Merge tag 'v4.20-rc5' into sched/core, to pick up fixes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

141 files changed, 2016 insertions, 1544 deletions

diff --git a/net/9p/Makefile b/net/9p/Makefile
index c0486cfc85d9..aa0a5641e5d0 100644
--- a/net/9p/Makefile
+++ b/net/9p/Makefile
@@ -8,7 +8,6 @@ obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o
 	mod.o \
 	client.o \
 	error.o \
-	util.o \
 	protocol.o \
 	trans_fd.o \
 	trans_common.o \
diff --git a/net/9p/client.c b/net/9p/client.c
index deae53a7dffc..2c9a17b9b46b 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -231,144 +231,170 @@ free_and_return:
 	return ret;
 }
 
-static struct p9_fcall *p9_fcall_alloc(int alloc_msize)
+static int p9_fcall_init(struct p9_client *c, struct p9_fcall *fc,
+			 int alloc_msize)
 {
-	struct p9_fcall *fc;
-	fc = kmalloc(sizeof(struct p9_fcall) + alloc_msize, GFP_NOFS);
-	if (!fc)
-		return NULL;
+	if (likely(c->fcall_cache) && alloc_msize == c->msize) {
+		fc->sdata = kmem_cache_alloc(c->fcall_cache, GFP_NOFS);
+		fc->cache = c->fcall_cache;
+	} else {
+		fc->sdata = kmalloc(alloc_msize, GFP_NOFS);
+		fc->cache = NULL;
+	}
+	if (!fc->sdata)
+		return -ENOMEM;
 	fc->capacity = alloc_msize;
-	fc->sdata = (char *) fc + sizeof(struct p9_fcall);
-	return fc;
+	return 0;
+}
+
+void p9_fcall_fini(struct p9_fcall *fc)
+{
+	/* sdata can be NULL for interrupted requests in trans_rdma,
+	 * and kmem_cache_free does not do NULL-check for us
+	 */
+	if (unlikely(!fc->sdata))
+		return;
+
+	if (fc->cache)
+		kmem_cache_free(fc->cache, fc->sdata);
+	else
+		kfree(fc->sdata);
 }
+EXPORT_SYMBOL(p9_fcall_fini);
+
+static struct kmem_cache *p9_req_cache;
 
 /**
- * p9_tag_alloc - lookup/allocate a request by tag
- * @c: client session to lookup tag within
- * @tag: numeric id for transaction
- *
- * this is a simple array lookup, but will grow the
- * request_slots as necessary to accommodate transaction
- * ids which did not previously have a slot.
- *
- * this code relies on the client spinlock to manage locks, its
- * possible we should switch to something else, but I'd rather
- * stick with something low-overhead for the common case.
+ * p9_req_alloc - Allocate a new request.
+ * @c: Client session.
+ * @type: Transaction type.
+ * @max_size: Maximum packet size for this request.
  *
+ * Context: Process context.
+ * Return: Pointer to new request.
  */
-
 static struct p9_req_t *
-p9_tag_alloc(struct p9_client *c, u16 tag, unsigned int max_size)
+p9_tag_alloc(struct p9_client *c, int8_t type, unsigned int max_size)
 {
-	unsigned long flags;
-	int row, col;
-	struct p9_req_t *req;
+	struct p9_req_t *req = kmem_cache_alloc(p9_req_cache, GFP_NOFS);
 	int alloc_msize = min(c->msize, max_size);
+	int tag;
 
-	/* This looks up the original request by tag so we know which
-	 * buffer to read the data into */
-	tag++;
-
-	if (tag >= c->max_tag) {
-		spin_lock_irqsave(&c->lock, flags);
-		/* check again since original check was outside of lock */
-		while (tag >= c->max_tag) {
-			row = (tag / P9_ROW_MAXTAG);
-			c->reqs[row] = kcalloc(P9_ROW_MAXTAG,
-					sizeof(struct p9_req_t), GFP_ATOMIC);
+	if (!req)
+		return ERR_PTR(-ENOMEM);
 
-			if (!c->reqs[row]) {
-				pr_err("Couldn't grow tag array\n");
-				spin_unlock_irqrestore(&c->lock, flags);
-				return ERR_PTR(-ENOMEM);
-			}
-			for (col = 0; col < P9_ROW_MAXTAG; col++) {
-				req = &c->reqs[row][col];
-				req->status = REQ_STATUS_IDLE;
-				init_waitqueue_head(&req->wq);
-			}
-			c->max_tag += P9_ROW_MAXTAG;
-		}
-		spin_unlock_irqrestore(&c->lock, flags);
-	}
-	row = tag / P9_ROW_MAXTAG;
-	col = tag % P9_ROW_MAXTAG;
+	if (p9_fcall_init(c, &req->tc, alloc_msize))
+		goto free_req;
+	if (p9_fcall_init(c, &req->rc, alloc_msize))
+		goto free;
 
-	req = &c->reqs[row][col];
-	if (!req->tc)
-		req->tc = p9_fcall_alloc(alloc_msize);
-	if (!req->rc)
-		req->rc = p9_fcall_alloc(alloc_msize);
-	if (!req->tc || !req->rc)
-		goto grow_failed;
+	p9pdu_reset(&req->tc);
+	p9pdu_reset(&req->rc);
+	req->status = REQ_STATUS_ALLOC;
+	init_waitqueue_head(&req->wq);
+	INIT_LIST_HEAD(&req->req_list);
 
-	p9pdu_reset(req->tc);
-	p9pdu_reset(req->rc);
+	idr_preload(GFP_NOFS);
+	spin_lock_irq(&c->lock);
+	if (type == P9_TVERSION)
+		tag = idr_alloc(&c->reqs, req, P9_NOTAG, P9_NOTAG + 1,
+				GFP_NOWAIT);
+	else
+		tag = idr_alloc(&c->reqs, req, 0, P9_NOTAG, GFP_NOWAIT);
+	req->tc.tag = tag;
+	spin_unlock_irq(&c->lock);
+	idr_preload_end();
+	if (tag < 0)
+		goto free;
 
-	req->tc->tag = tag-1;
-	req->status = REQ_STATUS_ALLOC;
+	/* Init ref to two because in the general case there is one ref
+	 * that is put asynchronously by a writer thread, one ref
+	 * temporarily given by p9_tag_lookup and put by p9_client_cb
+	 * in the recv thread, and one ref put by p9_tag_remove in the
+	 * main thread. The only exception is virtio that does not use
+	 * p9_tag_lookup but does not have a writer thread either
+	 * (the write happens synchronously in the request/zc_request
+	 * callback), so p9_client_cb eats the second ref there
+	 * as the pointer is duplicated directly by virtqueue_add_sgs()
+	 */
+	refcount_set(&req->refcount.refcount, 2);
 
 	return req;
 
-grow_failed:
-	pr_err("Couldn't grow tag array\n");
-	kfree(req->tc);
-	kfree(req->rc);
-	req->tc = req->rc = NULL;
+free:
+	p9_fcall_fini(&req->tc);
+	p9_fcall_fini(&req->rc);
+free_req:
+	kmem_cache_free(p9_req_cache, req);
 	return ERR_PTR(-ENOMEM);
 }
 
 /**
- * p9_tag_lookup - lookup a request by tag
- * @c: client session to lookup tag within
- * @tag: numeric id for transaction
+ * p9_tag_lookup - Look up a request by tag.
+ * @c: Client session.
+ * @tag: Transaction ID.
  *
+ * Context: Any context.
+ * Return: A request, or %NULL if there is no request with that tag.
  */
-
 struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag)
 {
-	int row, col;
-
-	/* This looks up the original request by tag so we know which
-	 * buffer to read the data into */
-	tag++;
-
-	if (tag >= c->max_tag)
-		return NULL;
+	struct p9_req_t *req;
 
-	row = tag / P9_ROW_MAXTAG;
-	col = tag % P9_ROW_MAXTAG;
+	rcu_read_lock();
+again:
+	req = idr_find(&c->reqs, tag);
+	if (req) {
+		/* We have to be careful with the req found under rcu_read_lock
+		 * Thanks to SLAB_TYPESAFE_BY_RCU we can safely try to get the
+		 * ref again without corrupting other data, then check again
+		 * that the tag matches once we have the ref
+		 */
+		if (!p9_req_try_get(req))
+			goto again;
+		if (req->tc.tag != tag) {
+			p9_req_put(req);
+			goto again;
+		}
+	}
+	rcu_read_unlock();
 
-	return &c->reqs[row][col];
+	return req;
 }
 EXPORT_SYMBOL(p9_tag_lookup);
 
 /**
- * p9_tag_init - setup tags structure and contents
- * @c:  v9fs client struct
- *
- * This initializes the tags structure for each client instance.
+ * p9_tag_remove - Remove a tag.
+ * @c: Client session.
+ * @r: Request of reference.
  *
+ * Context: Any context.
  */
+static int p9_tag_remove(struct p9_client *c, struct p9_req_t *r)
+{
+	unsigned long flags;
+	u16 tag = r->tc.tag;
+
+	p9_debug(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag);
+	spin_lock_irqsave(&c->lock, flags);
+	idr_remove(&c->reqs, tag);
+	spin_unlock_irqrestore(&c->lock, flags);
+	return p9_req_put(r);
+}
 
-static int p9_tag_init(struct p9_client *c)
+static void p9_req_free(struct kref *ref)
 {
-	int err = 0;
+	struct p9_req_t *r = container_of(ref, struct p9_req_t, refcount);
+	p9_fcall_fini(&r->tc);
+	p9_fcall_fini(&r->rc);
+	kmem_cache_free(p9_req_cache, r);
+}
 
-	c->tagpool = p9_idpool_create();
-	if (IS_ERR(c->tagpool)) {
-		err = PTR_ERR(c->tagpool);
-		goto error;
-	}
-	err = p9_idpool_get(c->tagpool); /* reserve tag 0 */
-	if (err < 0) {
-		p9_idpool_destroy(c->tagpool);
-		goto error;
-	}
-	c->max_tag = 0;
-error:
-	return err;
+int p9_req_put(struct p9_req_t *r)
+{
+	return kref_put(&r->refcount, p9_req_free);
 }
+EXPORT_SYMBOL(p9_req_put);
 
 /**
  * p9_tag_cleanup - cleans up tags structure and reclaims resources
@@ -379,52 +405,17 @@ error:
  */
 static void p9_tag_cleanup(struct p9_client *c)
 {
-	int row, col;
-
-	/* check to insure all requests are idle */
-	for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
-		for (col = 0; col < P9_ROW_MAXTAG; col++) {
-			if (c->reqs[row][col].status != REQ_STATUS_IDLE) {
-				p9_debug(P9_DEBUG_MUX,
-					 "Attempting to cleanup non-free tag %d,%d\n",
-					 row, col);
-				/* TODO: delay execution of cleanup */
-				return;
-			}
-		}
-	}
+	struct p9_req_t *req;
+	int id;
 
-	if (c->tagpool) {
-		p9_idpool_put(0, c->tagpool); /* free reserved tag 0 */
-		p9_idpool_destroy(c->tagpool);
+	rcu_read_lock();
+	idr_for_each_entry(&c->reqs, req, id) {
+		pr_info("Tag %d still in use\n", id);
+		if (p9_tag_remove(c, req) == 0)
+			pr_warn("Packet with tag %d has still references",
+				req->tc.tag);
 	}
-
-	/* free requests associated with tags */
-	for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
-		for (col = 0; col < P9_ROW_MAXTAG; col++) {
-			kfree(c->reqs[row][col].tc);
-			kfree(c->reqs[row][col].rc);
-		}
-		kfree(c->reqs[row]);
-	}
-	c->max_tag = 0;
-}
-
-/**
- * p9_free_req - free a request and clean-up as necessary
- * c: client state
- * r: request to release
- *
- */
-
-static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
-{
-	int tag = r->tc->tag;
-	p9_debug(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag);
-
-	r->status = REQ_STATUS_IDLE;
-	if (tag != P9_NOTAG && p9_idpool_check(tag, c->tagpool))
-		p9_idpool_put(tag, c->tagpool);
+	rcu_read_unlock();
 }
 
 /**
@@ -435,7 +426,7 @@ static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
  */
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
 {
-	p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc->tag);
+	p9_debug(P9_DEBUG_MUX, " tag %d\n", req->tc.tag);
 
 	/*
 	 * This barrier is needed to make sure any change made to req before
@@ -445,7 +436,8 @@ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
 	req->status = status;
 
 	wake_up(&req->wq);
-	p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
+	p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc.tag);
+	p9_req_put(req);
 }
 EXPORT_SYMBOL(p9_client_cb);
 
@@ -516,18 +508,18 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 	int err;
 	int ecode;
 
-	err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
-	if (req->rc->size >= c->msize) {
+	err = p9_parse_header(&req->rc, NULL, &type, NULL, 0);
+	if (req->rc.size >= c->msize) {
 		p9_debug(P9_DEBUG_ERROR,
 			 "requested packet size too big: %d\n",
-			 req->rc->size);
+			 req->rc.size);
 		return -EIO;
 	}
 	/*
 	 * dump the response from server
 	 * This should be after check errors which poplulate pdu_fcall.
 	 */
-	trace_9p_protocol_dump(c, req->rc);
+	trace_9p_protocol_dump(c, &req->rc);
 	if (err) {
 		p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err);
 		return err;
@@ -537,7 +529,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 
 	if (!p9_is_proto_dotl(c)) {
 		char *ename;
-		err = p9pdu_readf(req->rc, c->proto_version, "s?d",
+		err = p9pdu_readf(&req->rc, c->proto_version, "s?d",
 				  &ename, &ecode);
 		if (err)
 			goto out_err;
@@ -553,7 +545,7 @@ static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
 		}
 		kfree(ename);
 	} else {
-		err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode);
+		err = p9pdu_readf(&req->rc, c->proto_version, "d", &ecode);
 		err = -ecode;
 
 		p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
@@ -587,12 +579,12 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 	int8_t type;
 	char *ename = NULL;
 
-	err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
+	err = p9_parse_header(&req->rc, NULL, &type, NULL, 0);
 	/*
 	 * dump the response from server
 	 * This should be after parse_header which poplulate pdu_fcall.
 	 */
-	trace_9p_protocol_dump(c, req->rc);
+	trace_9p_protocol_dump(c, &req->rc);
 	if (err) {
 		p9_debug(P9_DEBUG_ERROR, "couldn't parse header %d\n", err);
 		return err;
@@ -607,13 +599,13 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 		/* 7 = header size for RERROR; */
 		int inline_len = in_hdrlen - 7;
 
-		len =  req->rc->size - req->rc->offset;
+		len = req->rc.size - req->rc.offset;
 		if (len > (P9_ZC_HDR_SZ - 7)) {
 			err = -EFAULT;
 			goto out_err;
 		}
 
-		ename = &req->rc->sdata[req->rc->offset];
+		ename = &req->rc.sdata[req->rc.offset];
 		if (len > inline_len) {
 			/* We have error in external buffer */
 			if (!copy_from_iter_full(ename + inline_len,
@@ -623,7 +615,7 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 			}
 		}
 		ename = NULL;
-		err = p9pdu_readf(req->rc, c->proto_version, "s?d",
+		err = p9pdu_readf(&req->rc, c->proto_version, "s?d",
 				  &ename, &ecode);
 		if (err)
 			goto out_err;
@@ -639,7 +631,7 @@ static int p9_check_zc_errors(struct p9_client *c, struct p9_req_t *req,
 		}
 		kfree(ename);
 	} else {
-		err = p9pdu_readf(req->rc, c->proto_version, "d", &ecode);
+		err = p9pdu_readf(&req->rc, c->proto_version, "d", &ecode);
 		err = -ecode;
 
 		p9_debug(P9_DEBUG_9P, "<<< RLERROR (%d)\n", -ecode);
@@ -672,7 +664,7 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
 	int16_t oldtag;
 	int err;
 
-	err = p9_parse_header(oldreq->tc, NULL, NULL, &oldtag, 1);
+	err = p9_parse_header(&oldreq->tc, NULL, NULL, &oldtag, 1);
 	if (err)
 		return err;
 
@@ -686,11 +678,12 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
 	 * if we haven't received a response for oldreq,
 	 * remove it from the list
 	 */
-	if (oldreq->status == REQ_STATUS_SENT)
+	if (oldreq->status == REQ_STATUS_SENT) {
 		if (c->trans_mod->cancelled)
 			c->trans_mod->cancelled(c, oldreq);
+	}
 
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
 	return 0;
 }
 
@@ -698,7 +691,7 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
 					      int8_t type, int req_size,
 					      const char *fmt, va_list ap)
 {
-	int tag, err;
+	int err;
 	struct p9_req_t *req;
 
 	p9_debug(P9_DEBUG_MUX, "client %p op %d\n", c, type);
@@ -711,27 +704,22 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
 	if ((c->status == BeginDisconnect) && (type != P9_TCLUNK))
 		return ERR_PTR(-EIO);
 
-	tag = P9_NOTAG;
-	if (type != P9_TVERSION) {
-		tag = p9_idpool_get(c->tagpool);
-		if (tag < 0)
-			return ERR_PTR(-ENOMEM);
-	}
-
-	req = p9_tag_alloc(c, tag, req_size);
+	req = p9_tag_alloc(c, type, req_size);
 	if (IS_ERR(req))
 		return req;
 
 	/* marshall the data */
-	p9pdu_prepare(req->tc, tag, type);
-	err = p9pdu_vwritef(req->tc, c->proto_version, fmt, ap);
+	p9pdu_prepare(&req->tc, req->tc.tag, type);
+	err = p9pdu_vwritef(&req->tc, c->proto_version, fmt, ap);
 	if (err)
 		goto reterr;
-	p9pdu_finalize(c, req->tc);
-	trace_9p_client_req(c, type, tag);
+	p9pdu_finalize(c, &req->tc);
+	trace_9p_client_req(c, type, req->tc.tag);
 	return req;
 reterr:
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
+	/* We have to put also the 2nd reference as it won't be used */
+	p9_req_put(req);
 	return ERR_PTR(err);
 }
 
@@ -741,7 +729,7 @@ reterr:
  * @type: type of request
  * @fmt: protocol format string (see protocol.c)
  *
- * Returns request structure (which client must free using p9_free_req)
+ * Returns request structure (which client must free using p9_tag_remove)
  */
 
 static struct p9_req_t *
@@ -766,6 +754,8 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
 
 	err = c->trans_mod->request(c, req);
 	if (err < 0) {
+		/* write won't happen */
+		p9_req_put(req);
 		if (err != -ERESTARTSYS && err != -EFAULT)
 			c->status = Disconnected;
 		goto recalc_sigpending;
@@ -813,11 +803,11 @@ recalc_sigpending:
 		goto reterr;
 
 	err = p9_check_errors(c, req);
-	trace_9p_client_res(c, type, req->rc->tag, err);
+	trace_9p_client_res(c, type, req->rc.tag, err);
 	if (!err)
 		return req;
 reterr:
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
 	return ERR_PTR(safe_errno(err));
 }
 
@@ -832,7 +822,7 @@ reterr:
  * @hdrlen: reader header size, This is the size of response protocol data
  * @fmt: protocol format string (see protocol.c)
  *
- * Returns request structure (which client must free using p9_free_req)
+ * Returns request structure (which client must free using p9_tag_remove)
  */
 static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 					 struct iov_iter *uidata,
@@ -895,11 +885,11 @@ recalc_sigpending:
 		goto reterr;
 
 	err = p9_check_zc_errors(c, req, uidata, in_hdrlen);
-	trace_9p_client_res(c, type, req->rc->tag, err);
+	trace_9p_client_res(c, type, req->rc.tag, err);
 	if (!err)
 		return req;
 reterr:
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
 	return ERR_PTR(safe_errno(err));
 }
 
@@ -978,10 +968,10 @@ static int p9_client_version(struct p9_client *c)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, c->proto_version, "ds", &msize, &version);
+	err = p9pdu_readf(&req->rc, c->proto_version, "ds", &msize, &version);
 	if (err) {
 		p9_debug(P9_DEBUG_9P, "version error %d\n", err);
-		trace_9p_protocol_dump(c, req->rc);
+		trace_9p_protocol_dump(c, &req->rc);
 		goto error;
 	}
 
@@ -1002,7 +992,7 @@ static int p9_client_version(struct p9_client *c)
 
 error:
 	kfree(version);
-	p9_free_req(c, req);
+	p9_tag_remove(c, req);
 
 	return err;
 }
@@ -1020,20 +1010,18 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 
 	clnt->trans_mod = NULL;
 	clnt->trans = NULL;
+	clnt->fcall_cache = NULL;
 
 	client_id = utsname()->nodename;
 	memcpy(clnt->name, client_id, strlen(client_id) + 1);
 
 	spin_lock_init(&clnt->lock);
 	idr_init(&clnt->fids);
-
-	err = p9_tag_init(clnt);
-	if (err < 0)
-		goto free_client;
+	idr_init(&clnt->reqs);
 
 	err = parse_opts(options, clnt);
 	if (err < 0)
-		goto destroy_tagpool;
+		goto free_client;
 
 	if (!clnt->trans_mod)
 		clnt->trans_mod = v9fs_get_default_trans();
@@ -1042,7 +1030,7 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 		err = -EPROTONOSUPPORT;
 		p9_debug(P9_DEBUG_ERROR,
 			 "No transport defined or default transport\n");
-		goto destroy_tagpool;
+		goto free_client;
 	}
 
 	p9_debug(P9_DEBUG_MUX, "clnt %p trans %p msize %d protocol %d\n",
@@ -1059,14 +1047,21 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 	if (err)
 		goto close_trans;
 
+	/* P9_HDRSZ + 4 is the smallest packet header we can have that is
+	 * followed by data accessed from userspace by read
+	 */
+	clnt->fcall_cache =
+		kmem_cache_create_usercopy("9p-fcall-cache", clnt->msize,
+					   0, 0, P9_HDRSZ + 4,
+					   clnt->msize - (P9_HDRSZ + 4),
+					   NULL);
+
 	return clnt;
 
 close_trans:
 	clnt->trans_mod->close(clnt);
 put_trans:
 	v9fs_put_trans(clnt->trans_mod);
-destroy_tagpool:
-	p9_idpool_destroy(clnt->tagpool);
 free_client:
 	kfree(clnt);
 	return ERR_PTR(err);
@@ -1092,6 +1087,7 @@ void p9_client_destroy(struct p9_client *clnt)
 
 	p9_tag_cleanup(clnt);
 
+	kmem_cache_destroy(clnt->fcall_cache);
 	kfree(clnt);
 }
 EXPORT_SYMBOL(p9_client_destroy);
@@ -1135,10 +1131,10 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", &qid);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", &qid);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto error;
 	}
 
@@ -1147,7 +1143,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 
 	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return fid;
 
 error:
@@ -1192,13 +1188,13 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, uint16_t nwname,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "R", &nwqids, &wqids);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "R", &nwqids, &wqids);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto clunk_fid;
 	}
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 
 	p9_debug(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids);
 
@@ -1259,9 +1255,9 @@ int p9_client_open(struct p9_fid *fid, int mode)
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 
@@ -1273,7 +1269,7 @@ int p9_client_open(struct p9_fid *fid, int mode)
 	fid->iounit = iounit;
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1303,9 +1299,9 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", qid, &iounit);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", qid, &iounit);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 
@@ -1318,7 +1314,7 @@ int p9_client_create_dotl(struct p9_fid *ofid, const char *name, u32 flags, u32
 	ofid->iounit = iounit;
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1348,9 +1344,9 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Qd", &qid, &iounit);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Qd", &qid, &iounit);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 
@@ -1363,7 +1359,7 @@ int p9_client_fcreate(struct p9_fid *fid, const char *name, u32 perm, int mode,
 	fid->iounit = iounit;
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1387,9 +1383,9 @@ int p9_client_symlink(struct p9_fid *dfid, const char *name,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 
@@ -1397,7 +1393,7 @@ int p9_client_symlink(struct p9_fid *dfid, const char *name,
 			qid->type, (unsigned long long)qid->path, qid->version);
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1417,7 +1413,7 @@ int p9_client_link(struct p9_fid *dfid, struct p9_fid *oldfid, const char *newna
 		return PTR_ERR(req);
 
 	p9_debug(P9_DEBUG_9P, "<<< RLINK\n");
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return 0;
 }
 EXPORT_SYMBOL(p9_client_link);
@@ -1441,7 +1437,7 @@ int p9_client_fsync(struct p9_fid *fid, int datasync)
 
 	p9_debug(P9_DEBUG_9P, "<<< RFSYNC fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 
 error:
 	return err;
@@ -1476,7 +1472,7 @@ again:
 
 	p9_debug(P9_DEBUG_9P, "<<< RCLUNK fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	/*
 	 * Fid is not valid even after a failed clunk
@@ -1510,7 +1506,7 @@ int p9_client_remove(struct p9_fid *fid)
 
 	p9_debug(P9_DEBUG_9P, "<<< RREMOVE fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	if (err == -ERESTARTSYS)
 		p9_client_clunk(fid);
@@ -1537,7 +1533,7 @@ int p9_client_unlinkat(struct p9_fid *dfid, const char *name, int flags)
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RUNLINKAT fid %d %s\n", dfid->fid, name);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1585,11 +1581,11 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 			break;
 		}
 
-		*err = p9pdu_readf(req->rc, clnt->proto_version,
+		*err = p9pdu_readf(&req->rc, clnt->proto_version,
 				   "D", &count, &dataptr);
 		if (*err) {
-			trace_9p_protocol_dump(clnt, req->rc);
-			p9_free_req(clnt, req);
+			trace_9p_protocol_dump(clnt, &req->rc);
+			p9_tag_remove(clnt, req);
 			break;
 		}
 		if (rsize < count) {
@@ -1599,7 +1595,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 
 		p9_debug(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
 		if (!count) {
-			p9_free_req(clnt, req);
+			p9_tag_remove(clnt, req);
 			break;
 		}
 
@@ -1609,7 +1605,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 			offset += n;
 			if (n != count) {
 				*err = -EFAULT;
-				p9_free_req(clnt, req);
+				p9_tag_remove(clnt, req);
 				break;
 			}
 		} else {
@@ -1617,7 +1613,7 @@ p9_client_read(struct p9_fid *fid, u64 offset, struct iov_iter *to, int *err)
 			total += count;
 			offset += count;
 		}
-		p9_free_req(clnt, req);
+		p9_tag_remove(clnt, req);
 	}
 	return total;
 }
@@ -1658,10 +1654,10 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
 			break;
 		}
 
-		*err = p9pdu_readf(req->rc, clnt->proto_version, "d", &count);
+		*err = p9pdu_readf(&req->rc, clnt->proto_version, "d", &count);
 		if (*err) {
-			trace_9p_protocol_dump(clnt, req->rc);
-			p9_free_req(clnt, req);
+			trace_9p_protocol_dump(clnt, &req->rc);
+			p9_tag_remove(clnt, req);
 			break;
 		}
 		if (rsize < count) {
@@ -1671,7 +1667,7 @@ p9_client_write(struct p9_fid *fid, u64 offset, struct iov_iter *from, int *err)
 
 		p9_debug(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
 
-		p9_free_req(clnt, req);
+		p9_tag_remove(clnt, req);
 		iov_iter_advance(from, count);
 		total += count;
 		offset += count;
@@ -1702,10 +1698,10 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "wS", &ignored, ret);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "wS", &ignored, ret);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto error;
 	}
 
@@ -1722,7 +1718,7 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
 		from_kgid(&init_user_ns, ret->n_gid),
 		from_kuid(&init_user_ns, ret->n_muid));
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return ret;
 
 error:
@@ -1755,10 +1751,10 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "A", ret);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "A", ret);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto error;
 	}
 
@@ -1783,7 +1779,7 @@ struct p9_stat_dotl *p9_client_getattr_dotl(struct p9_fid *fid,
 		ret->st_ctime_nsec, ret->st_btime_sec, ret->st_btime_nsec,
 		ret->st_gen, ret->st_data_version);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return ret;
 
 error:
@@ -1852,7 +1848,7 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
 
 	p9_debug(P9_DEBUG_9P, "<<< RWSTAT fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1884,7 +1880,7 @@ int p9_client_setattr(struct p9_fid *fid, struct p9_iattr_dotl *p9attr)
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RSETATTR fid %d\n", fid->fid);
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1907,12 +1903,12 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb)
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "ddqqqqqqd", &sb->type,
-		&sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail,
-		&sb->files, &sb->ffree, &sb->fsid, &sb->namelen);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "ddqqqqqqd", &sb->type,
+			  &sb->bsize, &sb->blocks, &sb->bfree, &sb->bavail,
+			  &sb->files, &sb->ffree, &sb->fsid, &sb->namelen);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto error;
 	}
 
@@ -1923,7 +1919,7 @@ int p9_client_statfs(struct p9_fid *fid, struct p9_rstatfs *sb)
 		sb->blocks, sb->bfree, sb->bavail, sb->files,  sb->ffree,
 		sb->fsid, (long int)sb->namelen);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1951,7 +1947,7 @@ int p9_client_rename(struct p9_fid *fid,
 
 	p9_debug(P9_DEBUG_9P, "<<< RRENAME fid %d\n", fid->fid);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -1981,7 +1977,7 @@ int p9_client_renameat(struct p9_fid *olddirfid, const char *old_name,
 	p9_debug(P9_DEBUG_9P, "<<< RRENAMEAT newdirfid %d new name %s\n",
 		   newdirfid->fid, new_name);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -2015,13 +2011,13 @@ struct p9_fid *p9_client_xattrwalk(struct p9_fid *file_fid,
 		err = PTR_ERR(req);
 		goto error;
 	}
-	err = p9pdu_readf(req->rc, clnt->proto_version, "q", attr_size);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "q", attr_size);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
-		p9_free_req(clnt, req);
+		trace_9p_protocol_dump(clnt, &req->rc);
+		p9_tag_remove(clnt, req);
 		goto clunk_fid;
 	}
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	p9_debug(P9_DEBUG_9P, "<<<  RXATTRWALK fid %d size %llu\n",
 		attr_fid->fid, *attr_size);
 	return attr_fid;
@@ -2055,7 +2051,7 @@ int p9_client_xattrcreate(struct p9_fid *fid, const char *name,
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RXATTRCREATE fid %d\n", fid->fid);
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -2070,7 +2066,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 	struct kvec kv = {.iov_base = data, .iov_len = count};
 	struct iov_iter to;
 
-	iov_iter_kvec(&to, READ | ITER_KVEC, &kv, 1, count);
+	iov_iter_kvec(&to, READ, &kv, 1, count);
 
 	p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n",
 				fid->fid, (unsigned long long) offset, count);
@@ -2103,9 +2099,9 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 		goto error;
 	}
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "D", &count, &dataptr);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "D", &count, &dataptr);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto free_and_error;
 	}
 	if (rsize < count) {
@@ -2118,11 +2114,11 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset)
 	if (non_zc)
 		memmove(data, dataptr, count);
 
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return count;
 
 free_and_error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 error:
 	return err;
 }
@@ -2144,16 +2140,16 @@ int p9_client_mknod_dotl(struct p9_fid *fid, const char *name, int mode,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RMKNOD qid %x.%llx.%x\n", qid->type,
 				(unsigned long long)qid->path, qid->version);
 
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 
 }
@@ -2175,16 +2171,16 @@ int p9_client_mkdir_dotl(struct p9_fid *fid, const char *name, int mode,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "Q", qid);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "Q", qid);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RMKDIR qid %x.%llx.%x\n", qid->type,
 				(unsigned long long)qid->path, qid->version);
 
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 
 }
@@ -2210,14 +2206,14 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "b", status);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "b", status);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RLOCK status %i\n", *status);
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 
 }
@@ -2241,18 +2237,18 @@ int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *glock)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "bqqds", &glock->type,
-			&glock->start, &glock->length, &glock->proc_id,
-			&glock->client_id);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "bqqds", &glock->type,
+			  &glock->start, &glock->length, &glock->proc_id,
+			  &glock->client_id);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RGETLOCK type %i start %lld length %lld "
 		"proc_id %d client_id %s\n", glock->type, glock->start,
 		glock->length, glock->proc_id, glock->client_id);
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 }
 EXPORT_SYMBOL(p9_client_getlock_dotl);
@@ -2271,14 +2267,25 @@ int p9_client_readlink(struct p9_fid *fid, char **target)
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
-	err = p9pdu_readf(req->rc, clnt->proto_version, "s", target);
+	err = p9pdu_readf(&req->rc, clnt->proto_version, "s", target);
 	if (err) {
-		trace_9p_protocol_dump(clnt, req->rc);
+		trace_9p_protocol_dump(clnt, &req->rc);
 		goto error;
 	}
 	p9_debug(P9_DEBUG_9P, "<<< RREADLINK target %s\n", *target);
 error:
-	p9_free_req(clnt, req);
+	p9_tag_remove(clnt, req);
 	return err;
 }
 EXPORT_SYMBOL(p9_client_readlink);
+
+int __init p9_client_init(void)
+{
+	p9_req_cache = KMEM_CACHE(p9_req_t, SLAB_TYPESAFE_BY_RCU);
+	return p9_req_cache ? 0 : -ENOMEM;
+}
+
+void __exit p9_client_exit(void)
+{
+	kmem_cache_destroy(p9_req_cache);
+}
diff --git a/net/9p/mod.c b/net/9p/mod.c
index 253ba824a325..0da56d6af73b 100644
--- a/net/9p/mod.c
+++ b/net/9p/mod.c
@@ -171,11 +171,17 @@ void v9fs_put_trans(struct p9_trans_module *m)
  */
 static int __init init_p9(void)
 {
+	int ret;
+
+	ret = p9_client_init();
+	if (ret)
+		return ret;
+
 	p9_error_init();
 	pr_info("Installing 9P2000 support\n");
 	p9_trans_fd_init();
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -188,6 +194,7 @@ static void __exit exit_p9(void)
 	pr_info("Unloading 9P2000 support\n");
 
 	p9_trans_fd_exit();
+	p9_client_exit();
 }
 
 module_init(init_p9)
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 4a1e1dd30b52..462ba144cb39 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -46,10 +46,15 @@ p9pdu_writef(struct p9_fcall *pdu, int proto_version, const char *fmt, ...);
 void p9stat_free(struct p9_wstat *stbuf)
 {
 	kfree(stbuf->name);
+	stbuf->name = NULL;
 	kfree(stbuf->uid);
+	stbuf->uid = NULL;
 	kfree(stbuf->gid);
+	stbuf->gid = NULL;
 	kfree(stbuf->muid);
+	stbuf->muid = NULL;
 	kfree(stbuf->extension);
+	stbuf->extension = NULL;
 }
 EXPORT_SYMBOL(p9stat_free);
 
@@ -566,9 +571,10 @@ int p9stat_read(struct p9_client *clnt, char *buf, int len, struct p9_wstat *st)
 	if (ret) {
 		p9_debug(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret);
 		trace_9p_protocol_dump(clnt, &fake_pdu);
+		return ret;
 	}
 
-	return ret;
+	return fake_pdu.offset;
 }
 EXPORT_SYMBOL(p9stat_read);
 
@@ -617,13 +623,19 @@ int p9dirent_read(struct p9_client *clnt, char *buf, int len,
 	if (ret) {
 		p9_debug(P9_DEBUG_9P, "<<< p9dirent_read failed: %d\n", ret);
 		trace_9p_protocol_dump(clnt, &fake_pdu);
-		goto out;
+		return ret;
 	}
 
-	strcpy(dirent->d_name, nameptr);
+	ret = strscpy(dirent->d_name, nameptr, sizeof(dirent->d_name));
+	if (ret < 0) {
+		p9_debug(P9_DEBUG_ERROR,
+			 "On the wire dirent name too long: %s\n",
+			 nameptr);
+		kfree(nameptr);
+		return ret;
+	}
 	kfree(nameptr);
 
-out:
 	return fake_pdu.offset;
 }
 EXPORT_SYMBOL(p9dirent_read);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index e2ef3c782c53..f868cf6fba79 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -131,7 +131,8 @@ struct p9_conn {
 	int err;
 	struct list_head req_list;
 	struct list_head unsent_req_list;
-	struct p9_req_t *req;
+	struct p9_req_t *rreq;
+	struct p9_req_t *wreq;
 	char tmp_buf[7];
 	struct p9_fcall rc;
 	int wpos;
@@ -291,7 +292,6 @@ static void p9_read_work(struct work_struct *work)
 	__poll_t n;
 	int err;
 	struct p9_conn *m;
-	int status = REQ_STATUS_ERROR;
 
 	m = container_of(work, struct p9_conn, rq);
 
@@ -322,7 +322,7 @@ static void p9_read_work(struct work_struct *work)
 	m->rc.offset += err;
 
 	/* header read in */
-	if ((!m->req) && (m->rc.offset == m->rc.capacity)) {
+	if ((!m->rreq) && (m->rc.offset == m->rc.capacity)) {
 		p9_debug(P9_DEBUG_TRANS, "got new header\n");
 
 		/* Header size */
@@ -346,23 +346,23 @@ static void p9_read_work(struct work_struct *work)
 			 "mux %p pkt: size: %d bytes tag: %d\n",
 			 m, m->rc.size, m->rc.tag);
 
-		m->req = p9_tag_lookup(m->client, m->rc.tag);
-		if (!m->req || (m->req->status != REQ_STATUS_SENT)) {
+		m->rreq = p9_tag_lookup(m->client, m->rc.tag);
+		if (!m->rreq || (m->rreq->status != REQ_STATUS_SENT)) {
 			p9_debug(P9_DEBUG_ERROR, "Unexpected packet tag %d\n",
 				 m->rc.tag);
 			err = -EIO;
 			goto error;
 		}
 
-		if (m->req->rc == NULL) {
+		if (!m->rreq->rc.sdata) {
 			p9_debug(P9_DEBUG_ERROR,
 				 "No recv fcall for tag %d (req %p), disconnecting!\n",
-				 m->rc.tag, m->req);
-			m->req = NULL;
+				 m->rc.tag, m->rreq);
+			m->rreq = NULL;
 			err = -EIO;
 			goto error;
 		}
-		m->rc.sdata = (char *)m->req->rc + sizeof(struct p9_fcall);
+		m->rc.sdata = m->rreq->rc.sdata;
 		memcpy(m->rc.sdata, m->tmp_buf, m->rc.capacity);
 		m->rc.capacity = m->rc.size;
 	}
@@ -370,20 +370,27 @@ static void p9_read_work(struct work_struct *work)
 	/* packet is read in
 	 * not an else because some packets (like clunk) have no payload
 	 */
-	if ((m->req) && (m->rc.offset == m->rc.capacity)) {
+	if ((m->rreq) && (m->rc.offset == m->rc.capacity)) {
 		p9_debug(P9_DEBUG_TRANS, "got new packet\n");
-		m->req->rc->size = m->rc.offset;
+		m->rreq->rc.size = m->rc.offset;
 		spin_lock(&m->client->lock);
-		if (m->req->status != REQ_STATUS_ERROR)
-			status = REQ_STATUS_RCVD;
-		list_del(&m->req->req_list);
-		/* update req->status while holding client->lock  */
-		p9_client_cb(m->client, m->req, status);
+		if (m->rreq->status == REQ_STATUS_SENT) {
+			list_del(&m->rreq->req_list);
+			p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD);
+		} else {
+			spin_unlock(&m->client->lock);
+			p9_debug(P9_DEBUG_ERROR,
+				 "Request tag %d errored out while we were reading the reply\n",
+				 m->rc.tag);
+			err = -EIO;
+			goto error;
+		}
 		spin_unlock(&m->client->lock);
 		m->rc.sdata = NULL;
 		m->rc.offset = 0;
 		m->rc.capacity = 0;
-		m->req = NULL;
+		p9_req_put(m->rreq);
+		m->rreq = NULL;
 	}
 
 end_clear:
@@ -469,9 +476,11 @@ static void p9_write_work(struct work_struct *work)
 		p9_debug(P9_DEBUG_TRANS, "move req %p\n", req);
 		list_move_tail(&req->req_list, &m->req_list);
 
-		m->wbuf = req->tc->sdata;
-		m->wsize = req->tc->size;
+		m->wbuf = req->tc.sdata;
+		m->wsize = req->tc.size;
 		m->wpos = 0;
+		p9_req_get(req);
+		m->wreq = req;
 		spin_unlock(&m->client->lock);
 	}
 
@@ -492,8 +501,11 @@ static void p9_write_work(struct work_struct *work)
 	}
 
 	m->wpos += err;
-	if (m->wpos == m->wsize)
+	if (m->wpos == m->wsize) {
 		m->wpos = m->wsize = 0;
+		p9_req_put(m->wreq);
+		m->wreq = NULL;
+	}
 
 end_clear:
 	clear_bit(Wworksched, &m->wsched);
@@ -663,7 +675,7 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
 	struct p9_conn *m = &ts->conn;
 
 	p9_debug(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n",
-		 m, current, req->tc, req->tc->id);
+		 m, current, &req->tc, req->tc.id);
 	if (m->err < 0)
 		return m->err;
 
@@ -694,6 +706,7 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 	if (req->status == REQ_STATUS_UNSENT) {
 		list_del(&req->req_list);
 		req->status = REQ_STATUS_FLSHD;
+		p9_req_put(req);
 		ret = 0;
 	}
 	spin_unlock(&client->lock);
@@ -711,6 +724,7 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
 	spin_lock(&client->lock);
 	list_del(&req->req_list);
 	spin_unlock(&client->lock);
+	p9_req_put(req);
 
 	return 0;
 }
@@ -862,7 +876,15 @@ static void p9_conn_destroy(struct p9_conn *m)
 
 	p9_mux_poll_stop(m);
 	cancel_work_sync(&m->rq);
+	if (m->rreq) {
+		p9_req_put(m->rreq);
+		m->rreq = NULL;
+	}
 	cancel_work_sync(&m->wq);
+	if (m->wreq) {
+		p9_req_put(m->wreq);
+		m->wreq = NULL;
+	}
 
 	p9_conn_cancel(m, -ECONNRESET);
 
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index b513cffeeb3c..119103bfa82e 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -122,7 +122,7 @@ struct p9_rdma_context {
 	dma_addr_t busa;
 	union {
 		struct p9_req_t *req;
-		struct p9_fcall *rc;
+		struct p9_fcall rc;
 	};
 };
 
@@ -274,8 +274,7 @@ p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
 	case RDMA_CM_EVENT_DISCONNECTED:
 		if (rdma)
 			rdma->state = P9_RDMA_CLOSED;
-		if (c)
-			c->status = Disconnected;
+		c->status = Disconnected;
 		break;
 
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
@@ -320,8 +319,8 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	if (wc->status != IB_WC_SUCCESS)
 		goto err_out;
 
-	c->rc->size = wc->byte_len;
-	err = p9_parse_header(c->rc, NULL, NULL, &tag, 1);
+	c->rc.size = wc->byte_len;
+	err = p9_parse_header(&c->rc, NULL, NULL, &tag, 1);
 	if (err)
 		goto err_out;
 
@@ -331,12 +330,13 @@ recv_done(struct ib_cq *cq, struct ib_wc *wc)
 
 	/* Check that we have not yet received a reply for this request.
 	 */
-	if (unlikely(req->rc)) {
+	if (unlikely(req->rc.sdata)) {
 		pr_err("Duplicate reply for request %d", tag);
 		goto err_out;
 	}
 
-	req->rc = c->rc;
+	req->rc.size = c->rc.size;
+	req->rc.sdata = c->rc.sdata;
 	p9_client_cb(client, req, REQ_STATUS_RCVD);
 
  out:
@@ -361,9 +361,10 @@ send_done(struct ib_cq *cq, struct ib_wc *wc)
 		container_of(wc->wr_cqe, struct p9_rdma_context, cqe);
 
 	ib_dma_unmap_single(rdma->cm_id->device,
-			    c->busa, c->req->tc->size,
+			    c->busa, c->req->tc.size,
 			    DMA_TO_DEVICE);
 	up(&rdma->sq_sem);
+	p9_req_put(c->req);
 	kfree(c);
 }
 
@@ -401,7 +402,7 @@ post_recv(struct p9_client *client, struct p9_rdma_context *c)
 	struct ib_sge sge;
 
 	c->busa = ib_dma_map_single(rdma->cm_id->device,
-				    c->rc->sdata, client->msize,
+				    c->rc.sdata, client->msize,
 				    DMA_FROM_DEVICE);
 	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa))
 		goto error;
@@ -443,9 +444,9 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 	 **/
 	if (unlikely(atomic_read(&rdma->excess_rc) > 0)) {
 		if ((atomic_sub_return(1, &rdma->excess_rc) >= 0)) {
-			/* Got one ! */
-			kfree(req->rc);
-			req->rc = NULL;
+			/* Got one! */
+			p9_fcall_fini(&req->rc);
+			req->rc.sdata = NULL;
 			goto dont_need_post_recv;
 		} else {
 			/* We raced and lost. */
@@ -459,7 +460,7 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 		err = -ENOMEM;
 		goto recv_error;
 	}
-	rpl_context->rc = req->rc;
+	rpl_context->rc.sdata = req->rc.sdata;
 
 	/*
 	 * Post a receive buffer for this request. We need to ensure
@@ -475,11 +476,11 @@ static int rdma_request(struct p9_client *client, struct p9_req_t *req)
 
 	err = post_recv(client, rpl_context);
 	if (err) {
-		p9_debug(P9_DEBUG_FCALL, "POST RECV failed\n");
+		p9_debug(P9_DEBUG_ERROR, "POST RECV failed: %d\n", err);
 		goto recv_error;
 	}
 	/* remove posted receive buffer from request structure */
-	req->rc = NULL;
+	req->rc.sdata = NULL;
 
 dont_need_post_recv:
 	/* Post the request */
@@ -491,7 +492,7 @@ dont_need_post_recv:
 	c->req = req;
 
 	c->busa = ib_dma_map_single(rdma->cm_id->device,
-				    c->req->tc->sdata, c->req->tc->size,
+				    c->req->tc.sdata, c->req->tc.size,
 				    DMA_TO_DEVICE);
 	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa)) {
 		err = -EIO;
@@ -501,7 +502,7 @@ dont_need_post_recv:
 	c->cqe.done = send_done;
 
 	sge.addr = c->busa;
-	sge.length = c->req->tc->size;
+	sge.length = c->req->tc.size;
 	sge.lkey = rdma->pd->local_dma_lkey;
 
 	wr.next = NULL;
@@ -544,7 +545,7 @@ dont_need_post_recv:
  recv_error:
 	kfree(rpl_context);
 	spin_lock_irqsave(&rdma->req_lock, flags);
-	if (rdma->state < P9_RDMA_CLOSING) {
+	if (err != -EINTR && rdma->state < P9_RDMA_CLOSING) {
 		rdma->state = P9_RDMA_CLOSING;
 		spin_unlock_irqrestore(&rdma->req_lock, flags);
 		rdma_disconnect(rdma->cm_id);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 7728b0acde09..b1d39cabf125 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -155,7 +155,7 @@ static void req_done(struct virtqueue *vq)
 		}
 
 		if (len) {
-			req->rc->size = len;
+			req->rc.size = len;
 			p9_client_cb(chan->client, req, REQ_STATUS_RCVD);
 		}
 	}
@@ -207,6 +207,13 @@ static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
 	return 1;
 }
 
+/* Reply won't come, so drop req ref */
+static int p9_virtio_cancelled(struct p9_client *client, struct p9_req_t *req)
+{
+	p9_req_put(req);
+	return 0;
+}
+
 /**
  * pack_sg_list_p - Just like pack_sg_list. Instead of taking a buffer,
  * this takes a list of pages.
@@ -273,12 +280,12 @@ req_retry:
 	out_sgs = in_sgs = 0;
 	/* Handle out VirtIO ring buffers */
 	out = pack_sg_list(chan->sg, 0,
-			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+			   VIRTQUEUE_NUM, req->tc.sdata, req->tc.size);
 	if (out)
 		sgs[out_sgs++] = chan->sg;
 
 	in = pack_sg_list(chan->sg, out,
-			  VIRTQUEUE_NUM, req->rc->sdata, req->rc->capacity);
+			  VIRTQUEUE_NUM, req->rc.sdata, req->rc.capacity);
 	if (in)
 		sgs[out_sgs + in_sgs++] = chan->sg + out;
 
@@ -322,7 +329,7 @@ static int p9_get_mapped_pages(struct virtio_chan *chan,
 	if (!iov_iter_count(data))
 		return 0;
 
-	if (!(data->type & ITER_KVEC)) {
+	if (!iov_iter_is_kvec(data)) {
 		int n;
 		/*
 		 * We allow only p9_max_pages pinned. We wait for the
@@ -404,6 +411,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 	struct scatterlist *sgs[4];
 	size_t offs;
 	int need_drop = 0;
+	int kicked = 0;
 
 	p9_debug(P9_DEBUG_TRANS, "virtio request\n");
 
@@ -411,29 +419,33 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
 		__le32 sz;
 		int n = p9_get_mapped_pages(chan, &out_pages, uodata,
 					    outlen, &offs, &need_drop);
-		if (n < 0)
-			return n;
+		if (n < 0) {
+			err = n;
+			goto err_out;
+		}
 		out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
 		if (n != outlen) {
 			__le32 v = cpu_to_le32(n);
-			memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+			memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4);
 			outlen = n;
 		}
 		/* The size field of the message must include the length of the
 		 * header and the length of the data.  We didn't actually know
 		 * the length of the data until this point so add it in now.
 		 */
-		sz = cpu_to_le32(req->tc->size + outlen);
-		memcpy(&req->tc->sdata[0], &sz, sizeof(sz));
+		sz = cpu_to_le32(req->tc.size + outlen);
+		memcpy(&req->tc.sdata[0], &sz, sizeof(sz));
 	} else if (uidata) {
 		int n = p9_get_mapped_pages(chan, &in_pages, uidata,
 					    inlen, &offs, &need_drop);
-		if (n < 0)
-			return n;
+		if (n < 0) {
+			err = n;
+			goto err_out;
+		}
 		in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
 		if (n != inlen) {
 			__le32 v = cpu_to_le32(n);
-			memcpy(&req->tc->sdata[req->tc->size - 4], &v, 4);
+			memcpy(&req->tc.sdata[req->tc.size - 4], &v, 4);
 			inlen = n;
 		}
 	}
@@ -445,7 +457,7 @@ req_retry_pinned:
 
 	/* out data */
 	out = pack_sg_list(chan->sg, 0,
-			   VIRTQUEUE_NUM, req->tc->sdata, req->tc->size);
+			   VIRTQUEUE_NUM, req->tc.sdata, req->tc.size);
 
 	if (out)
 		sgs[out_sgs++] = chan->sg;
@@ -464,7 +476,7 @@ req_retry_pinned:
 	 * alloced memory and payload onto the user buffer.
 	 */
 	in = pack_sg_list(chan->sg, out,
-			  VIRTQUEUE_NUM, req->rc->sdata, in_hdr_len);
+			  VIRTQUEUE_NUM, req->rc.sdata, in_hdr_len);
 	if (in)
 		sgs[out_sgs + in_sgs++] = chan->sg + out;
 
@@ -498,6 +510,7 @@ req_retry_pinned:
 	}
 	virtqueue_kick(chan->vq);
 	spin_unlock_irqrestore(&chan->lock, flags);
+	kicked = 1;
 	p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
 	err = wait_event_killable(req->wq, req->status >= REQ_STATUS_RCVD);
 	/*
@@ -518,6 +531,10 @@ err_out:
 	}
 	kvfree(in_pages);
 	kvfree(out_pages);
+	if (!kicked) {
+		/* reply won't come */
+		p9_req_put(req);
+	}
 	return err;
 }
 
@@ -750,6 +767,7 @@ static struct p9_trans_module p9_virtio_trans = {
 	.request = p9_virtio_request,
 	.zc_request = p9_virtio_zc_request,
 	.cancel = p9_virtio_cancel,
+	.cancelled = p9_virtio_cancelled,
 	/*
 	 * We leave one entry for input and one entry for response
 	 * headers. We also skip one more entry to accomodate, address
diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c
index c2d54ac76bfd..e2fbf3677b9b 100644
--- a/net/9p/trans_xen.c
+++ b/net/9p/trans_xen.c
@@ -141,7 +141,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
 	struct xen_9pfs_front_priv *priv = NULL;
 	RING_IDX cons, prod, masked_cons, masked_prod;
 	unsigned long flags;
-	u32 size = p9_req->tc->size;
+	u32 size = p9_req->tc.size;
 	struct xen_9pfs_dataring *ring;
 	int num;
 
@@ -154,7 +154,7 @@ static int p9_xen_request(struct p9_client *client, struct p9_req_t *p9_req)
 	if (!priv || priv->client != client)
 		return -EINVAL;
 
-	num = p9_req->tc->tag % priv->num_rings;
+	num = p9_req->tc.tag % priv->num_rings;
 	ring = &priv->rings[num];
 
 again:
@@ -176,7 +176,7 @@ again:
 	masked_prod = xen_9pfs_mask(prod, XEN_9PFS_RING_SIZE);
 	masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE);
 
-	xen_9pfs_write_packet(ring->data.out, p9_req->tc->sdata, size,
+	xen_9pfs_write_packet(ring->data.out, p9_req->tc.sdata, size,
 			      &masked_prod, masked_cons, XEN_9PFS_RING_SIZE);
 
 	p9_req->status = REQ_STATUS_SENT;
@@ -185,6 +185,7 @@ again:
 	ring->intf->out_prod = prod;
 	spin_unlock_irqrestore(&ring->lock, flags);
 	notify_remote_via_irq(ring->irq);
+	p9_req_put(p9_req);
 
 	return 0;
 }
@@ -229,12 +230,12 @@ static void p9_xen_response(struct work_struct *work)
 			continue;
 		}
 
-		memcpy(req->rc, &h, sizeof(h));
-		req->rc->offset = 0;
+		memcpy(&req->rc, &h, sizeof(h));
+		req->rc.offset = 0;
 
 		masked_cons = xen_9pfs_mask(cons, XEN_9PFS_RING_SIZE);
 		/* Then, read the whole packet (including the header) */
-		xen_9pfs_read_packet(req->rc->sdata, ring->data.in, h.size,
+		xen_9pfs_read_packet(req->rc.sdata, ring->data.in, h.size,
 				     masked_prod, &masked_cons,
 				     XEN_9PFS_RING_SIZE);
 
@@ -391,8 +392,8 @@ static int xen_9pfs_front_probe(struct xenbus_device *dev,
 	unsigned int max_rings, max_ring_order, len = 0;
 
 	versions = xenbus_read(XBT_NIL, dev->otherend, "versions", &len);
-	if (!len)
-		return -EINVAL;
+	if (IS_ERR(versions))
+		return PTR_ERR(versions);
 	if (strcmp(versions, "1")) {
 		kfree(versions);
 		return -EINVAL;
diff --git a/net/9p/util.c b/net/9p/util.c
deleted file mode 100644
index 55ad98277e85..000000000000
--- a/net/9p/util.c
+++ /dev/null
@@ -1,140 +0,0 @@
-/*
- *  net/9p/util.c
- *
- *  This file contains some helper functions
- *
- *  Copyright (C) 2007 by Latchesar Ionkov <lucho@ionkov.net>
- *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
- *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2
- *  as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to:
- *  Free Software Foundation
- *  51 Franklin Street, Fifth Floor
- *  Boston, MA  02111-1301  USA
- *
- */
-
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/sched.h>
-#include <linux/parser.h>
-#include <linux/idr.h>
-#include <linux/slab.h>
-#include <net/9p/9p.h>
-
-/**
- * struct p9_idpool - per-connection accounting for tag idpool
- * @lock: protects the pool
- * @pool: idr to allocate tag id from
- *
- */
-
-struct p9_idpool {
-	spinlock_t lock;
-	struct idr pool;
-};
-
-/**
- * p9_idpool_create - create a new per-connection id pool
- *
- */
-
-struct p9_idpool *p9_idpool_create(void)
-{
-	struct p9_idpool *p;
-
-	p = kmalloc(sizeof(struct p9_idpool), GFP_KERNEL);
-	if (!p)
-		return ERR_PTR(-ENOMEM);
-
-	spin_lock_init(&p->lock);
-	idr_init(&p->pool);
-
-	return p;
-}
-EXPORT_SYMBOL(p9_idpool_create);
-
-/**
- * p9_idpool_destroy - create a new per-connection id pool
- * @p: idpool to destroy
- */
-
-void p9_idpool_destroy(struct p9_idpool *p)
-{
-	idr_destroy(&p->pool);
-	kfree(p);
-}
-EXPORT_SYMBOL(p9_idpool_destroy);
-
-/**
- * p9_idpool_get - allocate numeric id from pool
- * @p: pool to allocate from
- *
- * Bugs: This seems to be an awful generic function, should it be in idr.c with
- *            the lock included in struct idr?
- */
-
-int p9_idpool_get(struct p9_idpool *p)
-{
-	int i;
-	unsigned long flags;
-
-	idr_preload(GFP_NOFS);
-	spin_lock_irqsave(&p->lock, flags);
-
-	/* no need to store exactly p, we just need something non-null */
-	i = idr_alloc(&p->pool, p, 0, 0, GFP_NOWAIT);
-
-	spin_unlock_irqrestore(&p->lock, flags);
-	idr_preload_end();
-	if (i < 0)
-		return -1;
-
-	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", i, p);
-	return i;
-}
-EXPORT_SYMBOL(p9_idpool_get);
-
-/**
- * p9_idpool_put - release numeric id from pool
- * @id: numeric id which is being released
- * @p: pool to release id into
- *
- * Bugs: This seems to be an awful generic function, should it be in idr.c with
- *            the lock included in struct idr?
- */
-
-void p9_idpool_put(int id, struct p9_idpool *p)
-{
-	unsigned long flags;
-
-	p9_debug(P9_DEBUG_MUX, " id %d pool %p\n", id, p);
-
-	spin_lock_irqsave(&p->lock, flags);
-	idr_remove(&p->pool, id);
-	spin_unlock_irqrestore(&p->lock, flags);
-}
-EXPORT_SYMBOL(p9_idpool_put);
-
-/**
- * p9_idpool_check - check if the specified id is available
- * @id: id to check
- * @p: pool to check
- */
-
-int p9_idpool_check(int id, struct p9_idpool *p)
-{
-	return idr_find(&p->pool, id) != NULL;
-}
-EXPORT_SYMBOL(p9_idpool_check);
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index 9f481cfdf77d..e8090f099eb8 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -352,19 +352,21 @@ out:
  */
 int batadv_v_elp_iface_enable(struct batadv_hard_iface *hard_iface)
 {
+	static const size_t tvlv_padding = sizeof(__be32);
 	struct batadv_elp_packet *elp_packet;
 	unsigned char *elp_buff;
 	u32 random_seqno;
 	size_t size;
 	int res = -ENOMEM;
 
-	size = ETH_HLEN + NET_IP_ALIGN + BATADV_ELP_HLEN;
+	size = ETH_HLEN + NET_IP_ALIGN + BATADV_ELP_HLEN + tvlv_padding;
 	hard_iface->bat_v.elp_skb = dev_alloc_skb(size);
 	if (!hard_iface->bat_v.elp_skb)
 		goto out;
 
 	skb_reserve(hard_iface->bat_v.elp_skb, ETH_HLEN + NET_IP_ALIGN);
-	elp_buff = skb_put_zero(hard_iface->bat_v.elp_skb, BATADV_ELP_HLEN);
+	elp_buff = skb_put_zero(hard_iface->bat_v.elp_skb,
+				BATADV_ELP_HLEN + tvlv_padding);
 	elp_packet = (struct batadv_elp_packet *)elp_buff;
 
 	elp_packet->packet_type = BATADV_ELP;
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 0fddc17106bd..5b71a289d04f 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -275,7 +275,7 @@ batadv_frag_merge_packets(struct hlist_head *chain)
 	kfree(entry);
 
 	packet = (struct batadv_frag_packet *)skb_out->data;
-	size = ntohs(packet->total_size);
+	size = ntohs(packet->total_size) + hdr_size;
 
 	/* Make room for the rest of the fragments. */
 	if (pskb_expand_head(skb_out, 0, size - skb_out->len, GFP_ATOMIC) < 0) {
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 4e2576fc0c59..828e87fe8027 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -467,7 +467,7 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb,
 	iv.iov_len = skb->len;
 
 	memset(&msg, 0, sizeof(msg));
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, skb->len);
+	iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, skb->len);
 
 	err = l2cap_chan_send(chan, &msg, skb->len);
 	if (err > 0) {
diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c
index 51c2cf2d8923..58fc6333d412 100644
--- a/net/bluetooth/a2mp.c
+++ b/net/bluetooth/a2mp.c
@@ -63,7 +63,7 @@ static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *dat
 
 	memset(&msg, 0, sizeof(msg));
 
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, total_len);
+	iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, total_len);
 
 	l2cap_chan_send(chan, &msg, total_len);
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index a1c1b7e8a45c..c822e626761b 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -622,7 +622,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
 
 	memset(&msg, 0, sizeof(msg));
 
-	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iv, 2, 1 + len);
+	iov_iter_kvec(&msg.msg_iter, WRITE, iv, 2, 1 + len);
 
 	l2cap_chan_send(chan, &msg, 1 + len);
 
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 41cdafbf2ebe..6bac0d6b7b94 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1428,8 +1428,7 @@ static void br_multicast_query_received(struct net_bridge *br,
 	 * is 0.0.0.0 should not be added to router port list.
 	 */
 	if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) ||
-	    (saddr->proto == htons(ETH_P_IPV6) &&
-	     !ipv6_addr_any(&saddr->u.ip6)))
+	    saddr->proto == htons(ETH_P_IPV6))
 		br_multicast_mark_router(br, port);
 }
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 2920e06a5403..04c19a37e500 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -102,12 +102,18 @@ struct br_tunnel_info {
 	struct metadata_dst	*tunnel_dst;
 };
 
+/* private vlan flags */
+enum {
+	BR_VLFLAG_PER_PORT_STATS = BIT(0),
+};
+
 /**
  * struct net_bridge_vlan - per-vlan entry
  *
  * @vnode: rhashtable member
  * @vid: VLAN id
  * @flags: bridge vlan flags
+ * @priv_flags: private (in-kernel) bridge vlan flags
  * @stats: per-cpu VLAN statistics
  * @br: if MASTER flag set, this points to a bridge struct
  * @port: if MASTER flag unset, this points to a port struct
@@ -127,6 +133,7 @@ struct net_bridge_vlan {
 	struct rhash_head		tnode;
 	u16				vid;
 	u16				flags;
+	u16				priv_flags;
 	struct br_vlan_stats __percpu	*stats;
 	union {
 		struct net_bridge	*br;
diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c
index 8c9297a01947..e84be08b8285 100644
--- a/net/bridge/br_vlan.c
+++ b/net/bridge/br_vlan.c
@@ -197,7 +197,7 @@ static void nbp_vlan_rcu_free(struct rcu_head *rcu)
 	v = container_of(rcu, struct net_bridge_vlan, rcu);
 	WARN_ON(br_vlan_is_master(v));
 	/* if we had per-port stats configured then free them here */
-	if (v->brvlan->stats != v->stats)
+	if (v->priv_flags & BR_VLFLAG_PER_PORT_STATS)
 		free_percpu(v->stats);
 	v->stats = NULL;
 	kfree(v);
@@ -264,6 +264,7 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags)
 				err = -ENOMEM;
 				goto out_filt;
 			}
+			v->priv_flags |= BR_VLFLAG_PER_PORT_STATS;
 		} else {
 			v->stats = masterv->stats;
 		}
diff --git a/net/can/raw.c b/net/can/raw.c
index 1051eee82581..3aab7664933f 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -745,18 +745,19 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 	} else
 		ifindex = ro->ifindex;
 
-	if (ro->fd_frames) {
+	dev = dev_get_by_index(sock_net(sk), ifindex);
+	if (!dev)
+		return -ENXIO;
+
+	err = -EINVAL;
+	if (ro->fd_frames && dev->mtu == CANFD_MTU) {
 		if (unlikely(size != CANFD_MTU && size != CAN_MTU))
-			return -EINVAL;
+			goto put_dev;
 	} else {
 		if (unlikely(size != CAN_MTU))
-			return -EINVAL;
+			goto put_dev;
 	}
 
-	dev = dev_get_by_index(sock_net(sk), ifindex);
-	if (!dev)
-		return -ENXIO;
-
 	skb = sock_alloc_send_skb(sk, size + sizeof(struct can_skb_priv),
 				  msg->msg_flags & MSG_DONTWAIT, &err);
 	if (!skb)
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 0a187196aeed..2f126eff275d 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -156,7 +156,6 @@ static bool con_flag_test_and_set(struct ceph_connection *con,
 /* Slab caches for frequently-allocated structures */
 
 static struct kmem_cache	*ceph_msg_cache;
-static struct kmem_cache	*ceph_msg_data_cache;
 
 /* static tag bytes (protocol control messages) */
 static char tag_msg = CEPH_MSGR_TAG_MSG;
@@ -235,23 +234,11 @@ static int ceph_msgr_slab_init(void)
 	if (!ceph_msg_cache)
 		return -ENOMEM;
 
-	BUG_ON(ceph_msg_data_cache);
-	ceph_msg_data_cache = KMEM_CACHE(ceph_msg_data, 0);
-	if (ceph_msg_data_cache)
-		return 0;
-
-	kmem_cache_destroy(ceph_msg_cache);
-	ceph_msg_cache = NULL;
-
-	return -ENOMEM;
+	return 0;
 }
 
 static void ceph_msgr_slab_exit(void)
 {
-	BUG_ON(!ceph_msg_data_cache);
-	kmem_cache_destroy(ceph_msg_data_cache);
-	ceph_msg_data_cache = NULL;
-
 	BUG_ON(!ceph_msg_cache);
 	kmem_cache_destroy(ceph_msg_cache);
 	ceph_msg_cache = NULL;
@@ -526,7 +513,7 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len)
 	if (!buf)
 		msg.msg_flags |= MSG_TRUNC;
 
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len);
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len);
 	r = sock_recvmsg(sock, &msg, msg.msg_flags);
 	if (r == -EAGAIN)
 		r = 0;
@@ -545,7 +532,7 @@ static int ceph_tcp_recvpage(struct socket *sock, struct page *page,
 	int r;
 
 	BUG_ON(page_offset + length > PAGE_SIZE);
-	iov_iter_bvec(&msg.msg_iter, READ | ITER_BVEC, &bvec, 1, length);
+	iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length);
 	r = sock_recvmsg(sock, &msg, msg.msg_flags);
 	if (r == -EAGAIN)
 		r = 0;
@@ -593,9 +580,15 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	struct bio_vec bvec;
 	int ret;
 
-	/* sendpage cannot properly handle pages with page_count == 0,
-	 * we need to fallback to sendmsg if that's the case */
-	if (page_count(page) >= 1)
+	/*
+	 * 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 (page_count(page) >= 1 && !PageSlab(page))
 		return __ceph_tcp_sendpage(sock, page, offset, size, more);
 
 	bvec.bv_page = page;
@@ -607,7 +600,7 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page,
 	else
 		msg.msg_flags |= MSG_EOR;  /* superfluous, but what the hell */
 
-	iov_iter_bvec(&msg.msg_iter, WRITE | ITER_BVEC, &bvec, 1, size);
+	iov_iter_bvec(&msg.msg_iter, WRITE, &bvec, 1, size);
 	ret = sock_sendmsg(sock, &msg);
 	if (ret == -EAGAIN)
 		ret = 0;
@@ -1141,16 +1134,13 @@ static void __ceph_msg_data_cursor_init(struct ceph_msg_data_cursor *cursor)
 static void ceph_msg_data_cursor_init(struct ceph_msg *msg, size_t length)
 {
 	struct ceph_msg_data_cursor *cursor = &msg->cursor;
-	struct ceph_msg_data *data;
 
 	BUG_ON(!length);
 	BUG_ON(length > msg->data_length);
-	BUG_ON(list_empty(&msg->data));
+	BUG_ON(!msg->num_data_items);
 
-	cursor->data_head = &msg->data;
 	cursor->total_resid = length;
-	data = list_first_entry(&msg->data, struct ceph_msg_data, links);
-	cursor->data = data;
+	cursor->data = msg->data;
 
 	__ceph_msg_data_cursor_init(cursor);
 }
@@ -1231,8 +1221,7 @@ static void ceph_msg_data_advance(struct ceph_msg_data_cursor *cursor,
 
 	if (!cursor->resid && cursor->total_resid) {
 		WARN_ON(!cursor->last_piece);
-		BUG_ON(list_is_last(&cursor->data->links, cursor->data_head));
-		cursor->data = list_next_entry(cursor->data, links);
+		cursor->data++;
 		__ceph_msg_data_cursor_init(cursor);
 		new_piece = true;
 	}
@@ -1248,9 +1237,6 @@ static size_t sizeof_footer(struct ceph_connection *con)
 
 static void prepare_message_data(struct ceph_msg *msg, u32 data_len)
 {
-	BUG_ON(!msg);
-	BUG_ON(!data_len);
-
 	/* Initialize data cursor */
 
 	ceph_msg_data_cursor_init(msg, (size_t)data_len);
@@ -1590,7 +1576,7 @@ static int write_partial_message_data(struct ceph_connection *con)
 
 	dout("%s %p msg %p\n", __func__, con, msg);
 
-	if (list_empty(&msg->data))
+	if (!msg->num_data_items)
 		return -EINVAL;
 
 	/*
@@ -2347,8 +2333,7 @@ static int read_partial_msg_data(struct ceph_connection *con)
 	u32 crc = 0;
 	int ret;
 
-	BUG_ON(!msg);
-	if (list_empty(&msg->data))
+	if (!msg->num_data_items)
 		return -EIO;
 
 	if (do_datacrc)
@@ -3256,32 +3241,16 @@ bool ceph_con_keepalive_expired(struct ceph_connection *con,
 	return false;
 }
 
-static struct ceph_msg_data *ceph_msg_data_create(enum ceph_msg_data_type type)
+static struct ceph_msg_data *ceph_msg_data_add(struct ceph_msg *msg)
 {
-	struct ceph_msg_data *data;
-
-	if (WARN_ON(!ceph_msg_data_type_valid(type)))
-		return NULL;
-
-	data = kmem_cache_zalloc(ceph_msg_data_cache, GFP_NOFS);
-	if (!data)
-		return NULL;
-
-	data->type = type;
-	INIT_LIST_HEAD(&data->links);
-
-	return data;
+	BUG_ON(msg->num_data_items >= msg->max_data_items);
+	return &msg->data[msg->num_data_items++];
 }
 
 static void ceph_msg_data_destroy(struct ceph_msg_data *data)
 {
-	if (!data)
-		return;
-
-	WARN_ON(!list_empty(&data->links));
 	if (data->type == CEPH_MSG_DATA_PAGELIST)
 		ceph_pagelist_release(data->pagelist);
-	kmem_cache_free(ceph_msg_data_cache, data);
 }
 
 void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
@@ -3292,13 +3261,12 @@ void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages,
 	BUG_ON(!pages);
 	BUG_ON(!length);
 
-	data = ceph_msg_data_create(CEPH_MSG_DATA_PAGES);
-	BUG_ON(!data);
+	data = ceph_msg_data_add(msg);
+	data->type = CEPH_MSG_DATA_PAGES;
 	data->pages = pages;
 	data->length = length;
 	data->alignment = alignment & ~PAGE_MASK;
 
-	list_add_tail(&data->links, &msg->data);
 	msg->data_length += length;
 }
 EXPORT_SYMBOL(ceph_msg_data_add_pages);
@@ -3311,11 +3279,11 @@ void ceph_msg_data_add_pagelist(struct ceph_msg *msg,
 	BUG_ON(!pagelist);
 	BUG_ON(!pagelist->length);
 
-	data = ceph_msg_data_create(CEPH_MSG_DATA_PAGELIST);
-	BUG_ON(!data);
+	data = ceph_msg_data_add(msg);
+	data->type = CEPH_MSG_DATA_PAGELIST;
+	refcount_inc(&pagelist->refcnt);
 	data->pagelist = pagelist;
 
-	list_add_tail(&data->links, &msg->data);
 	msg->data_length += pagelist->length;
 }
 EXPORT_SYMBOL(ceph_msg_data_add_pagelist);
@@ -3326,12 +3294,11 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos,
 {
 	struct ceph_msg_data *data;
 
-	data = ceph_msg_data_create(CEPH_MSG_DATA_BIO);
-	BUG_ON(!data);
+	data = ceph_msg_data_add(msg);
+	data->type = CEPH_MSG_DATA_BIO;
 	data->bio_pos = *bio_pos;
 	data->bio_length = length;
 
-	list_add_tail(&data->links, &msg->data);
 	msg->data_length += length;
 }
 EXPORT_SYMBOL(ceph_msg_data_add_bio);
@@ -3342,11 +3309,10 @@ void ceph_msg_data_add_bvecs(struct ceph_msg *msg,
 {
 	struct ceph_msg_data *data;
 
-	data = ceph_msg_data_create(CEPH_MSG_DATA_BVECS);
-	BUG_ON(!data);
+	data = ceph_msg_data_add(msg);
+	data->type = CEPH_MSG_DATA_BVECS;
 	data->bvec_pos = *bvec_pos;
 
-	list_add_tail(&data->links, &msg->data);
 	msg->data_length += bvec_pos->iter.bi_size;
 }
 EXPORT_SYMBOL(ceph_msg_data_add_bvecs);
@@ -3355,8 +3321,8 @@ EXPORT_SYMBOL(ceph_msg_data_add_bvecs);
  * construct a new message with given type, size
  * the new msg has a ref count of 1.
  */
-struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
-			      bool can_fail)
+struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items,
+			       gfp_t flags, bool can_fail)
 {
 	struct ceph_msg *m;
 
@@ -3370,7 +3336,6 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 
 	INIT_LIST_HEAD(&m->list_head);
 	kref_init(&m->kref);
-	INIT_LIST_HEAD(&m->data);
 
 	/* front */
 	if (front_len) {
@@ -3385,6 +3350,15 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
 	}
 	m->front_alloc_len = m->front.iov_len = front_len;
 
+	if (max_data_items) {
+		m->data = kmalloc_array(max_data_items, sizeof(*m->data),
+					flags);
+		if (!m->data)
+			goto out2;
+
+		m->max_data_items = max_data_items;
+	}
+
 	dout("ceph_msg_new %p front %d\n", m, front_len);
 	return m;
 
@@ -3401,6 +3375,13 @@ out:
 	}
 	return NULL;
 }
+EXPORT_SYMBOL(ceph_msg_new2);
+
+struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags,
+			      bool can_fail)
+{
+	return ceph_msg_new2(type, front_len, 0, flags, can_fail);
+}
 EXPORT_SYMBOL(ceph_msg_new);
 
 /*
@@ -3496,13 +3477,14 @@ static void ceph_msg_free(struct ceph_msg *m)
 {
 	dout("%s %p\n", __func__, m);
 	kvfree(m->front.iov_base);
+	kfree(m->data);
 	kmem_cache_free(ceph_msg_cache, m);
 }
 
 static void ceph_msg_release(struct kref *kref)
 {
 	struct ceph_msg *m = container_of(kref, struct ceph_msg, kref);
-	struct ceph_msg_data *data, *next;
+	int i;
 
 	dout("%s %p\n", __func__, m);
 	WARN_ON(!list_empty(&m->list_head));
@@ -3515,11 +3497,8 @@ static void ceph_msg_release(struct kref *kref)
 		m->middle = NULL;
 	}
 
-	list_for_each_entry_safe(data, next, &m->data, links) {
-		list_del_init(&data->links);
-		ceph_msg_data_destroy(data);
-	}
-	m->data_length = 0;
+	for (i = 0; i < m->num_data_items; i++)
+		ceph_msg_data_destroy(&m->data[i]);
 
 	if (m->pool)
 		ceph_msgpool_put(m->pool, m);
diff --git a/net/ceph/msgpool.c b/net/ceph/msgpool.c
index 72571535883f..e3ecb80cd182 100644
--- a/net/ceph/msgpool.c
+++ b/net/ceph/msgpool.c
@@ -14,7 +14,8 @@ static void *msgpool_alloc(gfp_t gfp_mask, void *arg)
 	struct ceph_msgpool *pool = arg;
 	struct ceph_msg *msg;
 
-	msg = ceph_msg_new(pool->type, pool->front_len, gfp_mask, true);
+	msg = ceph_msg_new2(pool->type, pool->front_len, pool->max_data_items,
+			    gfp_mask, true);
 	if (!msg) {
 		dout("msgpool_alloc %s failed\n", pool->name);
 	} else {
@@ -35,11 +36,13 @@ static void msgpool_free(void *element, void *arg)
 }
 
 int ceph_msgpool_init(struct ceph_msgpool *pool, int type,
-		      int front_len, int size, bool blocking, const char *name)
+		      int front_len, int max_data_items, int size,
+		      const char *name)
 {
 	dout("msgpool %s init\n", name);
 	pool->type = type;
 	pool->front_len = front_len;
+	pool->max_data_items = max_data_items;
 	pool->pool = mempool_create(size, msgpool_alloc, msgpool_free, pool);
 	if (!pool->pool)
 		return -ENOMEM;
@@ -53,18 +56,21 @@ void ceph_msgpool_destroy(struct ceph_msgpool *pool)
 	mempool_destroy(pool->pool);
 }
 
-struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool,
-				  int front_len)
+struct ceph_msg *ceph_msgpool_get(struct ceph_msgpool *pool, int front_len,
+				  int max_data_items)
 {
 	struct ceph_msg *msg;
 
-	if (front_len > pool->front_len) {
-		dout("msgpool_get %s need front %d, pool size is %d\n",
-		       pool->name, front_len, pool->front_len);
-		WARN_ON(1);
+	if (front_len > pool->front_len ||
+	    max_data_items > pool->max_data_items) {
+		pr_warn_ratelimited("%s need %d/%d, pool %s has %d/%d\n",
+		    __func__, front_len, max_data_items, pool->name,
+		    pool->front_len, pool->max_data_items);
+		WARN_ON_ONCE(1);
 
 		/* try to alloc a fresh message */
-		return ceph_msg_new(pool->type, front_len, GFP_NOFS, false);
+		return ceph_msg_new2(pool->type, front_len, max_data_items,
+				     GFP_NOFS, false);
 	}
 
 	msg = mempool_alloc(pool->pool, GFP_NOFS);
@@ -80,6 +86,9 @@ void ceph_msgpool_put(struct ceph_msgpool *pool, struct ceph_msg *msg)
 	msg->front.iov_len = pool->front_len;
 	msg->hdr.front_len = cpu_to_le32(pool->front_len);
 
+	msg->data_length = 0;
+	msg->num_data_items = 0;
+
 	kref_init(&msg->kref);  /* retake single ref */
 	mempool_free(msg, pool->pool);
 }
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 60934bd8796c..d23a9f81f3d7 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -126,6 +126,9 @@ static void ceph_osd_data_init(struct ceph_osd_data *osd_data)
 	osd_data->type = CEPH_OSD_DATA_TYPE_NONE;
 }
 
+/*
+ * Consumes @pages if @own_pages is true.
+ */
 static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data,
 			struct page **pages, u64 length, u32 alignment,
 			bool pages_from_pool, bool own_pages)
@@ -138,6 +141,9 @@ static void ceph_osd_data_pages_init(struct ceph_osd_data *osd_data,
 	osd_data->own_pages = own_pages;
 }
 
+/*
+ * Consumes a ref on @pagelist.
+ */
 static void ceph_osd_data_pagelist_init(struct ceph_osd_data *osd_data,
 			struct ceph_pagelist *pagelist)
 {
@@ -362,6 +368,8 @@ static void ceph_osd_data_release(struct ceph_osd_data *osd_data)
 		num_pages = calc_pages_for((u64)osd_data->alignment,
 						(u64)osd_data->length);
 		ceph_release_page_vector(osd_data->pages, num_pages);
+	} else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) {
+		ceph_pagelist_release(osd_data->pagelist);
 	}
 	ceph_osd_data_init(osd_data);
 }
@@ -402,6 +410,9 @@ static void osd_req_op_data_release(struct ceph_osd_request *osd_req,
 	case CEPH_OSD_OP_LIST_WATCHERS:
 		ceph_osd_data_release(&op->list_watchers.response_data);
 		break;
+	case CEPH_OSD_OP_COPY_FROM:
+		ceph_osd_data_release(&op->copy_from.osd_data);
+		break;
 	default:
 		break;
 	}
@@ -606,12 +617,15 @@ static int ceph_oloc_encoding_size(const struct ceph_object_locator *oloc)
 	return 8 + 4 + 4 + 4 + (oloc->pool_ns ? oloc->pool_ns->len : 0);
 }
 
-int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
+static int __ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp,
+				      int num_request_data_items,
+				      int num_reply_data_items)
 {
 	struct ceph_osd_client *osdc = req->r_osdc;
 	struct ceph_msg *msg;
 	int msg_size;
 
+	WARN_ON(req->r_request || req->r_reply);
 	WARN_ON(ceph_oid_empty(&req->r_base_oid));
 	WARN_ON(ceph_oloc_empty(&req->r_base_oloc));
 
@@ -633,9 +647,11 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
 	msg_size += 4 + 8; /* retry_attempt, features */
 
 	if (req->r_mempool)
-		msg = ceph_msgpool_get(&osdc->msgpool_op, 0);
+		msg = ceph_msgpool_get(&osdc->msgpool_op, msg_size,
+				       num_request_data_items);
 	else
-		msg = ceph_msg_new(CEPH_MSG_OSD_OP, msg_size, gfp, true);
+		msg = ceph_msg_new2(CEPH_MSG_OSD_OP, msg_size,
+				    num_request_data_items, gfp, true);
 	if (!msg)
 		return -ENOMEM;
 
@@ -648,9 +664,11 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
 	msg_size += req->r_num_ops * sizeof(struct ceph_osd_op);
 
 	if (req->r_mempool)
-		msg = ceph_msgpool_get(&osdc->msgpool_op_reply, 0);
+		msg = ceph_msgpool_get(&osdc->msgpool_op_reply, msg_size,
+				       num_reply_data_items);
 	else
-		msg = ceph_msg_new(CEPH_MSG_OSD_OPREPLY, msg_size, gfp, true);
+		msg = ceph_msg_new2(CEPH_MSG_OSD_OPREPLY, msg_size,
+				    num_reply_data_items, gfp, true);
 	if (!msg)
 		return -ENOMEM;
 
@@ -658,7 +676,6 @@ int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
 
 	return 0;
 }
-EXPORT_SYMBOL(ceph_osdc_alloc_messages);
 
 static bool osd_req_opcode_valid(u16 opcode)
 {
@@ -671,6 +688,65 @@ __CEPH_FORALL_OSD_OPS(GENERATE_CASE)
 	}
 }
 
+static void get_num_data_items(struct ceph_osd_request *req,
+			       int *num_request_data_items,
+			       int *num_reply_data_items)
+{
+	struct ceph_osd_req_op *op;
+
+	*num_request_data_items = 0;
+	*num_reply_data_items = 0;
+
+	for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) {
+		switch (op->op) {
+		/* request */
+		case CEPH_OSD_OP_WRITE:
+		case CEPH_OSD_OP_WRITEFULL:
+		case CEPH_OSD_OP_SETXATTR:
+		case CEPH_OSD_OP_CMPXATTR:
+		case CEPH_OSD_OP_NOTIFY_ACK:
+		case CEPH_OSD_OP_COPY_FROM:
+			*num_request_data_items += 1;
+			break;
+
+		/* reply */
+		case CEPH_OSD_OP_STAT:
+		case CEPH_OSD_OP_READ:
+		case CEPH_OSD_OP_LIST_WATCHERS:
+			*num_reply_data_items += 1;
+			break;
+
+		/* both */
+		case CEPH_OSD_OP_NOTIFY:
+			*num_request_data_items += 1;
+			*num_reply_data_items += 1;
+			break;
+		case CEPH_OSD_OP_CALL:
+			*num_request_data_items += 2;
+			*num_reply_data_items += 1;
+			break;
+
+		default:
+			WARN_ON(!osd_req_opcode_valid(op->op));
+			break;
+		}
+	}
+}
+
+/*
+ * oid, oloc and OSD op opcode(s) must be filled in before this function
+ * is called.
+ */
+int ceph_osdc_alloc_messages(struct ceph_osd_request *req, gfp_t gfp)
+{
+	int num_request_data_items, num_reply_data_items;
+
+	get_num_data_items(req, &num_request_data_items, &num_reply_data_items);
+	return __ceph_osdc_alloc_messages(req, gfp, num_request_data_items,
+					  num_reply_data_items);
+}
+EXPORT_SYMBOL(ceph_osdc_alloc_messages);
+
 /*
  * This is an osd op init function for opcodes that have no data or
  * other information associated with them.  It also serves as a
@@ -767,22 +843,19 @@ void osd_req_op_extent_dup_last(struct ceph_osd_request *osd_req,
 EXPORT_SYMBOL(osd_req_op_extent_dup_last);
 
 int osd_req_op_cls_init(struct ceph_osd_request *osd_req, unsigned int which,
-			u16 opcode, const char *class, const char *method)
+			const char *class, const char *method)
 {
-	struct ceph_osd_req_op *op = _osd_req_op_init(osd_req, which,
-						      opcode, 0);
+	struct ceph_osd_req_op *op;
 	struct ceph_pagelist *pagelist;
 	size_t payload_len = 0;
 	size_t size;
 
-	BUG_ON(opcode != CEPH_OSD_OP_CALL);
+	op = _osd_req_op_init(osd_req, which, CEPH_OSD_OP_CALL, 0);
 
-	pagelist = kmalloc(sizeof (*pagelist), GFP_NOFS);
+	pagelist = ceph_pagelist_alloc(GFP_NOFS);
 	if (!pagelist)
 		return -ENOMEM;
 
-	ceph_pagelist_init(pagelist);
-
 	op->cls.class_name = class;
 	size = strlen(class);
 	BUG_ON(size > (size_t) U8_MAX);
@@ -815,12 +888,10 @@ int osd_req_op_xattr_init(struct ceph_osd_request *osd_req, unsigned int which,
 
 	BUG_ON(opcode != CEPH_OSD_OP_SETXATTR && opcode != CEPH_OSD_OP_CMPXATTR);
 
-	pagelist = kmalloc(sizeof(*pagelist), GFP_NOFS);
+	pagelist = ceph_pagelist_alloc(GFP_NOFS);
 	if (!pagelist)
 		return -ENOMEM;
 
-	ceph_pagelist_init(pagelist);
-
 	payload_len = strlen(name);
 	op->xattr.name_len = payload_len;
 	ceph_pagelist_append(pagelist, name, payload_len);
@@ -900,12 +971,6 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg,
 static u32 osd_req_encode_op(struct ceph_osd_op *dst,
 			     const struct ceph_osd_req_op *src)
 {
-	if (WARN_ON(!osd_req_opcode_valid(src->op))) {
-		pr_err("unrecognized osd opcode %d\n", src->op);
-
-		return 0;
-	}
-
 	switch (src->op) {
 	case CEPH_OSD_OP_STAT:
 		break;
@@ -955,6 +1020,14 @@ static u32 osd_req_encode_op(struct ceph_osd_op *dst,
 	case CEPH_OSD_OP_CREATE:
 	case CEPH_OSD_OP_DELETE:
 		break;
+	case CEPH_OSD_OP_COPY_FROM:
+		dst->copy_from.snapid = cpu_to_le64(src->copy_from.snapid);
+		dst->copy_from.src_version =
+			cpu_to_le64(src->copy_from.src_version);
+		dst->copy_from.flags = src->copy_from.flags;
+		dst->copy_from.src_fadvise_flags =
+			cpu_to_le32(src->copy_from.src_fadvise_flags);
+		break;
 	default:
 		pr_err("unsupported osd opcode %s\n",
 			ceph_osd_op_name(src->op));
@@ -1038,7 +1111,15 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 	if (flags & CEPH_OSD_FLAG_WRITE)
 		req->r_data_offset = off;
 
-	r = ceph_osdc_alloc_messages(req, GFP_NOFS);
+	if (num_ops > 1)
+		/*
+		 * This is a special case for ceph_writepages_start(), but it
+		 * also covers ceph_uninline_data().  If more multi-op request
+		 * use cases emerge, we will need a separate helper.
+		 */
+		r = __ceph_osdc_alloc_messages(req, GFP_NOFS, num_ops, 0);
+	else
+		r = ceph_osdc_alloc_messages(req, GFP_NOFS);
 	if (r)
 		goto fail;
 
@@ -1845,48 +1926,55 @@ static bool should_plug_request(struct ceph_osd_request *req)
 	return true;
 }
 
-static void setup_request_data(struct ceph_osd_request *req,
-			       struct ceph_msg *msg)
+/*
+ * Keep get_num_data_items() in sync with this function.
+ */
+static void setup_request_data(struct ceph_osd_request *req)
 {
-	u32 data_len = 0;
-	int i;
+	struct ceph_msg *request_msg = req->r_request;
+	struct ceph_msg *reply_msg = req->r_reply;
+	struct ceph_osd_req_op *op;
 
-	if (!list_empty(&msg->data))
+	if (req->r_request->num_data_items || req->r_reply->num_data_items)
 		return;
 
-	WARN_ON(msg->data_length);
-	for (i = 0; i < req->r_num_ops; i++) {
-		struct ceph_osd_req_op *op = &req->r_ops[i];
-
+	WARN_ON(request_msg->data_length || reply_msg->data_length);
+	for (op = req->r_ops; op != &req->r_ops[req->r_num_ops]; op++) {
 		switch (op->op) {
 		/* request */
 		case CEPH_OSD_OP_WRITE:
 		case CEPH_OSD_OP_WRITEFULL:
 			WARN_ON(op->indata_len != op->extent.length);
-			ceph_osdc_msg_data_add(msg, &op->extent.osd_data);
+			ceph_osdc_msg_data_add(request_msg,
+					       &op->extent.osd_data);
 			break;
 		case CEPH_OSD_OP_SETXATTR:
 		case CEPH_OSD_OP_CMPXATTR:
 			WARN_ON(op->indata_len != op->xattr.name_len +
 						  op->xattr.value_len);
-			ceph_osdc_msg_data_add(msg, &op->xattr.osd_data);
+			ceph_osdc_msg_data_add(request_msg,
+					       &op->xattr.osd_data);
 			break;
 		case CEPH_OSD_OP_NOTIFY_ACK:
-			ceph_osdc_msg_data_add(msg,
+			ceph_osdc_msg_data_add(request_msg,
 					       &op->notify_ack.request_data);
 			break;
+		case CEPH_OSD_OP_COPY_FROM:
+			ceph_osdc_msg_data_add(request_msg,
+					       &op->copy_from.osd_data);
+			break;
 
 		/* reply */
 		case CEPH_OSD_OP_STAT:
-			ceph_osdc_msg_data_add(req->r_reply,
+			ceph_osdc_msg_data_add(reply_msg,
 					       &op->raw_data_in);
 			break;
 		case CEPH_OSD_OP_READ:
-			ceph_osdc_msg_data_add(req->r_reply,
+			ceph_osdc_msg_data_add(reply_msg,
 					       &op->extent.osd_data);
 			break;
 		case CEPH_OSD_OP_LIST_WATCHERS:
-			ceph_osdc_msg_data_add(req->r_reply,
+			ceph_osdc_msg_data_add(reply_msg,
 					       &op->list_watchers.response_data);
 			break;
 
@@ -1895,25 +1983,23 @@ static void setup_request_data(struct ceph_osd_request *req,
 			WARN_ON(op->indata_len != op->cls.class_len +
 						  op->cls.method_len +
 						  op->cls.indata_len);
-			ceph_osdc_msg_data_add(msg, &op->cls.request_info);
+			ceph_osdc_msg_data_add(request_msg,
+					       &op->cls.request_info);
 			/* optional, can be NONE */
-			ceph_osdc_msg_data_add(msg, &op->cls.request_data);
+			ceph_osdc_msg_data_add(request_msg,
+					       &op->cls.request_data);
 			/* optional, can be NONE */
-			ceph_osdc_msg_data_add(req->r_reply,
+			ceph_osdc_msg_data_add(reply_msg,
 					       &op->cls.response_data);
 			break;
 		case CEPH_OSD_OP_NOTIFY:
-			ceph_osdc_msg_data_add(msg,
+			ceph_osdc_msg_data_add(request_msg,
 					       &op->notify.request_data);
-			ceph_osdc_msg_data_add(req->r_reply,
+			ceph_osdc_msg_data_add(reply_msg,
 					       &op->notify.response_data);
 			break;
 		}
-
-		data_len += op->indata_len;
 	}
-
-	WARN_ON(data_len != msg->data_length);
 }
 
 static void encode_pgid(void **p, const struct ceph_pg *pgid)
@@ -1961,7 +2047,7 @@ static void encode_request_partial(struct ceph_osd_request *req,
 			req->r_data_offset || req->r_snapc);
 	}
 
-	setup_request_data(req, msg);
+	setup_request_data(req);
 
 	encode_spgid(&p, &req->r_t.spgid); /* actual spg */
 	ceph_encode_32(&p, req->r_t.pgid.seed); /* raw hash */
@@ -3001,11 +3087,21 @@ static void linger_submit(struct ceph_osd_linger_request *lreq)
 	struct ceph_osd_client *osdc = lreq->osdc;
 	struct ceph_osd *osd;
 
+	down_write(&osdc->lock);
+	linger_register(lreq);
+	if (lreq->is_watch) {
+		lreq->reg_req->r_ops[0].watch.cookie = lreq->linger_id;
+		lreq->ping_req->r_ops[0].watch.cookie = lreq->linger_id;
+	} else {
+		lreq->reg_req->r_ops[0].notify.cookie = lreq->linger_id;
+	}
+
 	calc_target(osdc, &lreq->t, NULL, false);
 	osd = lookup_create_osd(osdc, lreq->t.osd, true);
 	link_linger(osd, lreq);
 
 	send_linger(lreq);
+	up_write(&osdc->lock);
 }
 
 static void cancel_linger_map_check(struct ceph_osd_linger_request *lreq)
@@ -4318,9 +4414,7 @@ static void handle_watch_notify(struct ceph_osd_client *osdc,
 			     lreq->notify_id, notify_id);
 		} else if (!completion_done(&lreq->notify_finish_wait)) {
 			struct ceph_msg_data *data =
-			    list_first_entry_or_null(&msg->data,
-						     struct ceph_msg_data,
-						     links);
+			    msg->num_data_items ? &msg->data[0] : NULL;
 
 			if (data) {
 				if (lreq->preply_pages) {
@@ -4476,6 +4570,23 @@ alloc_linger_request(struct ceph_osd_linger_request *lreq)
 
 	ceph_oid_copy(&req->r_base_oid, &lreq->t.base_oid);
 	ceph_oloc_copy(&req->r_base_oloc, &lreq->t.base_oloc);
+	return req;
+}
+
+static struct ceph_osd_request *
+alloc_watch_request(struct ceph_osd_linger_request *lreq, u8 watch_opcode)
+{
+	struct ceph_osd_request *req;
+
+	req = alloc_linger_request(lreq);
+	if (!req)
+		return NULL;
+
+	/*
+	 * Pass 0 for cookie because we don't know it yet, it will be
+	 * filled in by linger_submit().
+	 */
+	osd_req_op_watch_init(req, 0, 0, watch_opcode);
 
 	if (ceph_osdc_alloc_messages(req, GFP_NOIO)) {
 		ceph_osdc_put_request(req);
@@ -4514,27 +4625,19 @@ ceph_osdc_watch(struct ceph_osd_client *osdc,
 	lreq->t.flags = CEPH_OSD_FLAG_WRITE;
 	ktime_get_real_ts64(&lreq->mtime);
 
-	lreq->reg_req = alloc_linger_request(lreq);
+	lreq->reg_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_WATCH);
 	if (!lreq->reg_req) {
 		ret = -ENOMEM;
 		goto err_put_lreq;
 	}
 
-	lreq->ping_req = alloc_linger_request(lreq);
+	lreq->ping_req = alloc_watch_request(lreq, CEPH_OSD_WATCH_OP_PING);
 	if (!lreq->ping_req) {
 		ret = -ENOMEM;
 		goto err_put_lreq;
 	}
 
-	down_write(&osdc->lock);
-	linger_register(lreq); /* before osd_req_op_* */
-	osd_req_op_watch_init(lreq->reg_req, 0, lreq->linger_id,
-			      CEPH_OSD_WATCH_OP_WATCH);
-	osd_req_op_watch_init(lreq->ping_req, 0, lreq->linger_id,
-			      CEPH_OSD_WATCH_OP_PING);
 	linger_submit(lreq);
-	up_write(&osdc->lock);
-
 	ret = linger_reg_commit_wait(lreq);
 	if (ret) {
 		linger_cancel(lreq);
@@ -4599,11 +4702,10 @@ static int osd_req_op_notify_ack_init(struct ceph_osd_request *req, int which,
 
 	op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY_ACK, 0);
 
-	pl = kmalloc(sizeof(*pl), GFP_NOIO);
+	pl = ceph_pagelist_alloc(GFP_NOIO);
 	if (!pl)
 		return -ENOMEM;
 
-	ceph_pagelist_init(pl);
 	ret = ceph_pagelist_encode_64(pl, notify_id);
 	ret |= ceph_pagelist_encode_64(pl, cookie);
 	if (payload) {
@@ -4641,12 +4743,12 @@ int ceph_osdc_notify_ack(struct ceph_osd_client *osdc,
 	ceph_oloc_copy(&req->r_base_oloc, oloc);
 	req->r_flags = CEPH_OSD_FLAG_READ;
 
-	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+	ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
+					 payload_len);
 	if (ret)
 		goto out_put_req;
 
-	ret = osd_req_op_notify_ack_init(req, 0, notify_id, cookie, payload,
-					 payload_len);
+	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
 	if (ret)
 		goto out_put_req;
 
@@ -4670,11 +4772,10 @@ static int osd_req_op_notify_init(struct ceph_osd_request *req, int which,
 	op = _osd_req_op_init(req, which, CEPH_OSD_OP_NOTIFY, 0);
 	op->notify.cookie = cookie;
 
-	pl = kmalloc(sizeof(*pl), GFP_NOIO);
+	pl = ceph_pagelist_alloc(GFP_NOIO);
 	if (!pl)
 		return -ENOMEM;
 
-	ceph_pagelist_init(pl);
 	ret = ceph_pagelist_encode_32(pl, 1); /* prot_ver */
 	ret |= ceph_pagelist_encode_32(pl, timeout);
 	ret |= ceph_pagelist_encode_32(pl, payload_len);
@@ -4733,29 +4834,30 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
 		goto out_put_lreq;
 	}
 
+	/*
+	 * Pass 0 for cookie because we don't know it yet, it will be
+	 * filled in by linger_submit().
+	 */
+	ret = osd_req_op_notify_init(lreq->reg_req, 0, 0, 1, timeout,
+				     payload, payload_len);
+	if (ret)
+		goto out_put_lreq;
+
 	/* for notify_id */
 	pages = ceph_alloc_page_vector(1, GFP_NOIO);
 	if (IS_ERR(pages)) {
 		ret = PTR_ERR(pages);
 		goto out_put_lreq;
 	}
-
-	down_write(&osdc->lock);
-	linger_register(lreq); /* before osd_req_op_* */
-	ret = osd_req_op_notify_init(lreq->reg_req, 0, lreq->linger_id, 1,
-				     timeout, payload, payload_len);
-	if (ret) {
-		linger_unregister(lreq);
-		up_write(&osdc->lock);
-		ceph_release_page_vector(pages, 1);
-		goto out_put_lreq;
-	}
 	ceph_osd_data_pages_init(osd_req_op_data(lreq->reg_req, 0, notify,
 						 response_data),
 				 pages, PAGE_SIZE, 0, false, true);
-	linger_submit(lreq);
-	up_write(&osdc->lock);
 
+	ret = ceph_osdc_alloc_messages(lreq->reg_req, GFP_NOIO);
+	if (ret)
+		goto out_put_lreq;
+
+	linger_submit(lreq);
 	ret = linger_reg_commit_wait(lreq);
 	if (!ret)
 		ret = linger_notify_finish_wait(lreq);
@@ -4881,10 +4983,6 @@ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
 	ceph_oloc_copy(&req->r_base_oloc, oloc);
 	req->r_flags = CEPH_OSD_FLAG_READ;
 
-	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
-	if (ret)
-		goto out_put_req;
-
 	pages = ceph_alloc_page_vector(1, GFP_NOIO);
 	if (IS_ERR(pages)) {
 		ret = PTR_ERR(pages);
@@ -4896,6 +4994,10 @@ int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
 						 response_data),
 				 pages, PAGE_SIZE, 0, false, true);
 
+	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+	if (ret)
+		goto out_put_req;
+
 	ceph_osdc_start_request(osdc, req, false);
 	ret = ceph_osdc_wait_request(osdc, req);
 	if (ret >= 0) {
@@ -4958,11 +5060,7 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 	ceph_oloc_copy(&req->r_base_oloc, oloc);
 	req->r_flags = flags;
 
-	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
-	if (ret)
-		goto out_put_req;
-
-	ret = osd_req_op_cls_init(req, 0, CEPH_OSD_OP_CALL, class, method);
+	ret = osd_req_op_cls_init(req, 0, class, method);
 	if (ret)
 		goto out_put_req;
 
@@ -4973,6 +5071,10 @@ int ceph_osdc_call(struct ceph_osd_client *osdc,
 		osd_req_op_cls_response_data_pages(req, 0, &resp_page,
 						   *resp_len, 0, false, false);
 
+	ret = ceph_osdc_alloc_messages(req, GFP_NOIO);
+	if (ret)
+		goto out_put_req;
+
 	ceph_osdc_start_request(osdc, req, false);
 	ret = ceph_osdc_wait_request(osdc, req);
 	if (ret >= 0) {
@@ -5021,11 +5123,12 @@ int ceph_osdc_init(struct ceph_osd_client *osdc, struct ceph_client *client)
 		goto out_map;
 
 	err = ceph_msgpool_init(&osdc->msgpool_op, CEPH_MSG_OSD_OP,
-				PAGE_SIZE, 10, true, "osd_op");
+				PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10, "osd_op");
 	if (err < 0)
 		goto out_mempool;
 	err = ceph_msgpool_init(&osdc->msgpool_op_reply, CEPH_MSG_OSD_OPREPLY,
-				PAGE_SIZE, 10, true, "osd_op_reply");
+				PAGE_SIZE, CEPH_OSD_SLAB_OPS, 10,
+				"osd_op_reply");
 	if (err < 0)
 		goto out_msgpool;
 
@@ -5168,6 +5271,80 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 }
 EXPORT_SYMBOL(ceph_osdc_writepages);
 
+static int osd_req_op_copy_from_init(struct ceph_osd_request *req,
+				     u64 src_snapid, u64 src_version,
+				     struct ceph_object_id *src_oid,
+				     struct ceph_object_locator *src_oloc,
+				     u32 src_fadvise_flags,
+				     u32 dst_fadvise_flags,
+				     u8 copy_from_flags)
+{
+	struct ceph_osd_req_op *op;
+	struct page **pages;
+	void *p, *end;
+
+	pages = ceph_alloc_page_vector(1, GFP_KERNEL);
+	if (IS_ERR(pages))
+		return PTR_ERR(pages);
+
+	op = _osd_req_op_init(req, 0, CEPH_OSD_OP_COPY_FROM, dst_fadvise_flags);
+	op->copy_from.snapid = src_snapid;
+	op->copy_from.src_version = src_version;
+	op->copy_from.flags = copy_from_flags;
+	op->copy_from.src_fadvise_flags = src_fadvise_flags;
+
+	p = page_address(pages[0]);
+	end = p + PAGE_SIZE;
+	ceph_encode_string(&p, end, src_oid->name, src_oid->name_len);
+	encode_oloc(&p, end, src_oloc);
+	op->indata_len = PAGE_SIZE - (end - p);
+
+	ceph_osd_data_pages_init(&op->copy_from.osd_data, pages,
+				 op->indata_len, 0, false, true);
+	return 0;
+}
+
+int ceph_osdc_copy_from(struct ceph_osd_client *osdc,
+			u64 src_snapid, u64 src_version,
+			struct ceph_object_id *src_oid,
+			struct ceph_object_locator *src_oloc,
+			u32 src_fadvise_flags,
+			struct ceph_object_id *dst_oid,
+			struct ceph_object_locator *dst_oloc,
+			u32 dst_fadvise_flags,
+			u8 copy_from_flags)
+{
+	struct ceph_osd_request *req;
+	int ret;
+
+	req = ceph_osdc_alloc_request(osdc, NULL, 1, false, GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	req->r_flags = CEPH_OSD_FLAG_WRITE;
+
+	ceph_oloc_copy(&req->r_t.base_oloc, dst_oloc);
+	ceph_oid_copy(&req->r_t.base_oid, dst_oid);
+
+	ret = osd_req_op_copy_from_init(req, src_snapid, src_version, src_oid,
+					src_oloc, src_fadvise_flags,
+					dst_fadvise_flags, copy_from_flags);
+	if (ret)
+		goto out;
+
+	ret = ceph_osdc_alloc_messages(req, GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	ceph_osdc_start_request(osdc, req, false);
+	ret = ceph_osdc_wait_request(osdc, req);
+
+out:
+	ceph_osdc_put_request(req);
+	return ret;
+}
+EXPORT_SYMBOL(ceph_osdc_copy_from);
+
 int __init ceph_osdc_setup(void)
 {
 	size_t size = sizeof(struct ceph_osd_request) +
@@ -5295,7 +5472,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr)
 	u32 front_len = le32_to_cpu(hdr->front_len);
 	u32 data_len = le32_to_cpu(hdr->data_len);
 
-	m = ceph_msg_new(type, front_len, GFP_NOIO, false);
+	m = ceph_msg_new2(type, front_len, 1, GFP_NOIO, false);
 	if (!m)
 		return NULL;
 
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
index 2ea0564771d2..65e34f78b05d 100644
--- a/net/ceph/pagelist.c
+++ b/net/ceph/pagelist.c
@@ -6,6 +6,26 @@
 #include <linux/highmem.h>
 #include <linux/ceph/pagelist.h>
 
+struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags)
+{
+	struct ceph_pagelist *pl;
+
+	pl = kmalloc(sizeof(*pl), gfp_flags);
+	if (!pl)
+		return NULL;
+
+	INIT_LIST_HEAD(&pl->head);
+	pl->mapped_tail = NULL;
+	pl->length = 0;
+	pl->room = 0;
+	INIT_LIST_HEAD(&pl->free_list);
+	pl->num_pages_free = 0;
+	refcount_set(&pl->refcnt, 1);
+
+	return pl;
+}
+EXPORT_SYMBOL(ceph_pagelist_alloc);
+
 static void ceph_pagelist_unmap_tail(struct ceph_pagelist *pl)
 {
 	if (pl->mapped_tail) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 022ad73d6253..ddc551f24ba2 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3272,7 +3272,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *first, struct net_device *de
 		}
 
 		skb = next;
-		if (netif_xmit_stopped(txq) && skb) {
+		if (netif_tx_queue_stopped(txq) && skb) {
 			rc = NETDEV_TX_BUSY;
 			break;
 		}
@@ -5457,7 +5457,7 @@ static void gro_flush_oldest(struct list_head *head)
 	/* Do not adjust napi->gro_hash[].count, caller is adding a new
 	 * SKB to the chain.
 	 */
-	list_del(&oldest->list);
+	skb_list_del_init(oldest);
 	napi_gro_complete(oldest);
 }
 
@@ -5655,6 +5655,10 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->vlan_tci = 0;
 	skb->dev = napi->dev;
 	skb->skb_iif = 0;
+
+	/* eth_type_trans() assumes pkt_type is PACKET_HOST */
+	skb->pkt_type = PACKET_HOST;
+
 	skb->encapsulation = 0;
 	skb_shinfo(skb)->gso_type = 0;
 	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
@@ -5966,11 +5970,14 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		if (work_done)
 			timeout = n->dev->gro_flush_timeout;
 
+		/* When the NAPI instance uses a timeout and keeps postponing
+		 * it, we need to bound somehow the time packets are kept in
+		 * the GRO layer
+		 */
+		napi_gro_flush(n, !!timeout);
 		if (timeout)
 			hrtimer_start(&n->timer, ns_to_ktime(timeout),
 				      HRTIMER_MODE_REL_PINNED);
-		else
-			napi_gro_flush(n, false);
 	}
 	if (unlikely(!list_empty(&n->poll_list))) {
 		/* If n->poll_list is not empty, we need to mask irqs */
diff --git a/net/core/filter.c b/net/core/filter.c
index 35c6933c2622..9a1327eb25fa 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4852,18 +4852,17 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 	} else {
 		struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
 		struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
-		u16 hnum = ntohs(tuple->ipv6.dport);
 		int sdif = inet6_sdif(skb);
 
 		if (proto == IPPROTO_TCP)
 			sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
 					    src6, tuple->ipv6.sport,
-					    dst6, hnum,
+					    dst6, ntohs(tuple->ipv6.dport),
 					    dif, sdif, &refcounted);
 		else if (likely(ipv6_bpf_stub))
 			sk = ipv6_bpf_stub->udp6_lib_lookup(net,
 							    src6, tuple->ipv6.sport,
-							    dst6, hnum,
+							    dst6, tuple->ipv6.dport,
 							    dif, sdif,
 							    &udp_table, skb);
 #endif
@@ -5264,8 +5263,6 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_msg_pull_data_proto;
 	case BPF_FUNC_msg_push_data:
 		return &bpf_msg_push_data_proto;
-	case BPF_FUNC_get_local_storage:
-		return &bpf_get_local_storage_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -5296,8 +5293,6 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_redirect_map_proto;
 	case BPF_FUNC_sk_redirect_hash:
 		return &bpf_sk_redirect_hash_proto;
-	case BPF_FUNC_get_local_storage:
-		return &bpf_get_local_storage_proto;
 #ifdef CONFIG_INET
 	case BPF_FUNC_sk_lookup_tcp:
 		return &bpf_sk_lookup_tcp_proto;
@@ -5496,7 +5491,13 @@ static bool cg_skb_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct __sk_buff, data_meta):
 	case bpf_ctx_range(struct __sk_buff, flow_keys):
 		return false;
+	case bpf_ctx_range(struct __sk_buff, data):
+	case bpf_ctx_range(struct __sk_buff, data_end):
+		if (!capable(CAP_SYS_ADMIN))
+			return false;
+		break;
 	}
+
 	if (type == BPF_WRITE) {
 		switch (off) {
 		case bpf_ctx_range(struct __sk_buff, mark):
@@ -5638,6 +5639,15 @@ static bool sock_filter_is_valid_access(int off, int size,
 					       prog->expected_attach_type);
 }
 
+static int bpf_noop_prologue(struct bpf_insn *insn_buf, bool direct_write,
+			     const struct bpf_prog *prog)
+{
+	/* Neither direct read nor direct write requires any preliminary
+	 * action.
+	 */
+	return 0;
+}
+
 static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write,
 				const struct bpf_prog *prog, int drop_verdict)
 {
@@ -7204,6 +7214,7 @@ const struct bpf_verifier_ops xdp_verifier_ops = {
 	.get_func_proto		= xdp_func_proto,
 	.is_valid_access	= xdp_is_valid_access,
 	.convert_ctx_access	= xdp_convert_ctx_access,
+	.gen_prologue		= bpf_noop_prologue,
 };
 
 const struct bpf_prog_ops xdp_prog_ops = {
@@ -7302,6 +7313,7 @@ const struct bpf_verifier_ops sk_msg_verifier_ops = {
 	.get_func_proto		= sk_msg_func_proto,
 	.is_valid_access	= sk_msg_is_valid_access,
 	.convert_ctx_access	= sk_msg_convert_ctx_access,
+	.gen_prologue		= bpf_noop_prologue,
 };
 
 const struct bpf_prog_ops sk_msg_prog_ops = {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 676f3ad629f9..588f475019d4 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1166,8 +1166,8 @@ ip_proto_again:
 		break;
 	}
 
-	if (dissector_uses_key(flow_dissector,
-			       FLOW_DISSECTOR_KEY_PORTS)) {
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS) &&
+	    !(key_control->flags & FLOW_DIS_IS_FRAGMENT)) {
 		key_ports = skb_flow_dissector_target(flow_dissector,
 						      FLOW_DISSECTOR_KEY_PORTS,
 						      target_container);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 5da9552b186b..2b9fdbc43205 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -717,7 +717,8 @@ int netpoll_setup(struct netpoll *np)
 
 				read_lock_bh(&idev->lock);
 				list_for_each_entry(ifp, &idev->addr_list, if_list) {
-					if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)
+					if (!!(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL) !=
+					    !!(ipv6_addr_type(&np->remote_ip.in6) & IPV6_ADDR_LINKLOCAL))
 						continue;
 					np->local_ip.in6 = ifp->addr;
 					err = 0;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index f679c7a7d761..33d9227a8b80 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3367,7 +3367,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 			cb->seq = 0;
 		}
 		ret = dumpit(skb, cb);
-		if (ret < 0)
+		if (ret)
 			break;
 	}
 	cb->family = idx;
@@ -3600,6 +3600,11 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	if (dev->type != ARPHRD_ETHER) {
+		NL_SET_ERR_MSG(extack, "FDB add only supported for Ethernet devices");
+		return -EINVAL;
+	}
+
 	addr = nla_data(tb[NDA_LLADDR]);
 
 	err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
@@ -3704,6 +3709,11 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	if (dev->type != ARPHRD_ETHER) {
+		NL_SET_ERR_MSG(extack, "FDB delete only supported for Ethernet devices");
+		return -EINVAL;
+	}
+
 	addr = nla_data(tb[NDA_LLADDR]);
 
 	err = fdb_vid_parse(tb[NDA_VLAN], &vid, extack);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 946de0e24c87..a8217e221e19 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4854,6 +4854,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	nf_reset(skb);
 	nf_reset_trace(skb);
 
+#ifdef CONFIG_NET_SWITCHDEV
+	skb->offload_fwd_mark = 0;
+	skb->offload_mr_fwd_mark = 0;
+#endif
+
 	if (!xnet)
 		return;
 
@@ -4944,6 +4949,8 @@ static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
  *
  * This is a helper to do that correctly considering GSO_BY_FRAGS.
  *
+ * @skb: GSO skb
+ *
  * @seg_len: The segmented length (from skb_gso_*_seglen). In the
  *           GSO_BY_FRAGS case this will be [header sizes + GSO_BY_FRAGS].
  *
diff --git a/net/core/sock.c b/net/core/sock.c
index 6fcc4bc07d19..080a880a1761 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3279,6 +3279,7 @@ int sock_load_diag_module(int family, int protocol)
 
 #ifdef CONFIG_INET
 	if (family == AF_INET &&
+	    protocol != IPPROTO_RAW &&
 	    !rcu_access_pointer(inet_protos[protocol]))
 		return -ENOENT;
 #endif
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index b1a2c5e38530..37b4667128a3 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -279,7 +279,6 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write,
 	return ret;
 }
 
-# ifdef CONFIG_HAVE_EBPF_JIT
 static int
 proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
 				    void __user *buffer, size_t *lenp,
@@ -290,7 +289,6 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write,
 
 	return proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 }
-# endif
 #endif
 
 static struct ctl_table net_core_table[] = {
@@ -397,6 +395,14 @@ static struct ctl_table net_core_table[] = {
 		.extra2		= &one,
 	},
 # endif
+	{
+		.procname	= "bpf_jit_limit",
+		.data		= &bpf_jit_limit,
+		.maxlen		= sizeof(int),
+		.mode		= 0600,
+		.proc_handler	= proc_dointvec_minmax_bpf_restricted,
+		.extra1		= &one,
+	},
 #endif
 	{
 		.procname	= "netdev_tstamp_prequeue",
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 4da39446da2d..765b2b32c4a4 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -111,13 +111,10 @@
 #ifdef CONFIG_IP_MULTICAST
 /* Parameter names and values are taken from igmp-v2-06 draft */
 
-#define IGMP_V1_ROUTER_PRESENT_TIMEOUT		(400*HZ)
-#define IGMP_V2_ROUTER_PRESENT_TIMEOUT		(400*HZ)
 #define IGMP_V2_UNSOLICITED_REPORT_INTERVAL	(10*HZ)
 #define IGMP_V3_UNSOLICITED_REPORT_INTERVAL	(1*HZ)
+#define IGMP_QUERY_INTERVAL			(125*HZ)
 #define IGMP_QUERY_RESPONSE_INTERVAL		(10*HZ)
-#define IGMP_QUERY_ROBUSTNESS_VARIABLE		2
-
 
 #define IGMP_INITIAL_REPORT_DELAY		(1)
 
@@ -935,13 +932,15 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 
 			max_delay = IGMP_QUERY_RESPONSE_INTERVAL;
 			in_dev->mr_v1_seen = jiffies +
-				IGMP_V1_ROUTER_PRESENT_TIMEOUT;
+				(in_dev->mr_qrv * in_dev->mr_qi) +
+				in_dev->mr_qri;
 			group = 0;
 		} else {
 			/* v2 router present */
 			max_delay = ih->code*(HZ/IGMP_TIMER_SCALE);
 			in_dev->mr_v2_seen = jiffies +
-				IGMP_V2_ROUTER_PRESENT_TIMEOUT;
+				(in_dev->mr_qrv * in_dev->mr_qi) +
+				in_dev->mr_qri;
 		}
 		/* cancel the interface change timer */
 		in_dev->mr_ifc_count = 0;
@@ -981,8 +980,21 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
 		if (!max_delay)
 			max_delay = 1;	/* can't mod w/ 0 */
 		in_dev->mr_maxdelay = max_delay;
-		if (ih3->qrv)
-			in_dev->mr_qrv = ih3->qrv;
+
+		/* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently
+		 * received value was zero, use the default or statically
+		 * configured value.
+		 */
+		in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv;
+		in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL;
+
+		/* RFC3376, 8.3. Query Response Interval:
+		 * The number of seconds represented by the [Query Response
+		 * Interval] must be less than the [Query Interval].
+		 */
+		if (in_dev->mr_qri >= in_dev->mr_qi)
+			in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ;
+
 		if (!group) { /* general query */
 			if (ih3->nsrcs)
 				return true;	/* no sources allowed */
@@ -1723,18 +1735,30 @@ void ip_mc_down(struct in_device *in_dev)
 	ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS);
 }
 
-void ip_mc_init_dev(struct in_device *in_dev)
-{
 #ifdef CONFIG_IP_MULTICAST
+static void ip_mc_reset(struct in_device *in_dev)
+{
 	struct net *net = dev_net(in_dev->dev);
+
+	in_dev->mr_qi = IGMP_QUERY_INTERVAL;
+	in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL;
+	in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
+}
+#else
+static void ip_mc_reset(struct in_device *in_dev)
+{
+}
 #endif
+
+void ip_mc_init_dev(struct in_device *in_dev)
+{
 	ASSERT_RTNL();
 
 #ifdef CONFIG_IP_MULTICAST
 	timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0);
 	timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0);
-	in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
 #endif
+	ip_mc_reset(in_dev);
 
 	spin_lock_init(&in_dev->mc_tomb_lock);
 }
@@ -1744,15 +1768,10 @@ void ip_mc_init_dev(struct in_device *in_dev)
 void ip_mc_up(struct in_device *in_dev)
 {
 	struct ip_mc_list *pmc;
-#ifdef CONFIG_IP_MULTICAST
-	struct net *net = dev_net(in_dev->dev);
-#endif
 
 	ASSERT_RTNL();
 
-#ifdef CONFIG_IP_MULTICAST
-	in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
-#endif
+	ip_mc_reset(in_dev);
 	ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS);
 
 	for_each_pmc_rtnl(in_dev, pmc) {
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index bcb11f3a27c0..760a9e52e02b 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -178,21 +178,22 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
 }
 
 static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
-						void *arg)
+						void *arg,
+						struct inet_frag_queue **prev)
 {
 	struct inet_frags *f = nf->f;
 	struct inet_frag_queue *q;
-	int err;
 
 	q = inet_frag_alloc(nf, f, arg);
-	if (!q)
+	if (!q) {
+		*prev = ERR_PTR(-ENOMEM);
 		return NULL;
-
+	}
 	mod_timer(&q->timer, jiffies + nf->timeout);
 
-	err = rhashtable_insert_fast(&nf->rhashtable, &q->node,
-				     f->rhash_params);
-	if (err < 0) {
+	*prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key,
+						 &q->node, f->rhash_params);
+	if (*prev) {
 		q->flags |= INET_FRAG_COMPLETE;
 		inet_frag_kill(q);
 		inet_frag_destroy(q);
@@ -204,22 +205,22 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
 /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key)
 {
-	struct inet_frag_queue *fq;
+	struct inet_frag_queue *fq = NULL, *prev;
 
 	if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh)
 		return NULL;
 
 	rcu_read_lock();
 
-	fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
-	if (fq) {
+	prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params);
+	if (!prev)
+		fq = inet_frag_create(nf, key, &prev);
+	if (prev && !IS_ERR(prev)) {
+		fq = prev;
 		if (!refcount_inc_not_zero(&fq->refcnt))
 			fq = NULL;
-		rcu_read_unlock();
-		return fq;
 	}
 	rcu_read_unlock();
-
-	return inet_frag_create(nf, key);
+	return fq;
 }
 EXPORT_SYMBOL(inet_frag_find);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index f5c9ef2586de..411dd7a90046 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -19,7 +19,7 @@
 #include <linux/slab.h>
 #include <linux/wait.h>
 #include <linux/vmalloc.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 
 #include <net/addrconf.h>
 #include <net/inet_connection_sock.h>
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 9b0158fa431f..d6ee343fdb86 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -722,10 +722,14 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 	if (ip_is_fragment(&iph)) {
 		skb = skb_share_check(skb, GFP_ATOMIC);
 		if (skb) {
-			if (!pskb_may_pull(skb, netoff + iph.ihl * 4))
-				return skb;
-			if (pskb_trim_rcsum(skb, netoff + len))
-				return skb;
+			if (!pskb_may_pull(skb, netoff + iph.ihl * 4)) {
+				kfree_skb(skb);
+				return NULL;
+			}
+			if (pskb_trim_rcsum(skb, netoff + len)) {
+				kfree_skb(skb);
+				return NULL;
+			}
 			memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
 			if (ip_defrag(net, skb, user))
 				return NULL;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c09219e7f230..5dbec21856f4 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -939,7 +939,7 @@ static int __ip_append_data(struct sock *sk,
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
-			unsigned int pagedlen = 0;
+			unsigned int pagedlen;
 			struct sk_buff *skb_prev;
 alloc_new_skb:
 			skb_prev = skb;
@@ -956,6 +956,7 @@ alloc_new_skb:
 			if (datalen > mtu - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen;
 			fraglen = datalen + fragheaderlen;
+			pagedlen = 0;
 
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 26c36cccabdc..fffcc130900e 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1246,7 +1246,7 @@ int ip_setsockopt(struct sock *sk, int level,
 		return -ENOPROTOOPT;
 
 	err = do_ip_setsockopt(sk, level, optname, optval, optlen);
-#ifdef CONFIG_BPFILTER
+#if IS_ENABLED(CONFIG_BPFILTER_UMH)
 	if (optname >= BPFILTER_IPT_SO_SET_REPLACE &&
 	    optname < BPFILTER_IPT_SET_MAX)
 		err = bpfilter_ip_set_sockopt(sk, optname, optval, optlen);
@@ -1559,7 +1559,7 @@ int ip_getsockopt(struct sock *sk, int level,
 	int err;
 
 	err = do_ip_getsockopt(sk, level, optname, optval, optlen, 0);
-#ifdef CONFIG_BPFILTER
+#if IS_ENABLED(CONFIG_BPFILTER_UMH)
 	if (optname >= BPFILTER_IPT_SO_GET_INFO &&
 	    optname < BPFILTER_IPT_GET_MAX)
 		err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
@@ -1596,7 +1596,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname,
 	err = do_ip_getsockopt(sk, level, optname, optval, optlen,
 		MSG_CMSG_COMPAT);
 
-#ifdef CONFIG_BPFILTER
+#if IS_ENABLED(CONFIG_BPFILTER_UMH)
 	if (optname >= BPFILTER_IPT_SO_GET_INFO &&
 	    optname < BPFILTER_IPT_GET_MAX)
 		err = bpfilter_ip_get_sockopt(sk, optname, optval, optlen);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index dde671e97829..c248e0dccbe1 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -80,7 +80,7 @@ void iptunnel_xmit(struct sock *sk, struct rtable *rt, struct sk_buff *skb,
 
 	iph->version	=	4;
 	iph->ihl	=	sizeof(struct iphdr) >> 2;
-	iph->frag_off	=	df;
+	iph->frag_off	=	ip_mtu_locked(&rt->dst) ? 0 : df;
 	iph->protocol	=	proto;
 	iph->tos	=	tos;
 	iph->daddr	=	dst;
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index ce1512b02cb2..fd3f9e8a74da 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -81,9 +81,12 @@ static int __init masquerade_tg_init(void)
 	int ret;
 
 	ret = xt_register_target(&masquerade_tg_reg);
+	if (ret)
+		return ret;
 
-	if (ret == 0)
-		nf_nat_masquerade_ipv4_register_notifier();
+	ret = nf_nat_masquerade_ipv4_register_notifier();
+	if (ret)
+		xt_unregister_target(&masquerade_tg_reg);
 
 	return ret;
 }
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index a9d5e013e555..41327bb99093 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -147,28 +147,50 @@ static struct notifier_block masq_inet_notifier = {
 	.notifier_call	= masq_inet_event,
 };
 
-static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+static int masq_refcnt;
+static DEFINE_MUTEX(masq_mutex);
 
-void nf_nat_masquerade_ipv4_register_notifier(void)
+int nf_nat_masquerade_ipv4_register_notifier(void)
 {
+	int ret = 0;
+
+	mutex_lock(&masq_mutex);
 	/* check if the notifier was already set */
-	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
-		return;
+	if (++masq_refcnt > 1)
+		goto out_unlock;
 
 	/* Register for device down reports */
-	register_netdevice_notifier(&masq_dev_notifier);
+	ret = register_netdevice_notifier(&masq_dev_notifier);
+	if (ret)
+		goto err_dec;
 	/* Register IP address change reports */
-	register_inetaddr_notifier(&masq_inet_notifier);
+	ret = register_inetaddr_notifier(&masq_inet_notifier);
+	if (ret)
+		goto err_unregister;
+
+	mutex_unlock(&masq_mutex);
+	return ret;
+
+err_unregister:
+	unregister_netdevice_notifier(&masq_dev_notifier);
+err_dec:
+	masq_refcnt--;
+out_unlock:
+	mutex_unlock(&masq_mutex);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_register_notifier);
 
 void nf_nat_masquerade_ipv4_unregister_notifier(void)
 {
+	mutex_lock(&masq_mutex);
 	/* check if the notifier still has clients */
-	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
-		return;
+	if (--masq_refcnt > 0)
+		goto out_unlock;
 
 	unregister_netdevice_notifier(&masq_dev_notifier);
 	unregister_inetaddr_notifier(&masq_inet_notifier);
+out_unlock:
+	mutex_unlock(&masq_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv4_unregister_notifier);
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
index f1193e1e928a..6847de1d1db8 100644
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ b/net/ipv4/netfilter/nft_masq_ipv4.c
@@ -69,7 +69,9 @@ static int __init nft_masq_ipv4_module_init(void)
 	if (ret < 0)
 		return ret;
 
-	nf_nat_masquerade_ipv4_register_notifier();
+	ret = nf_nat_masquerade_ipv4_register_notifier();
+	if (ret)
+		nft_unregister_expr(&nft_masq_ipv4_type);
 
 	return ret;
 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1834818ed07b..9e6bc4d6daa7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -262,7 +262,7 @@
 #include <linux/net.h>
 #include <linux/socket.h>
 #include <linux/random.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/highmem.h>
 #include <linux/swap.h>
 #include <linux/cache.h>
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index b7918d4caa30..3b45fe530f91 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -145,6 +145,7 @@ msg_bytes_ready:
 			ret = err;
 			goto out;
 		}
+		copied = -EAGAIN;
 	}
 	ret = copied;
 out:
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 2868ef28ce52..a9d9555a973f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -579,10 +579,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
 		u32 delta_us;
 
-		if (!delta)
-			delta = 1;
-		delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
-		tcp_rcv_rtt_update(tp, delta_us, 0);
+		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+			if (!delta)
+				delta = 1;
+			delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+			tcp_rcv_rtt_update(tp, delta_us, 0);
+		}
 	}
 }
 
@@ -2910,9 +2912,11 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag,
 	if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
 	    flag & FLAG_ACKED) {
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
-		u32 delta_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
 
-		seq_rtt_us = ca_rtt_us = delta_us;
+		if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) {
+			seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ);
+			ca_rtt_us = seq_rtt_us;
+		}
 	}
 	rs->rtt_us = ca_rtt_us; /* RTT of last (S)ACKed packet (or -1) */
 	if (seq_rtt_us < 0)
@@ -4268,7 +4272,7 @@ static void tcp_sack_new_ofo_skb(struct sock *sk, u32 seq, u32 end_seq)
 	 * If the sack array is full, forget about the last one.
 	 */
 	if (this_sack >= TCP_NUM_SACKS) {
-		if (tp->compressed_ack)
+		if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
 			tcp_send_ack(sk);
 		this_sack--;
 		tp->rx_opt.num_sacks--;
@@ -4363,6 +4367,7 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->has_rxtstamp) {
 		TCP_SKB_CB(to)->has_rxtstamp = true;
 		to->tstamp = from->tstamp;
+		skb_hwtstamps(to)->hwtstamp = skb_hwtstamps(from)->hwtstamp;
 	}
 
 	return true;
@@ -5188,7 +5193,17 @@ send_now:
 	if (!tcp_is_sack(tp) ||
 	    tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
 		goto send_now;
-	tp->compressed_ack++;
+
+	if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
+		tp->compressed_ack_rcv_nxt = tp->rcv_nxt;
+		if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
+			NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
+				      tp->compressed_ack - TCP_FASTRETRANS_THRESH);
+		tp->compressed_ack = 0;
+	}
+
+	if (++tp->compressed_ack <= TCP_FASTRETRANS_THRESH)
+		goto send_now;
 
 	if (hrtimer_is_queued(&tp->compressed_ack_timer))
 		return;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9c34b97d365d..3f510cad0b3e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -180,10 +180,10 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (unlikely(tp->compressed_ack)) {
+	if (unlikely(tp->compressed_ack > TCP_FASTRETRANS_THRESH)) {
 		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPACKCOMPRESSED,
-			      tp->compressed_ack);
-		tp->compressed_ack = 0;
+			      tp->compressed_ack - TCP_FASTRETRANS_THRESH);
+		tp->compressed_ack = TCP_FASTRETRANS_THRESH;
 		if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1)
 			__sock_put(sk);
 	}
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 676020663ce8..091c53925e4d 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -40,15 +40,17 @@ static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 elapsed, start_ts;
+	s32 remaining;
 
 	start_ts = tcp_retransmit_stamp(sk);
 	if (!icsk->icsk_user_timeout || !start_ts)
 		return icsk->icsk_rto;
 	elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts;
-	if (elapsed >= icsk->icsk_user_timeout)
+	remaining = icsk->icsk_user_timeout - elapsed;
+	if (remaining <= 0)
 		return 1; /* user timeout has passed; fire ASAP */
-	else
-		return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(icsk->icsk_user_timeout - elapsed));
+
+	return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining));
 }
 
 /**
@@ -209,7 +211,7 @@ static bool retransmits_timed_out(struct sock *sk,
 				(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
 		timeout = jiffies_to_msecs(timeout);
 	}
-	return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= timeout;
+	return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0;
 }
 
 /* A write timeout has occurred. Process the after effects. */
@@ -740,7 +742,7 @@ static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer)
 
 	bh_lock_sock(sk);
 	if (!sock_owned_by_user(sk)) {
-		if (tp->compressed_ack)
+		if (tp->compressed_ack > TCP_FASTRETRANS_THRESH)
 			tcp_send_ack(sk);
 	} else {
 		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ca3ed931f2a9..1976fddb9e00 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -81,7 +81,7 @@
 
 #include <linux/uaccess.h>
 #include <asm/ioctls.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/highmem.h>
 #include <linux/swap.h>
 #include <linux/types.h>
diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c
index d9ad986c7b2c..5cbb9be05295 100644
--- a/net/ipv4/udp_diag.c
+++ b/net/ipv4/udp_diag.c
@@ -42,6 +42,7 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb,
 
 	rcu_read_lock();
 	if (req->sdiag_family == AF_INET)
+		/* src and dst are swapped for historical reasons */
 		sk = __udp4_lib_lookup(net,
 				req->id.idiag_src[0], req->id.idiag_sport,
 				req->id.idiag_dst[0], req->id.idiag_dport,
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 63a808d5af15..045597b9a7c0 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -179,7 +179,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp);
 static void addrconf_dad_work(struct work_struct *w);
 static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
 				   bool send_na);
-static void addrconf_dad_run(struct inet6_dev *idev);
+static void addrconf_dad_run(struct inet6_dev *idev, bool restart);
 static void addrconf_rs_timer(struct timer_list *t);
 static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
 static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifa);
@@ -3439,6 +3439,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 			   void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_change_info *change_info;
 	struct netdev_notifier_changeupper_info *info;
 	struct inet6_dev *idev = __in6_dev_get(dev);
 	struct net *net = dev_net(dev);
@@ -3513,7 +3514,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 				break;
 			}
 
-			if (idev) {
+			if (!IS_ERR_OR_NULL(idev)) {
 				if (idev->if_flags & IF_READY) {
 					/* device is already configured -
 					 * but resend MLD reports, we might
@@ -3521,6 +3522,9 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 					 * multicast snooping switches
 					 */
 					ipv6_mc_up(idev);
+					change_info = ptr;
+					if (change_info->flags_changed & IFF_NOARP)
+						addrconf_dad_run(idev, true);
 					rt6_sync_up(dev, RTNH_F_LINKDOWN);
 					break;
 				}
@@ -3555,7 +3559,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
 
 		if (!IS_ERR_OR_NULL(idev)) {
 			if (run_pending)
-				addrconf_dad_run(idev);
+				addrconf_dad_run(idev, false);
 
 			/* Device has an address by now */
 			rt6_sync_up(dev, RTNH_F_DEAD);
@@ -4173,16 +4177,19 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp, bool bump_id,
 		addrconf_verify_rtnl();
 }
 
-static void addrconf_dad_run(struct inet6_dev *idev)
+static void addrconf_dad_run(struct inet6_dev *idev, bool restart)
 {
 	struct inet6_ifaddr *ifp;
 
 	read_lock_bh(&idev->lock);
 	list_for_each_entry(ifp, &idev->addr_list, if_list) {
 		spin_lock(&ifp->lock);
-		if (ifp->flags & IFA_F_TENTATIVE &&
-		    ifp->state == INET6_IFADDR_STATE_DAD)
+		if ((ifp->flags & IFA_F_TENTATIVE &&
+		     ifp->state == INET6_IFADDR_STATE_DAD) || restart) {
+			if (restart)
+				ifp->state = INET6_IFADDR_STATE_PREDAD;
 			addrconf_dad_kick(ifp);
+		}
 		spin_unlock(&ifp->lock);
 	}
 	read_unlock_bh(&idev->lock);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 3f4d61017a69..f0cd291034f0 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1001,6 +1001,9 @@ static int __init inet6_init(void)
 	err = ip6_flowlabel_init();
 	if (err)
 		goto ip6_flowlabel_fail;
+	err = ipv6_anycast_init();
+	if (err)
+		goto ipv6_anycast_fail;
 	err = addrconf_init();
 	if (err)
 		goto addrconf_fail;
@@ -1091,6 +1094,8 @@ ipv6_frag_fail:
 ipv6_exthdrs_fail:
 	addrconf_cleanup();
 addrconf_fail:
+	ipv6_anycast_cleanup();
+ipv6_anycast_fail:
 	ip6_flowlabel_cleanup();
 ip6_flowlabel_fail:
 	ndisc_late_cleanup();
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 4e0ff7031edd..94999058e110 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -44,8 +44,22 @@
 
 #include <net/checksum.h>
 
+#define IN6_ADDR_HSIZE_SHIFT	8
+#define IN6_ADDR_HSIZE		BIT(IN6_ADDR_HSIZE_SHIFT)
+/*	anycast address hash table
+ */
+static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE];
+static DEFINE_SPINLOCK(acaddr_hash_lock);
+
 static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr);
 
+static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr)
+{
+	u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net);
+
+	return hash_32(val, IN6_ADDR_HSIZE_SHIFT);
+}
+
 /*
  *	socket join an anycast group
  */
@@ -204,16 +218,39 @@ void ipv6_sock_ac_close(struct sock *sk)
 	rtnl_unlock();
 }
 
+static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca)
+{
+	unsigned int hash = inet6_acaddr_hash(net, &aca->aca_addr);
+
+	spin_lock(&acaddr_hash_lock);
+	hlist_add_head_rcu(&aca->aca_addr_lst, &inet6_acaddr_lst[hash]);
+	spin_unlock(&acaddr_hash_lock);
+}
+
+static void ipv6_del_acaddr_hash(struct ifacaddr6 *aca)
+{
+	spin_lock(&acaddr_hash_lock);
+	hlist_del_init_rcu(&aca->aca_addr_lst);
+	spin_unlock(&acaddr_hash_lock);
+}
+
 static void aca_get(struct ifacaddr6 *aca)
 {
 	refcount_inc(&aca->aca_refcnt);
 }
 
+static void aca_free_rcu(struct rcu_head *h)
+{
+	struct ifacaddr6 *aca = container_of(h, struct ifacaddr6, rcu);
+
+	fib6_info_release(aca->aca_rt);
+	kfree(aca);
+}
+
 static void aca_put(struct ifacaddr6 *ac)
 {
 	if (refcount_dec_and_test(&ac->aca_refcnt)) {
-		fib6_info_release(ac->aca_rt);
-		kfree(ac);
+		call_rcu(&ac->rcu, aca_free_rcu);
 	}
 }
 
@@ -229,6 +266,7 @@ static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i,
 	aca->aca_addr = *addr;
 	fib6_info_hold(f6i);
 	aca->aca_rt = f6i;
+	INIT_HLIST_NODE(&aca->aca_addr_lst);
 	aca->aca_users = 1;
 	/* aca_tstamp should be updated upon changes */
 	aca->aca_cstamp = aca->aca_tstamp = jiffies;
@@ -285,6 +323,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
 	aca_get(aca);
 	write_unlock_bh(&idev->lock);
 
+	ipv6_add_acaddr_hash(net, aca);
+
 	ip6_ins_rt(net, f6i);
 
 	addrconf_join_solict(idev->dev, &aca->aca_addr);
@@ -325,6 +365,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
 	else
 		idev->ac_list = aca->aca_next;
 	write_unlock_bh(&idev->lock);
+	ipv6_del_acaddr_hash(aca);
 	addrconf_leave_solict(idev, &aca->aca_addr);
 
 	ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
@@ -352,6 +393,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev)
 		idev->ac_list = aca->aca_next;
 		write_unlock_bh(&idev->lock);
 
+		ipv6_del_acaddr_hash(aca);
+
 		addrconf_leave_solict(idev, &aca->aca_addr);
 
 		ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
@@ -390,17 +433,25 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad
 bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev,
 			 const struct in6_addr *addr)
 {
+	unsigned int hash = inet6_acaddr_hash(net, addr);
+	struct net_device *nh_dev;
+	struct ifacaddr6 *aca;
 	bool found = false;
 
 	rcu_read_lock();
 	if (dev)
 		found = ipv6_chk_acast_dev(dev, addr);
 	else
-		for_each_netdev_rcu(net, dev)
-			if (ipv6_chk_acast_dev(dev, addr)) {
+		hlist_for_each_entry_rcu(aca, &inet6_acaddr_lst[hash],
+					 aca_addr_lst) {
+			nh_dev = fib6_info_nh_dev(aca->aca_rt);
+			if (!nh_dev || !net_eq(dev_net(nh_dev), net))
+				continue;
+			if (ipv6_addr_equal(&aca->aca_addr, addr)) {
 				found = true;
 				break;
 			}
+		}
 	rcu_read_unlock();
 	return found;
 }
@@ -540,3 +591,24 @@ void ac6_proc_exit(struct net *net)
 	remove_proc_entry("anycast6", net->proc_net);
 }
 #endif
+
+/*	Init / cleanup code
+ */
+int __init ipv6_anycast_init(void)
+{
+	int i;
+
+	for (i = 0; i < IN6_ADDR_HSIZE; i++)
+		INIT_HLIST_HEAD(&inet6_acaddr_lst[i]);
+	return 0;
+}
+
+void ipv6_anycast_cleanup(void)
+{
+	int i;
+
+	spin_lock(&acaddr_hash_lock);
+	for (i = 0; i < IN6_ADDR_HSIZE; i++)
+		WARN_ON(!hlist_empty(&inet6_acaddr_lst[i]));
+	spin_unlock(&acaddr_hash_lock);
+}
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 1b8bc008b53b..ae3786132c23 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -591,7 +591,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 
 	/* fib entries are never clones */
 	if (arg.filter.flags & RTM_F_CLONED)
-		return skb->len;
+		goto out;
 
 	w = (void *)cb->args[2];
 	if (!w) {
@@ -621,7 +621,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 		tb = fib6_get_table(net, arg.filter.table_id);
 		if (!tb) {
 			if (arg.filter.dump_all_families)
-				return skb->len;
+				goto out;
 
 			NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist");
 			return -ENOENT;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 89e0d5118afe..827a3f5ff3bb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1354,7 +1354,7 @@ emsgsize:
 			unsigned int fraglen;
 			unsigned int fraggap;
 			unsigned int alloclen;
-			unsigned int pagedlen = 0;
+			unsigned int pagedlen;
 alloc_new_skb:
 			/* There's no room in the current skb */
 			if (skb)
@@ -1378,6 +1378,7 @@ alloc_new_skb:
 			if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen)
 				datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len;
 			fraglen = datalen + fragheaderlen;
+			pagedlen = 0;
 
 			if ((flags & MSG_MORE) &&
 			    !(rt->dst.dev->features&NETIF_F_SG))
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 5ae8e1c51079..8b075f0bc351 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -24,7 +24,8 @@ int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
 	unsigned int hh_len;
 	struct dst_entry *dst;
 	struct flowi6 fl6 = {
-		.flowi6_oif = sk ? sk->sk_bound_dev_if : 0,
+		.flowi6_oif = sk && sk->sk_bound_dev_if ? sk->sk_bound_dev_if :
+			rt6_need_strict(&iph->daddr) ? skb_dst(skb)->dev->ifindex : 0,
 		.flowi6_mark = skb->mark,
 		.flowi6_uid = sock_net_uid(net, sk),
 		.daddr = iph->daddr,
diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c
index 491f808e356a..29c7f1915a96 100644
--- a/net/ipv6/netfilter/ip6t_MASQUERADE.c
+++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c
@@ -58,8 +58,12 @@ static int __init masquerade_tg6_init(void)
 	int err;
 
 	err = xt_register_target(&masquerade_tg6_reg);
-	if (err == 0)
-		nf_nat_masquerade_ipv6_register_notifier();
+	if (err)
+		return err;
+
+	err = nf_nat_masquerade_ipv6_register_notifier();
+	if (err)
+		xt_unregister_target(&masquerade_tg6_reg);
 
 	return err;
 }
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index b8ac369f98ad..d219979c3e52 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -587,11 +587,16 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	 */
 	ret = -EINPROGRESS;
 	if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
-	    fq->q.meat == fq->q.len &&
-	    nf_ct_frag6_reasm(fq, skb, dev))
-		ret = 0;
-	else
+	    fq->q.meat == fq->q.len) {
+		unsigned long orefdst = skb->_skb_refdst;
+
+		skb->_skb_refdst = 0UL;
+		if (nf_ct_frag6_reasm(fq, skb, dev))
+			ret = 0;
+		skb->_skb_refdst = orefdst;
+	} else {
 		skb_dst_drop(skb);
+	}
 
 out_unlock:
 	spin_unlock_bh(&fq->q.lock);
diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
index 3e4bf2286abe..0ad0da5a2600 100644
--- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
+++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c
@@ -132,8 +132,8 @@ static void iterate_cleanup_work(struct work_struct *work)
  * of ipv6 addresses being deleted), we also need to add an upper
  * limit to the number of queued work items.
  */
-static int masq_inet_event(struct notifier_block *this,
-			   unsigned long event, void *ptr)
+static int masq_inet6_event(struct notifier_block *this,
+			    unsigned long event, void *ptr)
 {
 	struct inet6_ifaddr *ifa = ptr;
 	const struct net_device *dev;
@@ -171,30 +171,53 @@ static int masq_inet_event(struct notifier_block *this,
 	return NOTIFY_DONE;
 }
 
-static struct notifier_block masq_inet_notifier = {
-	.notifier_call	= masq_inet_event,
+static struct notifier_block masq_inet6_notifier = {
+	.notifier_call	= masq_inet6_event,
 };
 
-static atomic_t masquerade_notifier_refcount = ATOMIC_INIT(0);
+static int masq_refcnt;
+static DEFINE_MUTEX(masq_mutex);
 
-void nf_nat_masquerade_ipv6_register_notifier(void)
+int nf_nat_masquerade_ipv6_register_notifier(void)
 {
+	int ret = 0;
+
+	mutex_lock(&masq_mutex);
 	/* check if the notifier is already set */
-	if (atomic_inc_return(&masquerade_notifier_refcount) > 1)
-		return;
+	if (++masq_refcnt > 1)
+		goto out_unlock;
+
+	ret = register_netdevice_notifier(&masq_dev_notifier);
+	if (ret)
+		goto err_dec;
+
+	ret = register_inet6addr_notifier(&masq_inet6_notifier);
+	if (ret)
+		goto err_unregister;
 
-	register_netdevice_notifier(&masq_dev_notifier);
-	register_inet6addr_notifier(&masq_inet_notifier);
+	mutex_unlock(&masq_mutex);
+	return ret;
+
+err_unregister:
+	unregister_netdevice_notifier(&masq_dev_notifier);
+err_dec:
+	masq_refcnt--;
+out_unlock:
+	mutex_unlock(&masq_mutex);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_register_notifier);
 
 void nf_nat_masquerade_ipv6_unregister_notifier(void)
 {
+	mutex_lock(&masq_mutex);
 	/* check if the notifier still has clients */
-	if (atomic_dec_return(&masquerade_notifier_refcount) > 0)
-		return;
+	if (--masq_refcnt > 0)
+		goto out_unlock;
 
-	unregister_inet6addr_notifier(&masq_inet_notifier);
+	unregister_inet6addr_notifier(&masq_inet6_notifier);
 	unregister_netdevice_notifier(&masq_dev_notifier);
+out_unlock:
+	mutex_unlock(&masq_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_nat_masquerade_ipv6_unregister_notifier);
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
index dd0122f3cffe..e06c82e9dfcd 100644
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ b/net/ipv6/netfilter/nft_masq_ipv6.c
@@ -70,7 +70,9 @@ static int __init nft_masq_ipv6_module_init(void)
 	if (ret < 0)
 		return ret;
 
-	nf_nat_masquerade_ipv6_register_notifier();
+	ret = nf_nat_masquerade_ipv6_register_notifier();
+	if (ret)
+		nft_unregister_expr(&nft_masq_ipv6_type);
 
 	return ret;
 }
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 2a7423c39456..059f0531f7c1 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2232,8 +2232,7 @@ static void ip6_link_failure(struct sk_buff *skb)
 	if (rt) {
 		rcu_read_lock();
 		if (rt->rt6i_flags & RTF_CACHE) {
-			if (dst_hold_safe(&rt->dst))
-				rt6_remove_exception_rt(rt);
+			rt6_remove_exception_rt(rt);
 		} else {
 			struct fib6_info *from;
 			struct fib6_node *fn;
@@ -2360,10 +2359,13 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
 
 void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
 {
+	int oif = sk->sk_bound_dev_if;
 	struct dst_entry *dst;
 
-	ip6_update_pmtu(skb, sock_net(sk), mtu,
-			sk->sk_bound_dev_if, sk->sk_mark, sk->sk_uid);
+	if (!oif && skb->dev)
+		oif = l3mdev_master_ifindex(skb->dev);
+
+	ip6_update_pmtu(skb, sock_net(sk), mtu, oif, sk->sk_mark, sk->sk_uid);
 
 	dst = __sk_dst_get(sk);
 	if (!dst || !dst->obsolete ||
@@ -3214,8 +3216,8 @@ static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
 	if (cfg->fc_flags & RTF_GATEWAY &&
 	    !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
 		goto out;
-	if (dst_hold_safe(&rt->dst))
-		rc = rt6_remove_exception_rt(rt);
+
+	rc = rt6_remove_exception_rt(rt);
 out:
 	return rc;
 }
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 82cdf9020b53..26f1d435696a 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1490,12 +1490,7 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 			goto err_sock;
 	}
 
-	sk = sock->sk;
-
-	sock_hold(sk);
-	tunnel->sock = sk;
 	tunnel->l2tp_net = net;
-
 	pn = l2tp_pernet(net);
 
 	spin_lock_bh(&pn->l2tp_tunnel_list_lock);
@@ -1510,6 +1505,10 @@ int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 	list_add_rcu(&tunnel->list, &pn->l2tp_tunnel_list);
 	spin_unlock_bh(&pn->l2tp_tunnel_list_lock);
 
+	sk = sock->sk;
+	sock_hold(sk);
+	tunnel->sock = sk;
+
 	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
 		struct udp_tunnel_sock_cfg udp_cfg = {
 			.sk_user_data = tunnel,
diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index bc4bd247bb7d..1577f2f76060 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -55,11 +55,15 @@ MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>");
 MODULE_DESCRIPTION("core IP set support");
 MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
 
-/* When the nfnl mutex is held: */
+/* When the nfnl mutex or ip_set_ref_lock is held: */
 #define ip_set_dereference(p)		\
-	rcu_dereference_protected(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
+	rcu_dereference_protected(p,	\
+		lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \
+		lockdep_is_held(&ip_set_ref_lock))
 #define ip_set(inst, id)		\
 	ip_set_dereference((inst)->ip_set_list)[id]
+#define ip_set_ref_netlink(inst,id)	\
+	rcu_dereference_raw((inst)->ip_set_list)[id]
 
 /* The set types are implemented in modules and registered set types
  * can be found in ip_set_type_list. Adding/deleting types is
@@ -693,21 +697,20 @@ ip_set_put_byindex(struct net *net, ip_set_id_t index)
 EXPORT_SYMBOL_GPL(ip_set_put_byindex);
 
 /* Get the name of a set behind a set index.
- * We assume the set is referenced, so it does exist and
- * can't be destroyed. The set cannot be renamed due to
- * the referencing either.
- *
+ * Set itself is protected by RCU, but its name isn't: to protect against
+ * renaming, grab ip_set_ref_lock as reader (see ip_set_rename()) and copy the
+ * name.
  */
-const char *
-ip_set_name_byindex(struct net *net, ip_set_id_t index)
+void
+ip_set_name_byindex(struct net *net, ip_set_id_t index, char *name)
 {
-	const struct ip_set *set = ip_set_rcu_get(net, index);
+	struct ip_set *set = ip_set_rcu_get(net, index);
 
 	BUG_ON(!set);
-	BUG_ON(set->ref == 0);
 
-	/* Referenced, so it's safe */
-	return set->name;
+	read_lock_bh(&ip_set_ref_lock);
+	strncpy(name, set->name, IPSET_MAXNAMELEN);
+	read_unlock_bh(&ip_set_ref_lock);
 }
 EXPORT_SYMBOL_GPL(ip_set_name_byindex);
 
@@ -961,7 +964,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
 			/* Wraparound */
 			goto cleanup;
 
-		list = kcalloc(i, sizeof(struct ip_set *), GFP_KERNEL);
+		list = kvcalloc(i, sizeof(struct ip_set *), GFP_KERNEL);
 		if (!list)
 			goto cleanup;
 		/* nfnl mutex is held, both lists are valid */
@@ -973,7 +976,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
 		/* Use new list */
 		index = inst->ip_set_max;
 		inst->ip_set_max = i;
-		kfree(tmp);
+		kvfree(tmp);
 		ret = 0;
 	} else if (ret) {
 		goto cleanup;
@@ -1153,7 +1156,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl,
 	if (!set)
 		return -ENOENT;
 
-	read_lock_bh(&ip_set_ref_lock);
+	write_lock_bh(&ip_set_ref_lock);
 	if (set->ref != 0) {
 		ret = -IPSET_ERR_REFERENCED;
 		goto out;
@@ -1170,7 +1173,7 @@ static int ip_set_rename(struct net *net, struct sock *ctnl,
 	strncpy(set->name, name2, IPSET_MAXNAMELEN);
 
 out:
-	read_unlock_bh(&ip_set_ref_lock);
+	write_unlock_bh(&ip_set_ref_lock);
 	return ret;
 }
 
@@ -1252,7 +1255,7 @@ ip_set_dump_done(struct netlink_callback *cb)
 		struct ip_set_net *inst =
 			(struct ip_set_net *)cb->args[IPSET_CB_NET];
 		ip_set_id_t index = (ip_set_id_t)cb->args[IPSET_CB_INDEX];
-		struct ip_set *set = ip_set(inst, index);
+		struct ip_set *set = ip_set_ref_netlink(inst, index);
 
 		if (set->variant->uref)
 			set->variant->uref(set, cb, false);
@@ -1441,7 +1444,7 @@ next_set:
 release_refcount:
 	/* If there was an error or set is done, release set */
 	if (ret || !cb->args[IPSET_CB_ARG0]) {
-		set = ip_set(inst, index);
+		set = ip_set_ref_netlink(inst, index);
 		if (set->variant->uref)
 			set->variant->uref(set, cb, false);
 		pr_debug("release set %s\n", set->name);
@@ -2059,7 +2062,7 @@ ip_set_net_init(struct net *net)
 	if (inst->ip_set_max >= IPSET_INVALID_ID)
 		inst->ip_set_max = IPSET_INVALID_ID - 1;
 
-	list = kcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL);
+	list = kvcalloc(inst->ip_set_max, sizeof(struct ip_set *), GFP_KERNEL);
 	if (!list)
 		return -ENOMEM;
 	inst->is_deleted = false;
@@ -2087,7 +2090,7 @@ ip_set_net_exit(struct net *net)
 		}
 	}
 	nfnl_unlock(NFNL_SUBSYS_IPSET);
-	kfree(rcu_dereference_protected(inst->ip_set_list, 1));
+	kvfree(rcu_dereference_protected(inst->ip_set_list, 1));
 }
 
 static struct pernet_operations ip_set_net_ops = {
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index d391485a6acd..613e18e720a4 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -213,13 +213,13 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_CIDR]) {
 		e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]);
-		if (!e.cidr[0] || e.cidr[0] > HOST_MASK)
+		if (e.cidr[0] > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
 
 	if (tb[IPSET_ATTR_CIDR2]) {
 		e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
-		if (!e.cidr[1] || e.cidr[1] > HOST_MASK)
+		if (e.cidr[1] > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
 
@@ -493,13 +493,13 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 
 	if (tb[IPSET_ATTR_CIDR]) {
 		e.cidr[0] = nla_get_u8(tb[IPSET_ATTR_CIDR]);
-		if (!e.cidr[0] || e.cidr[0] > HOST_MASK)
+		if (e.cidr[0] > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
 
 	if (tb[IPSET_ATTR_CIDR2]) {
 		e.cidr[1] = nla_get_u8(tb[IPSET_ATTR_CIDR2]);
-		if (!e.cidr[1] || e.cidr[1] > HOST_MASK)
+		if (e.cidr[1] > HOST_MASK)
 			return -IPSET_ERR_INVALID_CIDR;
 	}
 
diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c
index 072a658fde04..4eef55da0878 100644
--- a/net/netfilter/ipset/ip_set_list_set.c
+++ b/net/netfilter/ipset/ip_set_list_set.c
@@ -148,9 +148,7 @@ __list_set_del_rcu(struct rcu_head * rcu)
 {
 	struct set_elem *e = container_of(rcu, struct set_elem, rcu);
 	struct ip_set *set = e->set;
-	struct list_set *map = set->data;
 
-	ip_set_put_byindex(map->net, e->id);
 	ip_set_ext_destroy(set, e);
 	kfree(e);
 }
@@ -158,15 +156,21 @@ __list_set_del_rcu(struct rcu_head * rcu)
 static inline void
 list_set_del(struct ip_set *set, struct set_elem *e)
 {
+	struct list_set *map = set->data;
+
 	set->elements--;
 	list_del_rcu(&e->list);
+	ip_set_put_byindex(map->net, e->id);
 	call_rcu(&e->rcu, __list_set_del_rcu);
 }
 
 static inline void
-list_set_replace(struct set_elem *e, struct set_elem *old)
+list_set_replace(struct ip_set *set, struct set_elem *e, struct set_elem *old)
 {
+	struct list_set *map = set->data;
+
 	list_replace_rcu(&old->list, &e->list);
+	ip_set_put_byindex(map->net, old->id);
 	call_rcu(&old->rcu, __list_set_del_rcu);
 }
 
@@ -298,7 +302,7 @@ list_set_uadd(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	INIT_LIST_HEAD(&e->list);
 	list_set_init_extensions(set, ext, e);
 	if (n)
-		list_set_replace(e, n);
+		list_set_replace(set, e, n);
 	else if (next)
 		list_add_tail_rcu(&e->list, &next->list);
 	else if (prev)
@@ -486,6 +490,7 @@ list_set_list(const struct ip_set *set,
 	const struct list_set *map = set->data;
 	struct nlattr *atd, *nested;
 	u32 i = 0, first = cb->args[IPSET_CB_ARG0];
+	char name[IPSET_MAXNAMELEN];
 	struct set_elem *e;
 	int ret = 0;
 
@@ -504,8 +509,8 @@ list_set_list(const struct ip_set *set,
 		nested = ipset_nest_start(skb, IPSET_ATTR_DATA);
 		if (!nested)
 			goto nla_put_failure;
-		if (nla_put_string(skb, IPSET_ATTR_NAME,
-				   ip_set_name_byindex(map->net, e->id)))
+		ip_set_name_byindex(map->net, e->id, name);
+		if (nla_put_string(skb, IPSET_ATTR_NAME, name))
 			goto nla_put_failure;
 		if (ip_set_put_extensions(skb, set, e, true))
 			goto nla_put_failure;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 83395bf6dc35..432141f04af3 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3980,6 +3980,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct netns_ipvs *ipvs)
 
 static struct notifier_block ip_vs_dst_notifier = {
 	.notifier_call = ip_vs_dst_event,
+#ifdef CONFIG_IP_VS_IPV6
+	.priority = ADDRCONF_NOTIFY_PRIORITY + 5,
+#endif
 };
 
 int __net_init ip_vs_control_net_init(struct netns_ipvs *ipvs)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index d4020c5e831d..2526be6b3d90 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1616,7 +1616,7 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen)
 	EnterFunction(7);
 
 	/* Receive a packet */
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, buflen);
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, buflen);
 	len = sock_recvmsg(sock, &msg, MSG_DONTWAIT);
 	if (len < 0)
 		return len;
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 02ca7df793f5..b6d0f6deea86 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -49,6 +49,7 @@ struct nf_conncount_tuple {
 	struct nf_conntrack_zone	zone;
 	int				cpu;
 	u32				jiffies32;
+	bool				dead;
 	struct rcu_head			rcu_head;
 };
 
@@ -106,15 +107,16 @@ nf_conncount_add(struct nf_conncount_list *list,
 	conn->zone = *zone;
 	conn->cpu = raw_smp_processor_id();
 	conn->jiffies32 = (u32)jiffies;
-	spin_lock(&list->list_lock);
+	conn->dead = false;
+	spin_lock_bh(&list->list_lock);
 	if (list->dead == true) {
 		kmem_cache_free(conncount_conn_cachep, conn);
-		spin_unlock(&list->list_lock);
+		spin_unlock_bh(&list->list_lock);
 		return NF_CONNCOUNT_SKIP;
 	}
 	list_add_tail(&conn->node, &list->head);
 	list->count++;
-	spin_unlock(&list->list_lock);
+	spin_unlock_bh(&list->list_lock);
 	return NF_CONNCOUNT_ADDED;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_add);
@@ -132,19 +134,22 @@ static bool conn_free(struct nf_conncount_list *list,
 {
 	bool free_entry = false;
 
-	spin_lock(&list->list_lock);
+	spin_lock_bh(&list->list_lock);
 
-	if (list->count == 0) {
-		spin_unlock(&list->list_lock);
-                return free_entry;
+	if (conn->dead) {
+		spin_unlock_bh(&list->list_lock);
+		return free_entry;
 	}
 
 	list->count--;
+	conn->dead = true;
 	list_del_rcu(&conn->node);
-	if (list->count == 0)
+	if (list->count == 0) {
+		list->dead = true;
 		free_entry = true;
+	}
 
-	spin_unlock(&list->list_lock);
+	spin_unlock_bh(&list->list_lock);
 	call_rcu(&conn->rcu_head, __conn_free);
 	return free_entry;
 }
@@ -245,7 +250,7 @@ void nf_conncount_list_init(struct nf_conncount_list *list)
 {
 	spin_lock_init(&list->list_lock);
 	INIT_LIST_HEAD(&list->head);
-	list->count = 1;
+	list->count = 0;
 	list->dead = false;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_list_init);
@@ -259,6 +264,7 @@ bool nf_conncount_gc_list(struct net *net,
 	struct nf_conn *found_ct;
 	unsigned int collected = 0;
 	bool free_entry = false;
+	bool ret = false;
 
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
 		found = find_or_evict(net, list, conn, &free_entry);
@@ -288,7 +294,15 @@ bool nf_conncount_gc_list(struct net *net,
 		if (collected > CONNCOUNT_GC_MAX_NODES)
 			return false;
 	}
-	return false;
+
+	spin_lock_bh(&list->list_lock);
+	if (!list->count) {
+		list->dead = true;
+		ret = true;
+	}
+	spin_unlock_bh(&list->list_lock);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_gc_list);
 
@@ -309,11 +323,8 @@ static void tree_nodes_free(struct rb_root *root,
 	while (gc_count) {
 		rbconn = gc_nodes[--gc_count];
 		spin_lock(&rbconn->list.list_lock);
-		if (rbconn->list.count == 0 && rbconn->list.dead == false) {
-			rbconn->list.dead = true;
-			rb_erase(&rbconn->node, root);
-			call_rcu(&rbconn->rcu_head, __tree_nodes_free);
-		}
+		rb_erase(&rbconn->node, root);
+		call_rcu(&rbconn->rcu_head, __tree_nodes_free);
 		spin_unlock(&rbconn->list.list_lock);
 	}
 }
@@ -414,6 +425,7 @@ insert_tree(struct net *net,
 	nf_conncount_list_init(&rbconn->list);
 	list_add(&conn->node, &rbconn->list.head);
 	count = 1;
+	rbconn->list.count = count;
 
 	rb_link_node(&rbconn->node, parent, rbnode);
 	rb_insert_color(&rbconn->node, root);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index ca1168d67fac..e92e749aff53 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1073,19 +1073,22 @@ static unsigned int early_drop_list(struct net *net,
 	return drops;
 }
 
-static noinline int early_drop(struct net *net, unsigned int _hash)
+static noinline int early_drop(struct net *net, unsigned int hash)
 {
-	unsigned int i;
+	unsigned int i, bucket;
 
 	for (i = 0; i < NF_CT_EVICTION_RANGE; i++) {
 		struct hlist_nulls_head *ct_hash;
-		unsigned int hash, hsize, drops;
+		unsigned int hsize, drops;
 
 		rcu_read_lock();
 		nf_conntrack_get_ht(&ct_hash, &hsize);
-		hash = reciprocal_scale(_hash++, hsize);
+		if (!i)
+			bucket = reciprocal_scale(hash, hsize);
+		else
+			bucket = (bucket + 1) % hsize;
 
-		drops = early_drop_list(net, &ct_hash[hash]);
+		drops = early_drop_list(net, &ct_hash[bucket]);
 		rcu_read_unlock();
 
 		if (drops) {
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 171e9e122e5f..023c1445bc39 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -384,11 +384,6 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
 	},
 };
 
-static inline struct nf_dccp_net *dccp_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.dccp;
-}
-
 static noinline bool
 dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	 const struct dccp_hdr *dh)
@@ -401,7 +396,7 @@ dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE];
 	switch (state) {
 	default:
-		dn = dccp_pernet(net);
+		dn = nf_dccp_pernet(net);
 		if (dn->dccp_loose == 0) {
 			msg = "not picking up existing connection ";
 			goto out_invalid;
@@ -568,7 +563,7 @@ static int dccp_packet(struct nf_conn *ct, struct sk_buff *skb,
 
 	timeouts = nf_ct_timeout_lookup(ct);
 	if (!timeouts)
-		timeouts = dccp_pernet(nf_ct_net(ct))->dccp_timeout;
+		timeouts = nf_dccp_pernet(nf_ct_net(ct))->dccp_timeout;
 	nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
 
 	return NF_ACCEPT;
@@ -681,7 +676,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
 static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[],
 				      struct net *net, void *data)
 {
-	struct nf_dccp_net *dn = dccp_pernet(net);
+	struct nf_dccp_net *dn = nf_dccp_pernet(net);
 	unsigned int *timeouts = data;
 	int i;
 
@@ -814,7 +809,7 @@ static int dccp_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *pn,
 
 static int dccp_init_net(struct net *net)
 {
-	struct nf_dccp_net *dn = dccp_pernet(net);
+	struct nf_dccp_net *dn = nf_dccp_pernet(net);
 	struct nf_proto_net *pn = &dn->pn;
 
 	if (!pn->users) {
diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c
index e10e867e0b55..5da19d5fbc76 100644
--- a/net/netfilter/nf_conntrack_proto_generic.c
+++ b/net/netfilter/nf_conntrack_proto_generic.c
@@ -27,11 +27,6 @@ static bool nf_generic_should_process(u8 proto)
 	}
 }
 
-static inline struct nf_generic_net *generic_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.generic;
-}
-
 static bool generic_pkt_to_tuple(const struct sk_buff *skb,
 				 unsigned int dataoff,
 				 struct net *net, struct nf_conntrack_tuple *tuple)
@@ -58,7 +53,7 @@ static int generic_packet(struct nf_conn *ct,
 	}
 
 	if (!timeout)
-		timeout = &generic_pernet(nf_ct_net(ct))->timeout;
+		timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout;
 
 	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
 	return NF_ACCEPT;
@@ -72,7 +67,7 @@ static int generic_packet(struct nf_conn *ct,
 static int generic_timeout_nlattr_to_obj(struct nlattr *tb[],
 					 struct net *net, void *data)
 {
-	struct nf_generic_net *gn = generic_pernet(net);
+	struct nf_generic_net *gn = nf_generic_pernet(net);
 	unsigned int *timeout = data;
 
 	if (!timeout)
@@ -138,7 +133,7 @@ static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn,
 
 static int generic_init_net(struct net *net)
 {
-	struct nf_generic_net *gn = generic_pernet(net);
+	struct nf_generic_net *gn = nf_generic_pernet(net);
 	struct nf_proto_net *pn = &gn->pn;
 
 	gn->timeout = nf_ct_generic_timeout;
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 9b48dc8b4b88..2a5e56c6d8d9 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -43,24 +43,12 @@
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
 #include <linux/netfilter/nf_conntrack_pptp.h>
 
-enum grep_conntrack {
-	GRE_CT_UNREPLIED,
-	GRE_CT_REPLIED,
-	GRE_CT_MAX
-};
-
 static const unsigned int gre_timeouts[GRE_CT_MAX] = {
 	[GRE_CT_UNREPLIED]	= 30*HZ,
 	[GRE_CT_REPLIED]	= 180*HZ,
 };
 
 static unsigned int proto_gre_net_id __read_mostly;
-struct netns_proto_gre {
-	struct nf_proto_net	nf;
-	rwlock_t		keymap_lock;
-	struct list_head	keymap_list;
-	unsigned int		gre_timeouts[GRE_CT_MAX];
-};
 
 static inline struct netns_proto_gre *gre_pernet(struct net *net)
 {
@@ -402,6 +390,8 @@ static int __init nf_ct_proto_gre_init(void)
 {
 	int ret;
 
+	BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0);
+
 	ret = register_pernet_subsys(&proto_gre_net_ops);
 	if (ret < 0)
 		goto out_pernet;
diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c
index 3598520bd19b..de64d8a5fdfd 100644
--- a/net/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/netfilter/nf_conntrack_proto_icmp.c
@@ -25,11 +25,6 @@
 
 static const unsigned int nf_ct_icmp_timeout = 30*HZ;
 
-static inline struct nf_icmp_net *icmp_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.icmp;
-}
-
 static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 			      struct net *net, struct nf_conntrack_tuple *tuple)
 {
@@ -103,7 +98,7 @@ static int icmp_packet(struct nf_conn *ct,
 	}
 
 	if (!timeout)
-		timeout = &icmp_pernet(nf_ct_net(ct))->timeout;
+		timeout = &nf_icmp_pernet(nf_ct_net(ct))->timeout;
 
 	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
 	return NF_ACCEPT;
@@ -275,7 +270,7 @@ static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[],
 				      struct net *net, void *data)
 {
 	unsigned int *timeout = data;
-	struct nf_icmp_net *in = icmp_pernet(net);
+	struct nf_icmp_net *in = nf_icmp_pernet(net);
 
 	if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) {
 		if (!timeout)
@@ -337,7 +332,7 @@ static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn,
 
 static int icmp_init_net(struct net *net)
 {
-	struct nf_icmp_net *in = icmp_pernet(net);
+	struct nf_icmp_net *in = nf_icmp_pernet(net);
 	struct nf_proto_net *pn = &in->pn;
 
 	in->timeout = nf_ct_icmp_timeout;
diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c
index 378618feed5d..a15eefb8e317 100644
--- a/net/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/netfilter/nf_conntrack_proto_icmpv6.c
@@ -30,11 +30,6 @@
 
 static const unsigned int nf_ct_icmpv6_timeout = 30*HZ;
 
-static inline struct nf_icmp_net *icmpv6_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.icmpv6;
-}
-
 static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb,
 				unsigned int dataoff,
 				struct net *net,
@@ -87,7 +82,7 @@ static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple,
 
 static unsigned int *icmpv6_get_timeouts(struct net *net)
 {
-	return &icmpv6_pernet(net)->timeout;
+	return &nf_icmpv6_pernet(net)->timeout;
 }
 
 /* Returns verdict for packet, or -1 for invalid. */
@@ -286,7 +281,7 @@ static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[],
 					struct net *net, void *data)
 {
 	unsigned int *timeout = data;
-	struct nf_icmp_net *in = icmpv6_pernet(net);
+	struct nf_icmp_net *in = nf_icmpv6_pernet(net);
 
 	if (!timeout)
 		timeout = icmpv6_get_timeouts(net);
@@ -348,7 +343,7 @@ static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn,
 
 static int icmpv6_init_net(struct net *net)
 {
-	struct nf_icmp_net *in = icmpv6_pernet(net);
+	struct nf_icmp_net *in = nf_icmpv6_pernet(net);
 	struct nf_proto_net *pn = &in->pn;
 
 	in->timeout = nf_ct_icmpv6_timeout;
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 3d719d3eb9a3..d53e3e78f605 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -146,11 +146,6 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = {
 	}
 };
 
-static inline struct nf_sctp_net *sctp_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.sctp;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
@@ -480,7 +475,7 @@ static int sctp_packet(struct nf_conn *ct,
 
 	timeouts = nf_ct_timeout_lookup(ct);
 	if (!timeouts)
-		timeouts = sctp_pernet(nf_ct_net(ct))->timeouts;
+		timeouts = nf_sctp_pernet(nf_ct_net(ct))->timeouts;
 
 	nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
 
@@ -599,7 +594,7 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[],
 				      struct net *net, void *data)
 {
 	unsigned int *timeouts = data;
-	struct nf_sctp_net *sn = sctp_pernet(net);
+	struct nf_sctp_net *sn = nf_sctp_pernet(net);
 	int i;
 
 	/* set default SCTP timeouts. */
@@ -736,7 +731,7 @@ static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn,
 
 static int sctp_init_net(struct net *net)
 {
-	struct nf_sctp_net *sn = sctp_pernet(net);
+	struct nf_sctp_net *sn = nf_sctp_pernet(net);
 	struct nf_proto_net *pn = &sn->pn;
 
 	if (!pn->users) {
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 1bcf9984d45e..4dcbd51a8e97 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -272,11 +272,6 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
 	}
 };
 
-static inline struct nf_tcp_net *tcp_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.tcp;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
@@ -475,7 +470,7 @@ static bool tcp_in_window(const struct nf_conn *ct,
 			  const struct tcphdr *tcph)
 {
 	struct net *net = nf_ct_net(ct);
-	struct nf_tcp_net *tn = tcp_pernet(net);
+	struct nf_tcp_net *tn = nf_tcp_pernet(net);
 	struct ip_ct_tcp_state *sender = &state->seen[dir];
 	struct ip_ct_tcp_state *receiver = &state->seen[!dir];
 	const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
@@ -767,7 +762,7 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 {
 	enum tcp_conntrack new_state;
 	struct net *net = nf_ct_net(ct);
-	const struct nf_tcp_net *tn = tcp_pernet(net);
+	const struct nf_tcp_net *tn = nf_tcp_pernet(net);
 	const struct ip_ct_tcp_state *sender = &ct->proto.tcp.seen[0];
 	const struct ip_ct_tcp_state *receiver = &ct->proto.tcp.seen[1];
 
@@ -841,7 +836,7 @@ static int tcp_packet(struct nf_conn *ct,
 		      const struct nf_hook_state *state)
 {
 	struct net *net = nf_ct_net(ct);
-	struct nf_tcp_net *tn = tcp_pernet(net);
+	struct nf_tcp_net *tn = nf_tcp_pernet(net);
 	struct nf_conntrack_tuple *tuple;
 	enum tcp_conntrack new_state, old_state;
 	unsigned int index, *timeouts;
@@ -1283,7 +1278,7 @@ static unsigned int tcp_nlattr_tuple_size(void)
 static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[],
 				     struct net *net, void *data)
 {
-	struct nf_tcp_net *tn = tcp_pernet(net);
+	struct nf_tcp_net *tn = nf_tcp_pernet(net);
 	unsigned int *timeouts = data;
 	int i;
 
@@ -1508,7 +1503,7 @@ static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn,
 
 static int tcp_init_net(struct net *net)
 {
-	struct nf_tcp_net *tn = tcp_pernet(net);
+	struct nf_tcp_net *tn = nf_tcp_pernet(net);
 	struct nf_proto_net *pn = &tn->pn;
 
 	if (!pn->users) {
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index a7aa70370913..c879d8d78cfd 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -32,14 +32,9 @@ static const unsigned int udp_timeouts[UDP_CT_MAX] = {
 	[UDP_CT_REPLIED]	= 180*HZ,
 };
 
-static inline struct nf_udp_net *udp_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.udp;
-}
-
 static unsigned int *udp_get_timeouts(struct net *net)
 {
-	return udp_pernet(net)->timeouts;
+	return nf_udp_pernet(net)->timeouts;
 }
 
 static void udp_error_log(const struct sk_buff *skb,
@@ -212,7 +207,7 @@ static int udp_timeout_nlattr_to_obj(struct nlattr *tb[],
 				     struct net *net, void *data)
 {
 	unsigned int *timeouts = data;
-	struct nf_udp_net *un = udp_pernet(net);
+	struct nf_udp_net *un = nf_udp_pernet(net);
 
 	if (!timeouts)
 		timeouts = un->timeouts;
@@ -292,7 +287,7 @@ static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn,
 
 static int udp_init_net(struct net *net)
 {
-	struct nf_udp_net *un = udp_pernet(net);
+	struct nf_udp_net *un = nf_udp_pernet(net);
 	struct nf_proto_net *pn = &un->pn;
 
 	if (!pn->users) {
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 42487d01a3ed..2e61aab6ed73 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2457,7 +2457,7 @@ err:
 static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 				   struct nft_rule *rule)
 {
-	struct nft_expr *expr;
+	struct nft_expr *expr, *next;
 
 	/*
 	 * Careful: some expressions might not be initialized in case this
@@ -2465,8 +2465,9 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 	 */
 	expr = nft_expr_first(rule);
 	while (expr != nft_expr_last(rule) && expr->ops) {
+		next = nft_expr_next(expr);
 		nf_tables_expr_destroy(ctx, expr);
-		expr = nft_expr_next(expr);
+		expr = next;
 	}
 	kfree(rule);
 }
@@ -2589,17 +2590,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 
 		if (chain->use == UINT_MAX)
 			return -EOVERFLOW;
-	}
-
-	if (nla[NFTA_RULE_POSITION]) {
-		if (!(nlh->nlmsg_flags & NLM_F_CREATE))
-			return -EOPNOTSUPP;
 
-		pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
-		old_rule = __nft_rule_lookup(chain, pos_handle);
-		if (IS_ERR(old_rule)) {
-			NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]);
-			return PTR_ERR(old_rule);
+		if (nla[NFTA_RULE_POSITION]) {
+			pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION]));
+			old_rule = __nft_rule_lookup(chain, pos_handle);
+			if (IS_ERR(old_rule)) {
+				NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]);
+				return PTR_ERR(old_rule);
+			}
 		}
 	}
 
@@ -2669,21 +2667,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	}
 
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
-		if (!nft_is_active_next(net, old_rule)) {
-			err = -ENOENT;
-			goto err2;
-		}
-		trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
-					   old_rule);
+		trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule);
 		if (trans == NULL) {
 			err = -ENOMEM;
 			goto err2;
 		}
-		nft_deactivate_next(net, old_rule);
-		chain->use--;
-
-		if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
-			err = -ENOMEM;
+		err = nft_delrule(&ctx, old_rule);
+		if (err < 0) {
+			nft_trans_destroy(trans);
 			goto err2;
 		}
 
@@ -6324,7 +6315,7 @@ static void nf_tables_commit_chain_free_rules_old(struct nft_rule **rules)
 	call_rcu(&old->h, __nf_tables_commit_chain_free_rules_old);
 }
 
-static void nf_tables_commit_chain_active(struct net *net, struct nft_chain *chain)
+static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain)
 {
 	struct nft_rule **g0, **g1;
 	bool next_genbit;
@@ -6441,11 +6432,8 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 
 	/* step 2.  Make rules_gen_X visible to packet path */
 	list_for_each_entry(table, &net->nft.tables, list) {
-		list_for_each_entry(chain, &table->chains, list) {
-			if (!nft_is_active_next(net, chain))
-				continue;
-			nf_tables_commit_chain_active(net, chain);
-		}
+		list_for_each_entry(chain, &table->chains, list)
+			nf_tables_commit_chain(net, chain);
 	}
 
 	/*
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index e7a50af1b3d6..109b0d27345a 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -382,7 +382,8 @@ err:
 static int
 cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
 			    u32 seq, u32 type, int event, u16 l3num,
-			    const struct nf_conntrack_l4proto *l4proto)
+			    const struct nf_conntrack_l4proto *l4proto,
+			    const unsigned int *timeouts)
 {
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
@@ -408,7 +409,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
 	if (!nest_parms)
 		goto nla_put_failure;
 
-	ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL);
+	ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts);
 	if (ret < 0)
 		goto nla_put_failure;
 
@@ -430,6 +431,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl,
 				 struct netlink_ext_ack *extack)
 {
 	const struct nf_conntrack_l4proto *l4proto;
+	unsigned int *timeouts = NULL;
 	struct sk_buff *skb2;
 	int ret, err;
 	__u16 l3num;
@@ -442,12 +444,55 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl,
 	l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]);
 	l4proto = nf_ct_l4proto_find_get(l4num);
 
-	/* This protocol is not supported, skip. */
-	if (l4proto->l4proto != l4num) {
-		err = -EOPNOTSUPP;
+	err = -EOPNOTSUPP;
+	if (l4proto->l4proto != l4num)
 		goto err;
+
+	switch (l4proto->l4proto) {
+	case IPPROTO_ICMP:
+		timeouts = &nf_icmp_pernet(net)->timeout;
+		break;
+	case IPPROTO_TCP:
+		timeouts = nf_tcp_pernet(net)->timeouts;
+		break;
+	case IPPROTO_UDP: /* fallthrough */
+	case IPPROTO_UDPLITE:
+		timeouts = nf_udp_pernet(net)->timeouts;
+		break;
+	case IPPROTO_DCCP:
+#ifdef CONFIG_NF_CT_PROTO_DCCP
+		timeouts = nf_dccp_pernet(net)->dccp_timeout;
+#endif
+		break;
+	case IPPROTO_ICMPV6:
+		timeouts = &nf_icmpv6_pernet(net)->timeout;
+		break;
+	case IPPROTO_SCTP:
+#ifdef CONFIG_NF_CT_PROTO_SCTP
+		timeouts = nf_sctp_pernet(net)->timeouts;
+#endif
+		break;
+	case IPPROTO_GRE:
+#ifdef CONFIG_NF_CT_PROTO_GRE
+		if (l4proto->net_id) {
+			struct netns_proto_gre *net_gre;
+
+			net_gre = net_generic(net, *l4proto->net_id);
+			timeouts = net_gre->gre_timeouts;
+		}
+#endif
+		break;
+	case 255:
+		timeouts = &nf_generic_pernet(net)->timeout;
+		break;
+	default:
+		WARN_ONCE(1, "Missing timeouts for proto %d", l4proto->l4proto);
+		break;
 	}
 
+	if (!timeouts)
+		goto err;
+
 	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (skb2 == NULL) {
 		err = -ENOMEM;
@@ -458,8 +503,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl,
 					  nlh->nlmsg_seq,
 					  NFNL_MSG_TYPE(nlh->nlmsg_type),
 					  IPCTNL_MSG_TIMEOUT_DEFAULT_SET,
-					  l3num,
-					  l4proto);
+					  l3num, l4proto, timeouts);
 	if (ret <= 0) {
 		kfree_skb(skb2);
 		err = -ENOMEM;
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 768292eac2a4..7334e0b80a5e 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -54,9 +54,11 @@ static bool nft_xt_put(struct nft_xt *xt)
 	return false;
 }
 
-static int nft_compat_chain_validate_dependency(const char *tablename,
-						const struct nft_chain *chain)
+static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx,
+						const char *tablename)
 {
+	enum nft_chain_types type = NFT_CHAIN_T_DEFAULT;
+	const struct nft_chain *chain = ctx->chain;
 	const struct nft_base_chain *basechain;
 
 	if (!tablename ||
@@ -64,9 +66,12 @@ static int nft_compat_chain_validate_dependency(const char *tablename,
 		return 0;
 
 	basechain = nft_base_chain(chain);
-	if (strcmp(tablename, "nat") == 0 &&
-	    basechain->type->type != NFT_CHAIN_T_NAT)
-		return -EINVAL;
+	if (strcmp(tablename, "nat") == 0) {
+		if (ctx->family != NFPROTO_BRIDGE)
+			type = NFT_CHAIN_T_NAT;
+		if (basechain->type->type != type)
+			return -EINVAL;
+	}
 
 	return 0;
 }
@@ -342,8 +347,7 @@ static int nft_target_validate(const struct nft_ctx *ctx,
 		if (target->hooks && !(hook_mask & target->hooks))
 			return -EINVAL;
 
-		ret = nft_compat_chain_validate_dependency(target->table,
-							   ctx->chain);
+		ret = nft_compat_chain_validate_dependency(ctx, target->table);
 		if (ret < 0)
 			return ret;
 	}
@@ -516,6 +520,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		    void *info)
 {
 	struct xt_match *match = expr->ops->data;
+	struct module *me = match->me;
 	struct xt_mtdtor_param par;
 
 	par.net = ctx->net;
@@ -526,7 +531,7 @@ __nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr,
 		par.match->destroy(&par);
 
 	if (nft_xt_put(container_of(expr->ops, struct nft_xt, ops)))
-		module_put(match->me);
+		module_put(me);
 }
 
 static void
@@ -590,8 +595,7 @@ static int nft_match_validate(const struct nft_ctx *ctx,
 		if (match->hooks && !(hook_mask & match->hooks))
 			return -EINVAL;
 
-		ret = nft_compat_chain_validate_dependency(match->table,
-							   ctx->chain);
+		ret = nft_compat_chain_validate_dependency(ctx, match->table);
 		if (ret < 0)
 			return ret;
 	}
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index e82d9a966c45..974525eb92df 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -214,7 +214,9 @@ static int __init nft_flow_offload_module_init(void)
 {
 	int err;
 
-	register_netdevice_notifier(&flow_offload_netdev_notifier);
+	err = register_netdevice_notifier(&flow_offload_netdev_notifier);
+	if (err)
+		goto err;
 
 	err = nft_register_expr(&nft_flow_offload_type);
 	if (err < 0)
@@ -224,6 +226,7 @@ static int __init nft_flow_offload_module_init(void)
 
 register_expr:
 	unregister_netdevice_notifier(&flow_offload_netdev_notifier);
+err:
 	return err;
 }
 
diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c
index 649d1700ec5b..3cc1b3dc3c3c 100644
--- a/net/netfilter/nft_numgen.c
+++ b/net/netfilter/nft_numgen.c
@@ -24,7 +24,6 @@ struct nft_ng_inc {
 	u32			modulus;
 	atomic_t		counter;
 	u32			offset;
-	struct nft_set		*map;
 };
 
 static u32 nft_ng_inc_gen(struct nft_ng_inc *priv)
@@ -48,34 +47,11 @@ static void nft_ng_inc_eval(const struct nft_expr *expr,
 	regs->data[priv->dreg] = nft_ng_inc_gen(priv);
 }
 
-static void nft_ng_inc_map_eval(const struct nft_expr *expr,
-				struct nft_regs *regs,
-				const struct nft_pktinfo *pkt)
-{
-	struct nft_ng_inc *priv = nft_expr_priv(expr);
-	const struct nft_set *map = priv->map;
-	const struct nft_set_ext *ext;
-	u32 result;
-	bool found;
-
-	result = nft_ng_inc_gen(priv);
-	found = map->ops->lookup(nft_net(pkt), map, &result, &ext);
-
-	if (!found)
-		return;
-
-	nft_data_copy(&regs->data[priv->dreg],
-		      nft_set_ext_data(ext), map->dlen);
-}
-
 static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = {
 	[NFTA_NG_DREG]		= { .type = NLA_U32 },
 	[NFTA_NG_MODULUS]	= { .type = NLA_U32 },
 	[NFTA_NG_TYPE]		= { .type = NLA_U32 },
 	[NFTA_NG_OFFSET]	= { .type = NLA_U32 },
-	[NFTA_NG_SET_NAME]	= { .type = NLA_STRING,
-				    .len = NFT_SET_MAXNAMELEN - 1 },
-	[NFTA_NG_SET_ID]	= { .type = NLA_U32 },
 };
 
 static int nft_ng_inc_init(const struct nft_ctx *ctx,
@@ -101,22 +77,6 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx,
 					   NFT_DATA_VALUE, sizeof(u32));
 }
 
-static int nft_ng_inc_map_init(const struct nft_ctx *ctx,
-			       const struct nft_expr *expr,
-			       const struct nlattr * const tb[])
-{
-	struct nft_ng_inc *priv = nft_expr_priv(expr);
-	u8 genmask = nft_genmask_next(ctx->net);
-
-	nft_ng_inc_init(ctx, expr, tb);
-
-	priv->map = nft_set_lookup_global(ctx->net, ctx->table,
-					  tb[NFTA_NG_SET_NAME],
-					  tb[NFTA_NG_SET_ID], genmask);
-
-	return PTR_ERR_OR_ZERO(priv->map);
-}
-
 static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg,
 		       u32 modulus, enum nft_ng_types type, u32 offset)
 {
@@ -143,27 +103,10 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr)
 			   priv->offset);
 }
 
-static int nft_ng_inc_map_dump(struct sk_buff *skb,
-			       const struct nft_expr *expr)
-{
-	const struct nft_ng_inc *priv = nft_expr_priv(expr);
-
-	if (nft_ng_dump(skb, priv->dreg, priv->modulus,
-			NFT_NG_INCREMENTAL, priv->offset) ||
-	    nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name))
-		goto nla_put_failure;
-
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
 struct nft_ng_random {
 	enum nft_registers      dreg:8;
 	u32			modulus;
 	u32			offset;
-	struct nft_set		*map;
 };
 
 static u32 nft_ng_random_gen(struct nft_ng_random *priv)
@@ -183,25 +126,6 @@ static void nft_ng_random_eval(const struct nft_expr *expr,
 	regs->data[priv->dreg] = nft_ng_random_gen(priv);
 }
 
-static void nft_ng_random_map_eval(const struct nft_expr *expr,
-				   struct nft_regs *regs,
-				   const struct nft_pktinfo *pkt)
-{
-	struct nft_ng_random *priv = nft_expr_priv(expr);
-	const struct nft_set *map = priv->map;
-	const struct nft_set_ext *ext;
-	u32 result;
-	bool found;
-
-	result = nft_ng_random_gen(priv);
-	found = map->ops->lookup(nft_net(pkt), map, &result, &ext);
-	if (!found)
-		return;
-
-	nft_data_copy(&regs->data[priv->dreg],
-		      nft_set_ext_data(ext), map->dlen);
-}
-
 static int nft_ng_random_init(const struct nft_ctx *ctx,
 			      const struct nft_expr *expr,
 			      const struct nlattr * const tb[])
@@ -226,21 +150,6 @@ static int nft_ng_random_init(const struct nft_ctx *ctx,
 					   NFT_DATA_VALUE, sizeof(u32));
 }
 
-static int nft_ng_random_map_init(const struct nft_ctx *ctx,
-				  const struct nft_expr *expr,
-				  const struct nlattr * const tb[])
-{
-	struct nft_ng_random *priv = nft_expr_priv(expr);
-	u8 genmask = nft_genmask_next(ctx->net);
-
-	nft_ng_random_init(ctx, expr, tb);
-	priv->map = nft_set_lookup_global(ctx->net, ctx->table,
-					  tb[NFTA_NG_SET_NAME],
-					  tb[NFTA_NG_SET_ID], genmask);
-
-	return PTR_ERR_OR_ZERO(priv->map);
-}
-
 static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_ng_random *priv = nft_expr_priv(expr);
@@ -249,22 +158,6 @@ static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr)
 			   priv->offset);
 }
 
-static int nft_ng_random_map_dump(struct sk_buff *skb,
-				  const struct nft_expr *expr)
-{
-	const struct nft_ng_random *priv = nft_expr_priv(expr);
-
-	if (nft_ng_dump(skb, priv->dreg, priv->modulus,
-			NFT_NG_RANDOM, priv->offset) ||
-	    nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name))
-		goto nla_put_failure;
-
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
 static struct nft_expr_type nft_ng_type;
 static const struct nft_expr_ops nft_ng_inc_ops = {
 	.type		= &nft_ng_type,
@@ -274,14 +167,6 @@ static const struct nft_expr_ops nft_ng_inc_ops = {
 	.dump		= nft_ng_inc_dump,
 };
 
-static const struct nft_expr_ops nft_ng_inc_map_ops = {
-	.type		= &nft_ng_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)),
-	.eval		= nft_ng_inc_map_eval,
-	.init		= nft_ng_inc_map_init,
-	.dump		= nft_ng_inc_map_dump,
-};
-
 static const struct nft_expr_ops nft_ng_random_ops = {
 	.type		= &nft_ng_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ng_random)),
@@ -290,14 +175,6 @@ static const struct nft_expr_ops nft_ng_random_ops = {
 	.dump		= nft_ng_random_dump,
 };
 
-static const struct nft_expr_ops nft_ng_random_map_ops = {
-	.type		= &nft_ng_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_ng_random)),
-	.eval		= nft_ng_random_map_eval,
-	.init		= nft_ng_random_map_init,
-	.dump		= nft_ng_random_map_dump,
-};
-
 static const struct nft_expr_ops *
 nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 {
@@ -312,12 +189,8 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[])
 
 	switch (type) {
 	case NFT_NG_INCREMENTAL:
-		if (tb[NFTA_NG_SET_NAME])
-			return &nft_ng_inc_map_ops;
 		return &nft_ng_inc_ops;
 	case NFT_NG_RANDOM:
-		if (tb[NFTA_NG_SET_NAME])
-			return &nft_ng_random_map_ops;
 		return &nft_ng_random_ops;
 	}
 
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index ca5e5d8c5ef8..b13618c764ec 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -50,7 +50,7 @@ static int nft_osf_init(const struct nft_ctx *ctx,
 	int err;
 	u8 ttl;
 
-	if (nla_get_u8(tb[NFTA_OSF_TTL])) {
+	if (tb[NFTA_OSF_TTL]) {
 		ttl = nla_get_u8(tb[NFTA_OSF_TTL]);
 		if (ttl > 2)
 			return -EINVAL;
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index c6acfc2d9c84..eb4cbd244c3d 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -114,6 +114,22 @@ static void idletimer_tg_expired(struct timer_list *t)
 	schedule_work(&timer->work);
 }
 
+static int idletimer_check_sysfs_name(const char *name, unsigned int size)
+{
+	int ret;
+
+	ret = xt_check_proc_name(name, size);
+	if (ret < 0)
+		return ret;
+
+	if (!strcmp(name, "power") ||
+	    !strcmp(name, "subsystem") ||
+	    !strcmp(name, "uevent"))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int idletimer_tg_create(struct idletimer_tg_info *info)
 {
 	int ret;
@@ -124,6 +140,10 @@ static int idletimer_tg_create(struct idletimer_tg_info *info)
 		goto out;
 	}
 
+	ret = idletimer_check_sysfs_name(info->label, sizeof(info->label));
+	if (ret < 0)
+		goto out_free_timer;
+
 	sysfs_attr_init(&info->timer->attr.attr);
 	info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL);
 	if (!info->timer->attr.attr.name) {
diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c
index dec843cadf46..9e05c86ba5c4 100644
--- a/net/netfilter/xt_RATEEST.c
+++ b/net/netfilter/xt_RATEEST.c
@@ -201,18 +201,8 @@ static __net_init int xt_rateest_net_init(struct net *net)
 	return 0;
 }
 
-static void __net_exit xt_rateest_net_exit(struct net *net)
-{
-	struct xt_rateest_net *xn = net_generic(net, xt_rateest_id);
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(xn->hash); i++)
-		WARN_ON_ONCE(!hlist_empty(&xn->hash[i]));
-}
-
 static struct pernet_operations xt_rateest_net_ops = {
 	.init = xt_rateest_net_init,
-	.exit = xt_rateest_net_exit,
 	.id   = &xt_rateest_id,
 	.size = sizeof(struct xt_rateest_net),
 };
diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c
index 3e7d259e5d8d..1ad4017f9b73 100644
--- a/net/netfilter/xt_hashlimit.c
+++ b/net/netfilter/xt_hashlimit.c
@@ -295,9 +295,10 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg,
 
 	/* copy match config into hashtable config */
 	ret = cfg_copy(&hinfo->cfg, (void *)cfg, 3);
-
-	if (ret)
+	if (ret) {
+		vfree(hinfo);
 		return ret;
+	}
 
 	hinfo->cfg.size = size;
 	if (hinfo->cfg.max == 0)
@@ -814,7 +815,6 @@ hashlimit_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
 	int ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 1);
-
 	if (ret)
 		return ret;
 
@@ -830,7 +830,6 @@ hashlimit_mt_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	int ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 2);
-
 	if (ret)
 		return ret;
 
@@ -921,7 +920,6 @@ static int hashlimit_mt_check_v1(const struct xt_mtchk_param *par)
 		return ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 1);
-
 	if (ret)
 		return ret;
 
@@ -940,7 +938,6 @@ static int hashlimit_mt_check_v2(const struct xt_mtchk_param *par)
 		return ret;
 
 	ret = cfg_copy(&cfg, (void *)&info->cfg, 2);
-
 	if (ret)
 		return ret;
 
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 6bec37ab4472..a4660c48ff01 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1203,7 +1203,8 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key,
 					 &info->labels.mask);
 		if (err)
 			return err;
-	} else if (labels_nonzero(&info->labels.mask)) {
+	} else if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
+		   labels_nonzero(&info->labels.mask)) {
 		err = ovs_ct_set_labels(ct, key, &info->labels.value,
 					&info->labels.mask);
 		if (err)
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index a70097ecf33c..865ecef68196 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -3030,7 +3030,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			 * is already present */
 			if (mac_proto != MAC_PROTO_NONE)
 				return -EINVAL;
-			mac_proto = MAC_PROTO_NONE;
+			mac_proto = MAC_PROTO_ETHERNET;
 			break;
 
 		case OVS_ACTION_ATTR_POP_ETH:
@@ -3038,7 +3038,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 				return -EINVAL;
 			if (vlan_tci & htons(VLAN_TAG_PRESENT))
 				return -EINVAL;
-			mac_proto = MAC_PROTO_ETHERNET;
+			mac_proto = MAC_PROTO_NONE;
 			break;
 
 		case OVS_ACTION_ATTR_PUSH_NSH:
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index ec3095f13aae..a74650e98f42 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2394,7 +2394,7 @@ static void tpacket_destruct_skb(struct sk_buff *skb)
 		void *ph;
 		__u32 ts;
 
-		ph = skb_shinfo(skb)->destructor_arg;
+		ph = skb_zcopy_get_nouarg(skb);
 		packet_dec_pending(&po->tx_ring);
 
 		ts = __packet_set_timestamp(po, ph, skb);
@@ -2461,7 +2461,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->mark = po->sk.sk_mark;
 	skb->tstamp = sockc->transmit_time;
 	sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
-	skb_shinfo(skb)->destructor_arg = ph.raw;
+	skb_zcopy_set_nouarg(skb, ph.raw);
 
 	skb_reserve(skb, hlen);
 	skb_reset_network_header(skb);
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 64362d078da8..a2522f9d71e2 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -375,17 +375,36 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call);
  * getting ACKs from the server.  Returns a number representing the life state
  * which can be compared to that returned by a previous call.
  *
- * If this is a client call, ping ACKs will be sent to the server to find out
- * whether it's still responsive and whether the call is still alive on the
- * server.
+ * If the life state stalls, rxrpc_kernel_probe_life() should be called and
+ * then 2RTT waited.
  */
-u32 rxrpc_kernel_check_life(struct socket *sock, struct rxrpc_call *call)
+u32 rxrpc_kernel_check_life(const struct socket *sock,
+			    const struct rxrpc_call *call)
 {
 	return call->acks_latest;
 }
 EXPORT_SYMBOL(rxrpc_kernel_check_life);
 
 /**
+ * rxrpc_kernel_probe_life - Poke the peer to see if it's still alive
+ * @sock: The socket the call is on
+ * @call: The call to check
+ *
+ * In conjunction with rxrpc_kernel_check_life(), allow a kernel service to
+ * find out whether a call is still alive by pinging it.  This should cause the
+ * life state to be bumped in about 2*RTT.
+ *
+ * The must be called in TASK_RUNNING state on pain of might_sleep() objecting.
+ */
+void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call)
+{
+	rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false,
+			  rxrpc_propose_ack_ping_for_check_life);
+	rxrpc_send_ack_packet(call, true, NULL);
+}
+EXPORT_SYMBOL(rxrpc_kernel_probe_life);
+
+/**
  * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call.
  * @sock: The socket the call is on
  * @call: The call to query
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 382196e57a26..bc628acf4f4f 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -611,6 +611,7 @@ struct rxrpc_call {
 						 * not hard-ACK'd packet follows this.
 						 */
 	rxrpc_seq_t		tx_top;		/* Highest Tx slot allocated. */
+	u16			tx_backoff;	/* Delay to insert due to Tx failure */
 
 	/* TCP-style slow-start congestion control [RFC5681].  Since the SMSS
 	 * is fixed, we keep these numbers in terms of segments (ie. DATA
diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 8e7434e92097..468efc3660c0 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -123,6 +123,7 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason,
 		else
 			ack_at = expiry;
 
+		ack_at += READ_ONCE(call->tx_backoff);
 		ack_at += now;
 		if (time_before(ack_at, call->ack_at)) {
 			WRITE_ONCE(call->ack_at, ack_at);
@@ -311,6 +312,7 @@ void rxrpc_process_call(struct work_struct *work)
 		container_of(work, struct rxrpc_call, processor);
 	rxrpc_serial_t *send_ack;
 	unsigned long now, next, t;
+	unsigned int iterations = 0;
 
 	rxrpc_see_call(call);
 
@@ -319,6 +321,11 @@ void rxrpc_process_call(struct work_struct *work)
 	       call->debug_id, rxrpc_call_states[call->state], call->events);
 
 recheck_state:
+	/* Limit the number of times we do this before returning to the manager */
+	iterations++;
+	if (iterations > 5)
+		goto requeue;
+
 	if (test_and_clear_bit(RXRPC_CALL_EV_ABORT, &call->events)) {
 		rxrpc_send_abort_packet(call);
 		goto recheck_state;
@@ -447,13 +454,16 @@ recheck_state:
 	rxrpc_reduce_call_timer(call, next, now, rxrpc_timer_restart);
 
 	/* other events may have been raised since we started checking */
-	if (call->events && call->state < RXRPC_CALL_COMPLETE) {
-		__rxrpc_queue_call(call);
-		goto out;
-	}
+	if (call->events && call->state < RXRPC_CALL_COMPLETE)
+		goto requeue;
 
 out_put:
 	rxrpc_put_call(call, rxrpc_call_put);
 out:
 	_leave("");
+	return;
+
+requeue:
+	__rxrpc_queue_call(call);
+	goto out;
 }
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index 189418888839..736aa9281100 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -35,6 +35,21 @@ struct rxrpc_abort_buffer {
 static const char rxrpc_keepalive_string[] = "";
 
 /*
+ * Increase Tx backoff on transmission failure and clear it on success.
+ */
+static void rxrpc_tx_backoff(struct rxrpc_call *call, int ret)
+{
+	if (ret < 0) {
+		u16 tx_backoff = READ_ONCE(call->tx_backoff);
+
+		if (tx_backoff < HZ)
+			WRITE_ONCE(call->tx_backoff, tx_backoff + 1);
+	} else {
+		WRITE_ONCE(call->tx_backoff, 0);
+	}
+}
+
+/*
  * Arrange for a keepalive ping a certain time after we last transmitted.  This
  * lets the far side know we're still interested in this call and helps keep
  * the route through any intervening firewall open.
@@ -210,6 +225,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr,
 				      rxrpc_tx_point_call_ack);
+	rxrpc_tx_backoff(call, ret);
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		if (ret < 0) {
@@ -218,7 +234,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 			rxrpc_propose_ACK(call, pkt->ack.reason,
 					  ntohs(pkt->ack.maxSkew),
 					  ntohl(pkt->ack.serial),
-					  true, true,
+					  false, true,
 					  rxrpc_propose_ack_retry_tx);
 		} else {
 			spin_lock_bh(&call->lock);
@@ -300,7 +316,7 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
 				      rxrpc_tx_point_call_abort);
-
+	rxrpc_tx_backoff(call, ret);
 
 	rxrpc_put_connection(conn);
 	return ret;
@@ -413,6 +429,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &whdr,
 				      rxrpc_tx_point_call_data_nofrag);
+	rxrpc_tx_backoff(call, ret);
 	if (ret == -EMSGSIZE)
 		goto send_fragmentable;
 
@@ -445,9 +462,18 @@ done:
 			rxrpc_reduce_call_timer(call, expect_rx_by, nowj,
 						rxrpc_timer_set_for_normal);
 		}
-	}
 
-	rxrpc_set_keepalive(call);
+		rxrpc_set_keepalive(call);
+	} else {
+		/* Cancel the call if the initial transmission fails,
+		 * particularly if that's due to network routing issues that
+		 * aren't going away anytime soon.  The layer above can arrange
+		 * the retransmission.
+		 */
+		if (!test_and_set_bit(RXRPC_CALL_BEGAN_RX_TIMER, &call->flags))
+			rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR,
+						  RX_USER_ABORT, ret);
+	}
 
 	_leave(" = %d [%u]", ret, call->peer->maxdata);
 	return ret;
@@ -506,6 +532,7 @@ send_fragmentable:
 	else
 		trace_rxrpc_tx_packet(call->debug_id, &whdr,
 				      rxrpc_tx_point_call_data_frag);
+	rxrpc_tx_backoff(call, ret);
 
 	up_write(&conn->params.local->defrag_sem);
 	goto done;
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 1dae5f2b358f..c8cf4d10c435 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -258,7 +258,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 	if (is_redirect) {
 		skb2->tc_redirected = 1;
 		skb2->tc_from_ingress = skb2->tc_at_ingress;
-
+		if (skb2->tc_from_ingress)
+			skb2->tstamp = 0;
 		/* let's the caller reinsert the packet, if possible */
 		if (use_reinsert) {
 			res->ingress = want_ingress;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index da3dd0f68cc2..2b372a06b432 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -201,7 +201,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			goto out_release;
 		}
 	} else {
-		return err;
+		ret = err;
+		goto out_free;
 	}
 
 	p = to_pedit(*a);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 052855d47354..37c9b8f0e10f 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -27,10 +27,7 @@ struct tcf_police_params {
 	u32			tcfp_ewma_rate;
 	s64			tcfp_burst;
 	u32			tcfp_mtu;
-	s64			tcfp_toks;
-	s64			tcfp_ptoks;
 	s64			tcfp_mtu_ptoks;
-	s64			tcfp_t_c;
 	struct psched_ratecfg	rate;
 	bool			rate_present;
 	struct psched_ratecfg	peak;
@@ -41,6 +38,11 @@ struct tcf_police_params {
 struct tcf_police {
 	struct tc_action	common;
 	struct tcf_police_params __rcu *params;
+
+	spinlock_t		tcfp_lock ____cacheline_aligned_in_smp;
+	s64			tcfp_toks;
+	s64			tcfp_ptoks;
+	s64			tcfp_t_c;
 };
 
 #define to_police(pc) ((struct tcf_police *)pc)
@@ -122,6 +124,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 			return ret;
 		}
 		ret = ACT_P_CREATED;
+		spin_lock_init(&(to_police(*a)->tcfp_lock));
 	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
 		return -EEXIST;
@@ -186,12 +189,9 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	}
 
 	new->tcfp_burst = PSCHED_TICKS2NS(parm->burst);
-	new->tcfp_toks = new->tcfp_burst;
-	if (new->peak_present) {
+	if (new->peak_present)
 		new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak,
 							 new->tcfp_mtu);
-		new->tcfp_ptoks = new->tcfp_mtu_ptoks;
-	}
 
 	if (tb[TCA_POLICE_AVRATE])
 		new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]);
@@ -207,7 +207,12 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	}
 
 	spin_lock_bh(&police->tcf_lock);
-	new->tcfp_t_c = ktime_get_ns();
+	spin_lock_bh(&police->tcfp_lock);
+	police->tcfp_t_c = ktime_get_ns();
+	police->tcfp_toks = new->tcfp_burst;
+	if (new->peak_present)
+		police->tcfp_ptoks = new->tcfp_mtu_ptoks;
+	spin_unlock_bh(&police->tcfp_lock);
 	police->tcf_action = parm->action;
 	rcu_swap_protected(police->params,
 			   new,
@@ -257,25 +262,28 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a,
 		}
 
 		now = ktime_get_ns();
-		toks = min_t(s64, now - p->tcfp_t_c, p->tcfp_burst);
+		spin_lock_bh(&police->tcfp_lock);
+		toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst);
 		if (p->peak_present) {
-			ptoks = toks + p->tcfp_ptoks;
+			ptoks = toks + police->tcfp_ptoks;
 			if (ptoks > p->tcfp_mtu_ptoks)
 				ptoks = p->tcfp_mtu_ptoks;
 			ptoks -= (s64)psched_l2t_ns(&p->peak,
 						    qdisc_pkt_len(skb));
 		}
-		toks += p->tcfp_toks;
+		toks += police->tcfp_toks;
 		if (toks > p->tcfp_burst)
 			toks = p->tcfp_burst;
 		toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb));
 		if ((toks|ptoks) >= 0) {
-			p->tcfp_t_c = now;
-			p->tcfp_toks = toks;
-			p->tcfp_ptoks = ptoks;
+			police->tcfp_t_c = now;
+			police->tcfp_toks = toks;
+			police->tcfp_ptoks = ptoks;
+			spin_unlock_bh(&police->tcfp_lock);
 			ret = p->tcfp_result;
 			goto inc_drops;
 		}
+		spin_unlock_bh(&police->tcfp_lock);
 	}
 
 inc_overlimits:
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 9aada2d0ef06..c6c327874abc 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -709,11 +709,23 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			  struct netlink_ext_ack *extack)
 {
 	const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL;
-	int option_len, key_depth, msk_depth = 0;
+	int err, option_len, key_depth, msk_depth = 0;
+
+	err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS],
+				  TCA_FLOWER_KEY_ENC_OPTS_MAX,
+				  enc_opts_policy, extack);
+	if (err)
+		return err;
 
 	nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]);
 
 	if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) {
+		err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK],
+					  TCA_FLOWER_KEY_ENC_OPTS_MAX,
+					  enc_opts_policy, extack);
+		if (err)
+			return err;
+
 		nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
 		msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
 	}
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 4b1af706896c..25a7cf6d380f 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -469,22 +469,29 @@ begin:
 		goto begin;
 	}
 	prefetch(&skb->end);
-	f->credit -= qdisc_pkt_len(skb);
+	plen = qdisc_pkt_len(skb);
+	f->credit -= plen;
 
-	if (ktime_to_ns(skb->tstamp) || !q->rate_enable)
+	if (!q->rate_enable)
 		goto out;
 
 	rate = q->flow_max_rate;
-	if (skb->sk)
-		rate = min(skb->sk->sk_pacing_rate, rate);
 
-	if (rate <= q->low_rate_threshold) {
-		f->credit = 0;
-		plen = qdisc_pkt_len(skb);
-	} else {
-		plen = max(qdisc_pkt_len(skb), q->quantum);
-		if (f->credit > 0)
-			goto out;
+	/* If EDT time was provided for this skb, we need to
+	 * update f->time_next_packet only if this qdisc enforces
+	 * a flow max rate.
+	 */
+	if (!skb->tstamp) {
+		if (skb->sk)
+			rate = min(skb->sk->sk_pacing_rate, rate);
+
+		if (rate <= q->low_rate_threshold) {
+			f->credit = 0;
+		} else {
+			plen = max(plen, q->quantum);
+			if (f->credit > 0)
+				goto out;
+		}
 	}
 	if (rate != ~0UL) {
 		u64 len = (u64)plen * NSEC_PER_SEC;
diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index cbe4831f46f4..4a042abf844c 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -413,7 +413,7 @@ static int gred_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_GRED_PARMS] == NULL && tb[TCA_GRED_STAB] == NULL) {
 		if (tb[TCA_GRED_LIMIT] != NULL)
 			sch->limit = nla_get_u32(tb[TCA_GRED_LIMIT]);
-		return gred_change_table_def(sch, opt);
+		return gred_change_table_def(sch, tb[TCA_GRED_DPS]);
 	}
 
 	if (tb[TCA_GRED_PARMS] == NULL ||
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 57b3ad9394ad..2c38e3d07924 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -648,15 +648,6 @@ deliver:
 			 */
 			skb->dev = qdisc_dev(sch);
 
-#ifdef CONFIG_NET_CLS_ACT
-			/*
-			 * If it's at ingress let's pretend the delay is
-			 * from the network (tstamp will be updated).
-			 */
-			if (skb->tc_redirected && skb->tc_from_ingress)
-				skb->tstamp = 0;
-#endif
-
 			if (q->slot.slot_next) {
 				q->slot.packets_left--;
 				q->slot.bytes_left -= qdisc_pkt_len(skb);
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index a827a1f562bf..6a28b96e779e 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -499,8 +499,9 @@ void sctp_assoc_set_primary(struct sctp_association *asoc,
 void sctp_assoc_rm_peer(struct sctp_association *asoc,
 			struct sctp_transport *peer)
 {
-	struct list_head	*pos;
-	struct sctp_transport	*transport;
+	struct sctp_transport *transport;
+	struct list_head *pos;
+	struct sctp_chunk *ch;
 
 	pr_debug("%s: association:%p addr:%pISpc\n",
 		 __func__, asoc, &peer->ipaddr.sa);
@@ -564,7 +565,6 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
 	 */
 	if (!list_empty(&peer->transmitted)) {
 		struct sctp_transport *active = asoc->peer.active_path;
-		struct sctp_chunk *ch;
 
 		/* Reset the transport of each chunk on this list */
 		list_for_each_entry(ch, &peer->transmitted,
@@ -586,6 +586,10 @@ void sctp_assoc_rm_peer(struct sctp_association *asoc,
 				sctp_transport_hold(active);
 	}
 
+	list_for_each_entry(ch, &asoc->outqueue.out_chunk_list, list)
+		if (ch->transport == peer)
+			ch->transport = NULL;
+
 	asoc->peer.transport_count--;
 
 	sctp_transport_free(peer);
diff --git a/net/sctp/output.c b/net/sctp/output.c
index 67939ad99c01..025f48e14a91 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -118,6 +118,9 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag,
 		sctp_transport_route(tp, NULL, sp);
 		if (asoc->param_flags & SPP_PMTUD_ENABLE)
 			sctp_assoc_sync_pmtu(asoc);
+	} else if (!sctp_transport_pmtu_check(tp)) {
+		if (asoc->param_flags & SPP_PMTUD_ENABLE)
+			sctp_assoc_sync_pmtu(asoc);
 	}
 
 	if (asoc->pmtu_pending) {
@@ -396,25 +399,6 @@ finish:
 	return retval;
 }
 
-static void sctp_packet_release_owner(struct sk_buff *skb)
-{
-	sk_free(skb->sk);
-}
-
-static void sctp_packet_set_owner_w(struct sk_buff *skb, struct sock *sk)
-{
-	skb_orphan(skb);
-	skb->sk = sk;
-	skb->destructor = sctp_packet_release_owner;
-
-	/*
-	 * The data chunks have already been accounted for in sctp_sendmsg(),
-	 * therefore only reserve a single byte to keep socket around until
-	 * the packet has been transmitted.
-	 */
-	refcount_inc(&sk->sk_wmem_alloc);
-}
-
 static void sctp_packet_gso_append(struct sk_buff *head, struct sk_buff *skb)
 {
 	if (SCTP_OUTPUT_CB(head)->last == head)
@@ -426,6 +410,7 @@ static void sctp_packet_gso_append(struct sk_buff *head, struct sk_buff *skb)
 	head->truesize += skb->truesize;
 	head->data_len += skb->len;
 	head->len += skb->len;
+	refcount_add(skb->truesize, &head->sk->sk_wmem_alloc);
 
 	__skb_header_release(skb);
 }
@@ -601,7 +586,7 @@ int sctp_packet_transmit(struct sctp_packet *packet, gfp_t gfp)
 	if (!head)
 		goto out;
 	skb_reserve(head, packet->overhead + MAX_HEADER);
-	sctp_packet_set_owner_w(head, sk);
+	skb_set_owner_w(head, sk);
 
 	/* set sctp header */
 	sh = skb_push(head, sizeof(struct sctphdr));
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 9cb854b05342..c37e1c2dec9d 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q)
 	INIT_LIST_HEAD(&q->retransmit);
 	INIT_LIST_HEAD(&q->sacked);
 	INIT_LIST_HEAD(&q->abandoned);
-	sctp_sched_set_sched(asoc, SCTP_SS_FCFS);
+	sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT);
 }
 
 /* Free the outqueue structure and any related pending chunks.
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index e948db29ab53..9b277bd36d1a 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -46,7 +46,7 @@
 #include <linux/netdevice.h>
 #include <linux/inetdevice.h>
 #include <linux/seq_file.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/highmem.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index fc0386e8ff23..bf618d1b41fd 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -3940,32 +3940,16 @@ static int sctp_setsockopt_pr_supported(struct sock *sk,
 					unsigned int optlen)
 {
 	struct sctp_assoc_value params;
-	struct sctp_association *asoc;
-	int retval = -EINVAL;
 
 	if (optlen != sizeof(params))
-		goto out;
-
-	if (copy_from_user(&params, optval, optlen)) {
-		retval = -EFAULT;
-		goto out;
-	}
-
-	asoc = sctp_id2assoc(sk, params.assoc_id);
-	if (asoc) {
-		asoc->prsctp_enable = !!params.assoc_value;
-	} else if (!params.assoc_id) {
-		struct sctp_sock *sp = sctp_sk(sk);
+		return -EINVAL;
 
-		sp->ep->prsctp_enable = !!params.assoc_value;
-	} else {
-		goto out;
-	}
+	if (copy_from_user(&params, optval, optlen))
+		return -EFAULT;
 
-	retval = 0;
+	sctp_sk(sk)->ep->prsctp_enable = !!params.assoc_value;
 
-out:
-	return retval;
+	return 0;
 }
 
 static int sctp_setsockopt_default_prinfo(struct sock *sk,
@@ -7083,14 +7067,15 @@ static int sctp_getsockopt_pr_assocstatus(struct sock *sk, int len,
 	}
 
 	policy = params.sprstat_policy;
-	if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)))
+	if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) ||
+	    ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK)))
 		goto out;
 
 	asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
 	if (!asoc)
 		goto out;
 
-	if (policy & SCTP_PR_SCTP_ALL) {
+	if (policy == SCTP_PR_SCTP_ALL) {
 		params.sprstat_abandoned_unsent = 0;
 		params.sprstat_abandoned_sent = 0;
 		for (policy = 0; policy <= SCTP_PR_INDEX(MAX); policy++) {
@@ -7142,7 +7127,8 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
 	}
 
 	policy = params.sprstat_policy;
-	if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)))
+	if (!policy || (policy & ~(SCTP_PR_SCTP_MASK | SCTP_PR_SCTP_ALL)) ||
+	    ((policy & SCTP_PR_SCTP_ALL) && (policy & SCTP_PR_SCTP_MASK)))
 		goto out;
 
 	asoc = sctp_id2assoc(sk, params.sprstat_assoc_id);
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index ffb940d3b57c..3892e7630f3a 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -535,7 +535,6 @@ int sctp_send_add_streams(struct sctp_association *asoc,
 		goto out;
 	}
 
-	stream->incnt = incnt;
 	stream->outcnt = outcnt;
 
 	asoc->strreset_outstanding = !!out + !!in;
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 80e2119f1c70..5fbaf1901571 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -127,6 +127,8 @@ static int smc_release(struct socket *sock)
 	smc = smc_sk(sk);
 
 	/* cleanup for a dangling non-blocking connect */
+	if (smc->connect_info && sk->sk_state == SMC_INIT)
+		tcp_abort(smc->clcsock->sk, ECONNABORTED);
 	flush_work(&smc->connect_work);
 	kfree(smc->connect_info);
 	smc->connect_info = NULL;
@@ -547,7 +549,8 @@ static int smc_connect_rdma(struct smc_sock *smc,
 
 	mutex_lock(&smc_create_lgr_pending);
 	local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev,
-					ibport, &aclc->lcl, NULL, 0);
+					ibport, ntoh24(aclc->qpn), &aclc->lcl,
+					NULL, 0);
 	if (local_contact < 0) {
 		if (local_contact == -ENOMEM)
 			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
@@ -618,7 +621,7 @@ static int smc_connect_ism(struct smc_sock *smc,
 	int rc = 0;
 
 	mutex_lock(&smc_create_lgr_pending);
-	local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0,
+	local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, 0,
 					NULL, ismdev, aclc->gid);
 	if (local_contact < 0)
 		return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0);
@@ -1083,7 +1086,7 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc,
 				int *local_contact)
 {
 	/* allocate connection / link group */
-	*local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport,
+	*local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport, 0,
 					 &pclc->lcl, NULL, 0);
 	if (*local_contact < 0) {
 		if (*local_contact == -ENOMEM)
@@ -1107,7 +1110,7 @@ static int smc_listen_ism_init(struct smc_sock *new_smc,
 	struct smc_clc_msg_smcd *pclc_smcd;
 
 	pclc_smcd = smc_get_clc_msg_smcd(pclc);
-	*local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, NULL,
+	*local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, 0, NULL,
 					 ismdev, pclc_smcd->gid);
 	if (*local_contact < 0) {
 		if (*local_contact == -ENOMEM)
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index ed5dcf03fe0b..db83332ac1c8 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -81,7 +81,7 @@ static inline void smc_cdc_add_pending_send(struct smc_connection *conn,
 		sizeof(struct smc_cdc_msg) > SMC_WR_BUF_SIZE,
 		"must increase SMC_WR_BUF_SIZE to at least sizeof(struct smc_cdc_msg)");
 	BUILD_BUG_ON_MSG(
-		sizeof(struct smc_cdc_msg) != SMC_WR_TX_SIZE,
+		offsetofend(struct smc_cdc_msg, reserved) > SMC_WR_TX_SIZE,
 		"must adapt SMC_WR_TX_SIZE to sizeof(struct smc_cdc_msg); if not all smc_wr upper layer protocols use the same message size any more, must start to set link->wr_tx_sges[i].length on each individual smc_wr_tx_send()");
 	BUILD_BUG_ON_MSG(
 		sizeof(struct smc_cdc_tx_pend) > SMC_WR_TX_PEND_PRIV_SIZE,
@@ -177,23 +177,24 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn)
 int smcd_cdc_msg_send(struct smc_connection *conn)
 {
 	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	union smc_host_cursor curs;
 	struct smcd_cdc_msg cdc;
 	int rc, diff;
 
 	memset(&cdc, 0, sizeof(cdc));
 	cdc.common.type = SMC_CDC_MSG_TYPE;
-	cdc.prod_wrap = conn->local_tx_ctrl.prod.wrap;
-	cdc.prod_count = conn->local_tx_ctrl.prod.count;
-
-	cdc.cons_wrap = conn->local_tx_ctrl.cons.wrap;
-	cdc.cons_count = conn->local_tx_ctrl.cons.count;
-	cdc.prod_flags = conn->local_tx_ctrl.prod_flags;
-	cdc.conn_state_flags = conn->local_tx_ctrl.conn_state_flags;
+	curs.acurs.counter = atomic64_read(&conn->local_tx_ctrl.prod.acurs);
+	cdc.prod.wrap = curs.wrap;
+	cdc.prod.count = curs.count;
+	curs.acurs.counter = atomic64_read(&conn->local_tx_ctrl.cons.acurs);
+	cdc.cons.wrap = curs.wrap;
+	cdc.cons.count = curs.count;
+	cdc.cons.prod_flags = conn->local_tx_ctrl.prod_flags;
+	cdc.cons.conn_state_flags = conn->local_tx_ctrl.conn_state_flags;
 	rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1);
 	if (rc)
 		return rc;
-	smc_curs_copy(&conn->rx_curs_confirmed, &conn->local_tx_ctrl.cons,
-		      conn);
+	smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn);
 	/* Calculate transmitted data and increment free send buffer space */
 	diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin,
 			     &conn->tx_curs_sent);
@@ -331,13 +332,16 @@ static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc)
 static void smcd_cdc_rx_tsklet(unsigned long data)
 {
 	struct smc_connection *conn = (struct smc_connection *)data;
+	struct smcd_cdc_msg *data_cdc;
 	struct smcd_cdc_msg cdc;
 	struct smc_sock *smc;
 
 	if (!conn)
 		return;
 
-	memcpy(&cdc, conn->rmb_desc->cpu_addr, sizeof(cdc));
+	data_cdc = (struct smcd_cdc_msg *)conn->rmb_desc->cpu_addr;
+	smcd_curs_copy(&cdc.prod, &data_cdc->prod, conn);
+	smcd_curs_copy(&cdc.cons, &data_cdc->cons, conn);
 	smc = container_of(conn, struct smc_sock, conn);
 	smc_cdc_msg_recv(smc, (struct smc_cdc_msg *)&cdc);
 }
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 934df4473a7c..b5bfe38c7f9b 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -48,21 +48,31 @@ struct smc_cdc_msg {
 	struct smc_cdc_producer_flags	prod_flags;
 	struct smc_cdc_conn_state_flags	conn_state_flags;
 	u8				reserved[18];
-} __packed;					/* format defined in RFC7609 */
+};
+
+/* SMC-D cursor format */
+union smcd_cdc_cursor {
+	struct {
+		u16	wrap;
+		u32	count;
+		struct smc_cdc_producer_flags	prod_flags;
+		struct smc_cdc_conn_state_flags	conn_state_flags;
+	} __packed;
+#ifdef KERNEL_HAS_ATOMIC64
+	atomic64_t		acurs;		/* for atomic processing */
+#else
+	u64			acurs;		/* for atomic processing */
+#endif
+} __aligned(8);
 
 /* CDC message for SMC-D */
 struct smcd_cdc_msg {
 	struct smc_wr_rx_hdr common;	/* Type = 0xFE */
 	u8 res1[7];
-	u16 prod_wrap;
-	u32 prod_count;
-	u8 res2[2];
-	u16 cons_wrap;
-	u32 cons_count;
-	struct smc_cdc_producer_flags	prod_flags;
-	struct smc_cdc_conn_state_flags conn_state_flags;
+	union smcd_cdc_cursor	prod;
+	union smcd_cdc_cursor	cons;
 	u8 res3[8];
-} __packed;
+} __aligned(8);
 
 static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn)
 {
@@ -135,6 +145,21 @@ static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt,
 #endif
 }
 
+static inline void smcd_curs_copy(union smcd_cdc_cursor *tgt,
+				  union smcd_cdc_cursor *src,
+				  struct smc_connection *conn)
+{
+#ifndef KERNEL_HAS_ATOMIC64
+	unsigned long flags;
+
+	spin_lock_irqsave(&conn->acurs_lock, flags);
+	tgt->acurs = src->acurs;
+	spin_unlock_irqrestore(&conn->acurs_lock, flags);
+#else
+	atomic64_set(&tgt->acurs, atomic64_read(&src->acurs));
+#endif
+}
+
 /* calculate cursor difference between old and new, where old <= new */
 static inline int smc_curs_diff(unsigned int size,
 				union smc_host_cursor *old,
@@ -222,12 +247,17 @@ static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local,
 static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local,
 					struct smcd_cdc_msg *peer)
 {
-	local->prod.wrap = peer->prod_wrap;
-	local->prod.count = peer->prod_count;
-	local->cons.wrap = peer->cons_wrap;
-	local->cons.count = peer->cons_count;
-	local->prod_flags = peer->prod_flags;
-	local->conn_state_flags = peer->conn_state_flags;
+	union smc_host_cursor temp;
+
+	temp.wrap = peer->prod.wrap;
+	temp.count = peer->prod.count;
+	atomic64_set(&local->prod.acurs, atomic64_read(&temp.acurs));
+
+	temp.wrap = peer->cons.wrap;
+	temp.count = peer->cons.count;
+	atomic64_set(&local->cons.acurs, atomic64_read(&temp.acurs));
+	local->prod_flags = peer->cons.prod_flags;
+	local->conn_state_flags = peer->cons.conn_state_flags;
 }
 
 static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 52241d679cc9..89c3a8c7859a 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -286,7 +286,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	 */
 	krflags = MSG_PEEK | MSG_WAITALL;
 	smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME;
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1,
+	iov_iter_kvec(&msg.msg_iter, READ, &vec, 1,
 			sizeof(struct smc_clc_msg_hdr));
 	len = sock_recvmsg(smc->clcsock, &msg, krflags);
 	if (signal_pending(current)) {
@@ -325,7 +325,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 
 	/* receive the complete CLC message */
 	memset(&msg, 0, sizeof(struct msghdr));
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen);
+	iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, datlen);
 	krflags = MSG_WAITALL;
 	len = sock_recvmsg(smc->clcsock, &msg, krflags);
 	if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) {
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 18daebcef181..1c9fa7f0261a 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -184,6 +184,8 @@ free:
 
 		if (!lgr->is_smcd && lnk->state != SMC_LNK_INACTIVE)
 			smc_llc_link_inactive(lnk);
+		if (lgr->is_smcd)
+			smc_ism_signal_shutdown(lgr);
 		smc_lgr_free(lgr);
 	}
 }
@@ -485,7 +487,7 @@ void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport)
 }
 
 /* Called when SMC-D device is terminated or peer is lost */
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid)
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid, unsigned short vlan)
 {
 	struct smc_link_group *lgr, *l;
 	LIST_HEAD(lgr_free_list);
@@ -495,7 +497,7 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid)
 	list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
 		if (lgr->is_smcd && lgr->smcd == dev &&
 		    (!peer_gid || lgr->peer_gid == peer_gid) &&
-		    !list_empty(&lgr->list)) {
+		    (vlan == VLAN_VID_MASK || lgr->vlan_id == vlan)) {
 			__smc_lgr_terminate(lgr);
 			list_move(&lgr->list, &lgr_free_list);
 		}
@@ -506,6 +508,8 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid)
 	list_for_each_entry_safe(lgr, l, &lgr_free_list, list) {
 		list_del_init(&lgr->list);
 		cancel_delayed_work_sync(&lgr->free_work);
+		if (!peer_gid && vlan == VLAN_VID_MASK) /* dev terminated? */
+			smc_ism_signal_shutdown(lgr);
 		smc_lgr_free(lgr);
 	}
 }
@@ -559,7 +563,7 @@ out:
 
 static bool smcr_lgr_match(struct smc_link_group *lgr,
 			   struct smc_clc_msg_local *lcl,
-			   enum smc_lgr_role role)
+			   enum smc_lgr_role role, u32 clcqpn)
 {
 	return !memcmp(lgr->peer_systemid, lcl->id_for_peer,
 		       SMC_SYSTEMID_LEN) &&
@@ -567,7 +571,9 @@ static bool smcr_lgr_match(struct smc_link_group *lgr,
 			SMC_GID_SIZE) &&
 		!memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac,
 			sizeof(lcl->mac)) &&
-		lgr->role == role;
+		lgr->role == role &&
+		(lgr->role == SMC_SERV ||
+		 lgr->lnk[SMC_SINGLE_LINK].peer_qpn == clcqpn);
 }
 
 static bool smcd_lgr_match(struct smc_link_group *lgr,
@@ -578,7 +584,7 @@ static bool smcd_lgr_match(struct smc_link_group *lgr,
 
 /* create a new SMC connection (and a new link group if necessary) */
 int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
-		    struct smc_ib_device *smcibdev, u8 ibport,
+		    struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn,
 		    struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
 		    u64 peer_gid)
 {
@@ -603,7 +609,7 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
 	list_for_each_entry(lgr, &smc_lgr_list.list, list) {
 		write_lock_bh(&lgr->conns_lock);
 		if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) :
-		     smcr_lgr_match(lgr, lcl, role)) &&
+		     smcr_lgr_match(lgr, lcl, role, clcqpn)) &&
 		    !lgr->sync_err &&
 		    lgr->vlan_id == vlan_id &&
 		    (role == SMC_CLNT ||
@@ -1024,6 +1030,8 @@ void smc_core_exit(void)
 			smc_llc_link_inactive(lnk);
 		}
 		cancel_delayed_work_sync(&lgr->free_work);
+		if (lgr->is_smcd)
+			smc_ism_signal_shutdown(lgr);
 		smc_lgr_free(lgr); /* free link group */
 	}
 }
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index c156674733c9..cf98f4d6093e 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -247,7 +247,8 @@ void smc_lgr_free(struct smc_link_group *lgr);
 void smc_lgr_forget(struct smc_link_group *lgr);
 void smc_lgr_terminate(struct smc_link_group *lgr);
 void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
-void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid);
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid,
+			unsigned short vlan);
 int smc_buf_create(struct smc_sock *smc, bool is_smcd);
 int smc_uncompress_bufsize(u8 compressed);
 int smc_rmb_rtoken_handling(struct smc_connection *conn,
@@ -262,7 +263,7 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id);
 
 void smc_conn_free(struct smc_connection *conn);
 int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
-		    struct smc_ib_device *smcibdev, u8 ibport,
+		    struct smc_ib_device *smcibdev, u8 ibport, u32 clcqpn,
 		    struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
 		    u64 peer_gid);
 void smcd_conn_free(struct smc_connection *conn);
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index e36f21ce7252..2fff79db1a59 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -187,22 +187,28 @@ struct smc_ism_event_work {
 #define ISM_EVENT_REQUEST		0x0001
 #define ISM_EVENT_RESPONSE		0x0002
 #define ISM_EVENT_REQUEST_IR		0x00000001
+#define ISM_EVENT_CODE_SHUTDOWN		0x80
 #define ISM_EVENT_CODE_TESTLINK		0x83
 
+union smcd_sw_event_info {
+	u64	info;
+	struct {
+		u8		uid[SMC_LGR_ID_SIZE];
+		unsigned short	vlan_id;
+		u16		code;
+	};
+};
+
 static void smcd_handle_sw_event(struct smc_ism_event_work *wrk)
 {
-	union {
-		u64	info;
-		struct {
-			u32		uid;
-			unsigned short	vlanid;
-			u16		code;
-		};
-	} ev_info;
+	union smcd_sw_event_info ev_info;
 
+	ev_info.info = wrk->event.info;
 	switch (wrk->event.code) {
+	case ISM_EVENT_CODE_SHUTDOWN:	/* Peer shut down DMBs */
+		smc_smcd_terminate(wrk->smcd, wrk->event.tok, ev_info.vlan_id);
+		break;
 	case ISM_EVENT_CODE_TESTLINK:	/* Activity timer */
-		ev_info.info = wrk->event.info;
 		if (ev_info.code == ISM_EVENT_REQUEST) {
 			ev_info.code = ISM_EVENT_RESPONSE;
 			wrk->smcd->ops->signal_event(wrk->smcd,
@@ -215,6 +221,21 @@ static void smcd_handle_sw_event(struct smc_ism_event_work *wrk)
 	}
 }
 
+int smc_ism_signal_shutdown(struct smc_link_group *lgr)
+{
+	int rc;
+	union smcd_sw_event_info ev_info;
+
+	memcpy(ev_info.uid, lgr->id, SMC_LGR_ID_SIZE);
+	ev_info.vlan_id = lgr->vlan_id;
+	ev_info.code = ISM_EVENT_REQUEST;
+	rc = lgr->smcd->ops->signal_event(lgr->smcd, lgr->peer_gid,
+					  ISM_EVENT_REQUEST_IR,
+					  ISM_EVENT_CODE_SHUTDOWN,
+					  ev_info.info);
+	return rc;
+}
+
 /* worker for SMC-D events */
 static void smc_ism_event_work(struct work_struct *work)
 {
@@ -223,7 +244,7 @@ static void smc_ism_event_work(struct work_struct *work)
 
 	switch (wrk->event.type) {
 	case ISM_EVENT_GID:	/* GID event, token is peer GID */
-		smc_smcd_terminate(wrk->smcd, wrk->event.tok);
+		smc_smcd_terminate(wrk->smcd, wrk->event.tok, VLAN_VID_MASK);
 		break;
 	case ISM_EVENT_DMB:
 		break;
@@ -289,7 +310,7 @@ void smcd_unregister_dev(struct smcd_dev *smcd)
 	spin_unlock(&smcd_dev_list.lock);
 	flush_workqueue(smcd->event_wq);
 	destroy_workqueue(smcd->event_wq);
-	smc_smcd_terminate(smcd, 0);
+	smc_smcd_terminate(smcd, 0, VLAN_VID_MASK);
 
 	device_del(&smcd->dev);
 }
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
index aee45b860b79..4da946cbfa29 100644
--- a/net/smc/smc_ism.h
+++ b/net/smc/smc_ism.h
@@ -45,4 +45,5 @@ int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size,
 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);
 #endif
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 3c458d279855..c2694750a6a8 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -215,12 +215,14 @@ int smc_wr_tx_put_slot(struct smc_link *link,
 
 	pend = container_of(wr_pend_priv, struct smc_wr_tx_pend, priv);
 	if (pend->idx < link->wr_tx_cnt) {
+		u32 idx = pend->idx;
+
 		/* clear the full struct smc_wr_tx_pend including .priv */
 		memset(&link->wr_tx_pends[pend->idx], 0,
 		       sizeof(link->wr_tx_pends[pend->idx]));
 		memset(&link->wr_tx_bufs[pend->idx], 0,
 		       sizeof(link->wr_tx_bufs[pend->idx]));
-		test_and_clear_bit(pend->idx, link->wr_tx_mask);
+		test_and_clear_bit(idx, link->wr_tx_mask);
 		return 1;
 	}
 
diff --git a/net/socket.c b/net/socket.c
index 99c96851469f..334fcc617ef2 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -635,7 +635,7 @@ EXPORT_SYMBOL(sock_sendmsg);
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg,
 		   struct kvec *vec, size_t num, size_t size)
 {
-	iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size);
+	iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size);
 	return sock_sendmsg(sock, msg);
 }
 EXPORT_SYMBOL(kernel_sendmsg);
@@ -648,7 +648,7 @@ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
 	if (!sock->ops->sendmsg_locked)
 		return sock_no_sendmsg_locked(sk, msg, size);
 
-	iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size);
+	iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size);
 
 	return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg));
 }
@@ -823,7 +823,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg,
 	mm_segment_t oldfs = get_fs();
 	int result;
 
-	iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size);
+	iov_iter_kvec(&msg->msg_iter, READ, vec, num, size);
 	set_fs(KERNEL_DS);
 	result = sock_recvmsg(sock, msg, flags);
 	set_fs(oldfs);
@@ -853,7 +853,7 @@ static ssize_t sock_splice_read(struct file *file, loff_t *ppos,
 	struct socket *sock = file->private_data;
 
 	if (unlikely(!sock->ops->splice_read))
-		return -EINVAL;
+		return generic_file_splice_read(file, ppos, pipe, len, flags);
 
 	return sock->ops->splice_read(sock, ppos, pipe, len, flags);
 }
diff --git a/net/sunrpc/auth_generic.c b/net/sunrpc/auth_generic.c
index d8831b988b1e..ab4a3be1542a 100644
--- a/net/sunrpc/auth_generic.c
+++ b/net/sunrpc/auth_generic.c
@@ -281,13 +281,7 @@ static bool generic_key_to_expire(struct rpc_cred *cred)
 {
 	struct auth_cred *acred = &container_of(cred, struct generic_cred,
 						gc_base)->acred;
-	bool ret;
-
-	get_rpccred(cred);
-	ret = test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags);
-	put_rpccred(cred);
-
-	return ret;
+	return test_bit(RPC_CRED_KEY_EXPIRE_SOON, &acred->ac_flags);
 }
 
 static const struct rpc_credops generic_credops = {
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 30f970cdc7f6..5d3f252659f1 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1239,36 +1239,59 @@ gss_create(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt)
 	return &gss_auth->rpc_auth;
 }
 
+static struct gss_cred *
+gss_dup_cred(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
+{
+	struct gss_cred *new;
+
+	/* Make a copy of the cred so that we can reference count it */
+	new = kzalloc(sizeof(*gss_cred), GFP_NOIO);
+	if (new) {
+		struct auth_cred acred = {
+			.uid = gss_cred->gc_base.cr_uid,
+		};
+		struct gss_cl_ctx *ctx =
+			rcu_dereference_protected(gss_cred->gc_ctx, 1);
+
+		rpcauth_init_cred(&new->gc_base, &acred,
+				&gss_auth->rpc_auth,
+				&gss_nullops);
+		new->gc_base.cr_flags = 1UL << RPCAUTH_CRED_UPTODATE;
+		new->gc_service = gss_cred->gc_service;
+		new->gc_principal = gss_cred->gc_principal;
+		kref_get(&gss_auth->kref);
+		rcu_assign_pointer(new->gc_ctx, ctx);
+		gss_get_ctx(ctx);
+	}
+	return new;
+}
+
 /*
- * gss_destroying_context will cause the RPCSEC_GSS to send a NULL RPC call
+ * gss_send_destroy_context will cause the RPCSEC_GSS to send a NULL RPC call
  * to the server with the GSS control procedure field set to
  * RPC_GSS_PROC_DESTROY. This should normally cause the server to release
  * all RPCSEC_GSS state associated with that context.
  */
-static int
-gss_destroying_context(struct rpc_cred *cred)
+static void
+gss_send_destroy_context(struct rpc_cred *cred)
 {
 	struct gss_cred *gss_cred = container_of(cred, struct gss_cred, gc_base);
 	struct gss_auth *gss_auth = container_of(cred->cr_auth, struct gss_auth, rpc_auth);
 	struct gss_cl_ctx *ctx = rcu_dereference_protected(gss_cred->gc_ctx, 1);
+	struct gss_cred *new;
 	struct rpc_task *task;
 
-	if (test_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) == 0)
-		return 0;
-
-	ctx->gc_proc = RPC_GSS_PROC_DESTROY;
-	cred->cr_ops = &gss_nullops;
-
-	/* Take a reference to ensure the cred will be destroyed either
-	 * by the RPC call or by the put_rpccred() below */
-	get_rpccred(cred);
+	new = gss_dup_cred(gss_auth, gss_cred);
+	if (new) {
+		ctx->gc_proc = RPC_GSS_PROC_DESTROY;
 
-	task = rpc_call_null(gss_auth->client, cred, RPC_TASK_ASYNC|RPC_TASK_SOFT);
-	if (!IS_ERR(task))
-		rpc_put_task(task);
+		task = rpc_call_null(gss_auth->client, &new->gc_base,
+				RPC_TASK_ASYNC|RPC_TASK_SOFT);
+		if (!IS_ERR(task))
+			rpc_put_task(task);
 
-	put_rpccred(cred);
-	return 1;
+		put_rpccred(&new->gc_base);
+	}
 }
 
 /* gss_destroy_cred (and gss_free_ctx) are used to clean up after failure
@@ -1330,8 +1353,8 @@ static void
 gss_destroy_cred(struct rpc_cred *cred)
 {
 
-	if (gss_destroying_context(cred))
-		return;
+	if (test_and_clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags) != 0)
+		gss_send_destroy_context(cred);
 	gss_destroy_nullcred(cred);
 }
 
diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c
index 7f0424dfa8f6..eab71fc7af3e 100644
--- a/net/sunrpc/auth_gss/gss_krb5_mech.c
+++ b/net/sunrpc/auth_gss/gss_krb5_mech.c
@@ -274,6 +274,7 @@ out_err:
 static int
 gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx)
 {
+	u32 seq_send;
 	int tmp;
 
 	p = simple_get_bytes(p, end, &ctx->initiate, sizeof(ctx->initiate));
@@ -315,9 +316,10 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx)
 	p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime));
 	if (IS_ERR(p))
 		goto out_err;
-	p = simple_get_bytes(p, end, &ctx->seq_send, sizeof(ctx->seq_send));
+	p = simple_get_bytes(p, end, &seq_send, sizeof(seq_send));
 	if (IS_ERR(p))
 		goto out_err;
+	atomic_set(&ctx->seq_send, seq_send);
 	p = simple_get_netobj(p, end, &ctx->mech_used);
 	if (IS_ERR(p))
 		goto out_err;
@@ -607,6 +609,7 @@ static int
 gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx,
 		gfp_t gfp_mask)
 {
+	u64 seq_send64;
 	int keylen;
 
 	p = simple_get_bytes(p, end, &ctx->flags, sizeof(ctx->flags));
@@ -617,14 +620,15 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx,
 	p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime));
 	if (IS_ERR(p))
 		goto out_err;
-	p = simple_get_bytes(p, end, &ctx->seq_send64, sizeof(ctx->seq_send64));
+	p = simple_get_bytes(p, end, &seq_send64, sizeof(seq_send64));
 	if (IS_ERR(p))
 		goto out_err;
+	atomic64_set(&ctx->seq_send64, seq_send64);
 	/* set seq_send for use by "older" enctypes */
-	ctx->seq_send = ctx->seq_send64;
-	if (ctx->seq_send64 != ctx->seq_send) {
-		dprintk("%s: seq_send64 %lx, seq_send %x overflow?\n", __func__,
-			(unsigned long)ctx->seq_send64, ctx->seq_send);
+	atomic_set(&ctx->seq_send, seq_send64);
+	if (seq_send64 != atomic_read(&ctx->seq_send)) {
+		dprintk("%s: seq_send64 %llx, seq_send %x overflow?\n", __func__,
+			seq_send64, atomic_read(&ctx->seq_send));
 		p = ERR_PTR(-EINVAL);
 		goto out_err;
 	}
diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c
index b4adeb06660b..48fe4a591b54 100644
--- a/net/sunrpc/auth_gss/gss_krb5_seal.c
+++ b/net/sunrpc/auth_gss/gss_krb5_seal.c
@@ -123,30 +123,6 @@ setup_token_v2(struct krb5_ctx *ctx, struct xdr_netobj *token)
 	return krb5_hdr;
 }
 
-u32
-gss_seq_send_fetch_and_inc(struct krb5_ctx *ctx)
-{
-	u32 old, seq_send = READ_ONCE(ctx->seq_send);
-
-	do {
-		old = seq_send;
-		seq_send = cmpxchg(&ctx->seq_send, old, old + 1);
-	} while (old != seq_send);
-	return seq_send;
-}
-
-u64
-gss_seq_send64_fetch_and_inc(struct krb5_ctx *ctx)
-{
-	u64 old, seq_send = READ_ONCE(ctx->seq_send);
-
-	do {
-		old = seq_send;
-		seq_send = cmpxchg64(&ctx->seq_send64, old, old + 1);
-	} while (old != seq_send);
-	return seq_send;
-}
-
 static u32
 gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text,
 		struct xdr_netobj *token)
@@ -177,7 +153,7 @@ gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text,
 
 	memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data, md5cksum.len);
 
-	seq_send = gss_seq_send_fetch_and_inc(ctx);
+	seq_send = atomic_fetch_inc(&ctx->seq_send);
 
 	if (krb5_make_seq_num(ctx, ctx->seq, ctx->initiate ? 0 : 0xff,
 			      seq_send, ptr + GSS_KRB5_TOK_HDR_LEN, ptr + 8))
@@ -205,7 +181,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text,
 
 	/* Set up the sequence number. Now 64-bits in clear
 	 * text and w/o direction indicator */
-	seq_send_be64 = cpu_to_be64(gss_seq_send64_fetch_and_inc(ctx));
+	seq_send_be64 = cpu_to_be64(atomic64_fetch_inc(&ctx->seq_send64));
 	memcpy(krb5_hdr + 8, (char *) &seq_send_be64, 8);
 
 	if (ctx->initiate) {
diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c
index 962fa84e6db1..5cdde6cb703a 100644
--- a/net/sunrpc/auth_gss/gss_krb5_wrap.c
+++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c
@@ -228,7 +228,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset,
 
 	memcpy(ptr + GSS_KRB5_TOK_HDR_LEN, md5cksum.data, md5cksum.len);
 
-	seq_send = gss_seq_send_fetch_and_inc(kctx);
+	seq_send = atomic_fetch_inc(&kctx->seq_send);
 
 	/* XXX would probably be more efficient to compute checksum
 	 * and encrypt at the same time: */
@@ -475,7 +475,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset,
 	*be16ptr++ = 0;
 
 	be64ptr = (__be64 *)be16ptr;
-	*be64ptr = cpu_to_be64(gss_seq_send64_fetch_and_inc(kctx));
+	*be64ptr = cpu_to_be64(atomic64_fetch_inc(&kctx->seq_send64));
 
 	err = (*kctx->gk5e->encrypt_v2)(kctx, offset, buf, pages);
 	if (err)
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 860f2a1bbb67..1ece4bc3eb8d 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -76,6 +76,7 @@ struct rsi {
 	struct xdr_netobj	in_handle, in_token;
 	struct xdr_netobj	out_handle, out_token;
 	int			major_status, minor_status;
+	struct rcu_head		rcu_head;
 };
 
 static struct rsi *rsi_update(struct cache_detail *cd, struct rsi *new, struct rsi *old);
@@ -89,13 +90,21 @@ static void rsi_free(struct rsi *rsii)
 	kfree(rsii->out_token.data);
 }
 
-static void rsi_put(struct kref *ref)
+static void rsi_free_rcu(struct rcu_head *head)
 {
-	struct rsi *rsii = container_of(ref, struct rsi, h.ref);
+	struct rsi *rsii = container_of(head, struct rsi, rcu_head);
+
 	rsi_free(rsii);
 	kfree(rsii);
 }
 
+static void rsi_put(struct kref *ref)
+{
+	struct rsi *rsii = container_of(ref, struct rsi, h.ref);
+
+	call_rcu(&rsii->rcu_head, rsi_free_rcu);
+}
+
 static inline int rsi_hash(struct rsi *item)
 {
 	return hash_mem(item->in_handle.data, item->in_handle.len, RSI_HASHBITS)
@@ -282,7 +291,7 @@ static struct rsi *rsi_lookup(struct cache_detail *cd, struct rsi *item)
 	struct cache_head *ch;
 	int hash = rsi_hash(item);
 
-	ch = sunrpc_cache_lookup(cd, &item->h, hash);
+	ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash);
 	if (ch)
 		return container_of(ch, struct rsi, h);
 	else
@@ -330,6 +339,7 @@ struct rsc {
 	struct svc_cred		cred;
 	struct gss_svc_seq_data	seqdata;
 	struct gss_ctx		*mechctx;
+	struct rcu_head		rcu_head;
 };
 
 static struct rsc *rsc_update(struct cache_detail *cd, struct rsc *new, struct rsc *old);
@@ -343,12 +353,22 @@ static void rsc_free(struct rsc *rsci)
 	free_svc_cred(&rsci->cred);
 }
 
+static void rsc_free_rcu(struct rcu_head *head)
+{
+	struct rsc *rsci = container_of(head, struct rsc, rcu_head);
+
+	kfree(rsci->handle.data);
+	kfree(rsci);
+}
+
 static void rsc_put(struct kref *ref)
 {
 	struct rsc *rsci = container_of(ref, struct rsc, h.ref);
 
-	rsc_free(rsci);
-	kfree(rsci);
+	if (rsci->mechctx)
+		gss_delete_sec_context(&rsci->mechctx);
+	free_svc_cred(&rsci->cred);
+	call_rcu(&rsci->rcu_head, rsc_free_rcu);
 }
 
 static inline int
@@ -542,7 +562,7 @@ static struct rsc *rsc_lookup(struct cache_detail *cd, struct rsc *item)
 	struct cache_head *ch;
 	int hash = rsc_hash(item);
 
-	ch = sunrpc_cache_lookup(cd, &item->h, hash);
+	ch = sunrpc_cache_lookup_rcu(cd, &item->h, hash);
 	if (ch)
 		return container_of(ch, struct rsc, h);
 	else
@@ -1764,14 +1784,21 @@ out_err:
 }
 
 static void
-svcauth_gss_domain_release(struct auth_domain *dom)
+svcauth_gss_domain_release_rcu(struct rcu_head *head)
 {
+	struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head);
 	struct gss_domain *gd = container_of(dom, struct gss_domain, h);
 
 	kfree(dom->name);
 	kfree(gd);
 }
 
+static void
+svcauth_gss_domain_release(struct auth_domain *dom)
+{
+	call_rcu(&dom->rcu_head, svcauth_gss_domain_release_rcu);
+}
+
 static struct auth_ops svcauthops_gss = {
 	.name		= "rpcsec_gss",
 	.owner		= THIS_MODULE,
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 109fbe591e7b..f96345b1180e 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -54,28 +54,33 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail)
 	h->last_refresh = now;
 }
 
-struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
-				       struct cache_head *key, int hash)
+static struct cache_head *sunrpc_cache_find_rcu(struct cache_detail *detail,
+						struct cache_head *key,
+						int hash)
 {
-	struct cache_head *new = NULL, *freeme = NULL, *tmp = NULL;
-	struct hlist_head *head;
-
-	head = &detail->hash_table[hash];
-
-	read_lock(&detail->hash_lock);
+	struct hlist_head *head = &detail->hash_table[hash];
+	struct cache_head *tmp;
 
-	hlist_for_each_entry(tmp, head, cache_list) {
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp, head, cache_list) {
 		if (detail->match(tmp, key)) {
 			if (cache_is_expired(detail, tmp))
-				/* This entry is expired, we will discard it. */
-				break;
-			cache_get(tmp);
-			read_unlock(&detail->hash_lock);
+				continue;
+			tmp = cache_get_rcu(tmp);
+			rcu_read_unlock();
 			return tmp;
 		}
 	}
-	read_unlock(&detail->hash_lock);
-	/* Didn't find anything, insert an empty entry */
+	rcu_read_unlock();
+	return NULL;
+}
+
+static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail,
+						 struct cache_head *key,
+						 int hash)
+{
+	struct cache_head *new, *tmp, *freeme = NULL;
+	struct hlist_head *head = &detail->hash_table[hash];
 
 	new = detail->alloc();
 	if (!new)
@@ -87,35 +92,46 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 	cache_init(new, detail);
 	detail->init(new, key);
 
-	write_lock(&detail->hash_lock);
+	spin_lock(&detail->hash_lock);
 
 	/* check if entry appeared while we slept */
-	hlist_for_each_entry(tmp, head, cache_list) {
+	hlist_for_each_entry_rcu(tmp, head, cache_list) {
 		if (detail->match(tmp, key)) {
 			if (cache_is_expired(detail, tmp)) {
-				hlist_del_init(&tmp->cache_list);
+				hlist_del_init_rcu(&tmp->cache_list);
 				detail->entries --;
 				freeme = tmp;
 				break;
 			}
 			cache_get(tmp);
-			write_unlock(&detail->hash_lock);
+			spin_unlock(&detail->hash_lock);
 			cache_put(new, detail);
 			return tmp;
 		}
 	}
 
-	hlist_add_head(&new->cache_list, head);
+	hlist_add_head_rcu(&new->cache_list, head);
 	detail->entries++;
 	cache_get(new);
-	write_unlock(&detail->hash_lock);
+	spin_unlock(&detail->hash_lock);
 
 	if (freeme)
 		cache_put(freeme, detail);
 	return new;
 }
-EXPORT_SYMBOL_GPL(sunrpc_cache_lookup);
 
+struct cache_head *sunrpc_cache_lookup_rcu(struct cache_detail *detail,
+					   struct cache_head *key, int hash)
+{
+	struct cache_head *ret;
+
+	ret = sunrpc_cache_find_rcu(detail, key, hash);
+	if (ret)
+		return ret;
+	/* Didn't find anything, insert an empty entry */
+	return sunrpc_cache_add_entry(detail, key, hash);
+}
+EXPORT_SYMBOL_GPL(sunrpc_cache_lookup_rcu);
 
 static void cache_dequeue(struct cache_detail *detail, struct cache_head *ch);
 
@@ -151,18 +167,18 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 	struct cache_head *tmp;
 
 	if (!test_bit(CACHE_VALID, &old->flags)) {
-		write_lock(&detail->hash_lock);
+		spin_lock(&detail->hash_lock);
 		if (!test_bit(CACHE_VALID, &old->flags)) {
 			if (test_bit(CACHE_NEGATIVE, &new->flags))
 				set_bit(CACHE_NEGATIVE, &old->flags);
 			else
 				detail->update(old, new);
 			cache_fresh_locked(old, new->expiry_time, detail);
-			write_unlock(&detail->hash_lock);
+			spin_unlock(&detail->hash_lock);
 			cache_fresh_unlocked(old, detail);
 			return old;
 		}
-		write_unlock(&detail->hash_lock);
+		spin_unlock(&detail->hash_lock);
 	}
 	/* We need to insert a new entry */
 	tmp = detail->alloc();
@@ -173,7 +189,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 	cache_init(tmp, detail);
 	detail->init(tmp, old);
 
-	write_lock(&detail->hash_lock);
+	spin_lock(&detail->hash_lock);
 	if (test_bit(CACHE_NEGATIVE, &new->flags))
 		set_bit(CACHE_NEGATIVE, &tmp->flags);
 	else
@@ -183,7 +199,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 	cache_get(tmp);
 	cache_fresh_locked(tmp, new->expiry_time, detail);
 	cache_fresh_locked(old, 0, detail);
-	write_unlock(&detail->hash_lock);
+	spin_unlock(&detail->hash_lock);
 	cache_fresh_unlocked(tmp, detail);
 	cache_fresh_unlocked(old, detail);
 	cache_put(old, detail);
@@ -223,7 +239,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h
 {
 	int rv;
 
-	write_lock(&detail->hash_lock);
+	spin_lock(&detail->hash_lock);
 	rv = cache_is_valid(h);
 	if (rv == -EAGAIN) {
 		set_bit(CACHE_NEGATIVE, &h->flags);
@@ -231,7 +247,7 @@ static int try_to_negate_entry(struct cache_detail *detail, struct cache_head *h
 				   detail);
 		rv = -ENOENT;
 	}
-	write_unlock(&detail->hash_lock);
+	spin_unlock(&detail->hash_lock);
 	cache_fresh_unlocked(h, detail);
 	return rv;
 }
@@ -341,7 +357,7 @@ static struct delayed_work cache_cleaner;
 
 void sunrpc_init_cache_detail(struct cache_detail *cd)
 {
-	rwlock_init(&cd->hash_lock);
+	spin_lock_init(&cd->hash_lock);
 	INIT_LIST_HEAD(&cd->queue);
 	spin_lock(&cache_list_lock);
 	cd->nextcheck = 0;
@@ -361,11 +377,11 @@ void sunrpc_destroy_cache_detail(struct cache_detail *cd)
 {
 	cache_purge(cd);
 	spin_lock(&cache_list_lock);
-	write_lock(&cd->hash_lock);
+	spin_lock(&cd->hash_lock);
 	if (current_detail == cd)
 		current_detail = NULL;
 	list_del_init(&cd->others);
-	write_unlock(&cd->hash_lock);
+	spin_unlock(&cd->hash_lock);
 	spin_unlock(&cache_list_lock);
 	if (list_empty(&cache_list)) {
 		/* module must be being unloaded so its safe to kill the worker */
@@ -422,7 +438,7 @@ static int cache_clean(void)
 		struct hlist_head *head;
 		struct hlist_node *tmp;
 
-		write_lock(&current_detail->hash_lock);
+		spin_lock(&current_detail->hash_lock);
 
 		/* Ok, now to clean this strand */
 
@@ -433,13 +449,13 @@ static int cache_clean(void)
 			if (!cache_is_expired(current_detail, ch))
 				continue;
 
-			hlist_del_init(&ch->cache_list);
+			hlist_del_init_rcu(&ch->cache_list);
 			current_detail->entries--;
 			rv = 1;
 			break;
 		}
 
-		write_unlock(&current_detail->hash_lock);
+		spin_unlock(&current_detail->hash_lock);
 		d = current_detail;
 		if (!ch)
 			current_index ++;
@@ -494,9 +510,9 @@ void cache_purge(struct cache_detail *detail)
 	struct hlist_node *tmp = NULL;
 	int i = 0;
 
-	write_lock(&detail->hash_lock);
+	spin_lock(&detail->hash_lock);
 	if (!detail->entries) {
-		write_unlock(&detail->hash_lock);
+		spin_unlock(&detail->hash_lock);
 		return;
 	}
 
@@ -504,17 +520,17 @@ void cache_purge(struct cache_detail *detail)
 	for (i = 0; i < detail->hash_size; i++) {
 		head = &detail->hash_table[i];
 		hlist_for_each_entry_safe(ch, tmp, head, cache_list) {
-			hlist_del_init(&ch->cache_list);
+			hlist_del_init_rcu(&ch->cache_list);
 			detail->entries--;
 
 			set_bit(CACHE_CLEANED, &ch->flags);
-			write_unlock(&detail->hash_lock);
+			spin_unlock(&detail->hash_lock);
 			cache_fresh_unlocked(ch, detail);
 			cache_put(ch, detail);
-			write_lock(&detail->hash_lock);
+			spin_lock(&detail->hash_lock);
 		}
 	}
-	write_unlock(&detail->hash_lock);
+	spin_unlock(&detail->hash_lock);
 }
 EXPORT_SYMBOL_GPL(cache_purge);
 
@@ -1289,21 +1305,19 @@ EXPORT_SYMBOL_GPL(qword_get);
  * get a header, then pass each real item in the cache
  */
 
-void *cache_seq_start(struct seq_file *m, loff_t *pos)
-	__acquires(cd->hash_lock)
+static void *__cache_seq_start(struct seq_file *m, loff_t *pos)
 {
 	loff_t n = *pos;
 	unsigned int hash, entry;
 	struct cache_head *ch;
 	struct cache_detail *cd = m->private;
 
-	read_lock(&cd->hash_lock);
 	if (!n--)
 		return SEQ_START_TOKEN;
 	hash = n >> 32;
 	entry = n & ((1LL<<32) - 1);
 
-	hlist_for_each_entry(ch, &cd->hash_table[hash], cache_list)
+	hlist_for_each_entry_rcu(ch, &cd->hash_table[hash], cache_list)
 		if (!entry--)
 			return ch;
 	n &= ~((1LL<<32) - 1);
@@ -1315,12 +1329,12 @@ void *cache_seq_start(struct seq_file *m, loff_t *pos)
 	if (hash >= cd->hash_size)
 		return NULL;
 	*pos = n+1;
-	return hlist_entry_safe(cd->hash_table[hash].first,
+	return hlist_entry_safe(rcu_dereference_raw(
+				hlist_first_rcu(&cd->hash_table[hash])),
 				struct cache_head, cache_list);
 }
-EXPORT_SYMBOL_GPL(cache_seq_start);
 
-void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
+static void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	struct cache_head *ch = p;
 	int hash = (*pos >> 32);
@@ -1333,7 +1347,8 @@ void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
 		*pos += 1LL<<32;
 	} else {
 		++*pos;
-		return hlist_entry_safe(ch->cache_list.next,
+		return hlist_entry_safe(rcu_dereference_raw(
+					hlist_next_rcu(&ch->cache_list)),
 					struct cache_head, cache_list);
 	}
 	*pos &= ~((1LL<<32) - 1);
@@ -1345,18 +1360,32 @@ void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
 	if (hash >= cd->hash_size)
 		return NULL;
 	++*pos;
-	return hlist_entry_safe(cd->hash_table[hash].first,
+	return hlist_entry_safe(rcu_dereference_raw(
+				hlist_first_rcu(&cd->hash_table[hash])),
 				struct cache_head, cache_list);
 }
 EXPORT_SYMBOL_GPL(cache_seq_next);
 
-void cache_seq_stop(struct seq_file *m, void *p)
-	__releases(cd->hash_lock)
+void *cache_seq_start_rcu(struct seq_file *m, loff_t *pos)
+	__acquires(RCU)
 {
-	struct cache_detail *cd = m->private;
-	read_unlock(&cd->hash_lock);
+	rcu_read_lock();
+	return __cache_seq_start(m, pos);
+}
+EXPORT_SYMBOL_GPL(cache_seq_start_rcu);
+
+void *cache_seq_next_rcu(struct seq_file *file, void *p, loff_t *pos)
+{
+	return cache_seq_next(file, p, pos);
+}
+EXPORT_SYMBOL_GPL(cache_seq_next_rcu);
+
+void cache_seq_stop_rcu(struct seq_file *m, void *p)
+	__releases(RCU)
+{
+	rcu_read_unlock();
 }
-EXPORT_SYMBOL_GPL(cache_seq_stop);
+EXPORT_SYMBOL_GPL(cache_seq_stop_rcu);
 
 static int c_show(struct seq_file *m, void *p)
 {
@@ -1384,9 +1413,9 @@ static int c_show(struct seq_file *m, void *p)
 }
 
 static const struct seq_operations cache_content_op = {
-	.start	= cache_seq_start,
-	.next	= cache_seq_next,
-	.stop	= cache_seq_stop,
+	.start	= cache_seq_start_rcu,
+	.next	= cache_seq_next_rcu,
+	.stop	= cache_seq_stop_rcu,
 	.show	= c_show,
 };
 
@@ -1844,13 +1873,13 @@ EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs);
 
 void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h)
 {
-	write_lock(&cd->hash_lock);
+	spin_lock(&cd->hash_lock);
 	if (!hlist_unhashed(&h->cache_list)){
-		hlist_del_init(&h->cache_list);
+		hlist_del_init_rcu(&h->cache_list);
 		cd->entries--;
-		write_unlock(&cd->hash_lock);
+		spin_unlock(&cd->hash_lock);
 		cache_put(h, cd);
 	} else
-		write_unlock(&cd->hash_lock);
+		spin_unlock(&cd->hash_lock);
 }
 EXPORT_SYMBOL_GPL(sunrpc_cache_unhash);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 87533fbb96cf..51d36230b6e3 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -987,7 +987,7 @@ static void call_xpt_users(struct svc_xprt *xprt)
 	spin_lock(&xprt->xpt_lock);
 	while (!list_empty(&xprt->xpt_users)) {
 		u = list_first_entry(&xprt->xpt_users, struct svc_xpt_user, list);
-		list_del(&u->list);
+		list_del_init(&u->list);
 		u->callback(u);
 	}
 	spin_unlock(&xprt->xpt_lock);
diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c
index bb8db3cb8032..775b8c94265b 100644
--- a/net/sunrpc/svcauth.c
+++ b/net/sunrpc/svcauth.c
@@ -27,12 +27,32 @@
 extern struct auth_ops svcauth_null;
 extern struct auth_ops svcauth_unix;
 
-static DEFINE_SPINLOCK(authtab_lock);
-static struct auth_ops	*authtab[RPC_AUTH_MAXFLAVOR] = {
-	[0] = &svcauth_null,
-	[1] = &svcauth_unix,
+static struct auth_ops __rcu *authtab[RPC_AUTH_MAXFLAVOR] = {
+	[RPC_AUTH_NULL] = (struct auth_ops __force __rcu *)&svcauth_null,
+	[RPC_AUTH_UNIX] = (struct auth_ops __force __rcu *)&svcauth_unix,
 };
 
+static struct auth_ops *
+svc_get_auth_ops(rpc_authflavor_t flavor)
+{
+	struct auth_ops		*aops;
+
+	if (flavor >= RPC_AUTH_MAXFLAVOR)
+		return NULL;
+	rcu_read_lock();
+	aops = rcu_dereference(authtab[flavor]);
+	if (aops != NULL && !try_module_get(aops->owner))
+		aops = NULL;
+	rcu_read_unlock();
+	return aops;
+}
+
+static void
+svc_put_auth_ops(struct auth_ops *aops)
+{
+	module_put(aops->owner);
+}
+
 int
 svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
 {
@@ -45,14 +65,11 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
 
 	dprintk("svc: svc_authenticate (%d)\n", flavor);
 
-	spin_lock(&authtab_lock);
-	if (flavor >= RPC_AUTH_MAXFLAVOR || !(aops = authtab[flavor]) ||
-	    !try_module_get(aops->owner)) {
-		spin_unlock(&authtab_lock);
+	aops = svc_get_auth_ops(flavor);
+	if (aops == NULL) {
 		*authp = rpc_autherr_badcred;
 		return SVC_DENIED;
 	}
-	spin_unlock(&authtab_lock);
 
 	rqstp->rq_auth_slack = 0;
 	init_svc_cred(&rqstp->rq_cred);
@@ -82,7 +99,7 @@ int svc_authorise(struct svc_rqst *rqstp)
 
 	if (aops) {
 		rv = aops->release(rqstp);
-		module_put(aops->owner);
+		svc_put_auth_ops(aops);
 	}
 	return rv;
 }
@@ -90,13 +107,14 @@ int svc_authorise(struct svc_rqst *rqstp)
 int
 svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops)
 {
+	struct auth_ops *old;
 	int rv = -EINVAL;
-	spin_lock(&authtab_lock);
-	if (flavor < RPC_AUTH_MAXFLAVOR && authtab[flavor] == NULL) {
-		authtab[flavor] = aops;
-		rv = 0;
+
+	if (flavor < RPC_AUTH_MAXFLAVOR) {
+		old = cmpxchg((struct auth_ops ** __force)&authtab[flavor], NULL, aops);
+		if (old == NULL || old == aops)
+			rv = 0;
 	}
-	spin_unlock(&authtab_lock);
 	return rv;
 }
 EXPORT_SYMBOL_GPL(svc_auth_register);
@@ -104,10 +122,8 @@ EXPORT_SYMBOL_GPL(svc_auth_register);
 void
 svc_auth_unregister(rpc_authflavor_t flavor)
 {
-	spin_lock(&authtab_lock);
 	if (flavor < RPC_AUTH_MAXFLAVOR)
-		authtab[flavor] = NULL;
-	spin_unlock(&authtab_lock);
+		rcu_assign_pointer(authtab[flavor], NULL);
 }
 EXPORT_SYMBOL_GPL(svc_auth_unregister);
 
@@ -127,10 +143,11 @@ static struct hlist_head	auth_domain_table[DN_HASHMAX];
 static DEFINE_SPINLOCK(auth_domain_lock);
 
 static void auth_domain_release(struct kref *kref)
+	__releases(&auth_domain_lock)
 {
 	struct auth_domain *dom = container_of(kref, struct auth_domain, ref);
 
-	hlist_del(&dom->hash);
+	hlist_del_rcu(&dom->hash);
 	dom->flavour->domain_release(dom);
 	spin_unlock(&auth_domain_lock);
 }
@@ -159,7 +176,7 @@ auth_domain_lookup(char *name, struct auth_domain *new)
 		}
 	}
 	if (new)
-		hlist_add_head(&new->hash, head);
+		hlist_add_head_rcu(&new->hash, head);
 	spin_unlock(&auth_domain_lock);
 	return new;
 }
@@ -167,6 +184,21 @@ EXPORT_SYMBOL_GPL(auth_domain_lookup);
 
 struct auth_domain *auth_domain_find(char *name)
 {
-	return auth_domain_lookup(name, NULL);
+	struct auth_domain *hp;
+	struct hlist_head *head;
+
+	head = &auth_domain_table[hash_str(name, DN_HASHBITS)];
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(hp, head, hash) {
+		if (strcmp(hp->name, name)==0) {
+			if (!kref_get_unless_zero(&hp->ref))
+				hp = NULL;
+			rcu_read_unlock();
+			return hp;
+		}
+	}
+	rcu_read_unlock();
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(auth_domain_find);
diff --git a/net/sunrpc/svcauth_unix.c b/net/sunrpc/svcauth_unix.c
index af7f28fb8102..fb9041b92f72 100644
--- a/net/sunrpc/svcauth_unix.c
+++ b/net/sunrpc/svcauth_unix.c
@@ -37,20 +37,26 @@ struct unix_domain {
 extern struct auth_ops svcauth_null;
 extern struct auth_ops svcauth_unix;
 
-static void svcauth_unix_domain_release(struct auth_domain *dom)
+static void svcauth_unix_domain_release_rcu(struct rcu_head *head)
 {
+	struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head);
 	struct unix_domain *ud = container_of(dom, struct unix_domain, h);
 
 	kfree(dom->name);
 	kfree(ud);
 }
 
+static void svcauth_unix_domain_release(struct auth_domain *dom)
+{
+	call_rcu(&dom->rcu_head, svcauth_unix_domain_release_rcu);
+}
+
 struct auth_domain *unix_domain_find(char *name)
 {
 	struct auth_domain *rv;
 	struct unix_domain *new = NULL;
 
-	rv = auth_domain_lookup(name, NULL);
+	rv = auth_domain_find(name);
 	while(1) {
 		if (rv) {
 			if (new && rv != &new->h)
@@ -91,6 +97,7 @@ struct ip_map {
 	char			m_class[8]; /* e.g. "nfsd" */
 	struct in6_addr		m_addr;
 	struct unix_domain	*m_client;
+	struct rcu_head		m_rcu;
 };
 
 static void ip_map_put(struct kref *kref)
@@ -101,7 +108,7 @@ static void ip_map_put(struct kref *kref)
 	if (test_bit(CACHE_VALID, &item->flags) &&
 	    !test_bit(CACHE_NEGATIVE, &item->flags))
 		auth_domain_put(&im->m_client->h);
-	kfree(im);
+	kfree_rcu(im, m_rcu);
 }
 
 static inline int hash_ip6(const struct in6_addr *ip)
@@ -280,9 +287,9 @@ static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class,
 
 	strcpy(ip.m_class, class);
 	ip.m_addr = *addr;
-	ch = sunrpc_cache_lookup(cd, &ip.h,
-				 hash_str(class, IP_HASHBITS) ^
-				 hash_ip6(addr));
+	ch = sunrpc_cache_lookup_rcu(cd, &ip.h,
+				     hash_str(class, IP_HASHBITS) ^
+				     hash_ip6(addr));
 
 	if (ch)
 		return container_of(ch, struct ip_map, h);
@@ -412,6 +419,7 @@ struct unix_gid {
 	struct cache_head	h;
 	kuid_t			uid;
 	struct group_info	*gi;
+	struct rcu_head		rcu;
 };
 
 static int unix_gid_hash(kuid_t uid)
@@ -426,7 +434,7 @@ static void unix_gid_put(struct kref *kref)
 	if (test_bit(CACHE_VALID, &item->flags) &&
 	    !test_bit(CACHE_NEGATIVE, &item->flags))
 		put_group_info(ug->gi);
-	kfree(ug);
+	kfree_rcu(ug, rcu);
 }
 
 static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew)
@@ -619,7 +627,7 @@ static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, kuid_t uid)
 	struct cache_head *ch;
 
 	ug.uid = uid;
-	ch = sunrpc_cache_lookup(cd, &ug.h, unix_gid_hash(uid));
+	ch = sunrpc_cache_lookup_rcu(cd, &ug.h, unix_gid_hash(uid));
 	if (ch)
 		return container_of(ch, struct unix_gid, h);
 	else
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index db8bb6b3a2b0..986f3ed7d1a2 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -325,59 +325,34 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 /*
  * Generic recvfrom routine.
  */
-static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr,
-			int buflen)
+static ssize_t svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov,
+			    unsigned int nr, size_t buflen, unsigned int base)
 {
 	struct svc_sock *svsk =
 		container_of(rqstp->rq_xprt, struct svc_sock, sk_xprt);
-	struct msghdr msg = {
-		.msg_flags	= MSG_DONTWAIT,
-	};
-	int len;
+	struct msghdr msg = { NULL };
+	ssize_t len;
 
 	rqstp->rq_xprt_hlen = 0;
 
 	clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nr, buflen);
-	len = sock_recvmsg(svsk->sk_sock, &msg, msg.msg_flags);
+	iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen);
+	if (base != 0) {
+		iov_iter_advance(&msg.msg_iter, base);
+		buflen -= base;
+	}
+	len = sock_recvmsg(svsk->sk_sock, &msg, MSG_DONTWAIT);
 	/* If we read a full record, then assume there may be more
 	 * data to read (stream based sockets only!)
 	 */
 	if (len == buflen)
 		set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 
-	dprintk("svc: socket %p recvfrom(%p, %zu) = %d\n",
+	dprintk("svc: socket %p recvfrom(%p, %zu) = %zd\n",
 		svsk, iov[0].iov_base, iov[0].iov_len, len);
 	return len;
 }
 
-static int svc_partial_recvfrom(struct svc_rqst *rqstp,
-				struct kvec *iov, int nr,
-				int buflen, unsigned int base)
-{
-	size_t save_iovlen;
-	void *save_iovbase;
-	unsigned int i;
-	int ret;
-
-	if (base == 0)
-		return svc_recvfrom(rqstp, iov, nr, buflen);
-
-	for (i = 0; i < nr; i++) {
-		if (iov[i].iov_len > base)
-			break;
-		base -= iov[i].iov_len;
-	}
-	save_iovlen = iov[i].iov_len;
-	save_iovbase = iov[i].iov_base;
-	iov[i].iov_len -= base;
-	iov[i].iov_base += base;
-	ret = svc_recvfrom(rqstp, &iov[i], nr - i, buflen);
-	iov[i].iov_len = save_iovlen;
-	iov[i].iov_base = save_iovbase;
-	return ret;
-}
-
 /*
  * Set socket snd and rcv buffer lengths
  */
@@ -962,7 +937,8 @@ static int svc_tcp_recv_record(struct svc_sock *svsk, struct svc_rqst *rqstp)
 		want = sizeof(rpc_fraghdr) - svsk->sk_tcplen;
 		iov.iov_base = ((char *) &svsk->sk_reclen) + svsk->sk_tcplen;
 		iov.iov_len  = want;
-		if ((len = svc_recvfrom(rqstp, &iov, 1, want)) < 0)
+		len = svc_recvfrom(rqstp, &iov, 1, want, 0);
+		if (len < 0)
 			goto error;
 		svsk->sk_tcplen += len;
 
@@ -1088,14 +1064,13 @@ static int svc_tcp_recvfrom(struct svc_rqst *rqstp)
 
 	vec = rqstp->rq_vec;
 
-	pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0],
-						svsk->sk_datalen + want);
+	pnum = copy_pages_to_kvecs(&vec[0], &rqstp->rq_pages[0], base + want);
 
 	rqstp->rq_respages = &rqstp->rq_pages[pnum];
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
 	/* Now receive data */
-	len = svc_partial_recvfrom(rqstp, vec, pnum, want, base);
+	len = svc_recvfrom(rqstp, vec, pnum, base + want, base);
 	if (len >= 0) {
 		svsk->sk_tcplen += len;
 		svsk->sk_datalen += len;
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 2bbb8d38d2bf..f302c6eb8779 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -546,7 +546,7 @@ EXPORT_SYMBOL_GPL(xdr_commit_encode);
 static __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr,
 		size_t nbytes)
 {
-	static __be32 *p;
+	__be32 *p;
 	int space_left;
 	int frag1bytes, frag2bytes;
 
@@ -673,11 +673,10 @@ void xdr_truncate_encode(struct xdr_stream *xdr, size_t len)
 		WARN_ON_ONCE(xdr->iov);
 		return;
 	}
-	if (fraglen) {
+	if (fraglen)
 		xdr->end = head->iov_base + head->iov_len;
-		xdr->page_ptr--;
-	}
 	/* (otherwise assume xdr->end is already set) */
+	xdr->page_ptr--;
 	head->iov_len = len;
 	buf->len = len;
 	xdr->p = head->iov_base + head->iov_len;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
index d3a1a237cee6..f3c147d70286 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c
@@ -5,8 +5,6 @@
  * Support for backward direction RPCs on RPC/RDMA (server-side).
  */
 
-#include <linux/module.h>
-
 #include <linux/sunrpc/svc_rdma.h>
 
 #include "xprt_rdma.h"
@@ -32,7 +30,6 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
 	struct rpcrdma_xprt *r_xprt = rpcx_to_rdmax(xprt);
 	struct kvec *dst, *src = &rcvbuf->head[0];
 	struct rpc_rqst *req;
-	unsigned long cwnd;
 	u32 credits;
 	size_t len;
 	__be32 xid;
@@ -66,6 +63,8 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
 	if (dst->iov_len < len)
 		goto out_unlock;
 	memcpy(dst->iov_base, p, len);
+	xprt_pin_rqst(req);
+	spin_unlock(&xprt->queue_lock);
 
 	credits = be32_to_cpup(rdma_resp + 2);
 	if (credits == 0)
@@ -74,15 +73,13 @@ int svc_rdma_handle_bc_reply(struct rpc_xprt *xprt, __be32 *rdma_resp,
 		credits = r_xprt->rx_buf.rb_bc_max_requests;
 
 	spin_lock_bh(&xprt->transport_lock);
-	cwnd = xprt->cwnd;
 	xprt->cwnd = credits << RPC_CWNDSHIFT;
-	if (xprt->cwnd > cwnd)
-		xprt_release_rqst_cong(req->rq_task);
 	spin_unlock_bh(&xprt->transport_lock);
 
-
+	spin_lock(&xprt->queue_lock);
 	ret = 0;
 	xprt_complete_rqst(req->rq_task, rcvbuf->len);
+	xprt_unpin_rqst(req);
 	rcvbuf->len = 0;
 
 out_unlock:
@@ -251,7 +248,6 @@ xprt_rdma_bc_put(struct rpc_xprt *xprt)
 	dprintk("svcrdma: %s: xprt %p\n", __func__, xprt);
 
 	xprt_free(xprt);
-	module_put(THIS_MODULE);
 }
 
 static const struct rpc_xprt_ops xprt_rdma_bc_procs = {
@@ -323,20 +319,9 @@ xprt_setup_rdma_bc(struct xprt_create *args)
 	args->bc_xprt->xpt_bc_xprt = xprt;
 	xprt->bc_xprt = args->bc_xprt;
 
-	if (!try_module_get(THIS_MODULE))
-		goto out_fail;
-
 	/* Final put for backchannel xprt is in __svc_rdma_free */
 	xprt_get(xprt);
 	return xprt;
-
-out_fail:
-	xprt_rdma_free_addresses(xprt);
-	args->bc_xprt->xpt_bc_xprt = NULL;
-	args->bc_xprt->xpt_bc_xps = NULL;
-	xprt_put(xprt);
-	xprt_free(xprt);
-	return ERR_PTR(-EINVAL);
 }
 
 struct xprt_class xprt_rdma_bc = {
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 2848cafd4a17..2f7ec8912f49 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -475,10 +475,12 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt)
 
 	/* Qualify the transport resource defaults with the
 	 * capabilities of this particular device */
-	newxprt->sc_max_send_sges = dev->attrs.max_send_sge;
-	/* transport hdr, head iovec, one page list entry, tail iovec */
-	if (newxprt->sc_max_send_sges < 4) {
-		pr_err("svcrdma: too few Send SGEs available (%d)\n",
+	/* Transport header, head iovec, tail iovec */
+	newxprt->sc_max_send_sges = 3;
+	/* Add one SGE per page list entry */
+	newxprt->sc_max_send_sges += svcrdma_max_req_size / PAGE_SIZE;
+	if (newxprt->sc_max_send_sges > dev->attrs.max_send_sge) {
+		pr_err("svcrdma: too few Send SGEs available (%d needed)\n",
 		       newxprt->sc_max_send_sges);
 		goto errout;
 	}
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 1b51e04d3566..ae77c71c1f64 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -361,7 +361,7 @@ static ssize_t
 xs_read_kvec(struct socket *sock, struct msghdr *msg, int flags,
 		struct kvec *kvec, size_t count, size_t seek)
 {
-	iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, kvec, 1, count);
+	iov_iter_kvec(&msg->msg_iter, READ, kvec, 1, count);
 	return xs_sock_recvmsg(sock, msg, flags, seek);
 }
 
@@ -370,7 +370,7 @@ xs_read_bvec(struct socket *sock, struct msghdr *msg, int flags,
 		struct bio_vec *bvec, unsigned long nr, size_t count,
 		size_t seek)
 {
-	iov_iter_bvec(&msg->msg_iter, READ | ITER_BVEC, bvec, nr, count);
+	iov_iter_bvec(&msg->msg_iter, READ, bvec, nr, count);
 	return xs_sock_recvmsg(sock, msg, flags, seek);
 }
 
diff --git a/net/tipc/discover.c b/net/tipc/discover.c
index 2830709957bd..c138d68e8a69 100644
--- a/net/tipc/discover.c
+++ b/net/tipc/discover.c
@@ -166,7 +166,8 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d,
 
 	/* Apply trial address if we just left trial period */
 	if (!trial && !self) {
-		tipc_net_finalize(net, tn->trial_addr);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
 	}
 
@@ -300,14 +301,12 @@ static void tipc_disc_timeout(struct timer_list *t)
 		goto exit;
 	}
 
-	/* Trial period over ? */
-	if (!time_before(jiffies, tn->addr_trial_end)) {
-		/* Did we just leave it ? */
-		if (!tipc_own_addr(net))
-			tipc_net_finalize(net, tn->trial_addr);
-
-		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
-		msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net));
+	/* Did we just leave trial period ? */
+	if (!time_before(jiffies, tn->addr_trial_end) && !tipc_own_addr(net)) {
+		mod_timer(&d->timer, jiffies + TIPC_DISC_INIT);
+		spin_unlock_bh(&d->lock);
+		tipc_sched_net_finalize(net, tn->trial_addr);
+		return;
 	}
 
 	/* Adjust timeout interval according to discovery phase */
@@ -319,6 +318,8 @@ static void tipc_disc_timeout(struct timer_list *t)
 			d->timer_intv = TIPC_DISC_SLOW;
 		else if (!d->num_nodes && d->timer_intv > TIPC_DISC_FAST)
 			d->timer_intv = TIPC_DISC_FAST;
+		msg_set_type(buf_msg(d->skb), DSC_REQ_MSG);
+		msg_set_prevnode(buf_msg(d->skb), tn->trial_addr);
 	}
 
 	mod_timer(&d->timer, jiffies + d->timer_intv);
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 201c3b5bc96b..836727e363c4 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1594,14 +1594,17 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 		if (in_range(peers_prio, l->priority + 1, TIPC_MAX_LINK_PRI))
 			l->priority = peers_prio;
 
-		/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
-		if (msg_peer_stopping(hdr))
+		/* If peer is going down we want full re-establish cycle */
+		if (msg_peer_stopping(hdr)) {
 			rc = tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
-		else if ((mtyp == RESET_MSG) || !link_is_up(l))
+			break;
+		}
+		/* ACTIVATE_MSG serves as PEER_RESET if link is already down */
+		if (mtyp == RESET_MSG || !link_is_up(l))
 			rc = tipc_link_fsm_evt(l, LINK_PEER_RESET_EVT);
 
 		/* ACTIVATE_MSG takes up link if it was already locally reset */
-		if ((mtyp == ACTIVATE_MSG) && (l->state == LINK_ESTABLISHING))
+		if (mtyp == ACTIVATE_MSG && l->state == LINK_ESTABLISHING)
 			rc = TIPC_LINK_UP_EVT;
 
 		l->peer_session = msg_session(hdr);
diff --git a/net/tipc/net.c b/net/tipc/net.c
index 62199cf5a56c..f076edb74338 100644
--- a/net/tipc/net.c
+++ b/net/tipc/net.c
@@ -104,6 +104,14 @@
  *     - 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)
 {
 	if (tipc_own_id(net)) {
@@ -119,17 +127,38 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr)
 	return 0;
 }
 
-void tipc_net_finalize(struct net *net, u32 addr)
+static void tipc_net_finalize(struct net *net, u32 addr)
 {
 	struct tipc_net *tn = tipc_net(net);
 
-	if (!cmpxchg(&tn->node_addr, 0, addr)) {
-		tipc_set_node_addr(net, addr);
-		tipc_named_reinit(net);
-		tipc_sk_reinit(net);
-		tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
-				     TIPC_CLUSTER_SCOPE, 0, addr);
-	}
+	if (cmpxchg(&tn->node_addr, 0, addr))
+		return;
+	tipc_set_node_addr(net, addr);
+	tipc_named_reinit(net);
+	tipc_sk_reinit(net);
+	tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr,
+			     TIPC_CLUSTER_SCOPE, 0, addr);
+}
+
+static 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);
+
+	if (!fwork)
+		return;
+	INIT_WORK(&fwork->work, tipc_net_finalize_work);
+	fwork->net = net;
+	fwork->addr = addr;
+	schedule_work(&fwork->work);
 }
 
 void tipc_net_stop(struct net *net)
diff --git a/net/tipc/net.h b/net/tipc/net.h
index 09ad02b50bb1..b7f2e364eb99 100644
--- a/net/tipc/net.h
+++ b/net/tipc/net.h
@@ -42,7 +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(struct net *net, u32 addr);
+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);
 int tipc_nl_net_set(struct sk_buff *skb, struct genl_info *info);
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 2afc4f8c37a7..488019766433 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -584,12 +584,15 @@ static void  tipc_node_clear_links(struct tipc_node *node)
 /* tipc_node_cleanup - delete nodes that does not
  * have active links for NODE_CLEANUP_AFTER time
  */
-static int tipc_node_cleanup(struct tipc_node *peer)
+static bool tipc_node_cleanup(struct tipc_node *peer)
 {
 	struct tipc_net *tn = tipc_net(peer->net);
 	bool deleted = false;
 
-	spin_lock_bh(&tn->node_list_lock);
+	/* If lock held by tipc_node_stop() the node will be deleted anyway */
+	if (!spin_trylock_bh(&tn->node_list_lock))
+		return false;
+
 	tipc_node_write_lock(peer);
 
 	if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) {
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 636e6131769d..b57b1be7252b 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -1555,16 +1555,17 @@ static void tipc_sk_set_orig_addr(struct msghdr *m, struct sk_buff *skb)
 /**
  * tipc_sk_anc_data_recv - optionally capture ancillary data for received message
  * @m: descriptor for message info
- * @msg: received message header
+ * @skb: received message buffer
  * @tsk: TIPC port associated with message
  *
  * Note: Ancillary data is not captured if not requested by receiver.
  *
  * Returns 0 if successful, otherwise errno
  */
-static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
+static int tipc_sk_anc_data_recv(struct msghdr *m, struct sk_buff *skb,
 				 struct tipc_sock *tsk)
 {
+	struct tipc_msg *msg;
 	u32 anc_data[3];
 	u32 err;
 	u32 dest_type;
@@ -1573,6 +1574,7 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 
 	if (likely(m->msg_controllen == 0))
 		return 0;
+	msg = buf_msg(skb);
 
 	/* Optionally capture errored message object(s) */
 	err = msg ? msg_errcode(msg) : 0;
@@ -1583,6 +1585,9 @@ static int tipc_sk_anc_data_recv(struct msghdr *m, struct tipc_msg *msg,
 		if (res)
 			return res;
 		if (anc_data[1]) {
+			if (skb_linearize(skb))
+				return -ENOMEM;
+			msg = buf_msg(skb);
 			res = put_cmsg(m, SOL_TIPC, TIPC_RETDATA, anc_data[1],
 				       msg_data(msg));
 			if (res)
@@ -1744,9 +1749,10 @@ static int tipc_recvmsg(struct socket *sock, struct msghdr *m,
 
 	/* Collect msg meta data, including error code and rejected data */
 	tipc_sk_set_orig_addr(m, skb);
-	rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+	rc = tipc_sk_anc_data_recv(m, skb, tsk);
 	if (unlikely(rc))
 		goto exit;
+	hdr = buf_msg(skb);
 
 	/* Capture data if non-error msg, otherwise just set return value */
 	if (likely(!err)) {
@@ -1856,9 +1862,10 @@ static int tipc_recvstream(struct socket *sock, struct msghdr *m,
 		/* Collect msg meta data, incl. error code and rejected data */
 		if (!copied) {
 			tipc_sk_set_orig_addr(m, skb);
-			rc = tipc_sk_anc_data_recv(m, hdr, tsk);
+			rc = tipc_sk_anc_data_recv(m, skb, tsk);
 			if (rc)
 				break;
+			hdr = buf_msg(skb);
 		}
 
 		/* Copy data if msg ok, otherwise return error/partial data */
diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c
index 4bdea0057171..efb16f69bd2c 100644
--- a/net/tipc/topsrv.c
+++ b/net/tipc/topsrv.c
@@ -394,7 +394,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con)
 	iov.iov_base = &s;
 	iov.iov_len = sizeof(s);
 	msg.msg_name = NULL;
-	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len);
+	iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, iov.iov_len);
 	ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT);
 	if (ret == -EWOULDBLOCK)
 		return -EWOULDBLOCK;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 276edbc04f38..d753e362d2d9 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -489,7 +489,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page,
 
 	iov.iov_base = kaddr + offset;
 	iov.iov_len = size;
-	iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, &iov, 1, size);
+	iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size);
 	rc = tls_push_data(sk, &msg_iter, size,
 			   flags, TLS_RECORD_TYPE_DATA);
 	kunmap(page);
@@ -538,7 +538,7 @@ static int tls_device_push_pending_record(struct sock *sk, int flags)
 {
 	struct iov_iter	msg_iter;
 
-	iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, NULL, 0, 0);
+	iov_iter_kvec(&msg_iter, WRITE, NULL, 0, 0);
 	return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA);
 }
 
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 5cd88ba8acd1..7b1af8b59cd2 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -799,7 +799,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send);
 	bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC;
 	unsigned char record_type = TLS_RECORD_TYPE_DATA;
-	bool is_kvec = msg->msg_iter.type & ITER_KVEC;
+	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	bool eor = !(msg->msg_flags & MSG_MORE);
 	size_t try_to_copy, copied = 0;
 	struct sk_msg *msg_pl, *msg_en;
@@ -1457,7 +1457,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	bool cmsg = false;
 	int target, err = 0;
 	long timeo;
-	bool is_kvec = msg->msg_iter.type & ITER_KVEC;
+	bool is_kvec = iov_iter_is_kvec(&msg->msg_iter);
 	int num_async = 0;
 
 	flags |= nonblock;
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 4a9ee2d83158..140270a13d54 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -8,7 +8,6 @@ config XFRM
 
 config XFRM_OFFLOAD
        bool
-       depends on XFRM
 
 config XFRM_ALGO
 	tristate
diff --git a/net/xfrm/xfrm_hash.c b/net/xfrm/xfrm_hash.c
index 2ad33ce1ea17..eca8d84d99bf 100644
--- a/net/xfrm/xfrm_hash.c
+++ b/net/xfrm/xfrm_hash.c
@@ -6,7 +6,7 @@
 
 #include <linux/kernel.h>
 #include <linux/mm.h>
-#include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/xfrm.h>
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index b669262682c9..dc4a9f1fb941 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2077,10 +2077,8 @@ int xfrm_user_policy(struct sock *sk, int optname, u8 __user *optval, int optlen
 	struct xfrm_mgr *km;
 	struct xfrm_policy *pol = NULL;
 
-#ifdef CONFIG_COMPAT
 	if (in_compat_syscall())
 		return -EOPNOTSUPP;
-#endif
 
 	if (!optval && !optlen) {
 		xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL);
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index ca7a207b81a9..c9a84e22f5d5 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -2621,10 +2621,8 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	const struct xfrm_link *link;
 	int type, err;
 
-#ifdef CONFIG_COMPAT
 	if (in_compat_syscall())
 		return -EOPNOTSUPP;
-#endif
 
 	type = nlh->nlmsg_type;
 	if (type > XFRM_MSG_MAX)