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

Pull networking updates from David Miller:
 "Highlights:

   1) Support TX_RING in AF_PACKET TPACKET_V3 mode, from Sowmini
      Varadhan.

   2) Simplify classifier state on sk_buff in order to shrink it a bit.
      From Willem de Bruijn.

   3) Introduce SIPHASH and it's usage for secure sequence numbers and
      syncookies. From Jason A. Donenfeld.

   4) Reduce CPU usage for ICMP replies we are going to limit or
      suppress, from Jesper Dangaard Brouer.

   5) Introduce Shared Memory Communications socket layer, from Ursula
      Braun.

   6) Add RACK loss detection and allow it to actually trigger fast
      recovery instead of just assisting after other algorithms have
      triggered it. From Yuchung Cheng.

   7) Add xmit_more and BQL support to mvneta driver, from Simon Guinot.

   8) skb_cow_data avoidance in esp4 and esp6, from Steffen Klassert.

   9) Export MPLS packet stats via netlink, from Robert Shearman.

  10) Significantly improve inet port bind conflict handling, especially
      when an application is restarted and changes it's setting of
      reuseport. From Josef Bacik.

  11) Implement TX batching in vhost_net, from Jason Wang.

  12) Extend the dummy device so that VF (virtual function) features,
      such as configuration, can be more easily tested. From Phil
      Sutter.

  13) Avoid two atomic ops per page on x86 in bnx2x driver, from Eric
      Dumazet.

  14) Add new bpf MAP, implementing a longest prefix match trie. From
      Daniel Mack.

  15) Packet sample offloading support in mlxsw driver, from Yotam Gigi.

  16) Add new aquantia driver, from David VomLehn.

  17) Add bpf tracepoints, from Daniel Borkmann.

  18) Add support for port mirroring to b53 and bcm_sf2 drivers, from
      Florian Fainelli.

  19) Remove custom busy polling in many drivers, it is done in the core
      networking since 4.5 times. From Eric Dumazet.

  20) Support XDP adjust_head in virtio_net, from John Fastabend.

  21) Fix several major holes in neighbour entry confirmation, from
      Julian Anastasov.

  22) Add XDP support to bnxt_en driver, from Michael Chan.

  23) VXLAN offloads for enic driver, from Govindarajulu Varadarajan.

  24) Add IPVTAP driver (IP-VLAN based tap driver) from Sainath Grandhi.

  25) Support GRO in IPSEC protocols, from Steffen Klassert"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1764 commits)
  Revert "ath10k: Search SMBIOS for OEM board file extension"
  net: socket: fix recvmmsg not returning error from sock_error
  bnxt_en: use eth_hw_addr_random()
  bpf: fix unlocking of jited image when module ronx not set
  arch: add ARCH_HAS_SET_MEMORY config
  net: napi_watchdog() can use napi_schedule_irqoff()
  tcp: Revert "tcp: tcp_probe: use spin_lock_bh()"
  net/hsr: use eth_hw_addr_random()
  net: mvpp2: enable building on 64-bit platforms
  net: mvpp2: switch to build_skb() in the RX path
  net: mvpp2: simplify MVPP2_PRS_RI_* definitions
  net: mvpp2: fix indentation of MVPP2_EXT_GLOBAL_CTRL_DEFAULT
  net: mvpp2: remove unused register definitions
  net: mvpp2: simplify mvpp2_bm_bufs_add()
  net: mvpp2: drop useless fields in mvpp2_bm_pool and related code
  net: mvpp2: remove unused 'tx_skb' field of 'struct mvpp2_tx_queue'
  net: mvpp2: release reference to txq_cpu[] entry after unmapping
  net: mvpp2: handle too large value in mvpp2_rx_time_coal_set()
  net: mvpp2: handle too large value handling in mvpp2_rx_pkts_coal_set()
  net: mvpp2: remove useless arguments in mvpp2_rx_{pkts, time}_coal_set
  ...

14 files changed, 561 insertions, 419 deletions

diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 1e9d2f84e5b5..b29447e03ede 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -343,7 +343,7 @@ void afs_dispatch_give_up_callbacks(struct work_struct *work)
 	 *   had callbacks entirely, and the server will call us later to break
 	 *   them
 	 */
-	afs_fs_give_up_callbacks(server, &afs_async_call);
+	afs_fs_give_up_callbacks(server, true);
 }
 
 /*
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index d764236072b1..2edbdcbf6432 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -24,65 +24,86 @@ static int afs_deliver_cb_callback(struct afs_call *);
 static int afs_deliver_cb_probe_uuid(struct afs_call *);
 static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *);
 static void afs_cm_destructor(struct afs_call *);
+static void SRXAFSCB_CallBack(struct work_struct *);
+static void SRXAFSCB_InitCallBackState(struct work_struct *);
+static void SRXAFSCB_Probe(struct work_struct *);
+static void SRXAFSCB_ProbeUuid(struct work_struct *);
+static void SRXAFSCB_TellMeAboutYourself(struct work_struct *);
+
+#define CM_NAME(name) \
+	const char afs_SRXCB##name##_name[] __tracepoint_string =	\
+		"CB." #name
 
 /*
  * CB.CallBack operation type
  */
+static CM_NAME(CallBack);
 static const struct afs_call_type afs_SRXCBCallBack = {
-	.name		= "CB.CallBack",
+	.name		= afs_SRXCBCallBack_name,
 	.deliver	= afs_deliver_cb_callback,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_CallBack,
 };
 
 /*
  * CB.InitCallBackState operation type
  */
+static CM_NAME(InitCallBackState);
 static const struct afs_call_type afs_SRXCBInitCallBackState = {
-	.name		= "CB.InitCallBackState",
+	.name		= afs_SRXCBInitCallBackState_name,
 	.deliver	= afs_deliver_cb_init_call_back_state,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_InitCallBackState,
 };
 
 /*
  * CB.InitCallBackState3 operation type
  */
+static CM_NAME(InitCallBackState3);
 static const struct afs_call_type afs_SRXCBInitCallBackState3 = {
-	.name		= "CB.InitCallBackState3",
+	.name		= afs_SRXCBInitCallBackState3_name,
 	.deliver	= afs_deliver_cb_init_call_back_state3,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_InitCallBackState,
 };
 
 /*
  * CB.Probe operation type
  */
+static CM_NAME(Probe);
 static const struct afs_call_type afs_SRXCBProbe = {
-	.name		= "CB.Probe",
+	.name		= afs_SRXCBProbe_name,
 	.deliver	= afs_deliver_cb_probe,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_Probe,
 };
 
 /*
  * CB.ProbeUuid operation type
  */
+static CM_NAME(ProbeUuid);
 static const struct afs_call_type afs_SRXCBProbeUuid = {
-	.name		= "CB.ProbeUuid",
+	.name		= afs_SRXCBProbeUuid_name,
 	.deliver	= afs_deliver_cb_probe_uuid,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_ProbeUuid,
 };
 
 /*
  * CB.TellMeAboutYourself operation type
  */
+static CM_NAME(TellMeAboutYourself);
 static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
-	.name		= "CB.TellMeAboutYourself",
+	.name		= afs_SRXCBTellMeAboutYourself_name,
 	.deliver	= afs_deliver_cb_tell_me_about_yourself,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_TellMeAboutYourself,
 };
 
 /*
@@ -153,6 +174,7 @@ static void SRXAFSCB_CallBack(struct work_struct *work)
 	afs_send_empty_reply(call);
 
 	afs_break_callbacks(call->server, call->count, call->request);
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -274,9 +296,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		return -ENOTCONN;
 	call->server = server;
 
-	INIT_WORK(&call->work, SRXAFSCB_CallBack);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -290,6 +310,7 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
 
 	afs_init_callback_state(call->server);
 	afs_send_empty_reply(call);
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -320,9 +341,7 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
 		return -ENOTCONN;
 	call->server = server;
 
-	INIT_WORK(&call->work, SRXAFSCB_InitCallBackState);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -332,7 +351,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 {
 	struct sockaddr_rxrpc srx;
 	struct afs_server *server;
-	struct afs_uuid *r;
+	struct uuid_v1 *r;
 	unsigned loop;
 	__be32 *b;
 	int ret;
@@ -362,15 +381,15 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 		}
 
 		_debug("unmarshall UUID");
-		call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL);
+		call->request = kmalloc(sizeof(struct uuid_v1), GFP_KERNEL);
 		if (!call->request)
 			return -ENOMEM;
 
 		b = call->buffer;
 		r = call->request;
-		r->time_low			= ntohl(b[0]);
-		r->time_mid			= ntohl(b[1]);
-		r->time_hi_and_version		= ntohl(b[2]);
+		r->time_low			= b[0];
+		r->time_mid			= htons(ntohl(b[1]));
+		r->time_hi_and_version		= htons(ntohl(b[2]));
 		r->clock_seq_hi_and_reserved 	= ntohl(b[3]);
 		r->clock_seq_low		= ntohl(b[4]);
 
@@ -394,9 +413,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 		return -ENOTCONN;
 	call->server = server;
 
-	INIT_WORK(&call->work, SRXAFSCB_InitCallBackState);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -408,6 +425,7 @@ static void SRXAFSCB_Probe(struct work_struct *work)
 
 	_enter("");
 	afs_send_empty_reply(call);
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -427,9 +445,7 @@ static int afs_deliver_cb_probe(struct afs_call *call)
 	/* no unmarshalling required */
 	call->state = AFS_CALL_REPLYING;
 
-	INIT_WORK(&call->work, SRXAFSCB_Probe);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -438,7 +454,7 @@ static int afs_deliver_cb_probe(struct afs_call *call)
 static void SRXAFSCB_ProbeUuid(struct work_struct *work)
 {
 	struct afs_call *call = container_of(work, struct afs_call, work);
-	struct afs_uuid *r = call->request;
+	struct uuid_v1 *r = call->request;
 
 	struct {
 		__be32	match;
@@ -452,6 +468,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work)
 		reply.match = htonl(1);
 
 	afs_send_simple_reply(call, &reply, sizeof(reply));
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -460,7 +477,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work)
  */
 static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 {
-	struct afs_uuid *r;
+	struct uuid_v1 *r;
 	unsigned loop;
 	__be32 *b;
 	int ret;
@@ -486,15 +503,15 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 		}
 
 		_debug("unmarshall UUID");
-		call->request = kmalloc(sizeof(struct afs_uuid), GFP_KERNEL);
+		call->request = kmalloc(sizeof(struct uuid_v1), GFP_KERNEL);
 		if (!call->request)
 			return -ENOMEM;
 
 		b = call->buffer;
 		r = call->request;
-		r->time_low			= ntohl(b[0]);
-		r->time_mid			= ntohl(b[1]);
-		r->time_hi_and_version		= ntohl(b[2]);
+		r->time_low			= b[0];
+		r->time_mid			= htons(ntohl(b[1]));
+		r->time_hi_and_version		= htons(ntohl(b[2]));
 		r->clock_seq_hi_and_reserved 	= ntohl(b[3]);
 		r->clock_seq_low		= ntohl(b[4]);
 
@@ -510,9 +527,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 
 	call->state = AFS_CALL_REPLYING;
 
-	INIT_WORK(&call->work, SRXAFSCB_ProbeUuid);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -554,9 +569,9 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work)
 	memset(&reply, 0, sizeof(reply));
 	reply.ia.nifs = htonl(nifs);
 
-	reply.ia.uuid[0] = htonl(afs_uuid.time_low);
-	reply.ia.uuid[1] = htonl(afs_uuid.time_mid);
-	reply.ia.uuid[2] = htonl(afs_uuid.time_hi_and_version);
+	reply.ia.uuid[0] = afs_uuid.time_low;
+	reply.ia.uuid[1] = htonl(ntohs(afs_uuid.time_mid));
+	reply.ia.uuid[2] = htonl(ntohs(afs_uuid.time_hi_and_version));
 	reply.ia.uuid[3] = htonl((s8) afs_uuid.clock_seq_hi_and_reserved);
 	reply.ia.uuid[4] = htonl((s8) afs_uuid.clock_seq_low);
 	for (loop = 0; loop < 6; loop++)
@@ -574,7 +589,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work)
 	reply.cap.capcount = htonl(1);
 	reply.cap.caps[0] = htonl(AFS_CAP_ERROR_TRANSLATION);
 	afs_send_simple_reply(call, &reply, sizeof(reply));
-
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -594,7 +609,5 @@ static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call)
 	/* no unmarshalling required */
 	call->state = AFS_CALL_REPLYING;
 
-	INIT_WORK(&call->work, SRXAFSCB_TellMeAboutYourself);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 6344aee4ac4b..ba7b71fba34b 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -16,6 +16,7 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/gfp.h>
+#include <linux/task_io_accounting_ops.h>
 #include "internal.h"
 
 static int afs_readpage(struct file *file, struct page *page);
@@ -101,6 +102,21 @@ int afs_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+/*
+ * Dispose of a ref to a read record.
+ */
+void afs_put_read(struct afs_read *req)
+{
+	int i;
+
+	if (atomic_dec_and_test(&req->usage)) {
+		for (i = 0; i < req->nr_pages; i++)
+			if (req->pages[i])
+				put_page(req->pages[i]);
+		kfree(req);
+	}
+}
+
 #ifdef CONFIG_AFS_FSCACHE
 /*
  * deal with notification that a page was read from the cache
@@ -126,9 +142,8 @@ int afs_page_filler(void *data, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	struct afs_vnode *vnode = AFS_FS_I(inode);
+	struct afs_read *req;
 	struct key *key = data;
-	size_t len;
-	off_t offset;
 	int ret;
 
 	_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
@@ -164,12 +179,23 @@ int afs_page_filler(void *data, struct page *page)
 		_debug("cache said ENOBUFS");
 	default:
 	go_on:
-		offset = page->index << PAGE_SHIFT;
-		len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);
+		req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *),
+			      GFP_KERNEL);
+		if (!req)
+			goto enomem;
+
+		atomic_set(&req->usage, 1);
+		req->pos = (loff_t)page->index << PAGE_SHIFT;
+		req->len = min_t(size_t, i_size_read(inode) - req->pos,
+				 PAGE_SIZE);
+		req->nr_pages = 1;
+		req->pages[0] = page;
+		get_page(page);
 
 		/* read the contents of the file from the server into the
 		 * page */
-		ret = afs_vnode_fetch_data(vnode, key, offset, len, page);
+		ret = afs_vnode_fetch_data(vnode, key, req);
+		afs_put_read(req);
 		if (ret < 0) {
 			if (ret == -ENOENT) {
 				_debug("got NOENT from server"
@@ -201,6 +227,8 @@ int afs_page_filler(void *data, struct page *page)
 	_leave(" = 0");
 	return 0;
 
+enomem:
+	ret = -ENOMEM;
 error:
 	SetPageError(page);
 	unlock_page(page);
@@ -235,6 +263,131 @@ static int afs_readpage(struct file *file, struct page *page)
 }
 
 /*
+ * Make pages available as they're filled.
+ */
+static void afs_readpages_page_done(struct afs_call *call, struct afs_read *req)
+{
+#ifdef CONFIG_AFS_FSCACHE
+	struct afs_vnode *vnode = call->reply;
+#endif
+	struct page *page = req->pages[req->index];
+
+	req->pages[req->index] = NULL;
+	SetPageUptodate(page);
+
+	/* send the page to the cache */
+#ifdef CONFIG_AFS_FSCACHE
+	if (PageFsCache(page) &&
+	    fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) {
+		fscache_uncache_page(vnode->cache, page);
+		BUG_ON(PageFsCache(page));
+	}
+#endif
+	unlock_page(page);
+	put_page(page);
+}
+
+/*
+ * Read a contiguous set of pages.
+ */
+static int afs_readpages_one(struct file *file, struct address_space *mapping,
+			     struct list_head *pages)
+{
+	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
+	struct afs_read *req;
+	struct list_head *p;
+	struct page *first, *page;
+	struct key *key = file->private_data;
+	pgoff_t index;
+	int ret, n, i;
+
+	/* Count the number of contiguous pages at the front of the list.  Note
+	 * that the list goes prev-wards rather than next-wards.
+	 */
+	first = list_entry(pages->prev, struct page, lru);
+	index = first->index + 1;
+	n = 1;
+	for (p = first->lru.prev; p != pages; p = p->prev) {
+		page = list_entry(p, struct page, lru);
+		if (page->index != index)
+			break;
+		index++;
+		n++;
+	}
+
+	req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *) * n,
+		      GFP_NOFS);
+	if (!req)
+		return -ENOMEM;
+
+	atomic_set(&req->usage, 1);
+	req->page_done = afs_readpages_page_done;
+	req->pos = first->index;
+	req->pos <<= PAGE_SHIFT;
+
+	/* Transfer the pages to the request.  We add them in until one fails
+	 * to add to the LRU and then we stop (as that'll make a hole in the
+	 * contiguous run.
+	 *
+	 * Note that it's possible for the file size to change whilst we're
+	 * doing this, but we rely on the server returning less than we asked
+	 * for if the file shrank.  We also rely on this to deal with a partial
+	 * page at the end of the file.
+	 */
+	do {
+		page = list_entry(pages->prev, struct page, lru);
+		list_del(&page->lru);
+		index = page->index;
+		if (add_to_page_cache_lru(page, mapping, index,
+					  readahead_gfp_mask(mapping))) {
+#ifdef CONFIG_AFS_FSCACHE
+			fscache_uncache_page(vnode->cache, page);
+#endif
+			put_page(page);
+			break;
+		}
+
+		req->pages[req->nr_pages++] = page;
+		req->len += PAGE_SIZE;
+	} while (req->nr_pages < n);
+
+	if (req->nr_pages == 0) {
+		kfree(req);
+		return 0;
+	}
+
+	ret = afs_vnode_fetch_data(vnode, key, req);
+	if (ret < 0)
+		goto error;
+
+	task_io_account_read(PAGE_SIZE * req->nr_pages);
+	afs_put_read(req);
+	return 0;
+
+error:
+	if (ret == -ENOENT) {
+		_debug("got NOENT from server"
+		       " - marking file deleted and stale");
+		set_bit(AFS_VNODE_DELETED, &vnode->flags);
+		ret = -ESTALE;
+	}
+
+	for (i = 0; i < req->nr_pages; i++) {
+		page = req->pages[i];
+		if (page) {
+#ifdef CONFIG_AFS_FSCACHE
+			fscache_uncache_page(vnode->cache, page);
+#endif
+			SetPageError(page);
+			unlock_page(page);
+		}
+	}
+
+	afs_put_read(req);
+	return ret;
+}
+
+/*
  * read a set of pages
  */
 static int afs_readpages(struct file *file, struct address_space *mapping,
@@ -287,8 +440,11 @@ static int afs_readpages(struct file *file, struct address_space *mapping,
 		return ret;
 	}
 
-	/* load the missing pages from the network */
-	ret = read_cache_pages(mapping, pages, afs_page_filler, key);
+	while (!list_empty(pages)) {
+		ret = afs_readpages_one(file, mapping, pages);
+		if (ret < 0)
+			break;
+	}
 
 	_leave(" = %d [netting]", ret);
 	return ret;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 31c616ab9b40..ac8e766978dc 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -275,7 +275,7 @@ int afs_fs_fetch_file_status(struct afs_server *server,
 			     struct key *key,
 			     struct afs_vnode *vnode,
 			     struct afs_volsync *volsync,
-			     const struct afs_wait_mode *wait_mode)
+			     bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -300,7 +300,7 @@ int afs_fs_fetch_file_status(struct afs_server *server,
 	bp[2] = htonl(vnode->fid.vnode);
 	bp[3] = htonl(vnode->fid.unique);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -309,15 +309,19 @@ int afs_fs_fetch_file_status(struct afs_server *server,
 static int afs_deliver_fs_fetch_data(struct afs_call *call)
 {
 	struct afs_vnode *vnode = call->reply;
+	struct afs_read *req = call->reply3;
 	const __be32 *bp;
-	struct page *page;
+	unsigned int size;
 	void *buffer;
 	int ret;
 
-	_enter("{%u}", call->unmarshall);
+	_enter("{%u,%zu/%u;%u/%llu}",
+	       call->unmarshall, call->offset, call->count,
+	       req->remain, req->actual_len);
 
 	switch (call->unmarshall) {
 	case 0:
+		req->actual_len = 0;
 		call->offset = 0;
 		call->unmarshall++;
 		if (call->operation_ID != FSFETCHDATA64) {
@@ -334,10 +338,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		if (ret < 0)
 			return ret;
 
-		call->count = ntohl(call->tmp);
-		_debug("DATA length MSW: %u", call->count);
-		if (call->count > 0)
-			return -EBADMSG;
+		req->actual_len = ntohl(call->tmp);
+		req->actual_len <<= 32;
 		call->offset = 0;
 		call->unmarshall++;
 
@@ -349,26 +351,52 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		if (ret < 0)
 			return ret;
 
-		call->count = ntohl(call->tmp);
-		_debug("DATA length: %u", call->count);
-		if (call->count > PAGE_SIZE)
+		req->actual_len |= ntohl(call->tmp);
+		_debug("DATA length: %llu", req->actual_len);
+		/* Check that the server didn't want to send us extra.  We
+		 * might want to just discard instead, but that requires
+		 * cooperation from AF_RXRPC.
+		 */
+		if (req->actual_len > req->len)
 			return -EBADMSG;
-		call->offset = 0;
+
+		req->remain = req->actual_len;
+		call->offset = req->pos & (PAGE_SIZE - 1);
+		req->index = 0;
+		if (req->actual_len == 0)
+			goto no_more_data;
 		call->unmarshall++;
 
+	begin_page:
+		if (req->remain > PAGE_SIZE - call->offset)
+			size = PAGE_SIZE - call->offset;
+		else
+			size = req->remain;
+		call->count = call->offset + size;
+		ASSERTCMP(call->count, <=, PAGE_SIZE);
+		req->remain -= size;
+
 		/* extract the returned data */
 	case 3:
-		_debug("extract data");
-		if (call->count > 0) {
-			page = call->reply3;
-			buffer = kmap(page);
-			ret = afs_extract_data(call, buffer,
-					       call->count, true);
-			kunmap(page);
-			if (ret < 0)
-				return ret;
+		_debug("extract data %u/%llu %zu/%u",
+		       req->remain, req->actual_len, call->offset, call->count);
+
+		buffer = kmap(req->pages[req->index]);
+		ret = afs_extract_data(call, buffer, call->count, true);
+		kunmap(req->pages[req->index]);
+		if (ret < 0)
+			return ret;
+		if (call->offset == PAGE_SIZE) {
+			if (req->page_done)
+				req->page_done(call, req);
+			if (req->remain > 0) {
+				req->index++;
+				call->offset = 0;
+				goto begin_page;
+			}
 		}
 
+	no_more_data:
 		call->offset = 0;
 		call->unmarshall++;
 
@@ -393,17 +421,25 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 	}
 
 	if (call->count < PAGE_SIZE) {
-		_debug("clear");
-		page = call->reply3;
-		buffer = kmap(page);
+		buffer = kmap(req->pages[req->index]);
 		memset(buffer + call->count, 0, PAGE_SIZE - call->count);
-		kunmap(page);
+		kunmap(req->pages[req->index]);
+		if (req->page_done)
+			req->page_done(call, req);
 	}
 
 	_leave(" = 0 [done]");
 	return 0;
 }
 
+static void afs_fetch_data_destructor(struct afs_call *call)
+{
+	struct afs_read *req = call->reply3;
+
+	afs_put_read(req);
+	afs_flat_call_destructor(call);
+}
+
 /*
  * FS.FetchData operation type
  */
@@ -411,14 +447,14 @@ static const struct afs_call_type afs_RXFSFetchData = {
 	.name		= "FS.FetchData",
 	.deliver	= afs_deliver_fs_fetch_data,
 	.abort_to_error	= afs_abort_to_error,
-	.destructor	= afs_flat_call_destructor,
+	.destructor	= afs_fetch_data_destructor,
 };
 
 static const struct afs_call_type afs_RXFSFetchData64 = {
 	.name		= "FS.FetchData64",
 	.deliver	= afs_deliver_fs_fetch_data,
 	.abort_to_error	= afs_abort_to_error,
-	.destructor	= afs_flat_call_destructor,
+	.destructor	= afs_fetch_data_destructor,
 };
 
 /*
@@ -427,17 +463,14 @@ static const struct afs_call_type afs_RXFSFetchData64 = {
 static int afs_fs_fetch_data64(struct afs_server *server,
 			       struct key *key,
 			       struct afs_vnode *vnode,
-			       off_t offset, size_t length,
-			       struct page *buffer,
-			       const struct afs_wait_mode *wait_mode)
+			       struct afs_read *req,
+			       bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
 
 	_enter("");
 
-	ASSERTCMP(length, <, ULONG_MAX);
-
 	call = afs_alloc_flat_call(&afs_RXFSFetchData64, 32, (21 + 3 + 6) * 4);
 	if (!call)
 		return -ENOMEM;
@@ -445,7 +478,7 @@ static int afs_fs_fetch_data64(struct afs_server *server,
 	call->key = key;
 	call->reply = vnode;
 	call->reply2 = NULL; /* volsync */
-	call->reply3 = buffer;
+	call->reply3 = req;
 	call->service_id = FS_SERVICE;
 	call->port = htons(AFS_FS_PORT);
 	call->operation_ID = FSFETCHDATA64;
@@ -456,12 +489,13 @@ static int afs_fs_fetch_data64(struct afs_server *server,
 	bp[1] = htonl(vnode->fid.vid);
 	bp[2] = htonl(vnode->fid.vnode);
 	bp[3] = htonl(vnode->fid.unique);
-	bp[4] = htonl(upper_32_bits(offset));
-	bp[5] = htonl((u32) offset);
+	bp[4] = htonl(upper_32_bits(req->pos));
+	bp[5] = htonl(lower_32_bits(req->pos));
 	bp[6] = 0;
-	bp[7] = htonl((u32) length);
+	bp[7] = htonl(lower_32_bits(req->len));
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	atomic_inc(&req->usage);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -470,16 +504,16 @@ static int afs_fs_fetch_data64(struct afs_server *server,
 int afs_fs_fetch_data(struct afs_server *server,
 		      struct key *key,
 		      struct afs_vnode *vnode,
-		      off_t offset, size_t length,
-		      struct page *buffer,
-		      const struct afs_wait_mode *wait_mode)
+		      struct afs_read *req,
+		      bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
 
-	if (upper_32_bits(offset) || upper_32_bits(offset + length))
-		return afs_fs_fetch_data64(server, key, vnode, offset, length,
-					   buffer, wait_mode);
+	if (upper_32_bits(req->pos) ||
+	    upper_32_bits(req->len) ||
+	    upper_32_bits(req->pos + req->len))
+		return afs_fs_fetch_data64(server, key, vnode, req, async);
 
 	_enter("");
 
@@ -490,7 +524,7 @@ int afs_fs_fetch_data(struct afs_server *server,
 	call->key = key;
 	call->reply = vnode;
 	call->reply2 = NULL; /* volsync */
-	call->reply3 = buffer;
+	call->reply3 = req;
 	call->service_id = FS_SERVICE;
 	call->port = htons(AFS_FS_PORT);
 	call->operation_ID = FSFETCHDATA;
@@ -501,10 +535,11 @@ int afs_fs_fetch_data(struct afs_server *server,
 	bp[1] = htonl(vnode->fid.vid);
 	bp[2] = htonl(vnode->fid.vnode);
 	bp[3] = htonl(vnode->fid.unique);
-	bp[4] = htonl(offset);
-	bp[5] = htonl(length);
+	bp[4] = htonl(lower_32_bits(req->pos));
+	bp[5] = htonl(lower_32_bits(req->len));
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	atomic_inc(&req->usage);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -533,7 +568,7 @@ static const struct afs_call_type afs_RXFSGiveUpCallBacks = {
  * - the callbacks are held in the server->cb_break ring
  */
 int afs_fs_give_up_callbacks(struct afs_server *server,
-			     const struct afs_wait_mode *wait_mode)
+			     bool async)
 {
 	struct afs_call *call;
 	size_t ncallbacks;
@@ -587,7 +622,7 @@ int afs_fs_give_up_callbacks(struct afs_server *server,
 	ASSERT(ncallbacks > 0);
 	wake_up_nr(&server->cb_break_waitq, ncallbacks);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -638,7 +673,7 @@ int afs_fs_create(struct afs_server *server,
 		  struct afs_fid *newfid,
 		  struct afs_file_status *newstatus,
 		  struct afs_callback *newcb,
-		  const struct afs_wait_mode *wait_mode)
+		  bool async)
 {
 	struct afs_call *call;
 	size_t namesz, reqsz, padsz;
@@ -683,7 +718,7 @@ int afs_fs_create(struct afs_server *server,
 	*bp++ = htonl(mode & S_IALLUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -728,7 +763,7 @@ int afs_fs_remove(struct afs_server *server,
 		  struct afs_vnode *vnode,
 		  const char *name,
 		  bool isdir,
-		  const struct afs_wait_mode *wait_mode)
+		  bool async)
 {
 	struct afs_call *call;
 	size_t namesz, reqsz, padsz;
@@ -763,7 +798,7 @@ int afs_fs_remove(struct afs_server *server,
 		bp = (void *) bp + padsz;
 	}
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -809,7 +844,7 @@ int afs_fs_link(struct afs_server *server,
 		struct afs_vnode *dvnode,
 		struct afs_vnode *vnode,
 		const char *name,
-		const struct afs_wait_mode *wait_mode)
+		bool async)
 {
 	struct afs_call *call;
 	size_t namesz, reqsz, padsz;
@@ -848,7 +883,7 @@ int afs_fs_link(struct afs_server *server,
 	*bp++ = htonl(vnode->fid.vnode);
 	*bp++ = htonl(vnode->fid.unique);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -897,7 +932,7 @@ int afs_fs_symlink(struct afs_server *server,
 		   const char *contents,
 		   struct afs_fid *newfid,
 		   struct afs_file_status *newstatus,
-		   const struct afs_wait_mode *wait_mode)
+		   bool async)
 {
 	struct afs_call *call;
 	size_t namesz, reqsz, padsz, c_namesz, c_padsz;
@@ -952,7 +987,7 @@ int afs_fs_symlink(struct afs_server *server,
 	*bp++ = htonl(S_IRWXUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1001,7 +1036,7 @@ int afs_fs_rename(struct afs_server *server,
 		  const char *orig_name,
 		  struct afs_vnode *new_dvnode,
 		  const char *new_name,
-		  const struct afs_wait_mode *wait_mode)
+		  bool async)
 {
 	struct afs_call *call;
 	size_t reqsz, o_namesz, o_padsz, n_namesz, n_padsz;
@@ -1055,7 +1090,7 @@ int afs_fs_rename(struct afs_server *server,
 		bp = (void *) bp + n_padsz;
 	}
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1110,7 +1145,7 @@ static int afs_fs_store_data64(struct afs_server *server,
 			       pgoff_t first, pgoff_t last,
 			       unsigned offset, unsigned to,
 			       loff_t size, loff_t pos, loff_t i_size,
-			       const struct afs_wait_mode *wait_mode)
+			       bool async)
 {
 	struct afs_vnode *vnode = wb->vnode;
 	struct afs_call *call;
@@ -1159,7 +1194,7 @@ static int afs_fs_store_data64(struct afs_server *server,
 	*bp++ = htonl(i_size >> 32);
 	*bp++ = htonl((u32) i_size);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1168,7 +1203,7 @@ static int afs_fs_store_data64(struct afs_server *server,
 int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 		      pgoff_t first, pgoff_t last,
 		      unsigned offset, unsigned to,
-		      const struct afs_wait_mode *wait_mode)
+		      bool async)
 {
 	struct afs_vnode *vnode = wb->vnode;
 	struct afs_call *call;
@@ -1194,7 +1229,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 
 	if (pos >> 32 || i_size >> 32 || size >> 32 || (pos + size) >> 32)
 		return afs_fs_store_data64(server, wb, first, last, offset, to,
-					   size, pos, i_size, wait_mode);
+					   size, pos, i_size, async);
 
 	call = afs_alloc_flat_call(&afs_RXFSStoreData,
 				   (4 + 6 + 3) * 4,
@@ -1233,7 +1268,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 	*bp++ = htonl(size);
 	*bp++ = htonl(i_size);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_