write_space(sk);
 
 	mutex_unlock(&xs->mutex);
 	return err;
@@ -426,36 +530,85 @@ static int __xsk_sendmsg(struct sock *sk)
 	return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk);
 }
 
+static bool xsk_no_wakeup(struct sock *sk)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	/* Prefer busy-polling, skip the wakeup. */
+	return READ_ONCE(sk->sk_prefer_busy_poll) && READ_ONCE(sk->sk_ll_usec) &&
+		READ_ONCE(sk->sk_napi_id) >= MIN_NAPI_ID;
+#else
+	return false;
+#endif
+}
+
 static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len)
 {
 	bool need_wait = !(m->msg_flags & MSG_DONTWAIT);
 	struct sock *sk = sock->sk;
 	struct xdp_sock *xs = xdp_sk(sk);
+	struct xsk_buff_pool *pool;
+
+	if (unlikely(!xsk_is_bound(xs)))
+		return -ENXIO;
+	if (unlikely(need_wait))
+		return -EOPNOTSUPP;
+
+	if (sk_can_busy_loop(sk))
+		sk_busy_loop(sk, 1); /* only support non-blocking sockets */
+
+	if (xsk_no_wakeup(sk))
+		return 0;
+
+	pool = xs->pool;
+	if (pool->cached_need_wakeup & XDP_WAKEUP_TX)
+		return __xsk_sendmsg(sk);
+	return 0;
+}
+
+static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags)
+{
+	bool need_wait = !(flags & MSG_DONTWAIT);
+	struct sock *sk = sock->sk;
+	struct xdp_sock *xs = xdp_sk(sk);
 
 	if (unlikely(!xsk_is_bound(xs)))
 		return -ENXIO;
+	if (unlikely(!(xs->dev->flags & IFF_UP)))
+		return -ENETDOWN;
+	if (unlikely(!xs->rx))
+		return -ENOBUFS;
 	if (unlikely(need_wait))
 		return -EOPNOTSUPP;
 
-	return __xsk_sendmsg(sk);
+	if (sk_can_busy_loop(sk))
+		sk_busy_loop(sk, 1); /* only support non-blocking sockets */
+
+	if (xsk_no_wakeup(sk))
+		return 0;
+
+	if (xs->pool->cached_need_wakeup & XDP_WAKEUP_RX && xs->zc)
+		return xsk_wakeup(xs, XDP_WAKEUP_RX);
+	return 0;
 }
 
 static __poll_t xsk_poll(struct file *file, struct socket *sock,
 			     struct poll_table_struct *wait)
 {
-	__poll_t mask = datagram_poll(file, sock, wait);
+	__poll_t mask = 0;
 	struct sock *sk = sock->sk;
 	struct xdp_sock *xs = xdp_sk(sk);
-	struct xdp_umem *umem;
+	struct xsk_buff_pool *pool;
+
+	sock_poll_wait(file, sock, wait);
 
 	if (unlikely(!xsk_is_bound(xs)))
 		return mask;
 
-	umem = xs->umem;
+	pool = xs->pool;
 
-	if (umem->need_wakeup) {
+	if (pool->cached_need_wakeup) {
 		if (xs->zc)
-			xsk_wakeup(xs, umem->need_wakeup);
+			xsk_wakeup(xs, pool->cached_need_wakeup);
 		else
 			/* Poll needs to drive Tx also in copy mode */
 			__xsk_sendmsg(sk);
@@ -463,7 +616,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock,
 
 	if (xs->rx && !xskq_prod_is_empty(xs->rx))
 		mask |= EPOLLIN | EPOLLRDNORM;
-	if (xs->tx && !xskq_cons_is_full(xs->tx))
+	if (xs->tx && xsk_tx_writeable(xs))
 		mask |= EPOLLOUT | EPOLLWRNORM;
 
 	return mask;
@@ -496,7 +649,7 @@ static void xsk_unbind_dev(struct xdp_sock *xs)
 	WRITE_ONCE(xs->state, XSK_UNBOUND);
 
 	/* Wait for driver to stop using the xdp socket. */
-	xdp_del_sk_umem(xs->umem, xs);
+	xp_del_xsk(xs->pool, xs);
 	xs->dev = NULL;
 	synchronize_net();
 	dev_put(dev);
@@ -514,7 +667,7 @@ static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs,
 	node = list_first_entry_or_null(&xs->map_list, struct xsk_map_node,
 					node);
 	if (node) {
-		WARN_ON(xsk_map_inc(node->map));
+		bpf_map_inc(&node->map->map);
 		map = node->map;
 		*map_entry = node->map_entry;
 	}
@@ -544,7 +697,7 @@ static void xsk_delete_from_maps(struct xdp_sock *xs)
 
 	while ((map = xsk_get_map_list_entry(xs, &map_entry))) {
 		xsk_map_try_sock_delete(map, xs, map_entry);
-		xsk_map_put(map);
+		bpf_map_put(&map->map);
 	}
 }
 
@@ -574,6 +727,8 @@ static int xsk_release(struct socket *sock)
 
 	xskq_destroy(xs->rx);
 	xskq_destroy(xs->tx);
+	xskq_destroy(xs->fq_tmp);
+	xskq_destroy(xs->cq_tmp);
 
 	sock_orphan(sk);
 	sock->sk = NULL;
@@ -601,6 +756,11 @@ static struct socket *xsk_lookup_xsk_from_fd(int fd)
 	return sock;
 }
 
+static bool xsk_validate_queues(struct xdp_sock *xs)
+{
+	return xs->fq_tmp && xs->cq_tmp;
+}
+
 static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 {
 	struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr;
@@ -669,29 +829,70 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 			sockfd_put(sock);
 			goto out_unlock;
 		}
-		if (umem_xs->dev != dev || umem_xs->queue_id != qid) {
-			err = -EINVAL;
-			sockfd_put(sock);
-			goto out_unlock;
+
+		if (umem_xs->queue_id != qid || umem_xs->dev != dev) {
+			/* Share the umem with another socket on another qid
+			 * and/or device.
+			 */
+			xs->pool = xp_create_and_assign_umem(xs,
+							     umem_xs->umem);
+			if (!xs->pool) {
+				err = -ENOMEM;
+				sockfd_put(sock);
+				goto out_unlock;
+			}
+
+			err = xp_assign_dev_shared(xs->pool, umem_xs->umem,
+						   dev, qid);
+			if (err) {
+				xp_destroy(xs->pool);
+				xs->pool = NULL;
+				sockfd_put(sock);
+				goto out_unlock;
+			}
+		} else {
+			/* Share the buffer pool with the other socket. */
+			if (xs->fq_tmp || xs->cq_tmp) {
+				/* Do not allow setting your own fq or cq. */
+				err = -EINVAL;
+				sockfd_put(sock);
+				goto out_unlock;
+			}
+
+			xp_get_pool(umem_xs->pool);
+			xs->pool = umem_xs->pool;
 		}
 
 		xdp_get_umem(umem_xs->umem);
 		WRITE_ONCE(xs->umem, umem_xs->umem);
 		sockfd_put(sock);
-	} else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) {
+	} else if (!xs->umem || !xsk_validate_queues(xs)) {
 		err = -EINVAL;
 		goto out_unlock;
 	} else {
 		/* This xsk has its own umem. */
-		err = xdp_umem_assign_dev(xs->umem, dev, qid, flags);
-		if (err)
+		xs->pool = xp_create_and_assign_umem(xs, xs->umem);
+		if (!xs->pool) {
+			err = -ENOMEM;
+			goto out_unlock;
+		}
+
+		err = xp_assign_dev(xs->pool, dev, qid, flags);
+		if (err) {
+			xp_destroy(xs->pool);
+			xs->pool = NULL;
 			goto out_unlock;
+		}
 	}
 
+	/* FQ and CQ are now owned by the buffer pool and cleaned up with it. */
+	xs->fq_tmp = NULL;
+	xs->cq_tmp = NULL;
+
 	xs->dev = dev;
 	xs->zc = xs->umem->zc;
 	xs->queue_id = qid;
-	xdp_add_sk_umem(xs->umem, xs);
+	xp_add_xsk(xs->pool, xs);
 
 out_unlock:
 	if (err) {
@@ -797,16 +998,10 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname,
 			mutex_unlock(&xs->mutex);
 			return -EBUSY;
 		}
-		if (!xs->umem) {
-			mutex_unlock(&xs->mutex);
-			return -EINVAL;
-		}
 
-		q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq :
-			&xs->umem->cq;
+		q = (optname == XDP_UMEM_FILL_RING) ? &xs->fq_tmp :
+			&xs->cq_tmp;
 		err = xsk_init_queue(entries, q, true);
-		if (optname == XDP_UMEM_FILL_RING)
-			xp_set_fq(xs->umem->pool, *q);
 		mutex_unlock(&xs->mutex);
 		return err;
 	}
@@ -873,7 +1068,7 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname,
 		if (extra_stats) {
 			stats.rx_ring_full = xs->rx_queue_full;
 			stats.rx_fill_ring_empty_descs =
-				xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;
+				xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0;
 			stats.tx_ring_empty_descs = xskq_nb_queue_empty_descs(xs->tx);
 		} else {
 			stats.rx_dropped += xs->rx_queue_full;
@@ -975,7 +1170,6 @@ static int xsk_mmap(struct file *file, struct socket *sock,
 	unsigned long size = vma->vm_end - vma->vm_start;
 	struct xdp_sock *xs = xdp_sk(sock->sk);
 	struct xsk_queue *q = NULL;
-	struct xdp_umem *umem;
 	unsigned long pfn;
 	struct page *qpg;
 
@@ -987,16 +1181,12 @@ static int xsk_mmap(struct file *file, struct socket *sock,
 	} else if (offset == XDP_PGOFF_TX_RING) {
 		q = READ_ONCE(xs->tx);
 	} else {
-		umem = READ_ONCE(xs->umem);
-		if (!umem)
-			return -EINVAL;
-
 		/* Matches the smp_wmb() in XDP_UMEM_REG */
 		smp_rmb();
 		if (offset == XDP_UMEM_PGOFF_FILL_RING)
-			q = READ_ONCE(umem->fq);
+			q = READ_ONCE(xs->fq_tmp);
 		else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING)
-			q = READ_ONCE(umem->cq);
+			q = READ_ONCE(xs->cq_tmp);
 	}
 
 	if (!q)
@@ -1034,8 +1224,8 @@ static int xsk_notifier(struct notifier_block *this,
 
 				xsk_unbind_dev(xs);
 
-				/* Clear device references in umem. */
-				xdp_umem_clear_dev(xs->umem);
+				/* Clear device references. */
+				xp_clear_dev(xs->pool);
 			}
 			mutex_unlock(&xs->mutex);
 		}
@@ -1067,7 +1257,7 @@ static const struct proto_ops xsk_proto_ops = {
 	.setsockopt	= xsk_setsockopt,
 	.getsockopt	= xsk_getsockopt,
 	.sendmsg	= xsk_sendmsg,
-	.recvmsg	= sock_no_recvmsg,
+	.recvmsg	= xsk_recvmsg,
 	.mmap		= xsk_mmap,
 	.sendpage	= sock_no_sendpage,
 };
@@ -1079,7 +1269,8 @@ static void xsk_destruct(struct sock *sk)
 	if (!sock_flag(sk, SOCK_DEAD))
 		return;
 
-	xdp_put_umem(xs->umem);
+	if (!xp_put_pool(xs->pool))
+		xdp_put_umem(xs->umem, !xs->pool);
 
 	sk_refcnt_debug_dec(sk);
 }
@@ -1087,8 +1278,8 @@ static void xsk_destruct(struct sock *sk)
 static int xsk_create(struct net *net, struct socket *sock, int protocol,
 		      int kern)
 {
-	struct sock *sk;
 	struct xdp_sock *xs;
+	struct sock *sk;
 
 	if (!ns_capable(net->user_ns, CAP_NET_RAW))
 		return -EPERM;
@@ -1119,7 +1310,6 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol,
 	xs->state = XSK_READY;
 	mutex_init(&xs->mutex);
 	spin_lock_init(&xs->rx_lock);
-	spin_lock_init(&xs->tx_completion_lock);
 
 	INIT_LIST_HEAD(&xs->map_list);
 	spin_lock_init(&xs->map_list_lock);
diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h
index 455ddd480f3d..edcf249ad1f1 100644
--- a/net/xdp/xsk.h
+++ b/net/xdp/xsk.h
@@ -11,13 +11,6 @@
 #define XSK_NEXT_PG_CONTIG_SHIFT 0
 #define XSK_NEXT_PG_CONTIG_MASK BIT_ULL(XSK_NEXT_PG_CONTIG_SHIFT)
 
-/* Flags for the umem flags field.
- *
- * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public
- * flags. See inlude/uapi/include/linux/if_xdp.h.
- */
-#define XDP_UMEM_USES_NEED_WAKEUP BIT(1)
-
 struct xdp_ring_offset_v1 {
 	__u64 producer;
 	__u64 consumer;
@@ -46,10 +39,10 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk)
 	return (struct xdp_sock *)sk;
 }
 
-bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs);
 void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
 			     struct xdp_sock **map_entry);
-int xsk_map_inc(struct xsk_map *map);
-void xsk_map_put(struct xsk_map *map);
+void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id);
+int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool,
+			u16 queue_id);
 
 #endif /* XSK_H_ */
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index a2044c245215..20598eea658c 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -2,21 +2,34 @@
 
 #include <net/xsk_buff_pool.h>
 #include <net/xdp_sock.h>
+#include <net/xdp_sock_drv.h>
 
 #include "xsk_queue.h"
+#include "xdp_umem.h"
+#include "xsk.h"
 
-static void xp_addr_unmap(struct xsk_buff_pool *pool)
+void xp_add_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
 {
-	vunmap(pool->addrs);
+	unsigned long flags;
+
+	if (!xs->tx)
+		return;
+
+	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+	list_add_rcu(&xs->tx_list, &pool->xsk_tx_list);
+	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
 }
 
-static int xp_addr_map(struct xsk_buff_pool *pool,
-		       struct page **pages, u32 nr_pages)
+void xp_del_xsk(struct xsk_buff_pool *pool, struct xdp_sock *xs)
 {
-	pool->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
-	if (!pool->addrs)
-		return -ENOMEM;
-	return 0;
+	unsigned long flags;
+
+	if (!xs->tx)
+		return;
+
+	spin_lock_irqsave(&pool->xsk_tx_list_lock, flags);
+	list_del_rcu(&xs->tx_list);
+	spin_unlock_irqrestore(&pool->xsk_tx_list_lock, flags);
 }
 
 void xp_destroy(struct xsk_buff_pool *pool)
@@ -24,59 +37,60 @@ void xp_destroy(struct xsk_buff_pool *pool)
 	if (!pool)
 		return;
 
-	xp_addr_unmap(pool);
 	kvfree(pool->heads);
 	kvfree(pool);
 }
 
-struct xsk_buff_pool *xp_create(struct page **pages, u32 nr_pages, u32 chunks,
-				u32 chunk_size, u32 headroom, u64 size,
-				bool unaligned)
+struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
+						struct xdp_umem *umem)
 {
 	struct xsk_buff_pool *pool;
 	struct xdp_buff_xsk *xskb;
-	int err;
 	u32 i;
 
-	pool = kvzalloc(struct_size(pool, free_heads, chunks), GFP_KERNEL);
+	pool = kvzalloc(struct_size(pool, free_heads, umem->chunks),
+			GFP_KERNEL);
 	if (!pool)
 		goto out;
 
-	pool->heads = kvcalloc(chunks, sizeof(*pool->heads), GFP_KERNEL);
+	pool->heads = kvcalloc(umem->chunks, sizeof(*pool->heads), GFP_KERNEL);
 	if (!pool->heads)
 		goto out;
 
-	pool->chunk_mask = ~((u64)chunk_size - 1);
-	pool->addrs_cnt = size;
-	pool->heads_cnt = chunks;
-	pool->free_heads_cnt = chunks;
-	pool->headroom = headroom;
-	pool->chunk_size = chunk_size;
-	pool->unaligned = unaligned;
-	pool->frame_len = chunk_size - headroom - XDP_PACKET_HEADROOM;
+	pool->chunk_mask = ~((u64)umem->chunk_size - 1);
+	pool->addrs_cnt = umem->size;
+	pool->heads_cnt = umem->chunks;
+	pool->free_heads_cnt = umem->chunks;
+	pool->headroom = umem->headroom;
+	pool->chunk_size = umem->chunk_size;
+	pool->unaligned = umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG;
+	pool->frame_len = umem->chunk_size - umem->headroom -
+		XDP_PACKET_HEADROOM;
+	pool->umem = umem;
+	pool->addrs = umem->addrs;
 	INIT_LIST_HEAD(&pool->free_list);
+	INIT_LIST_HEAD(&pool->xsk_tx_list);
+	spin_lock_init(&pool->xsk_tx_list_lock);
+	spin_lock_init(&pool->cq_lock);
+	refcount_set(&pool->users, 1);
+
+	pool->fq = xs->fq_tmp;
+	pool->cq = xs->cq_tmp;
 
 	for (i = 0; i < pool->free_heads_cnt; i++) {
 		xskb = &pool->heads[i];
 		xskb->pool = pool;
-		xskb->xdp.frame_sz = chunk_size - headroom;
+		xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
 		pool->free_heads[i] = xskb;
 	}
 
-	err = xp_addr_map(pool, pages, nr_pages);
-	if (!err)
-		return pool;
+	return pool;
 
 out:
 	xp_destroy(pool);
 	return NULL;
 }
 
-void xp_set_fq(struct xsk_buff_pool *pool, struct xsk_queue *fq)
-{
-	pool->fq = fq;
-}
-
 void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 {
 	u32 i;
@@ -86,70 +100,325 @@ void xp_set_rxq_info(struct xsk_buff_pool *pool, struct xdp_rxq_info *rxq)
 }
 EXPORT_SYMBOL(xp_set_rxq_info);
 
-void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
+static void xp_disable_drv_zc(struct xsk_buff_pool *pool)
 {
-	dma_addr_t *dma;
-	u32 i;
+	struct netdev_bpf bpf;
+	int err;
 
-	if (pool->dma_pages_cnt == 0)
+	ASSERT_RTNL();
+
+	if (pool->umem->zc) {
+		bpf.command = XDP_SETUP_XSK_POOL;
+		bpf.xsk.pool = NULL;
+		bpf.xsk.queue_id = pool->queue_id;
+
+		err = pool->netdev->netdev_ops->ndo_bpf(pool->netdev, &bpf);
+
+		if (err)
+			WARN(1, "Failed to disable zero-copy!\n");
+	}
+}
+
+static int __xp_assign_dev(struct xsk_buff_pool *pool,
+			   struct net_device *netdev, u16 queue_id, u16 flags)
+{
+	bool force_zc, force_copy;
+	struct netdev_bpf bpf;
+	int err = 0;
+
+	ASSERT_RTNL();
+
+	force_zc = flags & XDP_ZEROCOPY;
+	force_copy = flags & XDP_COPY;
+
+	if (force_zc && force_copy)
+		return -EINVAL;
+
+	if (xsk_get_pool_from_qid(netdev, queue_id))
+		return -EBUSY;
+
+	pool->netdev = netdev;
+	pool->queue_id = queue_id;
+	err = xsk_reg_pool_at_qid(netdev, pool, queue_id);
+	if (err)
+		return err;
+
+	if (flags & XDP_USE_NEED_WAKEUP)
+		pool->uses_need_wakeup = true;
+	/* Tx needs to be explicitly woken up the first time.  Also
+	 * for supporting drivers that do not implement this
+	 * feature. They will always have to call sendto() or poll().
+	 */
+	pool->cached_need_wakeup = XDP_WAKEUP_TX;
+
+	dev_hold(netdev);
+
+	if (force_copy)
+		/* For copy-mode, we are done. */
+		return 0;
+
+	if (!netdev->netdev_ops->ndo_bpf ||
+	    !netdev->netdev_ops->ndo_xsk_wakeup) {
+		err = -EOPNOTSUPP;
+		goto err_unreg_pool;
+	}
+
+	bpf.command = XDP_SETUP_XSK_POOL;
+	bpf.xsk.pool = pool;
+	bpf.xsk.queue_id = queue_id;
+
+	err = netdev->netdev_ops->ndo_bpf(netdev, &bpf);
+	if (err)
+		goto err_unreg_pool;
+
+	if (!pool->dma_pages) {
+		WARN(1, "Driver did not DMA map zero-copy buffers");
+		err = -EINVAL;
+		goto err_unreg_xsk;
+	}
+	pool->umem->zc = true;
+	return 0;
+
+err_unreg_xsk:
+	xp_disable_drv_zc(pool);
+err_unreg_pool:
+	if (!force_zc)
+		err = 0; /* fallback to copy mode */
+	if (err) {
+		xsk_clear_pool_at_qid(netdev, queue_id);
+		dev_put(netdev);
+	}
+	return err;
+}
+
+int xp_assign_dev(struct xsk_buff_pool *pool, struct net_device *dev,
+		  u16 queue_id, u16 flags)
+{
+	return __xp_assign_dev(pool, dev, queue_id, flags);
+}
+
+int xp_assign_dev_shared(struct xsk_buff_pool *pool, struct xdp_umem *umem,
+			 struct net_device *dev, u16 queue_id)
+{
+	u16 flags;
+
+	/* One fill and completion ring required for each queue id. */
+	if (!pool->fq || !pool->cq)
+		return -EINVAL;
+
+	flags = umem->zc ? XDP_ZEROCOPY : XDP_COPY;
+	if (pool->uses_need_wakeup)
+		flags |= XDP_USE_NEED_WAKEUP;
+
+	return __xp_assign_dev(pool, dev, queue_id, flags);
+}
+
+void xp_clear_dev(struct xsk_buff_pool *pool)
+{
+	if (!pool->netdev)
 		return;
 
-	for (i = 0; i < pool->dma_pages_cnt; i++) {
-		dma = &pool->dma_pages[i];
+	xp_disable_drv_zc(pool);
+	xsk_clear_pool_at_qid(pool->netdev, pool->queue_id);
+	dev_put(pool->netdev);
+	pool->netdev = NULL;
+}
+
+static void xp_release_deferred(struct work_struct *work)
+{
+	struct xsk_buff_pool *pool = container_of(work, struct xsk_buff_pool,
+						  work);
+
+	rtnl_lock();
+	xp_clear_dev(pool);
+	rtnl_unlock();
+
+	if (pool->fq) {
+		xskq_destroy(pool->fq);
+		pool->fq = NULL;
+	}
+
+	if (pool->cq) {
+		xskq_destroy(pool->cq);
+		pool->cq = NULL;
+	}
+
+	xdp_put_umem(pool->umem, false);
+	xp_destroy(pool);
+}
+
+void xp_get_pool(struct xsk_buff_pool *pool)
+{
+	refcount_inc(&pool->users);
+}
+
+bool xp_put_pool(struct xsk_buff_pool *pool)
+{
+	if (!pool)
+		return false;
+
+	if (refcount_dec_and_test(&pool->users)) {
+		INIT_WORK(&pool->work, xp_release_deferred);
+		schedule_work(&pool->work);
+		return true;
+	}
+
+	return false;
+}
+
+static struct xsk_dma_map *xp_find_dma_map(struct xsk_buff_pool *pool)
+{
+	struct xsk_dma_map *dma_map;
+
+	list_for_each_entry(dma_map, &pool->umem->xsk_dma_list, list) {
+		if (dma_map->netdev == pool->netdev)
+			return dma_map;
+	}
+
+	return NULL;
+}
+
+static struct xsk_dma_map *xp_create_dma_map(struct device *dev, struct net_device *netdev,
+					     u32 nr_pages, struct xdp_umem *umem)
+{
+	struct xsk_dma_map *dma_map;
+
+	dma_map = kzalloc(sizeof(*dma_map), GFP_KERNEL);
+	if (!dma_map)
+		return NULL;
+
+	dma_map->dma_pages = kvcalloc(nr_pages, sizeof(*dma_map->dma_pages), GFP_KERNEL);
+	if (!dma_map->dma_pages) {
+		kfree(dma_map);
+		return NULL;
+	}
+
+	dma_map->netdev = netdev;
+	dma_map->dev = dev;
+	dma_map->dma_need_sync = false;
+	dma_map->dma_pages_cnt = nr_pages;
+	refcount_set(&dma_map->users, 1);
+	list_add(&dma_map->list, &umem->xsk_dma_list);
+	return dma_map;
+}
+
+static void xp_destroy_dma_map(struct xsk_dma_map *dma_map)
+{
+	list_del(&dma_map->list);
+	kvfree(dma_map->dma_pages);
+	kfree(dma_map);
+}
+
+static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs)
+{
+	dma_addr_t *dma;
+	u32 i;
+
+	for (i = 0; i < dma_map->dma_pages_cnt; i++) {
+		dma = &dma_map->dma_pages[i];
 		if (*dma) {
-			dma_unmap_page_attrs(pool->dev, *dma, PAGE_SIZE,
+			dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE,
 					     DMA_BIDIRECTIONAL, attrs);
 			*dma = 0;
 		}
 	}
 
+	xp_destroy_dma_map(dma_map);
+}
+
+void xp_dma_unmap(struct xsk_buff_pool *pool, unsigned long attrs)
+{
+	struct xsk_dma_map *dma_map;
+
+	if (pool->dma_pages_cnt == 0)
+		return;
+
+	dma_map = xp_find_dma_map(pool);
+	if (!dma_map) {
+		WARN(1, "Could not find dma_map for device");
+		return;
+	}
+
+	if (!refcount_dec_and_test(&dma_map->users))
+		return;
+
+	__xp_dma_unmap(dma_map, attrs);
 	kvfree(pool->dma_pages);
 	pool->dma_pages_cnt = 0;
 	pool->dev = NULL;
 }
 EXPORT_SYMBOL(xp_dma_unmap);
 
-static void xp_check_dma_contiguity(struct xsk_buff_pool *pool)
+static void xp_check_dma_contiguity(struct xsk_dma_map *dma_map)
 {
 	u32 i;
 
-	for (i = 0; i < pool->dma_pages_cnt - 1; i++) {
-		if (pool->dma_pages[i] + PAGE_SIZE == pool->dma_pages[i + 1])
-			pool->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK;
+	for (i = 0; i < dma_map->dma_pages_cnt - 1; i++) {
+		if (dma_map->dma_pages[i] + PAGE_SIZE == dma_map->dma_pages[i + 1])
+			dma_map->dma_pages[i] |= XSK_NEXT_PG_CONTIG_MASK;
 		else
-			pool->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK;
+			dma_map->dma_pages[i] &= ~XSK_NEXT_PG_CONTIG_MASK;
 	}
 }
 
+static int xp_init_dma_info(struct xsk_buff_pool *pool, struct xsk_dma_map *dma_map)
+{
+	pool->dma_pages = kvcalloc(dma_map->dma_pages_cnt, sizeof(*pool->dma_pages), GFP_KERNEL);
+	if (!pool->dma_pages)
+		return -ENOMEM;
+
+	pool->dev = dma_map->dev;
+	pool->dma_pages_cnt = dma_map->dma_pages_cnt;
+	pool->dma_need_sync = dma_map->dma_need_sync;
+	memcpy(pool->dma_pages, dma_map->dma_pages,
+	       pool->dma_pages_cnt * sizeof(*pool->dma_pages));
+
+	return 0;
+}
+
 int xp_dma_map(struct xsk_buff_pool *pool, struct device *dev,
 	       unsigned long attrs, struct page **pages, u32 nr_pages)
 {
+	struct xsk_dma_map *dma_map;
 	dma_addr_t dma;
+	int err;
 	u32 i;
 
-	pool->dma_pages = kvcalloc(nr_pages, sizeof(*pool->dma_pages),
-				   GFP_KERNEL);
-	if (!pool->dma_pages)
-		return -ENOMEM;
+	dma_map = xp_find_dma_map(pool);
+	if (dma_map) {
+		err = xp_init_dma_info(pool, dma_map);
+		if (err)
+			return err;
+
+		refcount_inc(&dma_map->users);
+		return 0;
+	}
 
-	pool->dev = dev;
-	pool->dma_pages_cnt = nr_pages;
-	pool->dma_need_sync = false;
+	dma_map = xp_create_dma_map(dev, pool->netdev, nr_pages, pool->umem);
+	if (!dma_map)
+		return -ENOMEM;
 
-	for (i = 0; i < pool->dma_pages_cnt; i++) {
+	for (i = 0; i < dma_map->dma_pages_cnt; i++) {
 		dma = dma_map_page_attrs(dev, pages[i], 0, PAGE_SIZE,
 					 DMA_BIDIRECTIONAL, attrs);
 		if (dma_mapping_error(dev, dma)) {
-			xp_dma_unmap(pool, attrs);
+			__xp_dma_unmap(dma_map, attrs);
 			return -ENOMEM;
 		}
 		if (dma_need_sync(dev, dma))
-			pool->dma_need_sync = true;
-		pool->dma_pages[i] = dma;
+			dma_map->dma_need_sync = true;
+		dma_map->dma_pages[i] = dma;
 	}
 
 	if (pool->unaligned)
-		xp_check_dma_contiguity(pool);
+		xp_check_dma_contiguity(dma_map);
+
+	err = xp_init_dma_info(pool, dma_map);
+	if (err) {
+		__xp_dma_unmap(dma_map, attrs);
+		return err;
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL(xp_dma_map);
diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c
index 21e9c2d123ee..c014217f5fa7 100644
--- a/net/xdp/xsk_diag.c
+++ b/net/xdp/xsk_diag.c
@@ -46,6 +46,7 @@ static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs,
 
 static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
 {
+	struct xsk_buff_pool *pool = xs->pool;
 	struct xdp_umem *umem = xs->umem;
 	struct xdp_diag_umem du = {};
 	int err;
@@ -58,21 +59,20 @@ static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb)
 	du.num_pages = umem->npgs;
 	du.chunk_size = umem->chunk_size;
 	du.headroom = umem->headroom;
-	du.ifindex = umem->dev ? umem->dev->ifindex : 0;
-	du.queue_id = umem->queue_id;
+	du.ifindex = (pool && pool->netdev) ? pool->netdev->ifindex : 0;
+	du.queue_id = pool ? pool->queue_id : 0;
 	du.flags = 0;
 	if (umem->zc)
 		du.flags |= XDP_DU_F_ZEROCOPY;
 	du.refs = refcount_read(&umem->users);
 
 	err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du);
-
-	if (!err && umem->fq)
-		err = xsk_diag_put_ring(umem->fq, XDP_DIAG_UMEM_FILL_RING, nlskb);
-	if (!err && umem->cq) {
-		err = xsk_diag_put_ring(umem->cq, XDP_DIAG_UMEM_COMPLETION_RING,
-					nlskb);
-	}
+	if (!err && pool && pool->fq)
+		err = xsk_diag_put_ring(pool->fq,
+					XDP_DIAG_UMEM_FILL_RING, nlskb);
+	if (!err && pool && pool->cq)
+		err = xsk_diag_put_ring(pool->cq,
+					XDP_DIAG_UMEM_COMPLETION_RING, nlskb);
 	return err;
 }
 
@@ -83,7 +83,7 @@ static int xsk_diag_put_stats(const struct xdp_sock *xs, struct sk_buff *nlskb)
 	du.n_rx_dropped = xs->rx_dropped;
 	du.n_rx_invalid = xskq_nb_invalid_descs(xs->rx);
 	du.n_rx_full = xs->rx_queue_full;
-	du.n_fill_ring_empty = xs->umem ? xskq_nb_queue_empty_descs(xs->umem->fq) : 0;
+	du.n_fill_ring_empty = xs->pool ? xskq_nb_queue_empty_descs(xs->pool->fq) : 0;
 	du.n_tx_invalid = xskq_nb_invalid_descs(xs->tx);
 	du.n_tx_ring_empty = xskq_nb_queue_empty_descs(xs->tx);
 	return nla_put(nlskb, XDP_DIAG_STATS, sizeof(du), &du);
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index bf42cfd74b89..2823b7c3302d 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -15,8 +15,14 @@
 
 struct xdp_ring {
 	u32 producer ____cacheline_aligned_in_smp;
+	/* Hinder the adjacent cache prefetcher to prefetch the consumer
+	 * pointer if the producer pointer is touched and vice versa.
+	 */
+	u32 pad1 ____cacheline_aligned_in_smp;
 	u32 consumer ____cacheline_aligned_in_smp;
+	u32 pad2 ____cacheline_aligned_in_smp;
 	u32 flags;
+	u32 pad3 ____cacheline_aligned_in_smp;
 };
 
 /* Used for the RX and TX queues for packets */
@@ -96,7 +102,7 @@ struct xsk_queue {
  * seen and read by the consumer.
  *
  * The consumer peeks into the ring to see if the producer has written
- * any new entries. If so, the producer can then read these entries
+ * any new entries. If so, the consumer can then read these entries
  * and when it is done reading them release them back to the producer
  * so that the producer can use these slots to fill in new entries.
  *
@@ -166,9 +172,9 @@ static inline bool xp_validate_desc(struct xsk_buff_pool *pool,
 
 static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
 					   struct xdp_desc *d,
-					   struct xdp_umem *umem)
+					   struct xsk_buff_pool *pool)
 {
-	if (!xp_validate_desc(umem->pool, d)) {
+	if (!xp_validate_desc(pool, d)) {
 		q->invalid_descs++;
 		return false;
 	}
@@ -177,14 +183,14 @@ static inline bool xskq_cons_is_valid_desc(struct xsk_queue *q,
 
 static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 				       struct xdp_desc *desc,
-				       struct xdp_umem *umem)
+				       struct xsk_buff_pool *pool)
 {
 	while (q->cached_cons != q->cached_prod) {
 		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
 		u32 idx = q->cached_cons & q->ring_mask;
 
 		*desc = ring->desc[idx];
-		if (xskq_cons_is_valid_desc(q, desc, umem))
+		if (xskq_cons_is_valid_desc(q, desc, pool))
 			return true;
 
 		q->cached_cons++;
@@ -193,6 +199,30 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q,
 	return false;
 }
 
+static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q,
+					    struct xdp_desc *descs,
+					    struct xsk_buff_pool *pool, u32 max)
+{
+	u32 cached_cons = q->cached_cons, nb_entries = 0;
+
+	while (cached_cons != q->cached_prod && nb_entries < max) {
+		struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring;
+		u32 idx = cached_cons & q->ring_mask;
+
+		descs[nb_entries] = ring->desc[idx];
+		if (unlikely(!xskq_cons_is_valid_desc(q, &descs[nb_entries], pool))) {
+			/* Skip the entry */
+			cached_cons++;
+			continue;
+		}
+
+		nb_entries++;
+		cached_cons++;
+	}
+
+	return nb_entries;
+}
+
 /* Functions for consumers */
 
 static inline void __xskq_cons_release(struct xsk_queue *q)
@@ -214,17 +244,22 @@ static inline void xskq_cons_get_entries(struct xsk_queue *q)
 	__xskq_cons_peek(q);
 }
 
-static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt)
+static inline u32 xskq_cons_nb_entries(struct xsk_queue *q, u32 max)
 {
 	u32 entries = q->cached_prod - q->cached_cons;
 
-	if (entries >= cnt)
-		return true;
+	if (entries >= max)
+		return max;
 
 	__xskq_cons_peek(q);
 	entries = q->cached_prod - q->cached_cons;
 
-	return entries >= cnt;
+	return entries >= max ? max : entries;
+}
+
+static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt)
+{
+	return xskq_cons_nb_entries(q, cnt) >= cnt ? true : false;
 }
 
 static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr)
@@ -236,23 +271,35 @@ static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr)
 
 static inline bool xskq_cons_peek_desc(struct xsk_queue *q,
 				       struct xdp_desc *desc,
-				       struct xdp_umem *umem)
+				       struct xsk_buff_pool *pool)
 {
 	if (q->cached_prod == q->cached_cons)
 		xskq_cons_get_entries(q);
-	return xskq_cons_read_desc(q, desc, umem);
+	return xskq_cons_read_desc(q, desc, pool);
 }
 
+static inline u32 xskq_cons_peek_desc_batch(struct xsk_queue *q, struct xdp_desc *descs,
+					    struct xsk_buff_pool *pool, u32 max)
+{
+	u32 entries = xskq_cons_nb_entries(q, max);
+
+	return xskq_cons_read_desc_batch(q, descs, pool, entries);
+}
+
+/* To improve performance in the xskq_cons_release functions, only update local state here.
+ * Reflect this to global state when we get new entries from the ring in
+ * xskq_cons_get_entries() and whenever Rx or Tx processing are completed in the NAPI loop.
+ */
 static inline void xskq_cons_release(struct xsk_queue *q)
 {
-	/* To improve performance, only update local state here.
-	 * Reflect this to global state when we get new entries
-	 * from the ring in xskq_cons_get_entries() and whenever
-	 * Rx or Tx processing are completed in the NAPI loop.
-	 */
 	q->cached_cons++;
 }
 
+static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt)
+{
+	q->cached_cons += cnt;
+}
+
 static inline bool xskq_cons_is_full(struct xsk_queue *q)
 {
 	/* No barriers needed since data is not accessed */
@@ -260,20 +307,36 @@ static inline bool xskq_cons_is_full(struct xsk_queue *q)
 		q->nentries;
 }
 
+static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
+{
+	/* No barriers needed since data is not accessed */
+	return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer);
+}
+
 /* Functions for producers */
 
-static inline bool xskq_prod_is_full(struct xsk_queue *q)
+static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max)
 {
 	u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons);
 
-	if (free_entries)
-		return false;
+	if (free_entries >= max)
+		return max;
 
 	/* Refresh the local tail pointer */
 	q->cached_cons = READ_ONCE(q->ring->consumer);
 	free_entries = q->nentries - (q->cached_prod - q->cached_cons);
 
-	return !free_entries;
+	return free_entries >= max ? max : free_entries;
+}
+
+static inline bool xskq_prod_is_full(struct xsk_queue *q)
+{
+	return xskq_prod_nb_free(q, 1) ? false : true;
+}
+
+static inline void xskq_prod_cancel(struct xsk_queue *q)
+{
+	q->cached_prod--;
 }
 
 static inline int xskq_prod_reserve(struct xsk_queue *q)
@@ -298,6 +361,23 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr)
 	return 0;
 }
 
+static inline u32 xskq_prod_reserve_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
+					       u32 max)
+{
+	struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
+	u32 nb_entries, i, cached_prod;
+
+	nb_entries = xskq_prod_nb_free(q, max);
+
+	/* A, matches D */
+	cached_prod = q->cached_prod;
+	for (i = 0; i < nb_entries; i++)
+		ring->desc[cached_prod++ & q->ring_mask] = descs[i].addr;
+	q->cached_prod = cached_prod;
+
+	return nb_entries;
+}
+
 static inline int xskq_prod_reserve_desc(struct xsk_queue *q,
 					 u64 addr, u32 len)
 {
diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c
index 8367adbbe9df..113fd9017203 100644
--- a/net/xdp/xskmap.c
+++ b/net/xdp/xskmap.c
@@ -11,32 +11,17 @@
 
 #include "xsk.h"
 
-int xsk_map_inc(struct xsk_map *map)
-{
-	bpf_map_inc(&map->map);
-	return 0;
-}
-
-void xsk_map_put(struct xsk_map *map)
-{
-	bpf_map_put(&map->map);
-}
-
 static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
 					       struct xdp_sock **map_entry)
 {
 	struct xsk_map_node *node;
-	int err;
 
-	node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN);
+	node = bpf_map_kzalloc(&map->map, sizeof(*node),
+			       GFP_ATOMIC | __GFP_NOWARN);
 	if (!node)
 		return ERR_PTR(-ENOMEM);
 
-	err = xsk_map_inc(map);
-	if (err) {
-		kfree(node);
-		return ERR_PTR(err);
-	}
+	bpf_map_inc(&map->map);
 
 	node->map = map;
 	node->map_entry = map_entry;
@@ -45,7 +30,7 @@ static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map,
 
 static void xsk_map_node_free(struct xsk_map_node *node)
 {
-	xsk_map_put(node->map);
+	bpf_map_put(&node->map->map);
 	kfree(node);
 }
 
@@ -73,9 +58,8 @@ static void xsk_map_sock_delete(struct xdp_sock *xs,
 
 static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 {
-	struct bpf_map_memory mem;
-	int err, numa_node;
 	struct xsk_map *m;
+	int numa_node;
 	u64 size;
 
 	if (!capable(CAP_NET_ADMIN))
@@ -89,18 +73,11 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr)
 	numa_node = bpf_map_attr_numa_node(attr);
 	size = struct_size(m, xsk_map, attr->max_entries);
 
-	err = bpf_map_charge_init(&mem, size);
-	if (err < 0)
-		return ERR_PTR(err);
-
 	m = bpf_map_area_alloc(size, numa_node);
-	if (!m) {
-		bpf_map_charge_finish(&mem);
+	if (!m)
 		return ERR_PTR(-ENOMEM);
-	}
 
 	bpf_map_init_from_attr(&m->map, attr);
-	bpf_map_charge_move(&m->map.memory, &mem);
 	spin_lock_init(&m->lock);
 
 	return &m->map;
@@ -132,7 +109,7 @@ static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
 	return 0;
 }
 
-static u32 xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
+static int xsk_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
 {
 	const int ret = BPF_REG_0, mp = BPF_REG_1, index = BPF_REG_2;
 	struct bpf_insn *insn = insn_buf;
@@ -185,11 +162,6 @@ static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value,
 
 	xs = (struct xdp_sock *)sock->sk;
 
-	if (!xsk_is_setup_for_bpf_map(xs)) {
-		sockfd_put(sock);
-		return -EOPNOTSUPP;
-	}
-
 	map_entry = &m->xsk_map[i];
 	node = xsk_map_node_alloc(m, map_entry);
 	if (IS_ERR(node)) {
@@ -254,8 +226,16 @@ void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
 	spin_unlock_bh(&map->lock);
 }
 
+static bool xsk_map_meta_equal(const struct bpf_map *meta0,
+			       const struct bpf_map *meta1)
+{
+	return meta0->max_entries == meta1->max_entries &&
+		bpf_map_meta_equal(meta0, meta1);
+}
+
 static int xsk_map_btf_id;
 const struct bpf_map_ops xsk_map_ops = {
+	.map_meta_equal = xsk_map_meta_equal,
 	.map_alloc = xsk_map_alloc,
 	.map_free = xsk_map_free,
 	.map_get_next_key = xsk_map_get_next_key,
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 5b9a5ab48111..3adf31a83a79 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -28,6 +28,17 @@ config XFRM_USER
 
 	  If unsure, say Y.
 
+config XFRM_USER_COMPAT
+	tristate "Compatible ABI support"
+	depends on XFRM_USER && COMPAT_FOR_U64_ALIGNMENT && \
+		HAVE_EFFICIENT_UNALIGNED_ACCESS
+	select WANT_COMPAT_NETLINK_MESSAGES
+	help
+	  Transformation(XFRM) user configuration interface like IPsec
+	  used by compatible Linux applications.
+
+	  If unsure, say N.
+
 config XFRM_INTERFACE
 	tristate "Transformation virtual interface"
 	depends on XFRM && IPV6
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index 2d4bb4b9f75e..494aa744bfb9 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_XFRM) := xfrm_policy.o xfrm_state.o xfrm_hash.o \
 obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o
 obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o
 obj-$(CONFIG_XFRM_USER) += xfrm_user.o
+obj-$(CONFIG_XFRM_USER_COMPAT) += xfrm_compat.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
 obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
 obj-$(CONFIG_XFRM_ESPINTCP) += espintcp.o
diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c
new file mode 100644
index 000000000000..d8e8a11ca845
--- /dev/null
+++ b/net/xfrm/xfrm_compat.c
@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * XFRM compat layer
+ * Author: Dmitry Safonov <dima@arista.com>
+ * Based on code and translator idea by: Florian Westphal <fw@strlen.de>
+ */
+#include <linux/compat.h>
+#include <linux/xfrm.h>
+#include <net/xfrm.h>
+
+struct compat_xfrm_lifetime_cfg {
+	compat_u64 soft_byte_limit, hard_byte_limit;
+	compat_u64 soft_packet_limit, hard_packet_limit;
+	compat_u64 soft_add_expires_seconds, hard_add_expires_seconds;
+	compat_u64 soft_use_expires_seconds, hard_use_expires_seconds;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_lifetime_cur {
+	compat_u64 bytes, packets, add_time, use_time;
+}; /* same size on 32bit, but only 4 byte alignment required */
+
+struct compat_xfrm_userpolicy_info {
+	struct xfrm_selector sel;
+	struct compat_xfrm_lifetime_cfg lft;
+	struct compat_xfrm_lifetime_cur curlft;
+	__u32 priority, index;
+	u8 dir, action, flags, share;
+	/* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_usersa_info {
+	struct xfrm_selector sel;
+	struct xfrm_id id;
+	xfrm_address_t saddr;
+	struct compat_xfrm_lifetime_cfg lft;
+	struct compat_xfrm_lifetime_cur curlft;
+	struct xfrm_stats stats;
+	__u32 seq, reqid;
+	u16 family;
+	u8 mode, replay_window, flags;
+	/* 4 bytes additional padding on 64bit */
+};
+
+struct compat_xfrm_user_acquire {
+	struct xfrm_id id;
+	xfrm_address_t saddr;
+	struct xfrm_selector sel;
+	struct compat_xfrm_userpolicy_info policy;
+	/* 4 bytes additional padding on 64bit */
+	__u32 aalgos, ealgos, calgos, seq;
+};
+
+struct compat_xfrm_userspi_info {
+	struct compat_xfrm_usersa_info info;
+	/* 4 bytes additional padding on 64bit */
+	__u32 min, max;
+};
+
+struct compat_xfrm_user_expire {
+	struct compat_xfrm_usersa_info state;
+	/* 8 bytes additional padding on 64bit */
+	u8 hard;
+};
+
+struct compat_xfrm_user_polexpire {
+	struct compat_xfrm_userpolicy_info pol;
+	/* 8 bytes additional padding on 64bit */
+	u8 hard;
+};
+
+#define XMSGSIZE(type) sizeof(struct type)
+
+static const int compat_msg_min[XFRM_NR_MSGTYPES] = {
+	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_GETSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
+	[XFRM_MSG_NEWPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+	[XFRM_MSG_DELPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_GETPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_ALLOCSPI    - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userspi_info),
+	[XFRM_MSG_ACQUIRE     - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_acquire),
+	[XFRM_MSG_EXPIRE      - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_expire),
+	[XFRM_MSG_UPDPOLICY   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_userpolicy_info),
+	[XFRM_MSG_UPDSA       - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_usersa_info),
+	[XFRM_MSG_POLEXPIRE   - XFRM_MSG_BASE] = XMSGSIZE(compat_xfrm_user_polexpire),
+	[XFRM_MSG_FLUSHSA     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_flush),
+	[XFRM_MSG_FLUSHPOLICY - XFRM_MSG_BASE] = 0,
+	[XFRM_MSG_NEWAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_GETAE       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_aevent_id),
+	[XFRM_MSG_REPORT      - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_report),
+	[XFRM_MSG_MIGRATE     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_userpolicy_id),
+	[XFRM_MSG_NEWSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_GETSADINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
+	[XFRM_MSG_MAPPING     - XFRM_MSG_BASE] = XMSGSIZE(xfrm_user_mapping)
+};
+
+static const struct nla_policy compat_policy[XFRMA_MAX+1] = {
+	[XFRMA_SA]		= { .len = XMSGSIZE(compat_xfrm_usersa_info)},
+	[XFRMA_POLICY]		= { .len = XMSGSIZE(compat_xfrm_userpolicy_info)},
+	[XFRMA_LASTUSED]	= { .type = NLA_U64},
+	[XFRMA_ALG_AUTH_TRUNC]	= { .len = sizeof(struct xfrm_algo_auth)},
+	[XFRMA_ALG_AEAD]	= { .len = sizeof(struct xfrm_algo_aead) },
+	[XFRMA_ALG_AUTH]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_CRYPT]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ALG_COMP]	= { .len = sizeof(struct xfrm_algo) },
+	[XFRMA_ENCAP]		= { .len = sizeof(struct xfrm_encap_tmpl) },
+	[XFRMA_TMPL]		= { .len = sizeof(struct xfrm_user_tmpl) },
+	[XFRMA_SEC_CTX]		= { .len = sizeof(struct xfrm_sec_ctx) },
+	[XFRMA_LTIME_VAL]	= { .len = sizeof(struct xfrm_lifetime_cur) },
+	[XFRMA_REPLAY_VAL]	= { .len = sizeof(struct xfrm_replay_state) },
+	[XFRMA_REPLAY_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_ETIMER_THRESH]	= { .type = NLA_U32 },
+	[XFRMA_SRCADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_COADDR]		= { .len = sizeof(xfrm_address_t) },
+	[XFRMA_POLICY_TYPE]	= { .len = sizeof(struct xfrm_userpolicy_type)},
+	[XFRMA_MIGRATE]		= { .len = sizeof(struct xfrm_user_migrate) },
+	[XFRMA_KMADDRESS]	= { .len = sizeof(struct xfrm_user_kmaddress) },
+	[XFRMA_MARK]		= { .len = sizeof(struct xfrm_mark) },
+	[XFRMA_TFCPAD]		= { .type = NLA_U32 },
+	[XFRMA_REPLAY_ESN_VAL]	= { .len = sizeof(struct xfrm_replay_state_esn) },
+	[XFRMA_SA_EXTRA_FLAGS]	= { .type = NLA_U32 },
+	[XFRMA_PROTO]		= { .type = NLA_U8 },
+	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
+	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
+	[XFRMA_SET_MARK]	= { .type = NLA_U32 },
+	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
+	[XFRMA_IF_ID]		= { .type = NLA_U32 },
+};
+
+static struct nlmsghdr *xfrm_nlmsg_put_compat(struct sk_buff *skb,
+			const struct nlmsghdr *nlh_src, u16 type)
+{
+	int payload = compat_msg_min[type];
+	int src_len = xfrm_msg_min[type];
+	struct nlmsghdr *nlh_dst;
+
+	/* Compat messages are shorter or equal to native (+padding) */
+	if (WARN_ON_ONCE(src_len < payload))
+		return ERR_PTR(-EMSGSIZE);
+
+	nlh_dst = nlmsg_put(skb, nlh_src->nlmsg_pid, nlh_src->nlmsg_seq,
+			    nlh_src->nlmsg_type, payload, nlh_src->nlmsg_flags);
+	if (!nlh_dst)
+		return ERR_PTR(-EMSGSIZE);
+
+	memset(nlmsg_data(nlh_dst), 0, payload);
+
+	switch (nlh_src->nlmsg_type) {
+	/* Compat message has the same layout as native */
+	case XFRM_MSG_DELSA:
+	case XFRM_MSG_DELPOLICY:
+	case XFRM_MSG_FLUSHSA:
+	case XFRM_MSG_FLUSHPOLICY:
+	case XFRM_MSG_NEWAE:
+	case XFRM_MSG_REPORT:
+	case XFRM_MSG_MIGRATE:
+	case XFRM_MSG_NEWSADINFO:
+	case XFRM_MSG_NEWSPDINFO:
+	case XFRM_MSG_MAPPING:
+		WARN_ON_ONCE(src_len != payload);
+		memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), src_len);
+		break;
+	/* 4 byte alignment for trailing u64 on native, but not on compat */
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_UPDSA:
+	case XFRM_MSG_UPDPOLICY:
+		WARN_ON_ONCE(src_len != payload + 4);
+		memcpy(nlmsg_data(nlh_dst), nlmsg_data(nlh_src), payload);
+		break;
+	case XFRM_MSG_EXPIRE: {
+		const struct xfrm_user_expire *src_ue  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_expire *dst_ue = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_expire has 4-byte smaller state */
+		memcpy(dst_ue, src_ue, sizeof(dst_ue->state));
+		dst_ue->hard = src_ue->hard;
+		break;
+	}
+	case XFRM_MSG_ACQUIRE: {
+		const struct xfrm_user_acquire *src_ua  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_acquire *dst_ua = nlmsg_data(nlh_dst);
+
+		memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+		dst_ua->aalgos = src_ua->aalgos;
+		dst_ua->ealgos = src_ua->ealgos;
+		dst_ua->calgos = src_ua->calgos;
+		dst_ua->seq    = src_ua->seq;
+		break;
+	}
+	case XFRM_MSG_POLEXPIRE: {
+		const struct xfrm_user_polexpire *src_upe  = nlmsg_data(nlh_src);
+		struct compat_xfrm_user_polexpire *dst_upe = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_upe, src_upe, sizeof(dst_upe->pol));
+		dst_upe->hard = src_upe->hard;
+		break;
+	}
+	case XFRM_MSG_ALLOCSPI: {
+		const struct xfrm_userspi_info *src_usi = nlmsg_data(nlh_src);
+		struct compat_xfrm_userspi_info *dst_usi = nlmsg_data(nlh_dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+		dst_usi->min = src_usi->min;
+		dst_usi->max = src_usi->max;
+		break;
+	}
+	/* Not being sent by kernel */
+	case XFRM_MSG_GETSA:
+	case XFRM_MSG_GETPOLICY:
+	case XFRM_MSG_GETAE:
+	case XFRM_MSG_GETSADINFO:
+	case XFRM_MSG_GETSPDINFO:
+	default:
+		WARN_ONCE(1, "unsupported nlmsg_type %d", nlh_src->nlmsg_type);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	return nlh_dst;
+}
+
+static int xfrm_nla_cpy(struct sk_buff *dst, const struct nlattr *src, int len)
+{
+	return nla_put(dst, src->nla_type, len, nla_data(src));
+}
+
+static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src)
+{
+	switch (src->nla_type) {
+	case XFRMA_PAD:
+		/* Ignore */
+		return 0;
+	case XFRMA_UNSPEC:
+	case XFRMA_ALG_AUTH:
+	case XFRMA_ALG_CRYPT:
+	case XFRMA_ALG_COMP:
+	case XFRMA_ENCAP:
+	case XFRMA_TMPL:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_SA:
+		return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_usersa_info));
+	case XFRMA_POLICY:
+		return xfrm_nla_cpy(dst, src, XMSGSIZE(compat_xfrm_userpolicy_info));
+	case XFRMA_SEC_CTX:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_LTIME_VAL:
+		return nla_put_64bit(dst, src->nla_type, nla_len(src),
+			nla_data(src), XFRMA_PAD);
+	case XFRMA_REPLAY_VAL:
+	case XFRMA_REPLAY_THRESH:
+	case XFRMA_ETIMER_THRESH:
+	case XFRMA_SRCADDR:
+	case XFRMA_COADDR:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	case XFRMA_LASTUSED:
+		return nla_put_64bit(dst, src->nla_type, nla_len(src),
+			nla_data(src), XFRMA_PAD);
+	case XFRMA_POLICY_TYPE:
+	case XFRMA_MIGRATE:
+	case XFRMA_ALG_AEAD:
+	case XFRMA_KMADDRESS:
+	case XFRMA_ALG_AUTH_TRUNC:
+	case XFRMA_MARK:
+	case XFRMA_TFCPAD:
+	case XFRMA_REPLAY_ESN_VAL:
+	case XFRMA_SA_EXTRA_FLAGS:
+	case XFRMA_PROTO:
+	case XFRMA_ADDRESS_FILTER:
+	case XFRMA_OFFLOAD_DEV:
+	case XFRMA_SET_MARK:
+	case XFRMA_SET_MARK_MASK:
+	case XFRMA_IF_ID:
+		return xfrm_nla_cpy(dst, src, nla_len(src));
+	default:
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
+		WARN_ONCE(1, "unsupported nla_type %d", src->nla_type);
+		return -EOPNOTSUPP;
+	}
+}
+
+/* Take kernel-built (64bit layout) and create 32bit layout for userspace */
+static int xfrm_xlate64(struct sk_buff *dst, const struct nlmsghdr *nlh_src)
+{
+	u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+	const struct nlattr *nla, *attrs;
+	struct nlmsghdr *nlh_dst;
+	int len, remaining;
+
+	nlh_dst = xfrm_nlmsg_put_compat(dst, nlh_src, type);
+	if (IS_ERR(nlh_dst))
+		return PTR_ERR(nlh_dst);
+
+	attrs = nlmsg_attrdata(nlh_src, xfrm_msg_min[type]);
+	len = nlmsg_attrlen(nlh_src, xfrm_msg_min[type]);
+
+	nla_for_each_attr(nla, attrs, len, remaining) {
+		int err = xfrm_xlate64_attr(dst, nla);
+
+		if (err)
+			return err;
+	}
+
+	nlmsg_end(dst, nlh_dst);
+
+	return 0;
+}
+
+static int xfrm_alloc_compat(struct sk_buff *skb, const struct nlmsghdr *nlh_src)
+{
+	u16 type = nlh_src->nlmsg_type - XFRM_MSG_BASE;
+	struct sk_buff *new = NULL;
+	int err;
+
+	if (WARN_ON_ONCE(type >= ARRAY_SIZE(xfrm_msg_min)))
+		return -EOPNOTSUPP;
+
+	if (skb_shinfo(skb)->frag_list == NULL) {
+		new = alloc_skb(skb->len + skb_tailroom(skb), GFP_ATOMIC);
+		if (!new)
+			return -ENOMEM;
+		skb_shinfo(skb)->frag_list = new;
+	}
+
+	err = xfrm_xlate64(skb_shinfo(skb)->frag_list, nlh_src);
+	if (err) {
+		if (new) {
+			kfree_skb(new);
+			skb_shinfo(skb)->frag_list = NULL;
+		}
+		return err;
+	}
+
+	return 0;
+}
+
+/* Calculates len of translated 64-bit message. */
+static size_t xfrm_user_rcv_calculate_len64(const struct nlmsghdr *src,
+					    struct nlattr *attrs[XFRMA_MAX+1])
+{
+	size_t len = nlmsg_len(src);
+
+	switch (src->nlmsg_type) {
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_ALLOCSPI:
+	case XFRM_MSG_ACQUIRE:
+	case XFRM_MSG_UPDPOLICY:
+	case XFRM_MSG_UPDSA:
+		len += 4;
+		break;
+	case XFRM_MSG_EXPIRE:
+	case XFRM_MSG_POLEXPIRE:
+		len += 8;
+		break;
+	default:
+		break;
+	}
+
+	if (attrs[XFRMA_SA])
+		len += 4;
+	if (attrs[XFRMA_POLICY])
+		len += 4;
+
+	/* XXX: some attrs may need to be realigned
+	 * if !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	 */
+
+	return len;
+}
+
+static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src,
+			   size_t size, int copy_len, int payload)
+{
+	struct nlmsghdr *nlmsg = dst;
+	struct nlattr *nla;
+
+	if (WARN_ON_ONCE(copy_len > payload))
+		copy_len = payload;
+
+	if (size - *pos < nla_attr_size(payload))
+		return -ENOBUFS;
+
+	nla = dst + *pos;
+
+	memcpy(nla, src, nla_attr_size(copy_len));
+	nla->nla_len = nla_attr_size(payload);
+	*pos += nla_attr_size(copy_len);
+	nlmsg->nlmsg_len += nla->nla_len;
+
+	memset(dst + *pos, 0, payload - copy_len);
+	*pos += payload - copy_len;
+
+	return 0;
+}
+
+static int xfrm_xlate32_attr(void *dst, const struct nlattr *nla,
+			     size_t *pos, size_t size,
+			     struct netlink_ext_ack *extack)
+{
+	int type = nla_type(nla);
+	u16 pol_len32, pol_len64;
+	int err;
+
+	if (type > XFRMA_MAX) {
+		BUILD_BUG_ON(XFRMA_MAX != XFRMA_IF_ID);
+		NL_SET_ERR_MSG(extack, "Bad attribute");
+		return -EOPNOTSUPP;
+	}
+	if (nla_len(nla) < compat_policy[type].len) {
+		NL_SET_ERR_MSG(extack, "Attribute bad length");
+		return -EOPNOTSUPP;
+	}
+
+	pol_len32 = compat_policy[type].len;
+	pol_len64 = xfrma_policy[type].len;
+
+	/* XFRMA_SA and XFRMA_POLICY - need to know how-to translate */
+	if (pol_len32 != pol_len64) {
+		if (nla_len(nla) != compat_policy[type].len) {
+			NL_SET_ERR_MSG(extack, "Attribute bad length");
+			return -EOPNOTSUPP;
+		}
+		err = xfrm_attr_cpy32(dst, pos, nla, size, pol_len32, pol_len64);
+		if (err)
+			return err;
+	}
+
+	return xfrm_attr_cpy32(dst, pos, nla, size, nla_len(nla), nla_len(nla));
+}
+
+static int xfrm_xlate32(struct nlmsghdr *dst, const struct nlmsghdr *src,
+			struct nlattr *attrs[XFRMA_MAX+1],
+			size_t size, u8 type, struct netlink_ext_ack *extack)
+{
+	size_t pos;
+	int i;
+
+	memcpy(dst, src, NLMSG_HDRLEN);
+	dst->nlmsg_len = NLMSG_HDRLEN + xfrm_msg_min[type];
+	memset(nlmsg_data(dst), 0, xfrm_msg_min[type]);
+
+	switch (src->nlmsg_type) {
+	/* Compat message has the same layout as native */
+	case XFRM_MSG_DELSA:
+	case XFRM_MSG_GETSA:
+	case XFRM_MSG_DELPOLICY:
+	case XFRM_MSG_GETPOLICY:
+	case XFRM_MSG_FLUSHSA:
+	case XFRM_MSG_FLUSHPOLICY:
+	case XFRM_MSG_NEWAE:
+	case XFRM_MSG_GETAE:
+	case XFRM_MSG_REPORT:
+	case XFRM_MSG_MIGRATE:
+	case XFRM_MSG_NEWSADINFO:
+	case XFRM_MSG_GETSADINFO:
+	case XFRM_MSG_NEWSPDINFO:
+	case XFRM_MSG_GETSPDINFO:
+	case XFRM_MSG_MAPPING:
+		memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+		break;
+	/* 4 byte alignment for trailing u64 on native, but not on compat */
+	case XFRM_MSG_NEWSA:
+	case XFRM_MSG_NEWPOLICY:
+	case XFRM_MSG_UPDSA:
+	case XFRM_MSG_UPDPOLICY:
+		memcpy(nlmsg_data(dst), nlmsg_data(src), compat_msg_min[type]);
+		break;
+	case XFRM_MSG_EXPIRE: {
+		const struct compat_xfrm_user_expire *src_ue = nlmsg_data(src);
+		struct xfrm_user_expire *dst_ue = nlmsg_data(dst);
+
+		/* compat_xfrm_user_expire has 4-byte smaller state */
+		memcpy(dst_ue, src_ue, sizeof(src_ue->state));
+		dst_ue->hard = src_ue->hard;
+		break;
+	}
+	case XFRM_MSG_ACQUIRE: {
+		const struct compat_xfrm_user_acquire *src_ua = nlmsg_data(src);
+		struct xfrm_user_acquire *dst_ua = nlmsg_data(dst);
+
+		memcpy(dst_ua, src_ua, offsetof(struct compat_xfrm_user_acquire, aalgos));
+		dst_ua->aalgos = src_ua->aalgos;
+		dst_ua->ealgos = src_ua->ealgos;
+		dst_ua->calgos = src_ua->calgos;
+		dst_ua->seq    = src_ua->seq;
+		break;
+	}
+	case XFRM_MSG_POLEXPIRE: {
+		const struct compat_xfrm_user_polexpire *src_upe = nlmsg_data(src);
+		struct xfrm_user_polexpire *dst_upe = nlmsg_data(dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_upe, src_upe, sizeof(src_upe->pol));
+		dst_upe->hard = src_upe->hard;
+		break;
+	}
+	case XFRM_MSG_ALLOCSPI: {
+		const struct compat_xfrm_userspi_info *src_usi = nlmsg_data(src);
+		struct xfrm_userspi_info *dst_usi = nlmsg_data(dst);
+
+		/* compat_xfrm_user_polexpire has 4-byte smaller state */
+		memcpy(dst_usi, src_usi, sizeof(src_usi->info));
+		dst_usi->min = src_usi->min;
+		dst_usi->max = src_usi->max;
+		break;
+	}
+	default:
+		NL_SET_ERR_MSG(extack, "Unsupported message type");
+		return -EOPNOTSUPP;
+	}
+	pos = dst->nlmsg_len;
+
+	for (i = 1; i < XFRMA_MAX + 1; i++) {
+		int err;
+
+		if (i == XFRMA_PAD)
+			continue;
+
+		if (!attrs[i])
+			continue;
+
+		err = xfrm_xlate32_attr(dst, attrs[i], &pos, size, extack);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32,
+			int maxtype, const struct nla_policy *policy,
+			struct netlink_ext_ack *extack)
+{
+	/* netlink_rcv_skb() checks if a message has full (struct nlmsghdr) */
+	u16 type = h32->nlmsg_type - XFRM_MSG_BASE;
+	struct nlattr *attrs[XFRMA_MAX+1];
+	struct nlmsghdr *h64;
+	size_t len;
+	int err;
+
+	BUILD_BUG_ON(ARRAY_SIZE(xfrm_msg_min) != ARRAY_SIZE(compat_msg_min));
+
+	if (type >= ARRAY_SIZE(xfrm_msg_min))
+		return ERR_PTR(-EINVAL);
+
+	/* Don't call parse: the message might have only nlmsg header */
+	if ((h32->nlmsg_type == XFRM_MSG_GETSA ||
+	     h32->nlmsg_type == XFRM_MSG_GETPOLICY) &&
+	    (h32->nlmsg_flags & NLM_F_DUMP))
+		return NULL;
+
+	err = nlmsg_parse_deprecated(h32, compat_msg_min[type], attrs,
+			maxtype ? : XFRMA_MAX, policy ? : compat_policy, extack);
+	if (err < 0)
+		return ERR_PTR(err);
+
+	len = xfrm_user_rcv_calculate_len64(h32, attrs);
+	/* The message doesn't need translation */
+	if (len == nlmsg_len(h32))
+		return NULL;
+
+	len += NLMSG_HDRLEN;
+	h64 = kvmalloc(len, GFP_KERNEL);
+	if (!h64)
+		return ERR_PTR(-ENOMEM);
+
+	err = xfrm_xlate32(h64, h32, attrs, len, type, extack);
+	if (err < 0) {
+		kvfree(h64);
+		return ERR_PTR(err);
+	}
+
+	return h64;
+}
+
+static int xfrm_user_policy_compat(u8 **pdata32, int optlen)
+{
+	struct compat_xfrm_userpolicy_info *p = (void *)*pdata32;
+	u8 *src_templates, *dst_templates;
+	u8 *data64;
+
+	if (optlen < sizeof(*p))
+		return -EINVAL;
+
+	data64 = kmalloc_track_caller(optlen + 4, GFP_USER | __GFP_NOWARN);
+	if (!data64)
+		return -ENOMEM;
+
+	memcpy(data64, *pdata32, sizeof(*p));
+	memset(data64 + sizeof(*p), 0, 4);
+
+	src_templates = *pdata32 + sizeof(*p);
+	dst_templates = data64 + sizeof(*p) + 4;
+	memcpy(dst_templates, src_templates, optlen - sizeof(*p));
+
+	kfree(*pdata32);
+	*pdata32 = data64;
+	return 0;
+}
+
+static struct xfrm_translator xfrm_translator = {
+	.owner				= THIS_MODULE,
+	.alloc_compat			= xfrm_alloc_compat,
+	.rcv_msg_compat			= xfrm_user_rcv_msg_compat,
+	.xlate_user_policy_sockptr	= xfrm_user_policy_compat,
+};
+
+static int __init xfrm_compat_init(void)
+{
+	return xfrm_register_translator(&xfrm_translator);
+}
+
+static void __exit xfrm_compat_exit(void)
+{
+	xfrm_unregister_translator(&xfrm_translator);
+}
+
+module_init(xfrm_compat_init);
+module_exit(xfrm_compat_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Dmitry Safonov");
+MODULE_DESCRIPTION("XFRM 32-bit compatibility layer");
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 37456d022cfa..1158cd0311d7 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -660,7 +660,7 @@ resume:
 		/* only the first xfrm gets the encap type */
 		encap_type = 0;
 
-		if (async && x->repl->recheck(x, skb, seq)) {
+		if (x->repl->recheck(x, skb, seq)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR);
 			goto drop_unlock;
 		}
@@ -760,9 +760,9 @@ int xfrm_input_resume(struct sk_buff *skb, int nexthdr)
 }
 EXPORT_SYMBOL(xfrm_input_resume);
 
-static void xfrm_trans_reinject(unsigned long data)
+static void xfrm_trans_reinject(struct tasklet_struct *t)
 {
-	struct xfrm_trans_tasklet *trans = (void *)data;
+	struct xfrm_trans_tasklet *trans = from_tasklet(trans, t, tasklet);
 	struct sk_buff_head queue;
 	struct sk_buff *skb;
 
@@ -818,7 +818,6 @@ void __init xfrm_input_init(void)
 
 		trans = &per_cpu(xfrm_trans_tasklet, i);
 		__skb_queue_head_init(&trans->queue);
-		tasklet_init(&trans->tasklet, xfrm_trans_reinject,
-			     (unsigned long)trans);
+		tasklet_setup(&trans->tasklet, xfrm_trans_reinject);
 	}
 }
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index a8f66112c52b..697cdcfbb5e1 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -210,7 +210,6 @@ static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
 static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
 {
 	const struct xfrm_mode *inner_mode;
-	struct pcpu_sw_netstats *tstats;
 	struct net_device *dev;
 	struct xfrm_state *x;
 	struct xfrm_if *xi;
@@ -255,13 +254,7 @@ static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
 	}
 
 	xfrmi_scrub_packet(skb, xnet);
-
-	tstats = this_cpu_ptr(dev->tstats);
-
-	u64_stats_update_begin(&tstats->syncp);
-	tstats->rx_packets++;
-	tstats->rx_bytes += skb->len;
-	u64_stats_update_end(&tstats->syncp);
+	dev_sw_netstats_rx_add(dev, skb->len);
 
 	return 0;
 }
@@ -326,12 +319,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 
 	err = dst_output(xi->net, skb->sk, skb);
 	if (net_xmit_eval(err) == 0) {
-		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
-
-		u64_stats_update_begin(&tstats->syncp);
-		tstats->tx_bytes += length;
-		tstats->tx_packets++;
-		u64_stats_update_end(&tstats->syncp);
+		dev_sw_netstats_tx_add(dev, 1, length);
 	} else {
 		stats->tx_errors++;
 		stats->tx_aborted_errors++;
@@ -545,35 +533,6 @@ static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p)
 	return err;
 }
 
-static void xfrmi_get_stats64(struct net_device *dev,
-			       struct rtnl_link_stats64 *s)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		struct pcpu_sw_netstats *stats;
-		struct pcpu_sw_netstats tmp;
-		int start;
-
-		stats = per_cpu_ptr(dev->tstats, cpu);
-		do {
-			start = u64_stats_fetch_begin_irq(&stats->syncp);
-			tmp.rx_packets = stats->rx_packets;
-			tmp.rx_bytes   = stats->rx_bytes;
-			tmp.tx_packets = stats->tx_packets;
-			tmp.tx_bytes   = stats->tx_bytes;
-		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
-
-		s->rx_packets += tmp.rx_packets;
-		s->rx_bytes   += tmp.rx_bytes;
-		s->tx_packets += tmp.tx_packets;
-		s->tx_bytes   += tmp.tx_bytes;
-	}
-
-	s->rx_dropped = dev->stats.rx_dropped;
-	s->tx_dropped = dev->stats.tx_dropped;
-}
-
 static int xfrmi_get_iflink(const struct net_device *dev)
 {
 	struct xfrm_if *xi = netdev_priv(dev);
@@ -581,12 +540,11 @@ static int xfrmi_get_iflink(const struct net_device *dev)
 	return xi->p.link;
 }
 
-
 static const struct net_device_ops xfrmi_netdev_ops = {
 	.ndo_init	= xfrmi_dev_init,
 	.ndo_uninit	= xfrmi_dev_uninit,
 	.ndo_start_xmit = xfrmi_xmit,
-	.ndo_get_stats64 = xfrmi_get_stats64,
+	.ndo_get_stats64 = dev_get_tstats64,
 	.ndo_get_iflink = xfrmi_get_iflink,
 };
 
@@ -830,14 +788,14 @@ static struct xfrm6_tunnel xfrmi_ipv6_handler __read_mostly = {
 	.handler	=	xfrmi6_rcv_tunnel,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi6_err,
-	.priority	=	-1,
+	.priority	=	2,
 };
 
 static struct xfrm6_tunnel xfrmi_ip6ip_handler __read_mostly = {
 	.handler	=	xfrmi6_rcv_tunnel,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi6_err,
-	.priority	=	-1,
+	.priority	=	2,
 };
 #endif
 
@@ -875,14 +833,14 @@ static struct xfrm_tunnel xfrmi_ipip_handler __read_mostly = {
 	.handler	=	xfrmi4_rcv_tunnel,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi4_err,
-	.priority	=	-1,
+	.priority	=	3,
 };
 
 static struct xfrm_tunnel xfrmi_ipip6_handler __read_mostly = {
 	.handler	=	xfrmi4_rcv_tunnel,
 	.cb_handler	=	xfrmi_rcv_cb,
 	.err_handler	=	xfrmi4_err,
-	.priority	=	-1,
+	.priority	=	2,
 };
 #endif
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d622c2548d22..b74f28cabe24 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -793,15 +793,22 @@ static int xfrm_policy_addr_delta(const xfrm_address_t *a,
 				  const xfrm_address_t *b,
 				  u8 prefixlen, u16 family)
 {
+	u32 ma, mb, mask;
 	unsigned int pdw, pbi;
 	int delta = 0;
 
 	switch (family) {
 	case AF_INET:
-		if (sizeof(long) == 4 && prefixlen == 0)
-			return ntohl(a->a4) - ntohl(b->a4);
-		return (ntohl(a->a4) & ((~0UL << (32 - prefixlen)))) -
-		       (ntohl(b->a4) & ((~0UL << (32 - prefixlen))));
+		if (prefixlen == 0)
+			return 0;
+		mask = ~0U << (32 - prefixlen);
+		ma = ntohl(a->a4) & mask;
+		mb = ntohl(b->a4) & mask;
+		if (ma < mb)
+			delta = -1;
+		else if (ma > mb)
+			delta = 1;
+		break;
 	case AF_INET6:
 		pdw = prefixlen >> 5;
 		pbi = prefixlen & 0x1f;
@@ -812,10 +819,13 @@ static int xfrm_policy_addr_delta(const xfrm_address_t *a,
 				return delta;
 		}
 		if (pbi) {
-			u32 mask = ~0u << (32 - pbi);
-
-			delta = (ntohl(a->a6[pdw]) & mask) -
-				(ntohl(b->a6[pdw]) & mask);
+			mask = ~0U << (32 - pbi);
+			ma = ntohl(a->a6[pdw]) & mask;
+			mb = ntohl(b->a6[pdw]) & mask;
+			if (ma < mb)
+				delta = -1;
+			else if (ma > mb)
+				delta = 1;
 		}
 		break;
 	default:
@@ -3078,8 +3088,8 @@ struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
 		xflo.flags = flags;
 
 		/* To accelerate a bit...  */
-		if ((dst_orig->flags & DST_NOXFRM) ||
-		    !net->xfrm.policy_count[XFRM_POLICY_OUT])
+		if (!if_id && ((dst_orig->flags & DST_NOXFRM) ||
+			       !net->xfrm.policy_count[XFRM_POLICY_OUT]))
 			goto nopol;
 
 		xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index efc89a92961d..d01ca1a18418 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1021,7 +1021,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
 		if ((x->sel.family &&
 		     (x->sel.family != family ||
 		      !xfrm_selector_match(&x->sel, fl, family))) ||
-		    !security_xfrm_state_pol_flow_match(x, pol, fl))
+		    !security_xfrm_state_pol_flow_match(x, pol,
+							&fl->u.__fl_common))
 			return;
 
 		if (!*best ||
@@ -1036,7 +1037,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x,
 		if ((!x->sel.family ||
 		     (x->sel.family == family &&
 		      xfrm_selector_match(&x->sel, fl, family))) &&
-		    security_xfrm_state_pol_flow_match(x, pol, fl))
+		    security_xfrm_state_pol_flow_match(x, pol,
+						       &fl->u.__fl_common))
 			*error = -ESRCH;
 	}
 }
@@ -2004,6 +2006,7 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 	int err = -ENOENT;
 	__be32 minspi = htonl(low);
 	__be32 maxspi = htonl(high);
+	__be32 newspi = 0;
 	u32 mark = x->mark.v & x->mark.m;
 
 	spin_lock_bh(&x->lock);
@@ -2022,21 +2025,22 @@ int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high)
 			xfrm_state_put(x0);
 			goto unlock;
 		}
-		x->id.spi = minspi;
+		newspi = minspi;
 	} else {
 		u32 spi = 0;
 		for (h = 0; h < high-low+1; h++) {
 			spi = low + prandom_u32()%(high-low+1);
 			x0 = xfrm_state_lookup(net, mark, &x->id.daddr, htonl(spi), x->id.proto, x->props.family);
 			if (x0 == NULL) {
-				x->id.spi = htonl(spi);
+				newspi = htonl(spi);
 				break;
 			}
 			xfrm_state_put(x0);
 		}
 	}
-	if (x->id.spi) {
+	if (newspi) {
 		spin_lock_bh(&net->xfrm.xfrm_state_lock);
+		x->id.spi = newspi;
 		h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family);
 		hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h);
 		spin_unlock_bh(&net->xfrm.xfrm_state_lock);
@@ -2296,6 +2300,66 @@ static bool km_is_alive(const struct km_event *c)
 	return is_alive;
 }
 
+#if IS_ENABLED(CONFIG_XFRM_USER_COMPAT)
+static DEFINE_SPINLOCK(xfrm_translator_lock);
+static struct xfrm_translator __rcu *xfrm_translator;
+
+struct xfrm_translator *xfrm_get_translator(void)
+{
+	struct xfrm_translator *xtr;
+
+	rcu_read_lock();
+	xtr = rcu_dereference(xfrm_translator);
+	if (unlikely(!xtr))
+		goto out;
+	if (!try_module_get(xtr->owner))
+		xtr = NULL;
+out:
+	rcu_read_unlock();
+	return xtr;
+}
+EXPORT_SYMBOL_GPL(xfrm_get_translator);
+
+void xfrm_put_translator(struct xfrm_translator *xtr)
+{
+	module_put(xtr->owner);
+}
+EXPORT_SYMBOL_GPL(xfrm_put_translator);
+
+int xfrm_register_translator(struct xfrm_translator *xtr)
+{
+	int err = 0;
+
+	spin_lock_bh(&xfrm_translator_lock);
+	if (unlikely(xfrm_translator != NULL))
+		err = -EEXIST;
+	else
+		rcu_assign_pointer(xfrm_translator, xtr);
+	spin_unlock_bh(&xfrm_translator_lock);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_register_translator);
+
+int xfrm_unregister_translator(struct xfrm_translator *xtr)
+{
+	int err = 0;
+
+	spin_lock_bh(&xfrm_translator_lock);
+	if (likely(xfrm_translator != NULL)) {
+		if (rcu_access_pointer(xfrm_translator) != xtr)
+			err = -EINVAL;
+		else
+			RCU_INIT_POINTER(xfrm_translator, NULL);
+	}
+	spin_unlock_bh(&xfrm_translator_lock);
+	synchronize_rcu();
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(xfrm_unregister_translator);
+#endif
+
 int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 {
 	int err;
@@ -2303,9 +2367,6 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 	struct xfrm_mgr *km;
 	struct xfrm_policy *pol = NULL;
 
-	if (in_compat_syscall())
-		return -EOPNOTSUPP;
-
 	if (sockptr_is_null(optval) && !optlen) {
 		xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL);
 		xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL);
@@ -2320,6 +2381,22 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen)
 	if (IS_ERR(data))
 		return PTR_ERR(data);
 
+	if (in_compat_syscall()) {
+		struct xfrm_translator *xtr = xfrm_get_translator();
+
+		if (!xtr) {
+			kfree(data);
+			return -EOPNOTSUPP;
+		}
+
+		err = xtr->xlate_user_policy_sockptr(&data, optlen);
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree(data);
+			return err;
+		}
+	}
+
 	err = -EINVAL;
 	rcu_read_lock();
 	list_for_each_entry_rcu(km, &xfrm_km_list, list) {
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index fbb7d9d06478..0727ac853b55 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -848,21 +848,84 @@ static int copy_user_offload(struct xfrm_state_offload *xso, struct sk_buff *skb
 	return 0;
 }
 
+static bool xfrm_redact(void)
+{
+	return IS_ENABLED(CONFIG_SECURITY) &&
+		security_locked_down(LOCKDOWN_XFRM_SECRET);
+}
+
 static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 {
 	struct xfrm_algo *algo;
+	struct xfrm_algo_auth *ap;
 	struct nlattr *nla;
+	bool redact_secret = xfrm_redact();
 
 	nla = nla_reserve(skb, XFRMA_ALG_AUTH,
 			  sizeof(*algo) + (auth->alg_key_len + 7) / 8);
 	if (!nla)
 		return -EMSGSIZE;
-
 	algo = nla_data(nla);
 	strncpy(algo->alg_name, auth->alg_name, sizeof(algo->alg_name));
-	memcpy(algo->alg_key, auth->alg_key, (auth->alg_key_len + 7) / 8);
+
+	if (redact_secret && auth->alg_key_len)
+		memset(algo->alg_key, 0, (auth->alg_key_len + 7) / 8);
+	else
+		memcpy(algo->alg_key, auth->alg_key,
+		       (auth->alg_key_len + 7) / 8);
 	algo->alg_key_len = auth->alg_key_len;
 
+	nla = nla_reserve(skb, XFRMA_ALG_AUTH_TRUNC, xfrm_alg_auth_len(auth));
+	if (!nla)
+		return -EMSGSIZE;
+	ap = nla_data(nla);
+	memcpy(ap, auth, sizeof(struct xfrm_algo_auth));
+	if (redact_secret && auth->alg_key_len)
+		memset(ap->alg_key, 0, (auth->alg_key_len + 7) / 8);
+	else
+		memcpy(ap->alg_key, auth->alg_key,
+		       (auth->alg_key_len + 7) / 8);
+	return 0;
+}
+
+static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb)
+{
+	struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_AEAD, aead_len(aead));
+	struct xfrm_algo_aead *ap;
+	bool redact_secret = xfrm_redact();
+
+	if (!nla)
+		return -EMSGSIZE;
+
+	ap = nla_data(nla);
+	memcpy(ap, aead, sizeof(*aead));
+
+	if (redact_secret && aead->alg_key_len)
+		memset(ap->alg_key, 0, (aead->alg_key_len + 7) / 8);
+	else
+		memcpy(ap->alg_key, aead->alg_key,
+		       (aead->alg_key_len + 7) / 8);
+	return 0;
+}
+
+static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb)
+{
+	struct xfrm_algo *ap;
+	bool redact_secret = xfrm_redact();
+	struct nlattr *nla = nla_reserve(skb, XFRMA_ALG_CRYPT,
+					 xfrm_alg_len(ealg));
+	if (!nla)
+		return -EMSGSIZE;
+
+	ap = nla_data(nla);
+	memcpy(ap, ealg, sizeof(*ealg));
+
+	if (redact_secret && ealg->alg_key_len)
+		memset(ap->alg_key, 0, (ealg->alg_key_len + 7) / 8);
+	else
+		memcpy(ap->alg_key, ealg->alg_key,
+		       (ealg->alg_key_len + 7) / 8);
+
 	return 0;
 }
 
@@ -906,20 +969,17 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 			goto out;
 	}
 	if (x->aead) {
-		ret = nla_put(skb, XFRMA_ALG_AEAD, aead_len(x->aead), x->aead);
+		ret = copy_to_user_aead(x->aead, skb);
 		if (ret)
 			goto out;
 	}
 	if (x->aalg) {
 		ret = copy_to_user_auth(x->aalg, skb);
-		if (!ret)
-			ret = nla_put(skb, XFRMA_ALG_AUTH_TRUNC,
-				      xfrm_alg_auth_len(x->aalg), x->aalg);
 		if (ret)
 			goto out;
 	}
 	if (x->ealg) {
-		ret = nla_put(skb, XFRMA_ALG_CRYPT, xfrm_alg_len(x->ealg), x->ealg);
+		ret = copy_to_user_ealg(x->ealg, skb);
 		if (ret)
 			goto out;
 	}
@@ -975,6 +1035,7 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
 	struct xfrm_dump_info *sp = ptr;
 	struct sk_buff *in_skb = sp->in_skb;
 	struct sk_buff *skb = sp->out_skb;
+	struct xfrm_translator *xtr;
 	struct xfrm_usersa_info *p;
 	struct nlmsghdr *nlh;
 	int err;
@@ -992,6 +1053,18 @@ static int dump_one_state(struct xfrm_state *x, int count, void *ptr)
 		return err;
 	}
 	nlmsg_end(skb, nlh);
+
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		err = xtr->alloc_compat(skb, nlh);
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			nlmsg_cancel(skb, nlh);
+			return err;
+		}
+	}
+
 	return 0;
 }
 
@@ -1006,7 +1079,6 @@ static int xfrm_dump_sa_done(struct netlink_callback *cb)
 	return 0;
 }
 
-static const struct nla_policy xfrma_policy[XFRMA_MAX+1];
 static int xfrm_dump_sa(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = sock_net(skb->sk);
@@ -1083,12 +1155,24 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb,
 				       u32 pid, unsigned int group)
 {
 	struct sock *nlsk = rcu_dereference(net->xfrm.nlsk);
+	struct xfrm_translator *xtr;
 
 	if (!nlsk) {
 		kfree_skb(skb);
 		return -EPIPE;
 	}
 
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		int err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree_skb(skb);
+			return err;
+		}
+	}
+
 	return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC);
 }
 
@@ -1308,6 +1392,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct xfrm_state *x;
 	struct xfrm_userspi_info *p;
+	struct xfrm_translator *xtr;
 	struct sk_buff *resp_skb;
 	xfrm_address_t *daddr;
 	int family;
@@ -1358,6 +1443,17 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 	}
 
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		err = xtr->alloc_compat(skb, nlmsg_hdr(skb));
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			kfree_skb(resp_skb);
+			goto out;
+		}
+	}
+
 	err = nlmsg_unicast(net->xfrm.nlsk, resp_skb, NETLINK_CB(skb).portid);
 
 out:
@@ -1764,6 +1860,7 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
 	struct xfrm_userpolicy_info *p;
 	struct sk_buff *in_skb = sp->in_skb;
 	struct sk_buff *skb = sp->out_skb;
+	struct xfrm_translator *xtr;
 	struct nlmsghdr *nlh;
 	int err;
 
@@ -1788,6 +1885,18 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
 		return err;
 	}
 	nlmsg_end(skb, nlh);
+
+	xtr = xfrm_get_translator();
+	if (xtr) {
+		err = xtr->alloc_compat(skb, nlh);
+
+		xfrm_put_translator(xtr);
+		if (err) {
+			nlmsg_cancel(skb, nlh);
+			return err;
+		}
+	}
+
 	return 0;
 }
 
@@ -2533,7 +2642,7 @@ static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type,
 
 #define XMSGSIZE(type) sizeof(struct type)
 
-static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
+const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_NEWSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_info),
 	[XFRM_MSG_DELSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
 	[XFRM_MSG_GETSA       - XFRM_MSG_BASE] = XMSGSIZE(xfrm_usersa_id),
@@ -2556,10 +2665,11 @@ static const int xfrm_msg_min[XFRM_NR_MSGTYPES] = {
 	[XFRM_MSG_NEWSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
 	[XFRM_MSG_GETSPDINFO  - XFRM_MSG_BASE] = sizeof(u32),
 };
+EXPORT_SYMBOL_GPL(xfrm_msg_min);
 
 #undef XMSGSIZE
 
-static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
+const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_SA]		= { .len = sizeof(struct xfrm_usersa_info)},
 	[XFRMA_POLICY]		= { .len = sizeof(struct xfrm_userpolicy_info)},
 	[XFRMA_LASTUSED]	= { .type = NLA_U64},
@@ -2591,6 +2701,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
 	[XFRMA_IF_ID]		= { .type = NLA_U32 },
 };
+EXPORT_SYMBOL_GPL(xfrma_policy);
 
 static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
 	[XFRMA_SPD_IPV4_HTHRESH] = { .len = sizeof(struct xfrmu_spdhthresh) },
@@ -2640,11 +2751,9 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	struct net *net = sock_net(skb->sk);
 	struct nlattr *attrs[XFRMA_MAX+1];
 	const struct xfrm_link *link;
+	struct nlmsghdr *nlh64 = NULL;
 	int type, err;
 
-	if (in_compat_syscall())
-		return -EOPNOTSUPP;
-
 	type = nlh->nlmsg_type;
 	if (type > XFRM_MSG_MAX)
 		return -EINVAL;
@@ -2656,32 +2765,55 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!netlink_net_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
+	if (in_compat_syscall()) {
+		struct xfrm_translator *xtr = xfrm_get_translator();
+
+		if (!xtr)
+			return -EOPNOTSUPP;
+
+		nlh64 = xtr->rcv_msg_compat(nlh, link->nla_max,
+					    link->nla_pol, extack);
+		xfrm_put_translator(xtr);
+		if (IS_ERR(nlh64))
+			return PTR_ERR(nlh64);
+		if (nlh64)
+			nlh = nlh64;
+	}
+
 	if ((type == (XFRM_MSG_GETSA - XFRM_MSG_BASE) ||
 	     type == (XFRM_MSG_GETPOLICY - XFRM_MSG_BASE)) &&
 	    (nlh->nlmsg_flags & NLM_F_DUMP)) {
-		if (link->dump == NULL)
-			return -EINVAL;
+		struct netlink_dump_control c = {
+			.start = link->start,
+			.dump = link->dump,
+			.done = link->done,
+		};
 
-		{
-			struct netlink_dump_control c = {
-				.start = link->start,
-				.dump = link->dump,
-				.done = link->done,
-			};
-			return netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+		if (link->dump == NULL) {
+			err = -EINVAL;
+			goto err;
 		}
+
+		err = netlink_dump_start(net->xfrm.nlsk, skb, nlh, &c);
+		goto err;
 	}
 
 	err = nlmsg_parse_deprecated(nlh, xfrm_msg_min[type], attrs,
 				     link->nla_max ? : XFRMA_MAX,
 				     link->nla_pol ? : xfrma_policy, extack);
 	if (err < 0)
-		return err;
+		goto err;
 
-	if (link->doit == NULL)
-		return -EINVAL;
+	if (link->doit == NULL) {
+		err = -EINVAL;
+		goto err;
+	}
 
-	return link->doit(skb, nlh, attrs);
+	err = link->doit(skb, nlh, attrs);
+
+err:
+	kvfree(nlh64);
+	return err;
 }
 
 static void xfrm_netlink_rcv(struct sk_buff *skb)