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

To obtain new flag FLOWI_FLAG_KNOWN_NH to fix netfilter's xt_TEE target.

63 files changed, 816 insertions, 796 deletions

diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index add69d0fd99d..65e06abe023f 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -5,7 +5,7 @@
 #include <linux/export.h>
 #include "vlan.h"
 
-bool vlan_do_receive(struct sk_buff **skbp, bool last_handler)
+bool vlan_do_receive(struct sk_buff **skbp)
 {
 	struct sk_buff *skb = *skbp;
 	u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK;
@@ -13,14 +13,8 @@ bool vlan_do_receive(struct sk_buff **skbp, bool last_handler)
 	struct vlan_pcpu_stats *rx_stats;
 
 	vlan_dev = vlan_find_dev(skb->dev, vlan_id);
-	if (!vlan_dev) {
-		/* Only the last call to vlan_do_receive() should change
-		 * pkt_type to PACKET_OTHERHOST
-		 */
-		if (vlan_id && last_handler)
-			skb->pkt_type = PACKET_OTHERHOST;
+	if (!vlan_dev)
 		return false;
-	}
 
 	skb = *skbp = skb_share_check(skb, GFP_ATOMIC);
 	if (unlikely(!skb))
@@ -372,6 +366,13 @@ EXPORT_SYMBOL(vlan_vids_del_by_dev);
 
 bool vlan_uses_dev(const struct net_device *dev)
 {
-	return rtnl_dereference(dev->vlan_info) ? true : false;
+	struct vlan_info *vlan_info;
+
+	ASSERT_RTNL();
+
+	vlan_info = rtnl_dereference(dev->vlan_info);
+	if (!vlan_info)
+		return false;
+	return vlan_info->grp.nr_vlan_devs ? true : false;
 }
 EXPORT_SYMBOL(vlan_uses_dev);
diff --git a/net/9p/client.c b/net/9p/client.c
index 8260f132b32e..34d417670935 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -76,6 +76,20 @@ inline int p9_is_proto_dotu(struct p9_client *clnt)
 }
 EXPORT_SYMBOL(p9_is_proto_dotu);
 
+/*
+ * Some error codes are taken directly from the server replies,
+ * make sure they are valid.
+ */
+static int safe_errno(int err)
+{
+	if ((err > 0) || (err < -MAX_ERRNO)) {
+		p9_debug(P9_DEBUG_ERROR, "Invalid error code %d\n", err);
+		return -EPROTO;
+	}
+	return err;
+}
+
+
 /* Interpret mount option for protocol version */
 static int get_protocol_version(char *s)
 {
@@ -782,7 +796,7 @@ again:
 		return req;
 reterr:
 	p9_free_req(c, req);
-	return ERR_PTR(err);
+	return ERR_PTR(safe_errno(err));
 }
 
 /**
@@ -865,7 +879,7 @@ static struct p9_req_t *p9_client_zc_rpc(struct p9_client *c, int8_t type,
 		return req;
 reterr:
 	p9_free_req(c, req);
-	return ERR_PTR(err);
+	return ERR_PTR(safe_errno(err));
 }
 
 static struct p9_fid *p9_fid_create(struct p9_client *clnt)
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 505f0ce3f10b..02efb25c2957 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -316,8 +316,7 @@ static void p9_read_work(struct work_struct *work)
 						m->rsize - m->rpos);
 	p9_debug(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err);
 	if (err == -EAGAIN) {
-		clear_bit(Rworksched, &m->wsched);
-		return;
+		goto end_clear;
 	}
 
 	if (err <= 0)
@@ -379,19 +378,20 @@ static void p9_read_work(struct work_struct *work)
 		m->req = NULL;
 	}
 
+end_clear:
+	clear_bit(Rworksched, &m->wsched);
+
 	if (!list_empty(&m->req_list)) {
 		if (test_and_clear_bit(Rpending, &m->wsched))
 			n = POLLIN;
 		else
 			n = p9_fd_poll(m->client, NULL);
 
-		if (n & POLLIN) {
+		if ((n & POLLIN) && !test_and_set_bit(Rworksched, &m->wsched)) {
 			p9_debug(P9_DEBUG_TRANS, "sched read work %p\n", m);
 			schedule_work(&m->rq);
-		} else
-			clear_bit(Rworksched, &m->wsched);
-	} else
-		clear_bit(Rworksched, &m->wsched);
+		}
+	}
 
 	return;
 error:
@@ -453,12 +453,13 @@ static void p9_write_work(struct work_struct *work)
 	}
 
 	if (!m->wsize) {
+		spin_lock(&m->client->lock);
 		if (list_empty(&m->unsent_req_list)) {
 			clear_bit(Wworksched, &m->wsched);
+			spin_unlock(&m->client->lock);
 			return;
 		}
 
-		spin_lock(&m->client->lock);
 		req = list_entry(m->unsent_req_list.next, struct p9_req_t,
 			       req_list);
 		req->status = REQ_STATUS_SENT;
@@ -476,10 +477,9 @@ static void p9_write_work(struct work_struct *work)
 	clear_bit(Wpending, &m->wsched);
 	err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos);
 	p9_debug(P9_DEBUG_TRANS, "mux %p sent %d bytes\n", m, err);
-	if (err == -EAGAIN) {
-		clear_bit(Wworksched, &m->wsched);
-		return;
-	}
+	if (err == -EAGAIN)
+		goto end_clear;
+
 
 	if (err < 0)
 		goto error;
@@ -492,19 +492,21 @@ static void p9_write_work(struct work_struct *work)
 	if (m->wpos == m->wsize)
 		m->wpos = m->wsize = 0;
 
-	if (m->wsize == 0 && !list_empty(&m->unsent_req_list)) {
+end_clear:
+	clear_bit(Wworksched, &m->wsched);
+
+	if (m->wsize || !list_empty(&m->unsent_req_list)) {
 		if (test_and_clear_bit(Wpending, &m->wsched))
 			n = POLLOUT;
 		else
 			n = p9_fd_poll(m->client, NULL);
 
-		if (n & POLLOUT) {
+		if ((n & POLLOUT) &&
+		   !test_and_set_bit(Wworksched, &m->wsched)) {
 			p9_debug(P9_DEBUG_TRANS, "sched write work %p\n", m);
 			schedule_work(&m->wq);
-		} else
-			clear_bit(Wworksched, &m->wsched);
-	} else
-		clear_bit(Wworksched, &m->wsched);
+		}
+	}
 
 	return;
 
@@ -793,30 +795,28 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd)
 static int p9_socket_open(struct p9_client *client, struct socket *csocket)
 {
 	struct p9_trans_fd *p;
-	int ret, fd;
+	struct file *file;
+	int ret;
 
 	p = kmalloc(sizeof(struct p9_trans_fd), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
 
 	csocket->sk->sk_allocation = GFP_NOIO;
-	fd = sock_map_fd(csocket, 0);
-	if (fd < 0) {
+	file = sock_alloc_file(csocket, 0, NULL);
+	if (IS_ERR(file)) {
 		pr_err("%s (%d): failed to map fd\n",
 		       __func__, task_pid_nr(current));
 		sock_release(csocket);
 		kfree(p);
-		return fd;
+		return PTR_ERR(file);
 	}
 
-	get_file(csocket->file);
-	get_file(csocket->file);
-	p->wr = p->rd = csocket->file;
+	get_file(file);
+	p->wr = p->rd = file;
 	client->trans = p;
 	client->status = Connected;
 
-	sys_close(fd);	/* still racy */
-
 	p->rd->f_flags |= O_NONBLOCK;
 
 	p->conn = p9_conn_create(client);
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 9d49ee6d7219..ba033f09196e 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -591,7 +591,7 @@ static int bt_seq_show(struct seq_file *seq, void *v)
 			   atomic_read(&sk->sk_refcnt),
 			   sk_rmem_alloc_get(sk),
 			   sk_wmem_alloc_get(sk),
-			   sock_i_uid(sk),
+			   from_kuid(seq_user_ns(seq), sock_i_uid(sk)),
 			   sock_i_ino(sk),
 			   &src_baswapped,
 			   &dst_baswapped,
diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c
index 68e8f364bbf8..fe43bc7b063f 100644
--- a/net/bridge/br_netfilter.c
+++ b/net/bridge/br_netfilter.c
@@ -265,6 +265,9 @@ static int br_parse_ip_options(struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 	u32 len;
 
+	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
+		goto inhdr_error;
+
 	iph = ip_hdr(skb);
 	opt = &(IPCB(skb)->opt);
 
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 821022a7214f..ddac1ee2ed20 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -63,7 +63,7 @@
 
 #include "af_can.h"
 
-static __initdata const char banner[] = KERN_INFO
+static __initconst const char banner[] = KERN_INFO
 	"can: controller area network core (" CAN_VERSION_STRING ")\n";
 
 MODULE_DESCRIPTION("Controller Area Network PF_CAN core");
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 151b7730c12c..6f747582718e 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -77,7 +77,7 @@
 		     (CAN_SFF_MASK | CAN_EFF_FLAG | CAN_RTR_FLAG))
 
 #define CAN_BCM_VERSION CAN_VERSION
-static __initdata const char banner[] = KERN_INFO
+static __initconst const char banner[] = KERN_INFO
 	"can: broadcast manager protocol (rev " CAN_BCM_VERSION " t)\n";
 
 MODULE_DESCRIPTION("PF_CAN broadcast manager protocol");
diff --git a/net/can/gw.c b/net/can/gw.c
index 127879c55fb6..1f5c9785a262 100644
--- a/net/can/gw.c
+++ b/net/can/gw.c
@@ -58,7 +58,7 @@
 #include <net/sock.h>
 
 #define CAN_GW_VERSION "20101209"
-static __initdata const char banner[] =
+static __initconst const char banner[] =
 	KERN_INFO "can: netlink gateway (rev " CAN_GW_VERSION ")\n";
 
 MODULE_DESCRIPTION("PF_CAN netlink gateway");
diff --git a/net/can/raw.c b/net/can/raw.c
index 3e9c89356a93..5b0e3e330d97 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -55,7 +55,7 @@
 #include <net/net_namespace.h>
 
 #define CAN_RAW_VERSION CAN_VERSION
-static __initdata const char banner[] =
+static __initconst const char banner[] =
 	KERN_INFO "can: raw protocol (rev " CAN_RAW_VERSION ")\n";
 
 MODULE_DESCRIPTION("PF_CAN raw protocol");
diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c
index 9da7fdd3cd8a..af14cb425164 100644
--- a/net/ceph/crypto.c
+++ b/net/ceph/crypto.c
@@ -423,14 +423,15 @@ int ceph_encrypt2(struct ceph_crypto_key *secret, void *dst, size_t *dst_len,
 	}
 }
 
-int ceph_key_instantiate(struct key *key, const void *data, size_t datalen)
+int ceph_key_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	struct ceph_crypto_key *ckey;
+	size_t datalen = prep->datalen;
 	int ret;
 	void *p;
 
 	ret = -EINVAL;
-	if (datalen <= 0 || datalen > 32767 || !data)
+	if (datalen <= 0 || datalen > 32767 || !prep->data)
 		goto err;
 
 	ret = key_payload_reserve(key, datalen);
@@ -443,8 +444,8 @@ int ceph_key_instantiate(struct key *key, const void *data, size_t datalen)
 		goto err;
 
 	/* TODO ceph_crypto_key_decode should really take const input */
-	p = (void *)data;
-	ret = ceph_crypto_key_decode(ckey, &p, (char*)data+datalen);
+	p = (void *)prep->data;
+	ret = ceph_crypto_key_decode(ckey, &p, (char*)prep->data+datalen);
 	if (ret < 0)
 		goto err_ckey;
 
diff --git a/net/ceph/mon_client.c b/net/ceph/mon_client.c
index 900ea0f043fc..812eb3b46c1f 100644
--- a/net/ceph/mon_client.c
+++ b/net/ceph/mon_client.c
@@ -637,7 +637,7 @@ bad:
 /*
  * Do a synchronous pool op.
  */
-int ceph_monc_do_poolop(struct ceph_mon_client *monc, u32 op,
+static int do_poolop(struct ceph_mon_client *monc, u32 op,
 			u32 pool, u64 snapid,
 			char *buf, int len)
 {
@@ -687,7 +687,7 @@ out:
 int ceph_monc_create_snapid(struct ceph_mon_client *monc,
 			    u32 pool, u64 *snapid)
 {
-	return ceph_monc_do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
+	return do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
 				   pool, 0, (char *)snapid, sizeof(*snapid));
 
 }
@@ -696,7 +696,7 @@ EXPORT_SYMBOL(ceph_monc_create_snapid);
 int ceph_monc_delete_snapid(struct ceph_mon_client *monc,
 			    u32 pool, u64 snapid)
 {
-	return ceph_monc_do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
+	return do_poolop(monc,  POOL_OP_CREATE_UNMANAGED_SNAP,
 				   pool, snapid, 0, 0);
 
 }
@@ -769,7 +769,6 @@ static int build_initial_monmap(struct ceph_mon_client *monc)
 		monc->monmap->mon_inst[i].name.num = cpu_to_le64(i);
 	}
 	monc->monmap->num_mon = num_mon;
-	monc->have_fsid = false;
 	return 0;
 }
 
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 42119c05e82c..c1d756cc7448 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -52,7 +52,7 @@ static int op_has_extent(int op)
 		op == CEPH_OSD_OP_WRITE);
 }
 
-void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
+int ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 			struct ceph_file_layout *layout,
 			u64 snapid,
 			u64 off, u64 *plen, u64 *bno,
@@ -62,12 +62,15 @@ void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 	struct ceph_osd_request_head *reqhead = req->r_request->front.iov_base;
 	u64 orig_len = *plen;
 	u64 objoff, objlen;    /* extent in object */
+	int r;
 
 	reqhead->snapid = cpu_to_le64(snapid);
 
 	/* object extent? */
-	ceph_calc_file_object_mapping(layout, off, plen, bno,
-				      &objoff, &objlen);
+	r = ceph_calc_file_object_mapping(layout, off, plen, bno,
+					  &objoff, &objlen);
+	if (r < 0)
+		return r;
 	if (*plen < orig_len)
 		dout(" skipping last %llu, final file extent %llu~%llu\n",
 		     orig_len - *plen, off, *plen);
@@ -83,7 +86,7 @@ void ceph_calc_raw_layout(struct ceph_osd_client *osdc,
 
 	dout("calc_layout bno=%llx %llu~%llu (%d pages)\n",
 	     *bno, objoff, objlen, req->r_num_pages);
-
+	return 0;
 }
 EXPORT_SYMBOL(ceph_calc_raw_layout);
 
@@ -112,20 +115,25 @@ EXPORT_SYMBOL(ceph_calc_raw_layout);
  *
  * fill osd op in request message.
  */
-static void calc_layout(struct ceph_osd_client *osdc,
-			struct ceph_vino vino,
-			struct ceph_file_layout *layout,
-			u64 off, u64 *plen,
-			struct ceph_osd_request *req,
-			struct ceph_osd_req_op *op)
+static int calc_layout(struct ceph_osd_client *osdc,
+		       struct ceph_vino vino,
+		       struct ceph_file_layout *layout,
+		       u64 off, u64 *plen,
+		       struct ceph_osd_request *req,
+		       struct ceph_osd_req_op *op)
 {
 	u64 bno;
+	int r;
 
-	ceph_calc_raw_layout(osdc, layout, vino.snap, off,
-			     plen, &bno, req, op);
+	r = ceph_calc_raw_layout(osdc, layout, vino.snap, off,
+				 plen, &bno, req, op);
+	if (r < 0)
+		return r;
 
 	snprintf(req->r_oid, sizeof(req->r_oid), "%llx.%08llx", vino.ino, bno);
 	req->r_oid_len = strlen(req->r_oid);
+
+	return r;
 }
 
 /*
@@ -213,7 +221,6 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 	kref_init(&req->r_kref);
 	init_completion(&req->r_completion);
 	init_completion(&req->r_safe_completion);
-	rb_init_node(&req->r_node);
 	INIT_LIST_HEAD(&req->r_unsafe_item);
 	INIT_LIST_HEAD(&req->r_linger_item);
 	INIT_LIST_HEAD(&req->r_linger_osd);
@@ -456,6 +463,7 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 {
 	struct ceph_osd_req_op ops[3];
 	struct ceph_osd_request *req;
+	int r;
 
 	ops[0].op = opcode;
 	ops[0].extent.truncate_seq = truncate_seq;
@@ -474,10 +482,12 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc,
 					 use_mempool,
 					 GFP_NOFS, NULL, NULL);
 	if (!req)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 
 	/* calculate max write size */
-	calc_layout(osdc, vino, layout, off, plen, req, ops);
+	r = calc_layout(osdc, vino, layout, off, plen, req, ops);
+	if (r < 0)
+		return ERR_PTR(r);
 	req->r_file_layout = *layout;  /* keep a copy */
 
 	/* in case it differs from natural (file) alignment that
@@ -1920,8 +1930,8 @@ int ceph_osdc_readpages(struct ceph_osd_client *osdc,
 				    CEPH_OSD_OP_READ, CEPH_OSD_FLAG_READ,
 				    NULL, 0, truncate_seq, truncate_size, NULL,
 				    false, 1, page_align);
-	if (!req)
-		return -ENOMEM;
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
 	/* it may be a short read due to an object boundary */
 	req->r_pages = pages;
@@ -1963,8 +1973,8 @@ int ceph_osdc_writepages(struct ceph_osd_client *osdc, struct ceph_vino vino,
 				    snapc, do_sync,
 				    truncate_seq, truncate_size, mtime,
 				    nofail, 1, page_align);
-	if (!req)
-		return -ENOMEM;
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
 	/* it may be a short write due to an object boundary */
 	req->r_pages = pages;
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index 3124b71a8883..5433fb0eb3c6 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -984,7 +984,7 @@ bad:
  * for now, we write only a single su, until we can
  * pass a stride back to the caller.
  */
-void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
+int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 				   u64 off, u64 *plen,
 				   u64 *ono,
 				   u64 *oxoff, u64 *oxlen)
@@ -998,11 +998,17 @@ void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 
 	dout("mapping %llu~%llu  osize %u fl_su %u\n", off, *plen,
 	     osize, su);
+	if (su == 0 || sc == 0)
+		goto invalid;
 	su_per_object = osize / su;
+	if (su_per_object == 0)
+		goto invalid;
 	dout("osize %u / su %u = su_per_object %u\n", osize, su,
 	     su_per_object);
 
-	BUG_ON((su & ~PAGE_MASK) != 0);
+	if ((su & ~PAGE_MASK) != 0)
+		goto invalid;
+
 	/* bl = *off / su; */
 	t = off;
 	do_div(t, su);
@@ -1030,6 +1036,14 @@ void ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
 	*plen = *oxlen;
 
 	dout(" obj extent %llu~%llu\n", *oxoff, *oxlen);
+	return 0;
+
+invalid:
+	dout(" invalid layout\n");
+	*ono = 0;
+	*oxoff = 0;
+	*oxlen = 0;
+	return -EINVAL;
 }
 EXPORT_SYMBOL(ceph_calc_file_object_mapping);
 
diff --git a/net/ceph/pagelist.c b/net/ceph/pagelist.c
index 665cd23020ff..92866bebb65f 100644
--- a/net/ceph/pagelist.c
+++ b/net/ceph/pagelist.c
@@ -1,4 +1,3 @@
-
 #include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/pagemap.h>
@@ -134,8 +133,8 @@ int ceph_pagelist_truncate(struct ceph_pagelist *pl,
 	ceph_pagelist_unmap_tail(pl);
 	while (pl->head.prev != c->page_lru) {
 		page = list_entry(pl->head.prev, struct page, lru);
-		list_del(&page->lru);                /* remove from pagelist */
-		list_add_tail(&page->lru, &pl->free_list); /* add to reserve */
+		/* move from pagelist to reserve */
+		list_move_tail(&page->lru, &pl->free_list);
 		++pl->num_pages_free;
 	}
 	pl->room = c->room;
diff --git a/net/compat.c b/net/compat.c
index 74ed1d7a84a2..79ae88485001 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -301,8 +301,7 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm)
 			break;
 		}
 		/* Bump the usage count and install the file. */
-		get_file(fp[i]);
-		fd_install(new_fd, fp[i]);
+		fd_install(new_fd, get_file(fp[i]));
 	}
 
 	if (i > 0) {
diff --git a/net/core/dev.c b/net/core/dev.c
index 1e0a1847c3bb..09cb3f6dc40c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3300,18 +3300,18 @@ ncls:
 				&& !skb_pfmemalloc_protocol(skb))
 		goto drop;
 
-	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (vlan_tx_tag_present(skb)) {
 		if (pt_prev) {
 			ret = deliver_skb(skb, pt_prev, orig_dev);
 			pt_prev = NULL;
 		}
-		if (vlan_do_receive(&skb, !rx_handler))
+		if (vlan_do_receive(&skb))
 			goto another_round;
 		else if (unlikely(!skb))
 			goto unlock;
 	}
 
+	rx_handler = rcu_dereference(skb->dev->rx_handler);
 	if (rx_handler) {
 		if (pt_prev) {
 			ret = deliver_skb(skb, pt_prev, orig_dev);
@@ -3331,6 +3331,9 @@ ncls:
 		}
 	}
 
+	if (vlan_tx_nonzero_tag_present(skb))
+		skb->pkt_type = PACKET_OTHERHOST;
+
 	/* deliver only exact match when indicated */
 	null_or_dev = deliver_exact ? skb->dev : NULL;
 
@@ -3471,17 +3474,31 @@ out:
 	return netif_receive_skb(skb);
 }
 
-inline void napi_gro_flush(struct napi_struct *napi)
+/* napi->gro_list contains packets ordered by age.
+ * youngest packets at the head of it.
+ * Complete skbs in reverse order to reduce latencies.
+ */
+void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-	struct sk_buff *skb, *next;
+	struct sk_buff *skb, *prev = NULL;
 
-	for (skb = napi->gro_list; skb; skb = next) {
-		next = skb->next;
+	/* scan list and build reverse chain */
+	for (skb = napi->gro_list; skb != NULL; skb = skb->next) {
+		skb->prev = prev;
+		prev = skb;
+	}
+
+	for (skb = prev; skb; skb = prev) {
 		skb->next = NULL;
+
+		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
+			return;
+
+		prev = skb->prev;
 		napi_gro_complete(skb);
+		napi->gro_count--;
 	}
 
-	napi->gro_count = 0;
 	napi->gro_list = NULL;
 }
 EXPORT_SYMBOL(napi_gro_flush);
@@ -3542,6 +3559,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 
 	napi->gro_count++;
 	NAPI_GRO_CB(skb)->count = 1;
+	NAPI_GRO_CB(skb)->age = jiffies;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
 	skb->next = napi->gro_list;
 	napi->gro_list = skb;
@@ -3631,20 +3649,22 @@ gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(napi_skb_finish);
 
-void skb_gro_reset_offset(struct sk_buff *skb)
+static void skb_gro_reset_offset(struct sk_buff *skb)
 {
+	const struct skb_shared_info *pinfo = skb_shinfo(skb);
+	const skb_frag_t *frag0 = &pinfo->frags[0];
+
 	NAPI_GRO_CB(skb)->data_offset = 0;
 	NAPI_GRO_CB(skb)->frag0 = NULL;
 	NAPI_GRO_CB(skb)->frag0_len = 0;
 
 	if (skb->mac_header == skb->tail &&
-	    !PageHighMem(skb_frag_page(&skb_shinfo(skb)->frags[0]))) {
-		NAPI_GRO_CB(skb)->frag0 =
-			skb_frag_address(&skb_shinfo(skb)->frags[0]);
-		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(&skb_shinfo(skb)->frags[0]);
+	    pinfo->nr_frags &&
+	    !PageHighMem(skb_frag_page(frag0))) {
+		NAPI_GRO_CB(skb)->frag0 = skb_frag_address(frag0);
+		NAPI_GRO_CB(skb)->frag0_len = skb_frag_size(frag0);
 	}
 }
-EXPORT_SYMBOL(skb_gro_reset_offset);
 
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
@@ -3876,7 +3896,7 @@ void napi_complete(struct napi_struct *n)
 	if (unlikely(test_bit(NAPI_STATE_NPSVC, &n->state)))
 		return;
 
-	napi_gro_flush(n);
+	napi_gro_flush(n, false);
 	local_irq_save(flags);
 	__napi_complete(n);
 	local_irq_restore(flags);
@@ -3981,8 +4001,17 @@ static void net_rx_action(struct softirq_action *h)
 				local_irq_enable();
 				napi_complete(n);
 				local_irq_disable();
-			} else
+			} else {
+				if (n->gro_list) {
+					/* flush too old packets
+					 * If HZ < 1000, flush all packets.
+					 */
+					local_irq_enable();
+					napi_gro_flush(n, HZ >= 1000);
+					local_irq_disable();
+				}
 				list_move_tail(&n->poll_list, &sd->poll_list);
+			}
 		}
 
 		netpoll_poll_unlock(have);
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index baca771caae2..22571488730a 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1301,8 +1301,6 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 	if (!dst)
 		goto discard;
 
-	__skb_pull(skb, skb_network_offset(skb));
-
 	if (!neigh_event_send(neigh, skb)) {
 		int err;
 		struct net_device *dev = neigh->dev;
@@ -1312,6 +1310,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb)
 			neigh_hh_init(neigh, dst);
 
 		do {
+			__skb_pull(skb, skb_network_offset(skb));
 			seq = read_seqbegin(&neigh->ha_lock);
 			err = dev_hard_header(skb, dev, ntohs(skb->protocol),
 					      neigh->ha, NULL, skb->len);
@@ -1342,9 +1341,8 @@ int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb)
 	unsigned int seq;
 	int err;
 
-	__skb_pull(skb, skb_network_offset(skb));
-
 	do {
+		__skb_pull(skb, skb_network_offset(skb));
 		seq = read_seqbegin(&neigh->ha_lock);
 		err = dev_hard_header(skb, dev, ntohs(skb->protocol),
 				      neigh->ha, NULL, skb->len);
diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index 4a83fb3c8e87..79285a36035f 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -239,38 +239,24 @@ out_free_devname:
 	return ret;
 }
 
+static int update_netprio(const void *v, struct file *file, unsigned n)
+{
+	int err;
+	struct socket *sock = sock_from_file(file, &err);
+	if (sock)
+		sock->sk->sk_cgrp_prioidx = (u32)(unsigned long)v;
+	return 0;
+}
+
 void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 {
 	struct task_struct *p;
+	void *v;
 
 	cgroup_taskset_for_each(p, cgrp, tset) {
-		unsigned int fd;
-		struct fdtable *fdt;
-		struct files_struct *files;
-
 		task_lock(p);
-		files = p->files;
-		if (!files) {
-			task_unlock(p);
-			continue;
-		}
-
-		spin_lock(&files->file_lock);
-		fdt = files_fdtable(files);
-		for (fd = 0; fd < fdt->max_fds; fd++) {
-			struct file *file;
-			struct socket *sock;
-			int err;
-
-			file = fcheck_files(files, fd);
-			if (!file)
-				continue;
-
-			sock = sock_from_file(file, &err);
-			if (sock)
-				sock_update_netprioidx(sock->sk, p);
-		}
-		spin_unlock(&files->file_lock);
+		v = (void *)(unsigned long)task_netprioidx(p);
+		iterate_fd(p->files, 0, update_netprio, v);
 		task_unlock(p);
 	}
 }
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 148e73d2c451..d1dc14c2aac4 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -248,8 +248,8 @@ struct pktgen_dev {
 	int removal_mark;	/* non-zero => the device is marked for
 				 * removal by worker thread */
 
-	int min_pkt_size;	/* = ETH_ZLEN; */
-	int max_pkt_size;	/* = ETH_ZLEN; */
+	int min_pkt_size;
+	int max_pkt_size;
 	int pkt_overhead;	/* overhead for MPLS, VLANs, IPSEC etc */
 	int nfrags;
 	struct page *page;
@@ -449,8 +449,6 @@ static void pktgen_stop_all_threads_ifs(void);
 static void pktgen_stop(struct pktgen_thread *t);
 static void pktgen_clear_counters(struct pktgen_dev *pkt_dev);
 
-static unsigned int scan_ip6(const char *s, char ip[16]);
-
 /* Module parameters, defaults. */
 static int pg_count_d __read_mostly = 1000;
 static int pg_delay_d __read_mostly;
@@ -702,8 +700,8 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 				&pkt_dev->cur_in6_saddr,
 				&pkt_dev->cur_in6_daddr);
 	} else
-		seq_printf(seq, "     cur_saddr: 0x%x  cur_daddr: 0x%x\n",
-			   pkt_dev->cur_saddr, pkt_dev->cur_daddr);
+		seq_printf(seq, "     cur_saddr: %pI4  cur_daddr: %pI4\n",
+			   &pkt_dev->cur_saddr, &pkt_dev->cur_daddr);
 
 	seq_printf(seq, "     cur_udp_dst: %d  cur_udp_src: %d\n",
 		   pkt_dev->cur_udp_dst, pkt_dev->cur_udp_src);
@@ -1299,7 +1297,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			return -EFAULT;
 		buf[len] = 0;
 
-		scan_ip6(buf, pkt_dev->in6_daddr.s6_addr);
+		in6_pton(buf, -1, pkt_dev->in6_daddr.s6_addr, -1, NULL);
 		snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_daddr);
 
 		pkt_dev->cur_in6_daddr = pkt_dev->in6_daddr;
@@ -1322,7 +1320,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			return -EFAULT;
 		buf[len] = 0;
 
-		scan_ip6(buf, pkt_dev->min_in6_daddr.s6_addr);
+		in6_pton(buf, -1, pkt_dev->min_in6_daddr.s6_addr, -1, NULL);
 		snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_daddr);
 
 		pkt_dev->cur_in6_daddr = pkt_dev->min_in6_daddr;
@@ -1344,7 +1342,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			return -EFAULT;
 		buf[len] = 0;
 
-		scan_ip6(buf, pkt_dev->max_in6_daddr.s6_addr);
+		in6_pton(buf, -1, pkt_dev->max_in6_daddr.s6_addr, -1, NULL);
 		snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_daddr);
 
 		if (debug)
@@ -1365,7 +1363,7 @@ static ssize_t pktgen_if_write(struct file *file,
 			return -EFAULT;
 		buf[len] = 0;
 
-		scan_ip6(buf, pkt_dev->in6_saddr.s6_addr);
+		in6_pton(buf, -1, pkt_dev->in6_saddr.s6_addr, -1, NULL);
 		snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->in6_saddr);
 
 		pkt_dev->cur_in6_saddr = pkt_dev->in6_saddr;
@@ -2036,19 +2034,17 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
 	/* Set up Dest MAC */
 	memcpy(&(pkt_dev->hh[0]), pkt_dev->dst_mac, ETH_ALEN);
 
-	/* Set up pkt size */
-	pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size;
-
 	if (pkt_dev->flags & F_IPV6) {
-		/*
-		 * Skip this automatic address setting until locks or functions
-		 * gets exported
-		 */
-
-#ifdef NOTNOW
 		int i, set = 0, err = 1;
 		struct inet6_dev *idev;
 
+		if (pkt_dev->min_pkt_size == 0) {
+			pkt_dev->min_pkt_size = 14 + sizeof(struct ipv6hdr)
+						+ sizeof(struct udphdr)
+						+ sizeof(struct pktgen_hdr)
+						+ pkt_dev->pkt_overhead;
+		}
+
 		for (i = 0; i < IN6_ADDR_HSIZE; i++)
 			if (pkt_dev->cur_in6_saddr.s6_addr[i]) {
 				set = 1;
@@ -2069,9 +2065,8 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
 				struct inet6_ifaddr *ifp;
 
 				read_lock_bh(&idev->lock);
-				for (ifp = idev->addr_list; ifp;
-				     ifp = ifp->if_next) {
-					if (ifp->scope == IFA_LINK &&
+				list_for_each_entry(ifp, &idev->addr_list, if_list) {
+					if ((ifp->scope & IFA_LINK) &&
 					    !(ifp->flags & IFA_F_TENTATIVE)) {
 						pkt_dev->cur_in6_saddr = ifp->addr;
 						err = 0;
@@ -2084,8 +2079,14 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
 			if (err)
 				pr_err("ERROR: IPv6 link address not available\n");
 		}
-#endif
 	} else {
+		if (pkt_dev->min_pkt_size == 0) {
+			pkt_dev->min_pkt_size = 14 + sizeof(struct iphdr)
+						+ sizeof(struct udphdr)
+						+ sizeof(struct pktgen_hdr)
+						+ pkt_dev->pkt_overhead;
+		}
+
 		pkt_dev->saddr_min = 0;
 		pkt_dev->saddr_max = 0;
 		if (strlen(pkt_dev->src_min) == 0) {
@@ -2111,6 +2112,10 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev)
 		pkt_dev->daddr_max = in_aton(pkt_dev->dst_max);
 	}
 	/* Initialize current values. */
+	pkt_dev->cur_pkt_size = pkt_dev->min_pkt_size;
+	if (pkt_dev->min_pkt_size > pkt_dev->max_pkt_size)
+		pkt_dev->max_pkt_size = pkt_dev->min_pkt_size;
+
 	pkt_dev->cur_dst_mac_offset = 0;
 	pkt_dev->cur_src_mac_offset = 0;
 	pkt_dev->cur_saddr = pkt_dev->saddr_min;
@@ -2758,97 +2763,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev,
 	return skb;
 }
 
-/*
- * scan_ip6, fmt_ip taken from dietlibc-0.21
- * Author Felix von Leitner <felix-dietlibc@fefe.de>
- *
- * Slightly modified for kernel.
- * Should be candidate for net/ipv4/utils.c
- * --ro
- */
-
-static unsigned int scan_ip6(const char *s, char ip[16])
-{
-	unsigned int i;
-	unsigned int len = 0;
-	unsigned long u;
-	char suffix[16];
-	unsigned int prefixlen = 0;
-	unsigned int suffixlen = 0;
-	__be32 tmp;
-	char *pos;
-
-	for (i = 0; i < 16; i++)
-		ip[i] = 0;
-
-	for (;;) {
-		if (*s == ':') {
-			len++;
-			if (s[1] == ':') {	/* Found "::", skip to part 2 */
-				s += 2;
-				len++;
-				break;
-			}
-			s++;
-		}
-
-		u = simple_strtoul(s, &pos, 16);
-		i = pos - s;
-		if (!i)
-			return 0;
-		if (prefixlen == 12 && s[i] == '.') {
-
-			/* the last 4 bytes may be written as IPv4 address */
-
-			tmp = in_aton(s);
-			memcpy((struct in_addr *)(ip + 12), &tmp, sizeof(tmp));
-			return i + len;
-		}
-		ip[prefixlen++] = (u >> 8);
-		ip[prefixlen++] = (u & 255);
-		s += i;
-		len += i;
-		if (prefixlen == 16)
-			return len;
-	}
-
-/* part 2, after "::" */
-	for (;;) {
-		if (*s == ':') {
-			if (suffixlen == 0)
-				break;
-			s++;
-			len++;
-		} else if (suffixlen != 0)
-			break;
-
-		u = simple_strtol(s, &pos, 16);
-		i = pos - s;
-		if (!i) {
-			if (*s)
-				len--;
-			break;
-		}
-		if (suffixlen + prefixlen <= 12 && s[i] == '.') {
-			tmp = in_aton(s);
-			memcpy((struct in_addr *)(suffix + suffixlen), &tmp,
-			       sizeof(tmp));
-			suffixlen += 4;
-			len += strlen(s);
-			break;
-		}
-		suffix[suffixlen++] = (u >> 8);
-		suffix[suffixlen++] = (u & 255);
-		s += i;
-		len += i;
-		if (prefixlen + suffixlen == 16)
-			break;
-	}
-	for (i = 0; i < suffixlen; i++)
-		ip[16 - suffixlen + i] = suffix[i];
-	return len;
-}
-
 static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 					struct pktgen_dev *pkt_dev)
 {
@@ -2927,7 +2841,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev,
 		  sizeof(struct ipv6hdr) - sizeof(struct udphdr) -
 		  pkt_dev->pkt_overhead;
 
-	if (datalen < sizeof(struct pktgen_hdr)) {
+	if (datalen < 0 || datalen < sizeof(struct pktgen_hdr)) {
 		datalen = sizeof(struct pktgen_hdr);
 		net_info_ratelimited("increased datalen to %d\n", datalen);
 	}
@@ -3548,8 +3462,6 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname)
 	}
 
 	pkt_dev->removal_mark = 0;
-	pkt_dev->min_pkt_size = ETH_ZLEN;
-	pkt_dev->max_pkt_size = ETH_ZLEN;
 	pkt_dev->nfrags = 0;
 	pkt_dev->delay = pg_delay_d;
 	pkt_dev->count = pg_count_d;
diff --git a/net/core/scm.c b/net/core/scm.c
index 9c1c63da3ca8..ab570841a532 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -301,11 +301,10 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
 			break;
 		}
 		/* Bump the usage count and install the file. */
-		get_file(fp[i]);
 		sock = sock_from_file(fp[i], &err);
 		if (sock)
 			sock_update_netprioidx(sock->sk, current);
-		fd_install(new_fd, fp[i]);
+		fd_install(new_fd, get_file(fp[i]));
 	}
 
 	if (i > 0)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cdc28598f4ef..6e04b1fa11f2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -655,53 +655,6 @@ void consume_skb(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(consume_skb);
 
-/**
- * 	skb_recycle - clean up an skb for reuse
- * 	@skb: buffer
- *
- * 	Recycles the skb to be reused as a receive buffer. This
- * 	function does any necessary reference count dropping, and
- * 	cleans up the skbuff as if it just came from __alloc_skb().
- */
-void skb_recycle(struct sk_buff *skb)
-{
-	struct skb_shared_info *shinfo;
-
-	skb_release_head_state(skb);
-
-	shinfo = skb_shinfo(skb);
-	memset(shinfo, 0, offsetof(struct skb_shared_info, dataref));
-	atomic_set(&shinfo->dataref, 1);
-
-	memset(skb, 0, offsetof(struct sk_buff, tail));
-	skb->data = skb->head + NET_SKB_PAD;
-	skb_reset_tail_pointer(skb);
-}
-EXPORT_SYMBOL(skb_recycle);
-
-/**
- *	skb_recycle_check - check if skb can be reused for receive
- *	@skb: buffer
- *	@skb_size: minimum receive buffer size
- *
- *	Checks that the skb passed in is not shared or cloned, and
- *	that it is linear and its head portion at least as large as
- *	skb_size so that it can be recycled as a receive buffer.
- *	If these conditions are met, this function does any necessary
- *	reference count dropping and cleans up the skbuff as if it
- *	just came from __alloc_skb().
- */
-bool skb_recycle_check(struct sk_buff *skb, int skb_size)
-{
-	if (!skb_is_recycleable(skb, skb_size))
-		return false;
-
-	skb_recycle(skb);
-
-	return true;
-}
-EXPORT_SYMBOL(skb_recycle_check);
-
 static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 {
 	new->tstamp		= old->tstamp;
diff --git a/net/core/utils.c b/net/core/utils.c
index f5613d569c23..e3487e461939 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -107,6 +107,18 @@ static inline int xdigit2bin(char c, int delim)
 	return IN6PTON_UNKNOWN;
 }
 
+/**
+ * in4_pton - convert an IPv4 address from literal to binary representation
+ * @src: the start of the IPv4 address string
+ * @srclen: the length of the string, -1 means strlen(src)
+ * @dst: the binary (u8[4] array) representation of the IPv4 address
+ * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter
+ * @end: A pointer to the end of the parsed string will be placed here
+ *
+ * Return one on success, return zero when any error occurs
+ * and @end will point to the end of the parsed string.
+ *
+ */
 int in4_pton(const char *src, int srclen,
 	     u8 *dst,
 	     int delim, const char **end)
@@ -161,6 +173,18 @@ out:
 }
 EXPORT_SYMBOL(in4_pton);
 
+/**
+ * in6_pton - convert an IPv6 address from literal to binary representation
+ * @src: the start of the IPv6 address string
+ * @srclen: the length of the string, -1 means strlen(src)
+ * @dst: the binary (u8[16] array) representation of the IPv6 address
+ * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter
+ * @end: A pointer to the end of the parsed string will be placed here
+ *
+ * Return one on success, return zero when any error occurs
+ * and @end will point to the end of the parsed string.
+ *
+ */
 int in6_pton(const char *src, int srclen,
 	     u8 *dst,
 	     int delim, const char **end)
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index e65f2c856e06..faf7cc3483fe 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -220,7 +220,7 @@ static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops)
 	dn_rt_cache_flush(-1);
 }
 
-static const struct fib_rules_ops __net_initdata dn_fib_rules_ops_template = {
+static const struct fib_rules_ops __net_initconst dn_fib_rules_ops_template = {
 	.family		= AF_DECnet,
 	.rule_size	= sizeof(struct dn_fib_rule),
 	.addr_size	= sizeof(u16),
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 9807945a56d9..8aa4b1115384 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -59,13 +59,13 @@ const struct cred *dns_resolver_cache;
  *        "ip1,ip2,...#foo=bar"
  */
 static int
-dns_resolver_instantiate(struct key *key, const void *_data, size_t datalen)
+dns_resolver_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	struct user_key_payload *upayload;
 	unsigned long derrno;
 	int ret;
-	size_t result_len = 0;
-	const char *data = _data, *end, *opt;
+	size_t datalen = prep->datalen, result_len = 0;
+	const char *data = prep->data, *end, *opt;
 
 	kenter("%%%d,%s,'%*.*s',%zu",
 	       key->serial, key->description,
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 68c93d1bb03a..825c608826de 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -322,7 +322,8 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 {
 	int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
 
-	if (!r && !fib_num_tclassid_users(dev_net(dev))) {
+	if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
+	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
 		*itag = 0;
 		return 0;
 	}
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 274309d3aded..26aa65d1fce4 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -262,7 +262,7 @@ static void fib4_rule_flush_cache(struct fib_rules_ops *ops)
 	rt_cache_flush(ops->fro_net);
 }
 
-static const struct fib_rules_ops __net_initdata fib4_rules_ops_template = {
+static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = {
 	.family		= AF_INET,
 	.rule_size	= sizeof(struct fib4_rule),
 	.addr_size	= sizeof(u32),
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 267753060ffc..71b125cd5db1 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -840,6 +840,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
 	change_nexthops(fi) {
 		nexthop_nh->nh_parent = fi;
 		nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
+		if (!nexthop_nh->nh_pcpu_rth_output)
+			goto failure;
 	} endfor_nexthops(fi)
 
 	if (cfg->fc_mx) {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index f0c5b9c1a957..d34ce2972c8f 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -406,7 +406,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	return &rt->dst;
 
@@ -442,7 +442,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
 	rt = ip_route_output_flow(net, fl4, sk);
 	if (IS_ERR(rt))
 		goto no_route;
-	if (opt && opt->opt.is_strictroute && rt->rt_gateway)
+	if (opt && opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto route_err;
 	rcu_read_unlock();
 	return &rt->dst;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index ab09b126423c..694de3b7aebf 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -85,7 +85,7 @@ int ip_forward(struct sk_buff *skb)
 
 	rt = skb_rtable(skb);
 
-	if (opt->is_strictroute && opt->nexthop != rt->rt_gateway)
+	if (opt->is_strictroute && rt->rt_uses_gateway)
 		goto sr_failed;
 
 	if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) &&
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 24a29a39e9a8..6537a408a4fb 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -193,7 +193,7 @@ static inline int ip_finish_output2(struct sk_buff *skb)
 	}
 
 	rcu_read_lock_bh();
-	nexthop = rt->rt_gateway ? rt->rt_gateway : ip_hdr(skb)->daddr;
+	nexthop = (__force u32) rt_nexthop(rt, ip_hdr(skb)->daddr);
 	neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
 	if (unlikely(!neigh))
 		neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
@@ -371,7 +371,7 @@ int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
 	skb_dst_set_noref(skb, &rt->dst);
 
 packet_routed:
-	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway)
+	if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_uses_gateway)
 		goto no_route;
 
 	/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 978bca4818ae..1831092f999f 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -374,7 +374,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	memset(&fl4, 0, sizeof(fl4));
 	flowi4_init_output(&fl4, tunnel->parms.link,
-			   htonl(tunnel->parms.i_key), RT_TOS(tos),
+			   be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
 			   RT_SCOPE_UNIVERSE,
 			   IPPROTO_IPIP, 0,
 			   dst, tiph->saddr, 0, 0);
@@ -441,7 +441,7 @@ static int vti_tunnel_bind_dev(struct net_device *dev)
 		struct flowi4 fl4;
 		memset(&fl4, 0, sizeof(fl4));
 		flowi4_init_output(&fl4, tunnel->parms.link,
-				   htonl(tunnel->parms.i_key),
+				   be32_to_cpu(tunnel->parms.i_key),
 				   RT_TOS(iph->tos), RT_SCOPE_UNIVERSE,
 				   IPPROTO_IPIP, 0,
 				   iph->daddr, iph->saddr, 0, 0);
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 1daa95c2a0ba..6168c4dc58b1 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -221,7 +221,7 @@ static int ipmr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	return 0;
 }
 
-static const struct fib_rules_ops __net_initdata ipmr_rules_ops_template = {
+static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = {
 	.family		= RTNL_FAMILY_IPMR,
 	.rule_size	= sizeof(struct ipmr_rule),
 	.addr_size	= sizeof(u32),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ff622069fcef..432f4bb77238 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -802,7 +802,8 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	net = dev_net(rt->dst.dev);
 	peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1);
 	if (!peer) {
-		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST,
+			  rt_nexthop(rt, ip_hdr(skb)->daddr));
 		return;
 	}
 
@@ -827,7 +828,9 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 	    time_after(jiffies,
 		       (peer->rate_last +
 			(ip_rt_redirect_load << peer->rate_tokens)))) {
-		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
+		__be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);
+
+		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
 		peer->rate_last = jiffies;
 		++peer->rate_tokens;
 #ifdef CONFIG_IP_ROUTE_VERBOSE
@@ -835,7 +838,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
 		    peer->rate_tokens == ip_rt_redirect_number)
 			net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
 					     &ip_hdr(skb)->saddr, inet_iif(skb),
-					     &ip_hdr(skb)->daddr, &rt->rt_gateway);
+					     &ip_hdr(skb)->daddr, &gw);
 #endif
 	}
 out_put_peer:
@@ -904,22 +907,32 @@ out:	kfree_skb(skb);
 	return 0;
 }
 
-static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
+static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
 {
+	struct dst_entry *dst = &rt->dst;
 	struct fib_result res;
 
+	if (dst->dev->mtu < mtu)
+		return;
+
 	if (mtu < ip_rt_min_pmtu)
 		mtu = ip_rt_min_pmtu;
 
+	if (!rt->rt_pmtu) {
+		dst->obsolete = DST_OBSOLETE_KILL;
+	} else {
+		rt->rt_pmtu = mtu;
+		dst->expires = max(1UL, jiffies + ip_rt_mtu_expires);
+	}
+
 	rcu_read_lock();
-	if (fib_lookup(dev_net(rt->dst.dev), fl4, &res) == 0) {
+	if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) {
 		struct fib_nh *nh = &FIB_RES_NH(res);
 
 		update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
 				      jiffies + ip_rt_mtu_expires);
 	}
 	rcu_read_unlock();
-	return mtu;
 }
 
 static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
@@ -929,14 +942,7 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 	struct flowi4 fl4;
 
 	ip_rt_build_flow_key(&fl4, sk, skb);
-	mtu = __ip_rt_update_pmtu(rt, &fl4, mtu);
-
-	if (!rt->rt_pmtu) {
-		dst->obsolete = DST_OBSOLETE_KILL;
-	} else {
-		rt->rt_pmtu = mtu;
-		rt->dst.expires = max(1UL, jiffies + ip_rt_mtu_expires);
-	}
+	__ip_rt_update_pmtu(rt, &fl4, mtu);
 }
 
 void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
@@ -1120,7 +1126,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	mtu = dst->dev->mtu;
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
-		if (rt->rt_gateway && mtu > 576)
+		if (rt->rt_uses_gateway && mtu > 576)
 			mtu = 576;
 	}
 
@@ -1171,7 +1177,9 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 		if (fnhe->fnhe_gw) {
 			rt->rt_flags |= RTCF_REDIRECTED;
 			rt->rt_gateway = fnhe->fnhe_gw;
-		}
+			rt->rt_uses_gateway = 1;
+		} else if (!rt->rt_gateway)
+			rt->rt_gateway = daddr;
 
 		orig = rcu_dereference(fnhe->fnhe_rth);
 		rcu_assign_pointer(fnhe->fnhe_rth, rt);
@@ -1180,13 +1188,6 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 
 		fnhe->fnhe_stamp = jiffies;
 		ret = true;
-	} else {
-		/* Routes we intend to cache in nexthop exception have
-		 * the DST_NOCACHE bit clear.  However, if we are
-		 * unsuccessful at storing this route into the cache
-		 * we really need to set it.
-		 */
-		rt->dst.flags |= DST_NOCACHE;
 	}
 	spin_unlock_bh(&fnhe_lock);
 
@@ -1201,8 +1202,6 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	if (rt_is_input_route(rt)) {
 		p = (struct rtable **)&nh->nh_rth_input;
 	} else {
-		if (!nh->nh_pcpu_rth_output)
-			goto nocache;
 		p = (struct rtable **)__this_cpu_ptr(nh->nh_pcpu_rth_output);
 	}
 	orig = *p;
@@ -1211,16 +1210,8 @@ static bool rt_cache_route(struct fib_nh *nh, struct rtable *rt)
 	if (prev == orig) {
 		if (orig)
 			rt_free(orig);
-	} else {
-		/* Routes we intend to cache in the FIB nexthop have
-		 * the DST_NOCACHE bit clear.  However, if we are
-		 * unsuccessful at storing this route into the cache
-		 * we really need to set it.
-		 */
-nocache:
-		rt->dst.flags |= DST_NOCACHE;
+	} else
 		ret = false;
-	}
 
 	return ret;
 }
@@ -1281,8 +1272,10 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 	if (fi) {
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
-		if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
+		if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK) {
 			rt->rt_gateway = nh->nh_gw;
+			rt->rt_uses_gateway = 1;
+		}
 		dst_init_metrics(&rt->dst, fi->fib_metrics, true);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
@@ -1291,8 +1284,18 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 			cached = rt_bind_exception(rt, fnhe, daddr);
 		else if (!(rt->dst.flags & DST_NOCACHE))
 			cached = rt_cache_route(nh, rt);
-	}
-	if (unlikely(!cached))
+		if (unlikely(!cached)) {
+			/* Routes we intend to cache in nexthop exception or
+			 * FIB nexthop have the DST_NOCACHE bit clear.
+			 * However, if we are unsuccessful at storing this
+			 * route into the cache we really need to set it.
+			 */
+			rt->dst.flags |= DST_NOCACHE;
+			if (!rt->rt_gateway)
+				rt->rt_gateway = daddr;
+			rt_add_uncached_list(rt);
+		}
+	} else
 		rt_add_uncached_list(rt);
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
@@ -1360,6 +1363,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	rth->rt_iif	= 0;
 	rth->rt_pmtu	= 0;
 	rth->rt_gateway	= 0;
+	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
 	if (our) {
 		rth->dst.input= ip_local_deliver;
@@ -1429,7 +1433,6 @@ static int __mkroute_input(struct sk_buff *skb,
 		return -EINVAL;
 	}
 
-
 	err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
 				  in_dev->dev, in_dev, &itag);
 	if (err < 0) {
@@ -1439,10 +1442,13 @@ static int __mkroute_input(struct sk_buff *skb,
 		goto cleanup;
 	}
 
-	if (out_dev == in_dev && err &&
+	do_cache = res->fi && !itag;
+	if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) &&
 	    (IN_DEV_SHARED_MEDIA(out_dev) ||
-	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
+	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) {
 		flags |= RTCF_DOREDIRECT;
+		do_cache = false;
+	}
 
 	if (skb->protocol != htons(ETH_P_IP)) {
 		/* Not IP (i.e. ARP). Do not create route, if it is
@@ -1459,15 +1465,11 @@ static int __mkroute_input(struct sk_buff *skb,
 		}
 	}
 
-	do_cache = false;
-	if (res->fi) {
-		if (!itag) {
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-			if (rt_cache_valid(rth)) {
-				skb_dst_set_noref(skb, &rth->dst);
-				goto out;
-			}
-			do_cache = true;
+	if (do_cache) {
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+		if (rt_cache_valid(rth)) {
+			skb_dst_set_noref(skb, &rth->dst);
+			goto out;
 		}
 	}
 
@@ -1486,6 +1488,7 @@ static int __mkroute_input(struct sk_buff *skb,
 	rth->rt_iif 	= 0;
 	rth->rt_pmtu	= 0;
 	rth->rt_gateway	= 0;
+	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
 
 	rth->dst.input = ip_forward;
@@ -1656,6 +1659,7 @@ local_input:
 	rth->rt_iif	= 0;
 	rth->rt_pmtu	= 0;
 	rth->rt_gateway	= 0;
+	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
 	if (res.type == RTN_UNREACHABLE) {
 		rth->dst.input= ip_error;
@@ -1758,6 +1762,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	struct in_device *in_dev;
 	u16 type = res->type;
 	struct rtable *rth;
+	bool do_cache;
 
 	in_dev = __in_dev_get_rcu(dev_out);
 	if (!in_dev)
@@ -1794,24 +1799,36 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	}
 
 	fnhe = NULL;
+	do_cache = fi != NULL;
 	if (fi) {
 		struct rtable __rcu **prth;
+		struct fib_nh *nh = &FIB_RES_NH(*res);
 
-		fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
+		fnhe = find_exception(nh, fl4->daddr);
 		if (fnhe)
 			prth = &fnhe->fnhe_rth;
-		else
-			prth = __this_cpu_ptr(FIB_RES_NH(*res).nh_pcpu_rth_output);
+		else {
+			if (unlikely(fl4->flowi4_flags &
+				     FLOWI_FLAG_KNOWN_NH &&
+				     !(nh->nh_gw &&
+				       nh->nh_scope == RT_SCOPE_LINK))) {
+				do_cache = false;
+				goto add;
+			}
+			prth = __this_cpu_ptr(nh->nh_pcpu_rth_output);
+		}
 		rth = rcu_dereference(*prth);
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
 		}
 	}
+
+add:
 	rth = rt_dst_alloc(dev_out,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY),
 			   IN_DEV_CONF_GET(in_dev, NOXFRM),
-			   fi);
+			   do_cache);
 	if (!rth)
 		return ERR_PTR(-ENOBUFS);
 
@@ -1824,6 +1841,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	rth->rt_iif	= orig_oif ? : 0;
 	rth->rt_pmtu	= 0;
 	rth->rt_gateway = 0;
+	rth->rt_uses_gateway = 0;
 	INIT_LIST_HEAD(&rth->rt_uncached);
 
 	RT_CACHE_STAT_INC(out_slow_tot);
@@ -2102,6 +2120,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_flags = ort->rt_flags;
 		rt->rt_type = ort->rt_type;
 		rt->rt_gateway = ort->rt_gateway;
+		rt->rt_uses_gateway = ort->rt_uses_gateway;
 
 		INIT_LIST_HEAD(&rt->rt_uncached);
 
@@ -2180,28 +2199,31 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src,
 		if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
 			goto nla_put_failure;
 	}
-	if (rt->rt_gateway &&
+	if (rt->rt_uses_gateway &&
 	    nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
 		goto nla_put_failure;
 
+	expires = rt->dst.expires;
+	if (expires) {
+		unsigned long now = jiffies;
+
+		if (time_before(now, expires))
+			expires -= now;
+		else
+			expires = 0;
+	}
+
 	memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
-	if (rt->rt_pmtu)
+	if (rt->rt_pmtu && expires)
 		metrics[RTAX_MTU - 1] = rt->rt_pmtu;
 	if (rtnetlink_put_metrics(skb, metrics) < 0)
 		goto nla_put_failure;
 
 	if (fl4->flowi4_mark &&
-	    nla_put_be32(skb, RTA_MARK, fl4->flowi4_mark))
+	    nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark))
 		goto nla_put_failure;
 
 	error = rt->dst.error;
-	expires = rt->dst.expires;
-	if (expires) {
-		if (time_before(jiffies, expires))
-			expires -= jiffies;
-		else
-			expires = 0;
-	}
 
 	if (rt_is_input_route(rt)) {
 		if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 9205e492dc9d..63d4eccc674d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -248,6 +248,8 @@ int proc_tcp_fastopen_key(ctl_table *ctl, int write, void __user *buffer,
 	ctxt = rcu_dereference(tcp_fastopen_ctx);
 	if (ctxt)
 		memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH);
+	else
+		memset(user_key, 0, sizeof(user_key));
 	rcu_read_unlock();
 
 	snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x",
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 75735c9a6a9d..ef998b008a57 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -708,10 +708,11 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	arg.csumoffset = offsetof(struct tcphdr, check) / 2;
 	arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
 	/* When socket is gone, all binding information is lost.
-	 * routing might fail in this case. using iif for oif to
-	 * make sure we can deliver it
+	 * routing might fail in this case. No choice here, if we choose to force
+	 * input interface, we will misroute in case of asymmetric route.
 	 */
-	arg.bound_dev_if = sk ? sk->sk_bound_dev_if : inet_iif(skb);
+	if (sk)
+		arg.bound_dev_if = sk->sk_bound_dev_if;
 
 	net = dev_net(skb_dst(skb)->dev);
 	arg.tos = ip_hdr(skb)->tos;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 681ea2f413e2..05c5ab8d983c 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -91,6 +91,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 					      RTCF_LOCAL);
 	xdst->u.rt.rt_type = rt->rt_type;
 	xdst->u.rt.rt_gateway = rt->rt_gateway;
+	xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway;
 	xdst->u.rt.rt_pmtu = rt->rt_pmtu;
 	INIT_LIST_HEAD(&xdst->u.rt.rt_uncached);
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index d7c56f8a5b4e..0424e4e27414 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3064,14 +3064,15 @@ static struct inet6_ifaddr *if6_get_first(struct seq_file *seq, loff_t pos)
 		struct hlist_node *n;
 		hlist_for_each_entry_rcu_bh(ifa, n, &inet6_addr_lst[state->bucket],
 					 addr_lst) {
+			if (!net_eq(dev_net(ifa->idev->dev), net))
+				continue;
 			/* sync with offset */
 			if (p < state->offset) {
 				p++;
 				continue;
 			}
 			state->offset++;
-			if (net_eq(dev_net(ifa->idev->dev), net))
-				return ifa;
+			return ifa;
 		}
 
 		/* prepare for next bucket */
@@ -3089,18 +3090,20 @@ static struct inet6_ifaddr *if6_get_next(struct seq_file *seq,
 	struct hlist_node *n = &ifa->addr_lst;
 
 	hlist_for_each_entry_continue_rcu_bh(ifa, n, addr_lst) {
+		if (!net_eq(dev_net(ifa->idev->dev), net))
+			continue;
 		state->offset++;
-		if (net_eq(dev_net(ifa->idev->dev), net))
-			return ifa;
+		return ifa;
 	}
 
 	while (++state->bucket < IN6_ADDR_HSIZE) {
 		state->offset = 0;
 		hlist_for_each_entry_rcu_bh(ifa, n,
 				     &inet6_addr_lst[state->bucket], addr_lst) {
+			if (!net_eq(dev_net(ifa->idev->dev), net))
+				continue;
 			state->offset++;
-			if (net_eq(dev_net(ifa->idev->dev), net))
-				return ifa;
+			return ifa;
 		}
 	}
 
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index 4be23da32b89..ff76eecfd622 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -79,7 +79,7 @@ struct net *ip6addrlbl_net(const struct ip6addrlbl_entry *lbl)
 
 #define IPV6_ADDR_LABEL_DEFAULT	0xffffffffUL
 
-static const __net_initdata struct ip6addrlbl_init_table
+static const __net_initconst struct ip6addrlbl_init_table
 {
 	const struct in6_addr *prefix;
 	int prefixlen;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index e22e6d88bac6..a974247a9ae4 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -822,13 +822,6 @@ out:
 	return segs;
 }
 
-struct ipv6_gro_cb {
-	struct napi_gro_cb napi;
-	int proto;
-};
-
-#define IPV6_GRO_CB(skb) ((struct ipv6_gro_cb *)(skb)->cb)
-
 static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 					 struct sk_buff *skb)
 {
@@ -874,28 +867,31 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 		iph = ipv6_hdr(skb);
 	}
 
-	IPV6_GRO_CB(skb)->proto = proto;
+	NAPI_GRO_CB(skb)->proto = proto;
 
 	flush--;
 	nlen = skb_network_header_len(skb);
 
 	for (p = *head; p; p = p->next) {
-		struct ipv6hdr *iph2;
+		const struct ipv6hdr *iph2;
+		__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */
 
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
 		iph2 = ipv6_hdr(p);
+		first_word = *(__be32 *)iph ^ *(__be32 *)iph2 ;
 
-		/* All fields must match except length. */
+		/* All fields must match except length and Traffic Class. */
 		if (nlen != skb_network_header_len(p) ||
-		    memcmp(iph, iph2, offsetof(struct ipv6hdr, payload_len)) ||
+		    (first_word & htonl(0xF00FFFFF)) ||
 		    memcmp(&iph->nexthdr, &iph2->nexthdr,
 			   nlen - offsetof(struct ipv6hdr, nexthdr))) {
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
-
+		/* flush if Traffic Class fields are different */
+		NAPI_GRO_CB(p)->flush |= !!(first_word & htonl(0x0FF00000));
 		NAPI_GRO_CB(p)->flush |= flush;
 	}
 
@@ -927,7 +923,7 @@ static int ipv6_gro_complete(struct sk_buff *skb)
 				 sizeof(*iph));
 
 	rcu_read_lock();
-	ops = rcu_dereference(inet6_protos[IPV6_GRO_CB(skb)->proto]);
+	ops = rcu_dereference(inet6_protos[NAPI_GRO_CB(skb)->proto]);
 	if (WARN_ON(!ops || !ops->gro_complete))
 		goto out_unlock;
 
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 0ff1cfd55bc4..d9fb9110f607 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -238,7 +238,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
 	       + nla_total_size(16); /* src */
 }
 
-static const struct fib_rules_ops __net_initdata fib6_rules_ops_template = {
+static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = {
 	.family			= AF_INET6,
 	.rule_size		= sizeof(struct fib6_rule),
 	.addr_size		= sizeof(struct in6_addr),
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 08ea3f0b6e55..f7c7c6319720 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -205,7 +205,7 @@ static int ip6mr_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	return 0;
 }
 
-static const struct fib_rules_ops __net_initdata ip6mr_rules_ops_template = {
+static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = {
 	.family		= RTNL_FAMILY_IP6MR,
 	.rule_size	= sizeof(struct ip6mr_rule),
 	.addr_size	= sizeof(struct in6_addr),
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 49c890386ce9..26175bffbaa0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -877,7 +877,8 @@ static void tcp_v6_send_response(struct sk_buff *skb, u32 seq, u32 ack, u32 win,
 	__tcp_v6_send_check(buff, &fl6.saddr, &fl6.daddr);
 
 	fl6.flowi6_proto = IPPROTO_TCP;
-	fl6.flowi6_oif = inet6_iif(skb);
+	if (ipv6_addr_type(&fl6.daddr) & IPV6_ADDR_LINKLOCAL)
+		fl6.flowi6_oif = inet6_iif(skb);
 	fl6.fl6_dport = t1->dest;
 	fl6.fl6_sport = t1->source;
 	security_skb_classify_flow(skb, flowi6_to_flowi(&fl6));
diff --git a/net/mac80211/mesh_sync.c b/net/mac80211/mesh_sync.c
index accfa00ffcdf..a16b7b4b1e02 100644
--- a/net/mac80211/mesh_sync.c
+++ b/net/mac80211/mesh_sync.c
@@ -56,7 +56,6 @@ void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata)
 	u64 tsfdelta;
 
 	spin_lock_bh(&ifmsh->sync_offset_lock);
-
 	if (ifmsh->sync_offset_clockdrift_max < beacon_int_fraction) {
 		msync_dbg(sdata, "TBTT : max clockdrift=%lld; adjusting\n",
 			  (long long) ifmsh->sync_offset_clockdrift_max);
@@ -69,11 +68,11 @@ void mesh_sync_adjust_tbtt(struct ieee80211_sub_if_data *sdata)
 		tsfdelta = -beacon_int_fraction;
 		ifmsh->sync_offset_clockdrift_max -= beacon_int_fraction;
 	}
+	spin_unlock_bh(&ifmsh->sync_offset_lock);
 
 	tsf = drv_get_tsf(local, sdata);
 	if (tsf != -1ULL)
 		drv_set_tsf(local, sdata, tsf + tsfdelta);
-	spin_unlock_bh(&ifmsh->sync_offset_lock);
 }
 
 static void mesh_sync_offset_rx_bcn_presp(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 2ce89732d0f2..3af0cc4130f1 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -34,7 +34,7 @@ void ieee80211_tx_status_irqsafe(struct ieee80211_hw *hw,
 		skb_queue_len(&local->skb_queue_unreliable);
 	while (tmp > IEEE80211_IRQSAFE_QUEUE_LIMIT &&
 	       (skb = skb_dequeue(&local->skb_queue_unreliable))) {
-		dev_kfree_skb_irq(skb);
+		ieee80211_free_txskb(hw, skb);
 		tmp--;
 		I802_DEBUG_INC(local->tx_status_drop);
 	}
@@ -159,7 +159,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local,
 			   "dropped TX filtered frame, queue_len=%d PS=%d @%lu\n",
 			   skb_queue_len(&sta->tx_filtered[ac]),
 			   !!test_sta_flag(sta, WLAN_STA_PS_STA), jiffies);
-	dev_kfree_skb(skb);
+	ieee80211_free_txskb(&local->hw, skb);
 }
 
 static void ieee80211_check_pending_bar(struct sta_info *sta, u8 *addr, u8 tid)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index e0e0d1d0e830..c9bf83f36657 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -354,7 +354,7 @@ static void purge_old_ps_buffers(struct ieee80211_local *local)
 			total += skb_queue_len(&sta->ps_tx_buf[ac]);
 			if (skb) {
 				purged++;
-				dev_kfree_skb(skb);
+				ieee80211_free_txskb(&local->hw, skb);
 				break;
 			}
 		}
@@ -466,7 +466,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 			ps_dbg(tx->sdata,
 			       "STA %pM TX buffer for AC %d full - dropping oldest frame\n",
 			       sta->sta.addr, ac);
-			dev_kfree_skb(old);
+			ieee80211_free_txskb(&local->hw, old);
 		} else
 			tx->local->total_ps_buffered++;
 
@@ -1103,7 +1103,7 @@ static bool ieee80211_tx_prep_agg(struct ieee80211_tx_data *tx,
 		spin_unlock(&tx->sta->lock);
 
 		if (purge_skb)
-			dev_kfree_skb(purge_skb);
+			ieee80211_free_txskb(&tx->local->hw, purge_skb);
 	}
 
 	/* reset session timer */
@@ -1214,7 +1214,7 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
 #ifdef CONFIG_MAC80211_VERBOSE_DEBUG
 		if (WARN_ON_ONCE(q >= local->hw.queues)) {
 			__skb_unlink(skb, skbs);
-			dev_kfree_skb(skb);
+			ieee80211_free_txskb(&local->hw, skb);
 			continue;
 		}
 #endif
@@ -1356,7 +1356,7 @@ static int invoke_tx_handlers(struct ieee80211_tx_data *tx)
 	if (unlikely(res == TX_DROP)) {
 		I802_DEBUG_INC(tx->local->tx_handlers_drop);
 		if (tx->skb)
-			dev_kfree_skb(tx->skb);
+			ieee80211_free_txskb(&tx->local->hw, tx->skb);
 		else
 			__skb_queue_purge(&tx->skbs);
 		return -1;
@@ -1393,7 +1393,7 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 	res_prepare = ieee80211_tx_prepare(sdata, &tx, skb);
 
 	if (unlikely(res_prepare == TX_DROP)) {
-		dev_kfree_skb(skb);
+		ieee80211_free_txskb(&local->hw, skb);
 		goto out;
 	} else if (unlikely(res_prepare == TX_QUEUED)) {
 		goto out;
@@ -1465,7 +1465,7 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb)
 	headroom = max_t(int, 0, headroom);
 
 	if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) {
-		dev_kfree_skb(skb);
+		ieee80211_free_txskb(&local->hw, skb);
 		rcu_read_unlock();
 		return;
 	}
@@ -2050,8 +2050,10 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb,
 		head_need += IEEE80211_ENCRYPT_HEADROOM;
 		head_need += local->tx_headroom;
 		head_need = max_t(int, 0, head_need);
-		if (ieee80211_skb_resize(sdata, skb, head_need, true))
-			goto fail;
+		if (ieee80211_skb_resize(sdata, skb, head_need, true)) {
+			ieee80211_free_txskb(&local->hw, skb);
+			return NETDEV_TX_OK;
+		}
 	}
 
 	if (encaps_data) {
@@ -2184,7 +2186,7 @@ void ieee80211_tx_pending(unsigned long data)
 			struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 
 			if (WARN_ON(!info->control.vif)) {
-				kfree_skb(skb);
+				ieee80211_free_txskb(&local->hw, skb);
 				continue;
 			}
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 56f6d5d81a77..cc4c8095681a 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -50,6 +50,7 @@ enum {
 				      * local
 				      */
 	IP_VS_RT_MODE_CONNECT	= 8, /* Always bind route to saddr */
+	IP_VS_RT_MODE_KNOWN_NH	= 16,/* Route via remote addr */
 };
 
 /*
@@ -113,6 +114,8 @@ static struct rtable *do_output_route4(struct net *net, __be32 daddr,
 	fl4.daddr = daddr;
 	fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
 	fl4.flowi4_tos = rtos;
+	fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
+			   FLOWI_FLAG_KNOWN_NH : 0;
 
 retry:
 	rt = ip_route_output_key(net, &fl4);
@@ -1061,7 +1064,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp,
 	if (!(rt = __ip_vs_get_out_rt(skb, cp->dest, cp->daddr.ip,
 				      RT_TOS(iph->tos),
 				      IP_VS_RT_MODE_LOCAL |
-					IP_VS_RT_MODE_NON_LOCAL, NULL)))
+				      IP_VS_RT_MODE_NON_LOCAL |
+				      IP_VS_RT_MODE_KNOWN_NH, NULL)))
 		goto tx_error_icmp;
 	if (rt->rt_flags & RTCF_LOCAL) {
 		ip_rt_put(rt);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 0f2e3ad69c47..01e944a017a4 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -169,6 +169,8 @@ static void netlink_sock_destruct(struct sock *sk)
 	if (nlk->cb) {
 		if (nlk->cb->done)
 			nlk->cb->done(nlk->cb);
+
+		module_put(nlk->cb->module);
 		netlink_destroy_callback(nlk->cb);
 	}
 
@@ -1758,6 +1760,7 @@ static int netlink_dump(struct sock *sk)
 	nlk->cb = NULL;
 	mutex_unlock(nlk->cb_mutex);
 
+	module_put(cb->module);
 	netlink_consume_callback(cb);
 	return 0;
 
@@ -1767,9 +1770,9 @@ errout_skb:
 	return err;
 }
 
-int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
-		       const struct nlmsghdr *nlh,
-		       struct netlink_dump_control *control)
+int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
+			 const struct nlmsghdr *nlh,
+			 struct netlink_dump_control *control)
 {
 	struct netlink_callback *cb;
 	struct sock *sk;
@@ -1784,6 +1787,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	cb->done = control->done;
 	cb->nlh = nlh;
 	cb->data = control->data;
+	cb->module = control->module;
 	cb->min_dump_alloc = control->min_dump_alloc;
 	atomic_inc(&skb->users);
 	cb->skb = skb;
@@ -1794,19 +1798,28 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 		return -ECONNREFUSED;
 	}
 	nlk = nlk_sk(sk);
-	/* A dump is in progress... */
+
 	mutex_lock(nlk->cb_mutex);
+	/* A dump is in progress... */
 	if (nlk->cb) {
 		mutex_unlock(nlk->cb_mutex);
 		netlink_destroy_callback(cb);
-		sock_put(sk);
-		return -EBUSY;
+		ret = -EBUSY;
+		goto out;
 	}
+	/* add reference of module which cb->dump belongs to */
+	if (!try_module_get(cb->module)) {
+		mutex_unlock(nlk->cb_mutex);
+		netlink_destroy_callback(cb);
+		ret = -EPROTONOSUPPORT;
+		goto out;
+	}
+
 	nlk->cb = cb;
 	mutex_unlock(nlk->cb_mutex);
 
 	ret = netlink_dump(sk);
-
+out:
 	sock_put(sk);
 
 	if (ret)
@@ -1817,7 +1830,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	 */
 	return -EINTR;
 }
-EXPORT_SYMBOL(netlink_dump_start);
+EXPORT_SYMBOL(__netlink_dump_start);
 
 void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
 {
diff --git a/net/rds/send.c b/net/rds/send.c
index 96531d4033a2..88eace57dd6b 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1122,7 +1122,7 @@ rds_send_pong(struct rds_connection *conn, __be16 dport)
 	rds_stats_inc(s_send_pong);
 
 	if (!test_bit(RDS_LL_SEND_FULL, &conn->c_flags))
-		rds_send_xmit(conn);
+		queue_delayed_work(rds_wq, &conn->c_send_w, 0);
 
 	rds_message_put(rm);
 	return 0;
diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c
index 011d2384b115..7633a752c65e 100644
--- a/net/rxrpc/ar-key.c
+++ b/net/rxrpc/ar-key.c
@@ -26,8 +26,8 @@
 #include "ar-internal.h"
 
 static int rxrpc_vet_description_s(const char *);
-static int rxrpc_instantiate(struct key *, const void *, size_t);
-static int rxrpc_instantiate_s(struct key *, const void *, size_t);
+static int rxrpc_instantiate(struct key *, struct key_preparsed_payload *);
+static int rxrpc_instantiate_s(struct key *, struct key_preparsed_payload *);
 static void rxrpc_destroy(struct key *);
 static void rxrpc_destroy_s(struct key *);
 static void rxrpc_describe(const struct key *, struct seq_file *);
@@ -678,7 +678,7 @@ error:
  *
  * if no data is provided, then a no-security key is made
  */
-static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen)
+static int rxrpc_instantiate(struct key *key, struct key_preparsed_payload *prep)
 {
 	const struct rxrpc_key_data_v1 *v1;
 	struct rxrpc_key_token *token, **pp;
@@ -686,26 +686,26 @@ static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen)
 	u32 kver;
 	int ret;
 
-	_enter("{%x},,%zu", key_serial(key), datalen);
+	_enter("{%x},,%zu", key_serial(key), prep->datalen);
 
 	/* handle a no-security key */
-	if (!data && datalen == 0)
+	if (!prep->data && prep->datalen == 0)
 		return 0;
 
 	/* determine if the XDR payload format is being used */
-	if (datalen > 7 * 4) {
-		ret = rxrpc_instantiate_xdr(key, data, datalen);
+	if (prep->datalen > 7 * 4) {
+		ret = rxrpc_instantiate_xdr(key, prep->data, prep->datalen);
 		if (ret != -EPROTO)
 			return ret;
 	}
 
 	/* get the key interface version number */
 	ret = -EINVAL;
-	if (datalen <= 4 || !data)
+	if (prep->datalen <= 4 || !prep->data)
 		goto error;
-	memcpy(&kver, data, sizeof(kver));
-	data += sizeof(kver);
-	datalen -= sizeof(kver);
+	memcpy(&kver, prep->data, sizeof(kver));
+	prep->data += sizeof(kver);
+	prep->datalen -= sizeof(kver);
 
 	_debug("KEY I/F VERSION: %u", kver);
 
@@ -715,11 +715,11 @@ static int rxrpc_instantiate(struct key *key, const void *data, size_t datalen)
 
 	/* deal with a version 1 key */
 	ret = -EINVAL;
-	if (datalen < sizeof(*v1))
+	if (prep->datalen < sizeof(*v1))
 		goto error;
 
-	v1 = data;
-	if (datalen != sizeof(*v1) + v1->ticket_length)
+	v1 = prep->data;
+	if (prep->datalen != sizeof(*v1) + v1->ticket_length)
 		goto error;
 
 	_debug("SCIX: %u", v1->security_index);
@@ -784,17 +784,17 @@ error:
  * instantiate a server secret key
  * data should be a pointer to the 8-byte secret key
  */
-static int rxrpc_instantiate_s(struct key *key, const void *data,
-			       size_t datalen)
+static int rxrpc_instantiate_s(struct key *key,
+			       struct key_preparsed_payload *prep)
 {
 	struct crypto_blkcipher *ci;
 
-	_enter("{%x},,%zu", key_serial(key), datalen);
+	_enter("{%x},,%zu", key_serial(key), prep->datalen);
 
-	if (datalen != 8)
+	if (prep->datalen != 8)
 		return -EINVAL;
 
-	memcpy(&key->type_data, data, 8);
+	memcpy(&key->type_data, prep->data, 8);
 
 	ci = crypto_alloc_blkcipher("pcbc(des)", 0, CRYPTO_ALG_ASYNC);
 	if (IS_ERR(ci)) {
@@ -802,7 +802,7 @@ static int rxrpc_instantiate_s(struct key *key, const void *data,
 		return PTR_ERR(ci);
 	}
 
-	if (crypto_blkcipher_setkey(ci, data, 8) < 0)
+	if (crypto_blkcipher_setkey(ci, prep->data, 8) < 0)
 		BUG();
 
 	key->payload.data = ci;
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 57f7de839b03..6773d7803627 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1642,8 +1642,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
 					asoc->outqueue.outstanding_bytes;
 			sackh.num_gap_ack_blocks = 0;
 			sackh.num_dup_tsns = 0;
+			chunk->subh.sack_hdr = &sackh;
 			sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_SACK,
-					SCTP_SACKH(&sackh));
+					SCTP_CHUNK(chunk));
 			break;
 
 		case SCTP_CMD_DISCARD_PACKET:
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d37d24ff197f..59d16ea927f0 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -70,6 +70,7 @@
 #include <linux/init.h>
 #include <linux/crypto.h>
 #include <linux/slab.h>
+#include <linux/file.h>
 
 #include <net/ip.h>
 #include <net/icmp.h>
@@ -4292,6 +4293,7 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval
 {
 	sctp_peeloff_arg_t peeloff;
 	struct socket *newsock;
+	struct file *newfile;
 	int retval = 0;
 
 	if (len < sizeof(sctp_peeloff_arg_t))
@@ -4305,22 +4307,35 @@ static int sctp_getsockopt_peeloff(struct sock *sk, int len, char __user *optval
 		goto out;
 
 	/* Map the socket to an unused fd that can be returned to the user.  */
-	retval = sock_map_fd(newsock, 0);
+	retval = get_unused_fd();
 	if (retval < 0) {
 		sock_release(newsock);
 		goto out;
 	}
 
+	newfile = sock_alloc_file(newsock, 0, NULL);
+	if (unlikely(IS_ERR(newfile))) {
+		put_unused_fd(retval);
+		sock_release(newsock);
+		return PTR_ERR(newfile);
+	}
+
 	SCTP_DEBUG_PRINTK("%s: sk: %p newsk: %p sd: %d\n",
 			  __func__, sk, newsock->sk, retval);
 
 	/* Return the fd mapped to the new socket.  */
+	if (put_user(len, optlen)) {
+		fput(newfile);
+		put_unused_fd(retval);
+		return -EFAULT;
+	}
 	peeloff.sd = retval;
-	if (put_user(len, optlen))
+	if (copy_to_user(optval, &peeloff, len)) {
+		fput(newfile);
+		put_unused_fd(retval);
 		return -EFAULT;
-	if (copy_to_user(optval, &peeloff, len))
-		retval = -EFAULT;
-
+	}
+	fd_install(retval, newfile);
 out:
 	return retval;
 }
diff --git a/net/socket.c b/net/socket.c
index 80dc7e84b046..d92c490e66fa 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -347,17 +347,11 @@ static struct file_system_type sock_fs_type = {
  *	but we take care of internal coherence yet.
  */
 
-static int sock_alloc_file(struct socket *sock, struct file **f, int flags,
-			   const char *dname)
+struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 {
 	struct qstr name = { .name = "" };
 	struct path path;
 	struct file *file;
-	int fd;
-
-	fd = get_unused_fd_flags(flags);
-	if (unlikely(fd < 0))
-		return fd;
 
 	if (dname) {
 		name.name = dname;
@@ -367,10 +361,8 @@ static int sock_alloc_file(struct socket *sock, struct file **f, int flags,
 		name.len = strlen(name.name);
 	}
 	path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
-	if (unlikely(!path.dentry)) {
-		put_unused_fd(fd);
-		return -ENOMEM;
-	}
+	if (unlikely(!path.dentry))
+		return ERR_PTR(-ENOMEM);
 	path.mnt = mntget(sock_mnt);
 
 	d_instantiate(path.dentry, SOCK_INODE(sock));
@@ -382,30 +374,33 @@ static int sock_alloc_file(struct socket *sock, struct file **f, int flags,
 		/* drop dentry, keep inode */
 		ihold(path.dentry->d_inode);
 		path_put(&path);
-		put_unused_fd(fd);
-		return -ENFILE;
+		return ERR_PTR(-ENFILE);
 	}
 
 	sock->file = file;
 	file->f_flags = O_RDWR | (flags & O_NONBLOCK);
 	file->f_pos = 0;
 	file->private_data = sock;
-
-	*f = file;
-	return fd;
+	return file;
 }
+EXPORT_SYMBOL(sock_alloc_file);
 
-int sock_map_fd(struct socket *sock, int flags)
+static int sock_map_fd(struct socket *sock, int flags)
 {
 	struct file *newfile;
-	int fd = sock_alloc_file(sock, &newfile, flags, NULL);
+	int fd = get_unused_fd_flags(flags);
+	if (unlikely(fd < 0))
+		return fd;
 
-	if (likely(fd >= 0))
+	newfile = sock_alloc_file(sock, flags, NULL);
+	if (likely(!IS_ERR(newfile))) {
 		fd_install(fd, newfile);
+		return fd;
+	}
 
-	return fd;
+	put_unused_fd(fd);
+	return PTR_ERR(newfile);
 }
-EXPORT_SYMBOL(sock_map_fd);
 
 struct socket *sock_from_file(struct file *file, int *err)
 {
@@ -1466,17 +1461,32 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
 	if (err < 0)
 		goto out_release_both;
 
-	fd1 = sock_alloc_file(sock1, &newfile1, flags, NULL);
+	fd1 = get_unused_fd_flags(flags);
 	if (unlikely(fd1 < 0)) {
 		err = fd1;
 		goto out_release_both;
 	}
-
-	fd2 = sock_alloc_file(sock2, &newfile2, flags, NULL);
+	fd2 = get_unused_fd_flags(flags);
 	if (unlikely(fd2 < 0)) {
 		err = fd2;
+		put_unused_fd(fd1);
+		goto out_release_both;
+	}
+
+	newfile1 = sock_alloc_file(sock1, flags, NULL);
+	if (unlikely(IS_ERR(newfile1))) {
+		err = PTR_ERR(newfile1);
+		put_unused_fd(fd1);
+		put_unused_fd(fd2);
+		goto out_release_both;
+	}
+
+	newfile2 = sock_alloc_file(sock2, flags, NULL);
+	if (IS_ERR(newfile2)) {
+		err = PTR_ERR(newfile2);
 		fput(newfile1);
 		put_unused_fd(fd1);
+		put_unused_fd(fd2);
 		sock_release(sock2);
 		goto out;
 	}
@@ -1608,13 +1618,19 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
 	 */
 	__module_get(newsock->ops->owner);
 
-	newfd = sock_alloc_file(newsock, &newfile, flags,
-				sock->sk->sk_prot_creator->name);
+	newfd = get_unused_fd_flags(flags);
 	if (unlikely(newfd < 0)) {
 		err = newfd;
 		sock_release(newsock);
 		goto out_put;
 	}
+	newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name);
+	if (unlikely(IS_ERR(newfile))) {
+		err = PTR_ERR(newfile);
+		put_unused_fd(newfd);
+		sock_release(newsock);
+		goto out_put;
+	}
 
 	err = security_socket_accept(sock, newsock);
 	if (err)
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 34c522021004..909dc0c31aab 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -239,7 +239,7 @@ gss_fill_context(const void *p, const void *end, struct gss_cl_ctx *ctx, struct
 	}
 	return q;
 err:
-	dprintk("RPC:       gss_fill_context returning %ld\n", -PTR_ERR(p));
+	dprintk("RPC:       %s returning %ld\n", __func__, -PTR_ERR(p));
 	return p;
 }
 
@@ -301,10 +301,10 @@ __gss_find_upcall(struct rpc_pipe *pipe, uid_t uid)
 		if (pos->uid != uid)
 			continue;
 		atomic_inc(&pos->count);
-		dprintk("RPC:       gss_find_upcall found msg %p\n", pos);
+		dprintk("RPC:       %s found msg %p\n", __func__, pos);
 		return pos;
 	}
-	dprintk("RPC:       gss_find_upcall found nothing\n");
+	dprintk("RPC:       %s found nothing\n", __func__);
 	return NULL;
 }
 
@@ -507,8 +507,8 @@ gss_refresh_upcall(struct rpc_task *task)
 	struct rpc_pipe *pipe;
 	int err = 0;
 
-	dprintk("RPC: %5u gss_refresh_upcall for uid %u\n", task->tk_pid,
-								cred->cr_uid);
+	dprintk("RPC: %5u %s for uid %u\n",
+		task->tk_pid, __func__, cred->cr_uid);
 	gss_msg = gss_setup_upcall(task->tk_client, gss_auth, cred);
 	if (PTR_ERR(gss_msg) == -EAGAIN) {
 		/* XXX: warning on the first, under the assumption we
@@ -539,8 +539,8 @@ gss_refresh_upcall(struct rpc_task *task)
 	spin_unlock(&pipe->lock);
 	gss_release_msg(gss_msg);
 out:
-	dprintk("RPC: %5u gss_refresh_upcall for uid %u result %d\n",
-			task->tk_pid, cred->cr_uid, err);
+	dprintk("RPC: %5u %s for uid %u result %d\n",
+		task->tk_pid, __func__, cred->cr_uid, err);
 	return err;
 }
 
@@ -553,7 +553,7 @@ gss_create_upcall(struct gss_auth *gss_auth, struct gss_cred *gss_cred)
 	DEFINE_WAIT(wait);
 	int err = 0;
 
-	dprintk("RPC:       gss_upcall for uid %u\n", cred->cr_uid);
+	dprintk("RPC:       %s for uid %u\n", __func__, cred->cr_uid);
 retry:
 	gss_msg = gss_setup_upcall(gss_auth->client, gss_auth, cred);
 	if (PTR_ERR(gss_msg) == -EAGAIN) {
@@ -594,8 +594,8 @@ out_intr:
 	finish_wait(&gss_msg->waitqueue, &wait);
 	gss_release_msg(gss_msg);
 out:
-	dprintk("RPC:       gss_create_upcall for uid %u result %d\n",
-			cred->cr_uid, err);
+	dprintk("RPC:       %s for uid %u result %d\n",
+		__func__, cred->cr_uid, err);
 	return err;
 }
 
@@ -681,7 +681,7 @@ err_put_ctx:
 err:
 	kfree(buf);
 out:
-	dprintk("RPC:       gss_pipe_downcall returning %Zd\n", err);
+	dprintk("RPC:       %s returning %Zd\n", __func__, err);
 	return err;
 }
 
@@ -747,8 +747,8 @@ gss_pipe_destroy_msg(struct rpc_pipe_msg *msg)
 	struct gss_upcall_msg *gss_msg = container_of(msg, struct gss_upcall_msg, msg);
 
 	if (msg->errno < 0) {
-		dprintk("RPC:       gss_pipe_destroy_msg releasing msg %p\n",
-				gss_msg);
+		dprintk("RPC:       %s releasing msg %p\n",
+			__func__, gss_msg);
 		atomic_inc(&gss_msg->count);
 		gss_unhash_msg(gss_msg);
 		if (msg->errno == -ETIMEDOUT)
@@ -976,7 +976,7 @@ gss_destroying_context(struct rpc_cred *cred)
 static void
 gss_do_free_ctx(struct gss_cl_ctx *ctx)
 {
-	dprintk("RPC:       gss_free_ctx\n");
+	dprintk("RPC:       %s\n", __func__);
 
 	gss_delete_sec_context(&ctx->gc_gss_ctx);
 	kfree(ctx->gc_wire_ctx.data);
@@ -999,7 +999,7 @@ gss_free_ctx(struct gss_cl_ctx *ctx)
 static void
 gss_free_cred(struct gss_cred *gss_cred)
 {
-	dprintk("RPC:       gss_free_cred %p\n", gss_cred);
+	dprintk("RPC:       %s cred=%p\n", __func__, gss_cred);
 	kfree(gss_cred);
 }
 
@@ -1049,8 +1049,8 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 	struct gss_cred	*cred = NULL;
 	int err = -ENOMEM;
 
-	dprintk("RPC:       gss_create_cred for uid %d, flavor %d\n",
-		acred->uid, auth->au_flavor);
+	dprintk("RPC:       %s for uid %d, flavor %d\n",
+		__func__, acred->uid, auth->au_flavor);
 
 	if (!(cred = kzalloc(sizeof(*cred), GFP_NOFS)))
 		goto out_err;
@@ -1069,7 +1069,7 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 	return &cred->gc_base;
 
 out_err:
-	dprintk("RPC:       gss_create_cred failed with error %d\n", err);
+	dprintk("RPC:       %s failed with error %d\n", __func__, err);
 	return ERR_PTR(err);
 }
 
@@ -1127,7 +1127,7 @@ gss_marshal(struct rpc_task *task, __be32 *p)
 	struct kvec	iov;
 	struct xdr_buf	verf_buf;
 
-	dprintk("RPC: %5u gss_marshal\n", task->tk_pid);
+	dprintk("RPC: %5u %s\n", task->tk_pid, __func__);
 
 	*p++ = htonl(RPC_AUTH_GSS);
 	cred_len = p++;
@@ -1253,7 +1253,7 @@ gss_validate(struct rpc_task *task, __be32 *p)
 	u32		flav,len;
 	u32		maj_stat;
 
-	dprintk("RPC: %5u gss_validate\n", task->tk_pid);
+	dprintk("RPC: %5u %s\n", task->tk_pid, __func__);
 
 	flav = ntohl(*p++);
 	if ((len = ntohl(*p++)) > RPC_MAX_AUTH_SIZE)
@@ -1271,20 +1271,20 @@ gss_validate(struct rpc_task *task, __be32 *p)
 	if (maj_stat == GSS_S_CONTEXT_EXPIRED)
 		clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
 	if (maj_stat) {
-		dprintk("RPC: %5u gss_validate: gss_verify_mic returned "
-				"error 0x%08x\n", task->tk_pid, maj_stat);
+		dprintk("RPC: %5u %s: gss_verify_mic returned error 0x%08x\n",
+			task->tk_pid, __func__, maj_stat);
 		goto out_bad;
 	}
 	/* We leave it to unwrap to calculate au_rslack. For now we just
 	 * calculate the length of the verifier: */
 	cred->cr_auth->au_verfsize = XDR_QUADLEN(len) + 2;
 	gss_put_ctx(ctx);
-	dprintk("RPC: %5u gss_validate: gss_verify_mic succeeded.\n",
-			task->tk_pid);
+	dprintk("RPC: %5u %s: gss_verify_mic succeeded.\n",
+			task->tk_pid, __func__);
 	return p + XDR_QUADLEN(len);
 out_bad:
 	gss_put_ctx(ctx);
-	dprintk("RPC: %5u gss_validate failed.\n", task->tk_pid);
+	dprintk("RPC: %5u %s failed.\n", task->tk_pid, __func__);
 	return NULL;
 }
 
@@ -1466,7 +1466,7 @@ gss_wrap_req(struct rpc_task *task,
 	struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
 	int             status = -EIO;
 
-	dprintk("RPC: %5u gss_wrap_req\n", task->tk_pid);
+	dprintk("RPC: %5u %s\n", task->tk_pid, __func__);
 	if (ctx->gc_proc != RPC_GSS_PROC_DATA) {
 		/* The spec seems a little ambiguous here, but I think that not
 		 * wrapping context destruction requests makes the most sense.
@@ -1489,7 +1489,7 @@ gss_wrap_req(struct rpc_task *task,
 	}
 out:
 	gss_put_ctx(ctx);
-	dprintk("RPC: %5u gss_wrap_req returning %d\n", task->tk_pid, status);
+	dprintk("RPC: %5u %s returning %d\n", task->tk_pid, __func__, status);
 	return status;
 }
 
@@ -1604,8 +1604,8 @@ out_decode:
 	status = gss_unwrap_req_decode(decode, rqstp, p, obj);
 out:
 	gss_put_ctx(ctx);
-	dprintk("RPC: %5u gss_unwrap_resp returning %d\n", task->tk_pid,
-			status);
+	dprintk("RPC: %5u %s returning %d\n",
+		task->tk_pid, __func__, status);
 	return status;
 }
 
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index fa48c60aef23..cdc7564b4512 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -490,61 +490,86 @@ EXPORT_SYMBOL_GPL(rpc_create);
  * same transport while varying parameters such as the authentication
  * flavour.
  */
-struct rpc_clnt *
-rpc_clone_client(struct rpc_clnt *clnt)
+static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args,
+					   struct rpc_clnt *clnt)
 {
-	struct rpc_clnt *new;
 	struct rpc_xprt *xprt;
-	int err = -ENOMEM;
+	struct rpc_clnt *new;
+	int err;
 
-	new = kmemdup(clnt, sizeof(*new), GFP_KERNEL);
-	if (!new)
-		goto out_no_clnt;
-	new->cl_parent = clnt;
-	/* Turn off autobind on clones */
-	new->cl_autobind = 0;
-	INIT_LIST_HEAD(&new->cl_tasks);
-	spin_lock_init(&new->cl_lock);
-	rpc_init_rtt(&new->cl_rtt_default, clnt->cl_timeout->to_initval);
-	new->cl_metrics = rpc_alloc_iostats(clnt);
-	if (new->cl_metrics == NULL)
-		goto out_no_stats;
-	if (clnt->cl_principal) {
-		new->cl_principal = kstrdup(clnt->cl_principal, GFP_KERNEL);
-		if (new->cl_principal == NULL)
-			goto out_no_principal;
-	}
+	err = -ENOMEM;
 	rcu_read_lock();
 	xprt = xprt_get(rcu_dereference(clnt->cl_xprt));
 	rcu_read_unlock();
 	if (xprt == NULL)
-		goto out_no_transport;
-	rcu_assign_pointer(new->cl_xprt, xprt);
-	atomic_set(&new->cl_count, 1);
-	err = rpc_setup_pipedir(new, clnt->cl_program->pipe_dir_name);
-	if (err != 0)
-		goto out_no_path;
-	rpc_clnt_set_nodename(new, utsname()->nodename);
-	if (new->cl_auth)
-		atomic_inc(&new->cl_auth->au_count);
+		goto out_err;
+	args->servername = xprt->servername;
+
+	new = rpc_new_client(args, xprt);
+	if (IS_ERR(new)) {
+		err = PTR_ERR(new);
+		goto out_put;
+	}
+
 	atomic_inc(&clnt->cl_count);
-	rpc_register_client(new);
-	rpciod_up();
+	new->cl_parent = clnt;
+
+	/* Turn off autobind on clones */
+	new->cl_autobind = 0;
+	new->cl_softrtry = clnt->cl_softrtry;
+	new->cl_discrtry = clnt->cl_discrtry;
+	new->cl_chatty = clnt->cl_chatty;
 	return new;
-out_no_path:
+
+out_put:
 	xprt_put(xprt);
-out_no_transport:
-	kfree(new->cl_principal);
-out_no_principal:
-	rpc_free_iostats(new->cl_metrics);
-out_no_stats:
-	kfree(new);
-out_no_clnt:
+out_err:
 	dprintk("RPC:       %s: returned error %d\n", __func__, err);
 	return ERR_PTR(err);
 }
+
+/**
+ * rpc_clone_client - Clone an RPC client structure
+ *
+ * @clnt: RPC client whose parameters are copied
+ *
+ * Returns a fresh RPC client or an ERR_PTR.
+ */
+struct rpc_clnt *rpc_clone_client(struct rpc_clnt *clnt)
+{
+	struct rpc_create_args args = {
+		.program	= clnt->cl_program,
+		.prognumber	= clnt->cl_prog,
+		.version	= clnt->cl_vers,
+		.authflavor	= clnt->cl_auth->au_flavor,
+		.client_name	= clnt->cl_principal,
+	};
+	return __rpc_clone_client(&args, clnt);
+}
 EXPORT_SYMBOL_GPL(rpc_clone_client);
 
+/**
+ * rpc_clone_client_set_auth - Clone an RPC client structure and set its auth
+ *
+ * @clnt: RPC client whose parameters are copied
+ * @auth: security flavor for new client
+ *
+ * Returns a fresh RPC client or an ERR_PTR.
+ */
+struct rpc_clnt *
+rpc_clone_client_set_auth(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
+{
+	struct rpc_create_args args = {
+		.program	= clnt->cl_program,
+		.prognumber	= clnt->cl_prog,
+		.version	= clnt->cl_vers,
+		.authflavor	= flavor,
+		.client_name	= clnt->cl_principal,
+	};
+	return __rpc_clone_client(&args, clnt);
+}
+EXPORT_SYMBOL_GPL(rpc_clone_client_set_auth);
+
 /*
  * Kill all tasks for the given client.
  * XXX: kill their descendants as well?
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 21fde99e5c56..80f5dd23417d 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1119,8 +1119,8 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
 		return -ENOMEM;
 	if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL))
 		return -ENOMEM;
-	dprintk("RPC:	sending pipefs MOUNT notification for net %p%s\n", net,
-								NET_NAME(net));
+	dprintk("RPC:       sending pipefs MOUNT notification for net %p%s\n",
+		net, NET_NAME(net));
 	sn->pipefs_sb = sb;
 	err = blocking_notifier_call_chain(&rpc_pipefs_notifier_list,
 					   RPC_PIPEFS_MOUNT,
@@ -1155,8 +1155,8 @@ static void rpc_kill_sb(struct super_block *sb)
 	sn->pipefs_sb = NULL;
 	mutex_unlock(&sn->pipefs_sb_lock);
 	put_net(net);
-	dprintk("RPC:	sending pipefs UMOUNT notification for net %p%s\n", net,
-								NET_NAME(net));
+	dprintk("RPC:       sending pipefs UMOUNT notification for net %p%s\n",
+		net, NET_NAME(net));
 	blocking_notifier_call_chain(&rpc_pipefs_notifier_list,
 					   RPC_PIPEFS_UMOUNT,
 					   sb);
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 128494ec9a64..6357fcb00c7e 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -1022,7 +1022,7 @@ static int rpciod_start(void)
 	 * Create the rpciod thread and wait for it to start.
 	 */
 	dprintk("RPC:       creating workqueue rpciod\n");
-	wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM, 0);
+	wq = alloc_workqueue("rpciod", WQ_MEM_RECLAIM, 1);
 	rpciod_workqueue = wq;
 	return rpciod_workqueue != NULL;
 }
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index bac973a31367..194d865fae72 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -208,6 +208,35 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 	return xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
 }
 
+/*
+ * svc_xprt_received conditionally queues the transport for processing
+ * by another thread. The caller must hold the XPT_BUSY bit and must
+ * not thereafter touch transport data.
+ *
+ * Note: XPT_DATA only gets cleared when a read-attempt finds no (or
+ * insufficient) data.
+ */
+static void svc_xprt_received(struct svc_xprt *xprt)
+{
+	BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags));
+	/* As soon as we clear busy, the xprt could be closed and
+	 * 'put', so we need a reference to call svc_xprt_enqueue with:
+	 */
+	svc_xprt_get(xprt);
+	clear_bit(XPT_BUSY, &xprt->xpt_flags);
+	svc_xprt_enqueue(xprt);
+	svc_xprt_put(xprt);
+}
+
+void svc_add_new_perm_xprt(struct svc_serv *serv, struct svc_xprt *new)
+{
+	clear_bit(XPT_TEMP, &new->xpt_flags);
+	spin_lock_bh(&serv->sv_lock);
+	list_add(&new->xpt_list, &serv->sv_permsocks);
+	spin_unlock_bh(&serv->sv_lock);
+	svc_xprt_received(new);
+}
+
 int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
 		    struct net *net, const int family,
 		    const unsigned short port, int flags)
@@ -232,13 +261,8 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
 			module_put(xcl->xcl_owner);
 			return PTR_ERR(newxprt);
 		}
-
-		clear_bit(XPT_TEMP, &newxprt->xpt_flags);
-		spin_lock_bh(&serv->sv_lock);
-		list_add(&newxprt->xpt_list, &serv->sv_permsocks);
-		spin_unlock_bh(&serv->sv_lock);
+		svc_add_new_perm_xprt(serv, newxprt);
 		newport = svc_xprt_local_port(newxprt);
-		clear_bit(XPT_BUSY, &newxprt->xpt_flags);
 		return newport;
 	}
  err:
@@ -394,27 +418,6 @@ static struct svc_xprt *svc_xprt_dequeue(struct svc_pool *pool)
 	return xprt;
 }
 
-/*
- * svc_xprt_received conditionally queues the transport for processing
- * by another thread. The caller must hold the XPT_BUSY bit and must
- * not thereafter touch transport data.
- *
- * Note: XPT_DATA only gets cleared when a read-attempt finds no (or
- * insufficient) data.
- */
-void svc_xprt_received(struct svc_xprt *xprt)
-{
-	BUG_ON(!test_bit(XPT_BUSY, &xprt->xpt_flags));
-	/* As soon as we clear busy, the xprt could be closed and
-	 * 'put', so we need a reference to call svc_xprt_enqueue with:
-	 */
-	svc_xprt_get(xprt);
-	clear_bit(XPT_BUSY, &xprt->xpt_flags);
-	svc_xprt_enqueue(xprt);
-	svc_xprt_put(xprt);
-}
-EXPORT_SYMBOL_GPL(svc_xprt_received);
-
 /**
  * svc_reserve - change the space reserved for the reply to a request.
  * @rqstp:  The request in question
@@ -565,33 +568,12 @@ static void svc_check_conn_limits(struct svc_serv *serv)
 	}
 }
 
-/*
- * Receive the next request on any transport.  This code is carefully
- * organised not to touch any cachelines in the shared svc_serv
- * structure, only cachelines in the local svc_pool.
- */
-int svc_recv(struct svc_rqst *rqstp, long timeout)
+int svc_alloc_arg(struct svc_rqst *rqstp)
 {
-	struct svc_xprt		*xprt = NULL;
-	struct svc_serv		*serv = rqstp->rq_server;
-	struct svc_pool		*pool = rqstp->rq_pool;
-	int			len, i;
-	int			pages;
-	struct xdr_buf		*arg;
-	DECLARE_WAITQUEUE(wait, current);
-	long			time_left;
-
-	dprintk("svc: server %p waiting for data (to = %ld)\n",
-		rqstp, timeout);
-
-	if (rqstp->rq_xprt)
-		printk(KERN_ERR
-			"svc_recv: service %p, transport not NULL!\n",
-			 rqstp);
-	if (waitqueue_active(&rqstp->rq_wait))
-		printk(KERN_ERR
-			"svc_recv: service %p, wait queue active!\n",
-			 rqstp);
+	struct svc_serv *serv = rqstp->rq_server;
+	struct xdr_buf *arg;
+	int pages;
+	int i;
 
 	/* now allocate needed pages.  If we get a failure, sleep briefly */
 	pages = (serv->sv_max_mesg + PAGE_SIZE) / PAGE_SIZE;
@@ -621,11 +603,15 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	arg->page_len = (pages-2)*PAGE_SIZE;
 	arg->len = (pages-1)*PAGE_SIZE;
 	arg->tail[0].iov_len = 0;
+	return 0;
+}
 
-	try_to_freeze();
-	cond_resched();
-	if (signalled() || kthread_should_stop())
-		return -EINTR;
+struct svc_xprt *svc_get_next_xprt(struct svc_rqst *rqstp, long timeout)
+{
+	struct svc_xprt *xprt;
+	struct svc_pool		*pool = rqstp->rq_pool;
+	DECLARE_WAITQUEUE(wait, current);
+	long			time_left;
 
 	/* Normally we will wait up to 5 seconds for any required
 	 * cache information to be provided.
@@ -663,7 +649,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		if (kthread_should_stop()) {
 			set_current_state(TASK_RUNNING);
 			spin_unlock_bh(&pool->sp_lock);
-			return -EINTR;
+			return ERR_PTR(-EINTR);
 		}
 
 		add_wait_queue(&rqstp->rq_wait, &wait);
@@ -684,48 +670,58 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 			spin_unlock_bh(&pool->sp_lock);
 			dprintk("svc: server %p, no data yet\n", rqstp);
 			if (signalled() || kthread_should_stop())
-				return -EINTR;
+				return ERR_PTR(-EINTR);
 			else
-				return -EAGAIN;
+				return ERR_PTR(-EAGAIN);
 		}
 	}
 	spin_unlock_bh(&pool->sp_lock);
+	return xprt;
+}
+
+void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt)
+{
+	spin_lock_bh(&serv->sv_lock);
+	set_bit(XPT_TEMP, &newxpt->xpt_flags);
+	list_add(&newxpt->xpt_list, &serv->sv_tempsocks);
+	serv->sv_tmpcnt++;
+	if (serv->sv_temptimer.function == NULL) {
+		/* setup timer to age temp transports */
+		setup_timer(&serv->sv_temptimer, svc_age_temp_xprts,
+			    (unsigned long)serv);
+		mod_timer(&serv->sv_temptimer,
+			  jiffies + svc_conn_age_period * HZ);
+	}
+	spin_unlock_bh(&serv->sv_lock);
+	svc_xprt_received(newxpt);
+}
+
+static int svc_handle_xprt(struct svc_rqst *rqstp, struct svc_xprt *xprt)
+{
+	struct svc_serv *serv = rqstp->rq_server;
+	int len = 0;
 
-	len = 0;
 	if (test_bit(XPT_CLOSE, &xprt->xpt_flags)) {
 		dprintk("svc_recv: found XPT_CLOSE\n");
 		svc_delete_xprt(xprt);
 		/* Leave XPT_BUSY set on the dead xprt: */
-		goto out;
+		return 0;
 	}
 	if (test_bit(XPT_LISTENER, &xprt->xpt_flags)) {
 		struct svc_xprt *newxpt;
+		/*
+		 * We know this module_get will succeed because the
+		 * listener holds a reference too
+		 */
+		__module_get(xprt->xpt_class->xcl_owner);
+		svc_check_conn_limits(xprt->xpt_server);
 		newxpt = xprt->xpt_ops->xpo_accept(xprt);
-		if (newxpt) {
-			/*
-			 * We know this module_get will succeed because the
-			 * listener holds a reference too
-			 */
-			__module_get(newxpt->xpt_class->xcl_owner);
-			svc_check_conn_limits(xprt->xpt_server);
-			spin_lock_bh(&serv->sv_lock);
-			set_bit(XPT_TEMP, &newxpt->xpt_flags);
-			list_add(&newxpt->xpt_list, &serv->sv_tempsocks);
-			serv->sv_tmpcnt++;
-			if (serv->sv_temptimer.function == NULL) {
-				/* setup timer to age temp transports */
-				setup_timer(&serv->sv_temptimer,
-					    svc_age_temp_xprts,
-					    (unsigned long)serv);
-				mod_timer(&serv->sv_temptimer,
-					  jiffies + svc_conn_age_period * HZ);
-			}
-			spin_unlock_bh(&serv->sv_lock);
-			svc_xprt_received(newxpt);
-		}
+		if (newxpt)
+			svc_add_new_temp_xprt(serv, newxpt);
 	} else if (xprt->xpt_ops->xpo_has_wspace(xprt)) {
+		/* XPT_DATA|XPT_DEFERRED case: */
 		dprintk("svc: server %p, pool %u, transport %p, inuse=%d\n",
-			rqstp, pool->sp_id, xprt,
+			rqstp, rqstp->rq_pool->sp_id, xprt,
 			atomic_read(&xprt->xpt_ref.refcount));
 		rqstp->rq_deferred = svc_deferred_dequeue(xprt);
 		if (rqstp->rq_deferred)
@@ -736,10 +732,51 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		rqstp->rq_reserved = serv->sv_max_mesg;
 		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
 	}
+	/* clear XPT_BUSY: */
 	svc_xprt_received(xprt);
+	return len;
+}
+
+/*
+ * Receive the next request on any transport.  This code is carefully
+ * organised not to touch any cachelines in the shared svc_serv
+ * structure, only cachelines in the local svc_pool.
+ */
+int svc_recv(struct svc_rqst *rqstp, long timeout)
+{
+	struct svc_xprt		*xprt = NULL;
+	struct svc_serv		*serv = rqstp->rq_server;
+	int			len, err;
+
+	dprintk("svc: server %p waiting for data (to = %ld)\n",
+		rqstp, timeout);
+
+	if (rqstp->rq_xprt)
+		printk(KERN_ERR
+			"svc_recv: service %p, transport not NULL!\n",
+			 rqstp);
+	if (waitqueue_active(&rqstp->rq_wait))
+		printk(KERN_ERR
+			"svc_recv: service %p, wait queue active!\n",
+			 rqstp);
+
+	err = svc_alloc_arg(rqstp);
+	if (err)
+		return err;
+
+	try_to_freeze();
+	cond_resched();
+	if (signalled() || kthread_should_stop())
+		return -EINTR;
+
+	xprt = svc_get_next_xprt(rqstp, timeout);
+	if (IS_ERR(xprt))
+		return PTR_ERR(xprt);
+
+	len = svc_handle_xprt(rqstp, xprt);
 
 	/* No data, incomplete (TCP) read, or accept() */
-	if (len == 0 || len == -EAGAIN)
+	if (len <= 0)
 		goto out;
 
 	clear_bit(XPT_OLD, &xprt->xpt_flags);
@@ -917,16 +954,18 @@ void svc_close_xprt(struct svc_xprt *xprt)
 }
 EXPORT_SYMBOL_GPL(svc_close_xprt);
 
-static void svc_close_list(struct list_head *xprt_list, struct net *net)
+static void svc_close_list(struct svc_serv *serv, struct list_head *xprt_list, struct net *net)
 {
 	struct svc_xprt *xprt;
 
+	spin_lock(&serv->sv_lock);
 	list_for_each_entry(xprt, xprt_list, xpt_list) {
 		if (xprt->xpt_net != net)
 			continue;
 		set_bit(XPT_CLOSE, &xprt->xpt_flags);
 		set_bit(XPT_BUSY, &xprt->xpt_flags);
 	}
+	spin_unlock(&serv->sv_lock);
 }
 
 static void svc_clear_pools(struct svc_serv *serv, struct net *net)
@@ -949,24 +988,28 @@ static void svc_clear_pools(struct svc_serv *serv, struct net *net)
 	}
 }
 
-static void svc_clear_list(struct list_head *xprt_list, struct net *net)
+static void svc_clear_list(struct svc_serv *serv, struct list_head *xprt_list, struct net *net)
 {
 	struct svc_xprt *xprt;
 	struct svc_xprt *tmp;
+	LIST_HEAD(victims);
 
+	spin_lock(&serv->sv_lock);
 	list_for_each_entry_safe(xprt, tmp, xprt_list, xpt_list) {
 		if (xprt->xpt_net != net)
 			continue;
-		svc_delete_xprt(xprt);
+		list_move(&xprt->xpt_list, &victims);
 	}
-	list_for_each_entry(xprt, xprt_list, xpt_list)
-		BUG_ON(xprt->xpt_net == net);
+	spin_unlock(&serv->sv_lock);
+
+	list_for_each_entry_safe(xprt, tmp, &victims, xpt_list)
+		svc_delete_xprt(xprt);
 }
 
 void svc_close_net(struct svc_serv *serv, struct net *net)
 {
-	svc_close_list(&serv->sv_tempsocks, net);
-	svc_close_list(&serv->sv_permsocks, net);
+	svc_close_list(serv, &serv->sv_tempsocks, net);
+	svc_close_list(serv, &serv->sv_permsocks, net);
 
 	svc_clear_pools(serv, net);
 	/*
@@ -974,8 +1017,8 @@ void svc_close_net(struct svc_serv *serv, struct net *net)
 	 * svc_xprt_enqueue will not add new entries without taking the
 	 * sp_lock and checking XPT_BUSY.
 	 */
-	svc_clear_list(&serv->sv_tempsocks, net);
-	svc_clear_list(&serv->sv_permsocks, net);
+	svc_clear_list(serv, &serv->sv_tempsocks, net);
+	svc_clear_list(serv, &serv->sv_permsocks, net);
 }
 
 /*
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 998aa8c1807c..03827cef1fa7 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -59,7 +59,7 @@
 
 
 static struct svc_sock *svc_setup_socket(struct svc_serv *, struct socket *,
-					 int *errp, int flags);
+					 int flags);
 static void		svc_udp_data_ready(struct sock *, int);
 static int		svc_udp_recvfrom(struct svc_rqst *);
 static int		svc_udp_sendto(struct svc_rqst *);
@@ -305,57 +305,6 @@ static int svc_one_sock_name(struct svc_sock *svsk, char *buf, int remaining)
 	return len;
 }
 
-/**
- * svc_sock_names - construct a list of listener names in a string
- * @serv: pointer to RPC service
- * @buf: pointer to a buffer to fill in with socket names
- * @buflen: size of the buffer to be filled
- * @toclose: pointer to '\0'-terminated C string containing the name
- *		of a listener to be closed
- *
- * Fills in @buf with a '\n'-separated list of names of listener
- * sockets.  If @toclose is not NULL, the socket named by @toclose
- * is closed, and is not included in the output list.
- *
- * Returns positive length of the socket name string, or a negative
- * errno value on error.
- */
-int svc_sock_names(struct svc_serv *serv, char *buf, const size_t buflen,
-		   const char *toclose)
-{
-	struct svc_sock *svsk, *closesk = NULL;
-	int len = 0;
-
-	if (!serv)
-		return 0;
-
-	spin_lock_bh(&serv->sv_lock);
-	list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list) {
-		int onelen = svc_one_sock_name(svsk, buf + len, buflen - len);
-		if (onelen < 0) {
-			len = onelen;
-			break;
-		}
-		if (toclose && strcmp(toclose, buf + len) == 0) {
-			closesk = svsk;
-			svc_xprt_get(&closesk->sk_xprt);
-		} else
-			len += onelen;
-	}
-	spin_unlock_bh(&serv->sv_lock);
-
-	if (closesk) {
-		/* Should unregister with portmap, but you cannot
-		 * unregister just one protocol...
-		 */
-		svc_close_xprt(&closesk->sk_xprt);
-		svc_xprt_put(&closesk->sk_xprt);
-	} else if (toclose)
-		return -ENOENT;
-	return len;
-}
-EXPORT_SYMBOL_GPL(svc_sock_names);
-
 /*
  * Check input queue length
  */
@@ -598,11 +547,9 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 			dprintk("svc: recvfrom returned error %d\n", -err);
 			set_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags);
 		}
-		return -EAGAIN;
+		return 0;
 	}
 	len = svc_addr_len(svc_addr(rqstp));
-	if (len == 0)
-		return -EAFNOSUPPORT;
 	rqstp->rq_addrlen = len;
 	if (skb->tstamp.tv64 == 0) {
 		skb->tstamp = ktime_get_real();
@@ -620,10 +567,7 @@ static int svc_udp_recvfrom(struct svc_rqst *rqstp)
 	if (!svc_udp_get_dest_address(rqstp, cmh)) {
 		net_warn_ratelimited("svc: received unknown control message %d/%d; dropping RPC reply datagram\n",
 				     cmh->cmsg_level, cmh->cmsg_type);
-out_free:
-		trace_kfree_skb(skb, svc_udp_recvfrom);
-		skb_free_datagram_locked(svsk->sk_sk, skb);
-		return 0;
+		goto out_free;
 	}
 	rqstp->rq_daddrlen = svc_addr_len(svc_daddr(rqstp));
 
@@ -662,6 +606,10 @@ out_free:
 		serv->sv_stats->netudpcnt++;
 
 	return len;
+out_free:
+	trace_kfree_skb(skb, svc_udp_recvfrom);
+	skb_free_datagram_locked(svsk->sk_sk, skb);
+	return 0;
 }
 
 static int
@@ -900,8 +848,9 @@ static struct svc_xprt *svc_tcp_accept(struct svc_xprt *xprt)
 	 */
 	newsock->sk->sk_sndtimeo = HZ*30;
 
-	if (!(newsvsk = svc_setup_socket(serv, newsock, &err,
-				 (SVC_SOCK_ANONYMOUS | SVC_SOCK_TEMPORARY))))
+	newsvsk = svc_setup_socket(serv, newsock,
+				 (SVC_SOCK_ANONYMOUS | SVC_SOCK_TEMPORARY));
+	if (IS_ERR(newsvsk))
 		goto failed;
 	svc_xprt_set_remote(&newsvsk->sk_xprt, sin, slen);
 	err = kernel_getsockname(newsock, sin, &slen);
@@ -1174,13 +1123,13 @@ error:
 	if (len != -EAGAIN)
 		goto err_other;
 	dprintk("RPC: TCP recvfrom got EAGAIN\n");
-	return -EAGAIN;
+	return 0;
 err_other:
 	printk(KERN_NOTICE "%s: recvfrom returned errno %d\n",
 	       svsk->sk_xprt.xpt_server->sv_name, -len);
 	set_bit(XPT_CLOSE, &svsk->sk_xprt.xpt_flags);
 err_noclose:
-	return -EAGAIN;	/* record not complete */
+	return 0;	/* record not complete */
 }
 
 /*
@@ -1383,29 +1332,29 @@ EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
  */
 static struct svc_sock *svc_setup_socket(struct svc_serv *serv,
 						struct socket *sock,
-						int *errp, int flags)
+						int flags)
 {
 	struct svc_sock	*svsk;
 	struct sock	*inet;
 	int		pmap_register = !(flags & SVC_SOCK_ANONYMOUS);
+	int		err = 0;
 
 	dprintk("svc: svc_setup_socket %p\n", sock);
-	if (!(svsk = kzalloc(sizeof(*svsk), GFP_KERNEL))) {
-		*errp = -ENOMEM;
-		return NULL;
-	}
+	svsk = kzalloc(sizeof(*svsk), GFP_KERNEL);
+	if (!svsk)
+		return ERR_PTR(-ENOMEM);
 
 	inet = sock->sk;
 
 	/* Register socket with portmapper */
-	if (*errp >= 0 && pmap_register)
-		*errp = svc_register(serv, sock_net(sock->sk), inet->sk_family,
+	if (pmap_register)
+		err = svc_register(serv, sock_net(sock->sk), inet->sk_family,
 				     inet->sk_protocol,
 				     ntohs(inet_sk(inet)->inet_sport));
 
-	if (*errp < 0) {
+	if (err < 0) {
 		kfree(svsk);
-		return NULL;
+		return ERR_PTR(err);
 	}
 
 	inet->sk_user_data = svsk;
@@ -1450,42 +1399,38 @@ int svc_addsock(struct svc_serv *serv, const int fd, char *name_return,
 	int err = 0;
 	struct socket *so = sockfd_lookup(fd, &err);
 	struct svc_sock *svsk = NULL;
+	struct sockaddr_storage addr;
+	struct sockaddr *sin = (struct sockaddr *)&addr;
+	int salen;
 
 	if (!so)
 		return err;
+	err = -EAFNOSUPPORT;
 	if ((so->sk->sk_family != PF_INET) && (so->sk->sk_family != PF_INET6))
-		err =  -EAFNOSUPPORT;
-	else if (so->sk->sk_protocol != IPPROTO_TCP &&
+		goto out;
+	err =  -EPROTONOSUPPORT;
+	if (so->sk->sk_protocol != IPPROTO_TCP &&
 	    so->sk->sk_protocol != IPPROTO_UDP)
-		err =  -EPROTONOSUPPORT;
-	else if (so->state > SS_UNCONNECTED)
-		err = -EISCONN;
-	else {
-		if (!try_module_get(THIS_MODULE))
-			err = -ENOENT;
-		else
-			svsk = svc_setup_socket(serv, so, &err,
-						SVC_SOCK_DEFAULTS);
-		if (svsk) {
-			struct sockaddr_storage addr;
-			struct sockaddr *sin = (struct sockaddr *)&addr;
-			int salen;
-			if (kernel_getsockname(svsk->sk_sock, sin, &salen) == 0)
-				svc_xprt_set_local(&svsk->sk_xprt, sin, salen);
-			clear_bit(XPT_TEMP, &svsk->sk_xprt.xpt_flags);
-			spin_lock_bh(&serv->sv_lock);
-			list_add(&svsk->sk_xprt.xpt_list, &serv->sv_permsocks);
-			spin_unlock_bh(&serv->sv_lock);
-			svc_xprt_received(&svsk->sk_xprt);
-			err = 0;
-		} else
-			module_put(THIS_MODULE);
-	}
-	if (err) {
-		sockfd_put(so);
-		return err;
+		goto out;
+	err = -EISCONN;
+	if (so->state > SS_UNCONNECTED)
+		goto out;
+	err = -ENOENT;
+	if (!try_module_get(THIS_MODULE))
+		goto out;
+	svsk = svc_setup_socket(serv, so, SVC_SOCK_DEFAULTS);
+	if (IS_ERR(svsk)) {
+		module_put(THIS_MODULE);
+		err = PTR_ERR(svsk);
+		goto out;
 	}
+	if (kernel_getsockname(svsk->sk_sock, sin, &salen) == 0)
+		svc_xprt_set_local(&svsk->sk_xprt, sin, salen);
+	svc_add_new_perm_xprt(serv, &svsk->sk_xprt);
 	return svc_one_sock_name(svsk, name_return, len);
+out:
+	sockfd_put(so);
+	return err;
 }
 EXPORT_SYMBOL_GPL(svc_addsock);
 
@@ -1563,11 +1508,13 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 			goto bummer;
 	}
 
-	if ((svsk = svc_setup_socket(serv, sock, &error, flags)) != NULL) {
-		svc_xprt_set_local(&svsk->sk_xprt, newsin, newlen);
-		return (struct svc_xprt *)svsk;
+	svsk = svc_setup_socket(serv, sock, flags);
+	if (IS_ERR(svsk)) {
+		error = PTR_ERR(svsk);
+		goto bummer;
 	}
-
+	svc_xprt_set_local(&svsk->sk_xprt, newsin, newlen);
+	return (struct svc_xprt *)svsk;
 bummer:
 	dprintk("svc: svc_create_socket error = %d\n", -error);
 	sock_release(sock);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 0afba1b4b656..08f50afd5f2a 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -730,19 +730,24 @@ static unsigned int xdr_align_pages(struct xdr_stream *xdr, unsigned int len)
 
 	if (xdr->nwords == 0)
 		return 0;
-	if (nwords > xdr->nwords) {
-		nwords = xdr->nwords;
-		len = nwords << 2;
-	}
 	/* Realign pages to current pointer position */
 	iov  = buf->head;
-	if (iov->iov_len > cur)
+	if (iov->iov_len > cur) {
 		xdr_shrink_bufhead(buf, iov->iov_len - cur);
+		xdr->nwords = XDR_QUADLEN(buf->len - cur);
+	}
 
-	/* Truncate page data and move it into the tail */
-	if (buf->page_len > len)
+	if (nwords > xdr->nwords) {
+		nwords = xdr->nwords;
+		len = nwords << 2;
+	}
+	if (buf->page_len <= len)
+		len = buf->page_len;
+	else if (nwords < xdr->nwords) {
+		/* Truncate page data and move it into the tail */
 		xdr_shrink_pagelen(buf, buf->page_len - len);
-	xdr->nwords = XDR_QUADLEN(buf->len - cur);
+		xdr->nwords = XDR_QUADLEN(buf->len - cur);
+	}
 	return len;
 }
 
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 5d7f61d7559c..bd462a532acf 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -231,7 +231,7 @@ EXPORT_SYMBOL_GPL(xprt_reserve_xprt);
 static void xprt_clear_locked(struct rpc_xprt *xprt)
 {
 	xprt->snd_task = NULL;
-	if (!test_bit(XPRT_CLOSE_WAIT, &xprt->state) || xprt->shutdown) {
+	if (!test_bit(XPRT_CLOSE_WAIT, &xprt->state)) {
 		smp_mb__before_clear_bit();
 		clear_bit(XPRT_LOCKED, &xprt->state);
 		smp_mb__after_clear_bit();
@@ -504,9 +504,6 @@ EXPORT_SYMBOL_GPL(xprt_wait_for_buffer_space);
  */
 void xprt_write_space(struct rpc_xprt *xprt)
 {
-	if (unlikely(xprt->shutdown))
-		return;
-
 	spin_lock_bh(&xprt->transport_lock);
 	if (xprt->snd_task) {
 		dprintk("RPC:       write space: waking waiting task on "
@@ -679,7 +676,7 @@ xprt_init_autodisconnect(unsigned long data)
 	struct rpc_xprt *xprt = (struct rpc_xprt *)data;
 
 	spin_lock(&xprt->transport_lock);
-	if (!list_empty(&xprt->recv) || xprt->shutdown)
+	if (!list_empty(&xprt->recv))
 		goto out_abort;
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state))
 		goto out_abort;
@@ -1262,7 +1259,6 @@ out:
 static void xprt_destroy(struct rpc_xprt *xprt)
 {
 	dprintk("RPC:       destroying transport %p\n", xprt);
-	xprt->shutdown = 1;
 	del_timer_sync(&xprt->timer);
 
 	rpc_destroy_wait_queue(&xprt->binding);
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 73b428bef598..62e4f9bcc387 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -578,10 +578,6 @@ static void handle_connect_req(struct rdma_cm_id *new_cma_id, size_t client_ird)
 	list_add_tail(&newxprt->sc_accept_q, &listen_xprt->sc_accept_q);
 	spin_unlock_bh(&listen_xprt->sc_lock);
 
-	/*
-	 * Can't use svc_xprt_received here because we are not on a
-	 * rqstp thread
-	*/
 	set_bit(XPT_CONN, &listen_xprt->sc_xprt.xpt_flags);
 	svc_xprt_enqueue(&listen_xprt->sc_xprt);
 }
diff --git a/net/sunrpc/xprtrdma/transport.c b/net/sunrpc/xprtrdma/transport.c
index 5d9202dc7cb1..c9aa7a35f3bf 100644
--- a/net/sunrpc/xprtrdma/transport.c
+++ b/net/sunrpc/xprtrdma/transport.c
@@ -199,21 +199,15 @@ xprt_rdma_connect_worker(struct work_struct *work)
 	struct rpc_xprt *xprt = &r_xprt->xprt;
 	int rc = 0;
 
-	if (!xprt->shutdown) {
-		current->flags |= PF_FSTRANS;
-		xprt_clear_connected(xprt);
-
-		dprintk("RPC:       %s: %sconnect\n", __func__,
-				r_xprt->rx_ep.rep_connected != 0 ? "re" : "");
-		rc = rpcrdma_ep_connect(&r_xprt->rx_ep, &r_xprt->rx_ia);
-		if (rc)
-			goto out;
-	}
-	goto out_clear;
+	current->flags |= PF_FSTRANS;
+	xprt_clear_connected(xprt);
+
+	dprintk("RPC:       %s: %sconnect\n", __func__,
+			r_xprt->rx_ep.rep_connected != 0 ? "re" : "");
+	rc = rpcrdma_ep_connect(&r_xprt->rx_ep, &r_xprt->rx_ia);
+	if (rc)
+		xprt_wake_pending_tasks(xprt, rc);
 
-out:
-	xprt_wake_pending_tasks(xprt, rc);
-out_clear:
 	dprintk("RPC:       %s: exit\n", __func__);
 	xprt_clear_connecting(xprt);
 	current->flags &= ~PF_FSTRANS;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index a35b8e52e551..aaaadfbe36e9 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -917,9 +917,6 @@ static void xs_local_data_ready(struct sock *sk, int len)
 	if (skb == NULL)
 		goto out;
 
-	if (xprt->shutdown)
-		goto dropit;
-
 	repsize = skb->len - sizeof(rpc_fraghdr);
 	if (repsize < 4) {
 		dprintk("RPC:       impossible RPC reply size %d\n", repsize);
@@ -981,9 +978,6 @@ static void xs_udp_data_ready(struct sock *sk, int len)
 	if ((skb = skb_recv_datagram(sk, 0, 1, &err)) == NULL)
 		goto out;
 
-	if (xprt->shutdown)
-		goto dropit;
-
 	repsize = skb->len - sizeof(struct udphdr);
 	if (repsize < 4) {
 		dprintk("RPC:       impossible RPC reply size %d!\n", repsize);
@@ -1025,6 +1019,16 @@ static void xs_udp_data_ready(struct sock *sk, int len)
 	read_unlock_bh(&sk->sk_callback_lock);
 }
 
+/*
+ * Helper function to force a TCP close if the server is sending
+ * junk and/or it has put us in CLOSE_WAIT
+ */
+static void xs_tcp_force_close(struct rpc_xprt *xprt)
+{
+	set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
+	xprt_force_disconnect(xprt);
+}
+
 static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_reader *desc)
 {
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
@@ -1051,7 +1055,7 @@ static inline void xs_tcp_read_fraghdr(struct rpc_xprt *xprt, struct xdr_skb_rea
 	/* Sanity check of the record length */
 	if (unlikely(transport->tcp_reclen < 8)) {
 		dprintk("RPC:       invalid TCP record fragment length\n");
-		xprt_force_disconnect(xprt);
+		xs_tcp_force_close(xprt);
 		return;
 	}
 	dprintk("RPC:       reading TCP record fragment of length %d\n",
@@ -1132,7 +1136,7 @@ static inline void xs_tcp_read_calldir(struct sock_xprt *transport,
 		break;
 	default:
 		dprintk("RPC:       invalid request message type\n");
-		xprt_force_disconnect(&transport->xprt);
+		xs_tcp_force_close(&transport->xprt);
 	}
 	xs_tcp_check_fraghdr(transport);
 }
@@ -1402,9 +1406,6 @@ static void xs_tcp_data_ready(struct sock *sk, int bytes)
 	read_lock_bh(&sk->sk_callback_lock);
 	if (!(xprt = xprt_from_sock(sk)))
 		goto out;
-	if (xprt->shutdown)
-		goto out;
-
 	/* Any data means we had a useful conversation, so
 	 * the we don't need to delay the next reconnect
 	 */
@@ -1455,6 +1456,8 @@ static void xs_tcp_cancel_linger_timeout(struct rpc_xprt *xprt)
 static void xs_sock_mark_closed(struct rpc_xprt *xprt)
 {
 	smp_mb__before_clear_bit();
+	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
+	clear_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
 	clear_bit(XPRT_CLOSE_WAIT, &xprt->state);
 	clear_bit(XPRT_CLOSING, &xprt->state);
 	smp_mb__after_clear_bit();
@@ -1512,8 +1515,8 @@ static void xs_tcp_state_change(struct sock *sk)
 		break;
 	case TCP_CLOSE_WAIT:
 		/* The server initiated a shutdown of the socket */
-		xprt_force_disconnect(xprt);
 		xprt->connect_cookie++;
+		xs_tcp_force_close(xprt);
 	case TCP_CLOSING:
 		/*
 		 * If the server closed down the connection, make sure that
@@ -1889,9 +1892,6 @@ static void xs_local_setup_socket(struct work_struct *work)
 	struct socket *sock;
 	int status = -EIO;
 
-	if (xprt->shutdown)
-		goto out;
-
 	current->flags |= PF_FSTRANS;
 
 	clear_bit(XPRT_CONNECTION_ABORT, &xprt->state);
@@ -2008,9 +2008,6 @@ static void xs_udp_setup_socket(struct work_struct *work)
 	struct socket *sock = transport->sock;
 	int status = -EIO;
 
-	if (xprt->shutdown)
-		goto out;
-
 	current->flags |= PF_FSTRANS;
 
 	/* Start by resetting any existing state */
@@ -2156,9 +2153,6 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 	struct rpc_xprt *xprt = &transport->xprt;
 	int status = -EIO;
 
-	if (xprt->shutdown)
-		goto out;
-
 	current->flags |= PF_FSTRANS;
 
 	if (!sock) {
@@ -2199,8 +2193,7 @@ static void xs_tcp_setup_socket(struct work_struct *work)
 		/* We're probably in TIME_WAIT. Get rid of existing socket,
 		 * and retry
 		 */
-		set_bit(XPRT_CONNECTION_CLOSE, &xprt->state);
-		xprt_force_disconnect(xprt);
+		xs_tcp_force_close(xprt);
 		break;
 	case -ECONNREFUSED:
 	case -ECONNRESET:
@@ -2528,6 +2521,7 @@ static struct rpc_xprt_ops xs_tcp_ops = {
 static struct rpc_xprt_ops bc_tcp_ops = {
 	.reserve_xprt		= xprt_reserve_xprt,
 	.release_xprt		= xprt_release_xprt,
+	.alloc_slot		= xprt_alloc_slot,
 	.rpcbind		= xs_local_rpcbind,
 	.buf_alloc		= bc_malloc,
 	.buf_free		= bc_free,