Add Flexfile Layout Module

386 lines not on this page · raw message

index 7c9f800..a5ce9b4 100644
@@ -119,17 +119,6 @@ FILELAYOUT_DEVID_NODE(struct pnfs_layout_segment *lseg)
 	return &FILELAYOUT_LSEG(lseg)->dsaddr->id_node;
 }
 
-static inline void
-filelayout_mark_devid_invalid(struct nfs4_deviceid_node *node)
-{
-	u32 *p = (u32 *)&node->deviceid;
-
-	printk(KERN_WARNING "NFS: Deviceid [%x%x%x%x] marked out of use.\n",
-		p[0], p[1], p[2], p[3]);
-
-	set_bit(NFS_DEVICEID_INVALID, &node->flags);
-}
-
 static inline bool
 filelayout_test_devid_invalid(struct nfs4_deviceid_node *node)
 {

index bfecac7..d21080a 100644
@@ -708,7 +708,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
 			__func__, ds_idx);
-		filelayout_mark_devid_invalid(devid);
+		pnfs_generic_mark_devid_invalid(devid);
 		goto out;
 	}
 	smp_rmb();

index 9ae5b76..f176634 100644
@@ -275,6 +275,23 @@ void nfs4_mark_deviceid_unavailable(struct nfs4_deviceid_node *node);
 bool nfs4_test_deviceid_unavailable(struct nfs4_deviceid_node *node);
 void nfs4_deviceid_purge_client(const struct nfs_client *);
 
+/* pnfs_nfs.c */
+void pnfs_generic_clear_request_commit(struct nfs_page *req,
+				       struct nfs_commit_info *cinfo);
+void pnfs_generic_commit_release(void *calldata);
+void pnfs_generic_prepare_to_resend_writes(struct nfs_commit_data *data);
+void pnfs_generic_rw_release(void *data);
+void pnfs_generic_recover_commit_reqs(struct list_head *dst,
+				      struct nfs_commit_info *cinfo);
+int pnfs_generic_commit_pagelist(struct inode *inode,
+				 struct list_head *mds_pages,
+				 int how,
+				 struct nfs_commit_info *cinfo,
+				 int (*initiate_commit)(struct nfs_commit_data *data,
+							int how));
+int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max);
+void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
+
 static inline struct nfs4_deviceid_node *
 nfs4_get_deviceid(struct nfs4_deviceid_node *d)
 {

@@ -317,6 +334,12 @@ pnfs_get_ds_info(struct inode *inode)
 	return ld->get_ds_info(inode);
 }
 
+static inline void
+pnfs_generic_mark_devid_invalid(struct nfs4_deviceid_node *node)
+{
+	set_bit(NFS_DEVICEID_INVALID, &node->flags);
+}
+
 static inline bool
 pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
 			 struct nfs_commit_info *cinfo)

291 lines not on this page · raw message

index 294692f..1df2594 100644
@@ -579,6 +579,20 @@ out:
 	return result;
 }
 
+static void
+nfs_direct_write_scan_commit_list(struct inode *inode,
+				  struct list_head *list,
+				  struct nfs_commit_info *cinfo)
+{
+	spin_lock(cinfo->lock);
+#ifdef CONFIG_NFS_V4_1
+	if (cinfo->ds != NULL && cinfo->ds->nwritten != 0)
+		NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
+#endif
+	nfs_scan_commit_list(&cinfo->mds->list, list, cinfo, 0);
+	spin_unlock(cinfo->lock);
+}
+
 static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 {
 	struct nfs_pageio_descriptor desc;

@@ -588,10 +602,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq)
 	LIST_HEAD(failed);
 
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
-	pnfs_recover_commit_reqs(dreq->inode, &reqs, &cinfo);
-	spin_lock(cinfo.lock);
-	nfs_scan_commit_list(&cinfo.mds->list, &reqs, &cinfo, 0);
-	spin_unlock(cinfo.lock);
+	nfs_direct_write_scan_commit_list(dreq->inode, &reqs, &cinfo);
 
 	dreq->count = 0;
 	get_dreq(dreq);

index f176634..e94f605 100644
@@ -375,15 +375,6 @@ pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
 		return NFS_SERVER(inode)->pnfs_curr_ld->scan_commit_lists(cinfo, max);
 }
 
-static inline void
-pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
-			 struct nfs_commit_info *cinfo)
-{
-	if (cinfo->ds == NULL || cinfo->ds->nwritten == 0)
-		return;
-	NFS_SERVER(inode)->pnfs_curr_ld->recover_commit_reqs(list, cinfo);
-}
-
 static inline struct nfs_page *
 pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo,
 			struct page *page)

@@ -554,12 +545,6 @@ pnfs_scan_commit_lists(struct inode *inode, struct nfs_commit_info *cinfo,
 	return 0;
 }
 
-static inline void
-pnfs_recover_commit_reqs(struct inode *inode, struct list_head *list,
-			 struct nfs_commit_info *cinfo)
-{
-}
-
 static inline struct nfs_page *
 pnfs_search_commit_reqs(struct inode *inode, struct nfs_commit_info *cinfo,
 			struct page *page)

index e5f841c..fd2a2f0 100644
@@ -66,7 +66,7 @@ EXPORT_SYMBOL_GPL(pnfs_generic_commit_release);
 
 /* The generic layer is about to remove the req from the commit list.
  * If this will make the bucket empty, it will need to put the lseg reference.
- * Note this is must be called holding the inode (/cinfo) lock
+ * Note this must be called holding the inode (/cinfo) lock
  */
 void
 pnfs_generic_clear_request_commit(struct nfs_page *req,

@@ -115,7 +115,6 @@ pnfs_generic_transfer_commit_list(struct list_head *src, struct list_head *dst,
 	return ret;
 }
 
-/* Note called with cinfo->lock held. */
 static int
 pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
 				 struct nfs_commit_info *cinfo,

@@ -125,6 +124,7 @@ pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
 	struct list_head *dst = &bucket->committing;
 	int ret;
 
+	lockdep_assert_held(cinfo->lock);
 	ret = pnfs_generic_transfer_commit_list(src, dst, cinfo, max);
 	if (ret) {
 		cinfo->ds->nwritten -= ret;

@@ -138,14 +138,15 @@ pnfs_generic_scan_ds_commit_list(struct pnfs_commit_bucket *bucket,
 	return ret;
 }
 
-/* Move reqs from written to committing lists, returning count of number moved.
- * Note called with cinfo->lock held.
+/* Move reqs from written to committing lists, returning count
+ * of number moved.
  */
 int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo,
 				   int max)
 {
 	int i, rv = 0, cnt;
 
+	lockdep_assert_held(cinfo->lock);
 	for (i = 0; i < cinfo->ds->nbuckets && max != 0; i++) {
 		cnt = pnfs_generic_scan_ds_commit_list(&cinfo->ds->buckets[i],
 						       cinfo, max);

@@ -156,7 +157,7 @@ int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo,
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_scan_commit_lists);
 
-/* Pull everything off the committing lists and dump into @dst */
+/* Pull everything off the committing lists and dump into @dst.  */
 void pnfs_generic_recover_commit_reqs(struct list_head *dst,
 				      struct nfs_commit_info *cinfo)
 {

@@ -164,8 +165,8 @@ void pnfs_generic_recover_commit_reqs(struct list_head *dst,
 	struct pnfs_layout_segment *freeme;
 	int i;
 
+	lockdep_assert_held(cinfo->lock);
 restart:
-	spin_lock(cinfo->lock);
 	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
 		if (pnfs_generic_transfer_commit_list(&b->written, dst,
 						      cinfo, 0)) {

@@ -173,11 +174,11 @@ restart:
 			b->wlseg = NULL;
 			spin_unlock(cinfo->lock);
 			pnfs_put_lseg(freeme);
+			spin_lock(cinfo->lock);
 			goto restart;
 		}
 	}
 	cinfo->ds->nwritten = 0;
-	spin_unlock(cinfo->lock);
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs);
 

index a5ce9b4..f97eea6 100644
@@ -56,24 +56,6 @@ enum stripetype4 {
 	STRIPE_DENSE = 2
 };
 
-/* Individual ip address */
-struct nfs4_pnfs_ds_addr {
-	struct sockaddr_storage	da_addr;
-	size_t			da_addrlen;
-	struct list_head	da_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
-	char			*da_remotestr;	/* human readable addr+port */
-};
-
-struct nfs4_pnfs_ds {
-	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
-	char			*ds_remotestr;	/* comma sep list of addrs */
-	struct list_head	ds_addrs;
-	struct nfs_client	*ds_clp;
-	atomic_t		ds_count;
-	unsigned long		ds_state;
-#define NFS4DS_CONNECTING	0	/* ds is establishing connection */
-};
-
 struct nfs4_file_layout_dsaddr {
 	struct nfs4_deviceid_node	id_node;
 	u32				stripe_count;

@@ -131,7 +113,6 @@ filelayout_test_devid_unavailable(struct nfs4_deviceid_node *node);
 extern struct nfs_fh *
 nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j);
 
-extern void print_ds(struct nfs4_pnfs_ds *ds);
 u32 nfs4_fl_calc_j_index(struct pnfs_layout_segment *lseg, loff_t offset);
 u32 nfs4_fl_calc_ds_index(struct pnfs_layout_segment *lseg, u32 j);
 struct nfs4_pnfs_ds *nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg,

259 lines not on this page · raw message

index e94f605..b0168f1 100644
@@ -40,6 +40,24 @@ enum {
 	NFS_LSEG_LAYOUTCOMMIT,	/* layoutcommit bit set for layoutcommit */
 };
 
+/* Individual ip address */
+struct nfs4_pnfs_ds_addr {
+	struct sockaddr_storage	da_addr;
+	size_t			da_addrlen;
+	struct list_head	da_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+	char			*da_remotestr;	/* human readable addr+port */
+};
+
+struct nfs4_pnfs_ds {
+	struct list_head	ds_node;  /* nfs4_pnfs_dev_hlist dev_dslist */
+	char			*ds_remotestr;	/* comma sep list of addrs */
+	struct list_head	ds_addrs;
+	struct nfs_client	*ds_clp;
+	atomic_t		ds_count;
+	unsigned long		ds_state;
+#define NFS4DS_CONNECTING	0	/* ds is establishing connection */
+};
+
 struct pnfs_layout_segment {
 	struct list_head pls_list;
 	struct list_head pls_lc_list;

@@ -291,6 +309,9 @@ int pnfs_generic_commit_pagelist(struct inode *inode,
 							int how));
 int pnfs_generic_scan_commit_lists(struct nfs_commit_info *cinfo, int max);
 void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
+void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
+struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
+				      gfp_t gfp_flags);
 
 static inline struct nfs4_deviceid_node *
 nfs4_get_deviceid(struct nfs4_deviceid_node *d)

251 lines not on this page · raw message

index fbfbb70..c7f6041 100644
@@ -31,7 +31,6 @@
 #include <linux/nfs_fs.h>
 #include <linux/vmalloc.h>
 #include <linux/module.h>
-#include <linux/sunrpc/addr.h>
 
 #include "../internal.h"
 #include "../nfs4session.h"

@@ -104,153 +103,6 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 	kfree(dsaddr);
 }
 
-/*
- * Currently only supports ipv4, ipv6 and one multi-path address.
- */
-static struct nfs4_pnfs_ds_addr *
-decode_ds_addr(struct net *net, struct xdr_stream *streamp, gfp_t gfp_flags)
-{
-	struct nfs4_pnfs_ds_addr *da = NULL;
-	char *buf, *portstr;
-	__be16 port;
-	int nlen, rlen;
-	int tmp[2];
-	__be32 *p;
-	char *netid, *match_netid;
-	size_t len, match_netid_len;
-	char *startsep = "";
-	char *endsep = "";
-
-
-	/* r_netid */
-	p = xdr_inline_decode(streamp, 4);
-	if (unlikely(!p))
-		goto out_err;
-	nlen = be32_to_cpup(p++);
-
-	p = xdr_inline_decode(streamp, nlen);
-	if (unlikely(!p))
-		goto out_err;
-
-	netid = kmalloc(nlen+1, gfp_flags);
-	if (unlikely(!netid))
-		goto out_err;
-
-	netid[nlen] = '\0';
-	memcpy(netid, p, nlen);
-
-	/* r_addr: ip/ip6addr with port in dec octets - see RFC 5665 */
-	p = xdr_inline_decode(streamp, 4);
-	if (unlikely(!p))
-		goto out_free_netid;
-	rlen = be32_to_cpup(p);
-
-	p = xdr_inline_decode(streamp, rlen);
-	if (unlikely(!p))
-		goto out_free_netid;
-
-	/* port is ".ABC.DEF", 8 chars max */
-	if (rlen > INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN + 8) {
-		dprintk("%s: Invalid address, length %d\n", __func__,
-			rlen);
-		goto out_free_netid;
-	}
-	buf = kmalloc(rlen + 1, gfp_flags);
-	if (!buf) {
-		dprintk("%s: Not enough memory\n", __func__);
-		goto out_free_netid;
-	}
-	buf[rlen] = '\0';
-	memcpy(buf, p, rlen);
-
-	/* replace port '.' with '-' */
-	portstr = strrchr(buf, '.');
-	if (!portstr) {
-		dprintk("%s: Failed finding expected dot in port\n",
-			__func__);
-		goto out_free_buf;
-	}
-	*portstr = '-';
-
-	/* find '.' between address and port */
-	portstr = strrchr(buf, '.');
-	if (!portstr) {
-		dprintk("%s: Failed finding expected dot between address and "
-			"port\n", __func__);
-		goto out_free_buf;
-	}
-	*portstr = '\0';
-
-	da = kzalloc(sizeof(*da), gfp_flags);
-	if (unlikely(!da))
-		goto out_free_buf;
-
-	INIT_LIST_HEAD(&da->da_node);
-
-	if (!rpc_pton(net, buf, portstr-buf, (struct sockaddr *)&da->da_addr,
-		      sizeof(da->da_addr))) {
-		dprintk("%s: error parsing address %s\n", __func__, buf);
-		goto out_free_da;
-	}
-
-	portstr++;
-	sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
-	port = htons((tmp[0] << 8) | (tmp[1]));
-
-	switch (da->da_addr.ss_family) {
-	case AF_INET:
-		((struct sockaddr_in *)&da->da_addr)->sin_port = port;
-		da->da_addrlen = sizeof(struct sockaddr_in);
-		match_netid = "tcp";
-		match_netid_len = 3;
-		break;
-
-	case AF_INET6:
-		((struct sockaddr_in6 *)&da->da_addr)->sin6_port = port;
-		da->da_addrlen = sizeof(struct sockaddr_in6);
-		match_netid = "tcp6";
-		match_netid_len = 4;
-		startsep = "[";
-		endsep = "]";
-		break;
-
-	default:
-		dprintk("%s: unsupported address family: %u\n",
-			__func__, da->da_addr.ss_family);
-		goto out_free_da;
-	}
-
-	if (nlen != match_netid_len || strncmp(netid, match_netid, nlen)) {
-		dprintk("%s: ERROR: r_netid \"%s\" != \"%s\"\n",
-			__func__, netid, match_netid);
-		goto out_free_da;
-	}
-
-	/* save human readable address */
-	len = strlen(startsep) + strlen(buf) + strlen(endsep) + 7;
-	da->da_remotestr = kzalloc(len, gfp_flags);
-
-	/* NULL is ok, only used for dprintk */
-	if (da->da_remotestr)
-		snprintf(da->da_remotestr, len, "%s%s%s:%u", startsep,
-			 buf, endsep, ntohs(port));
-
-	dprintk("%s: Parsed DS addr %s\n", __func__, da->da_remotestr);
-	kfree(buf);
-	kfree(netid);
-	return da;
-
-out_free_da:
-	kfree(da);
-out_free_buf:
-	dprintk("%s: Error parsing DS addr: %s\n", __func__, buf);
-	kfree(buf);
-out_free_netid:
-	kfree(netid);
-out_err:
-	return NULL;
-}
-
 /* Decode opaque device data and return the result */
 struct nfs4_file_layout_dsaddr *
 nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,

@@ -353,8 +205,8 @@ nfs4_fl_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 
 		mp_count = be32_to_cpup(p); /* multipath count */
 		for (j = 0; j < mp_count; j++) {
-			da = decode_ds_addr(server->nfs_client->cl_net,
-					    &stream, gfp_flags);
+			da = nfs4_decode_mp_ds_addr(server->nfs_client->cl_net,
+						    &stream, gfp_flags);
 			if (da)
 				list_add_tail(&da->da_node, &dsaddrs);
 		}

index b0168f1..403d7bb 100644
@@ -312,6 +312,9 @@ void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
 void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
 struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
 				      gfp_t gfp_flags);
+struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
+						 struct xdr_stream *xdr,
+						 gfp_t gfp_flags);
 
 static inline struct nfs4_deviceid_node *
 nfs4_get_deviceid(struct nfs4_deviceid_node *d)

158 lines not on this page · raw message

index c7f6041..27bdd8c 100644
@@ -41,51 +41,6 @@
 static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
 static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
 
-/*
- * Create an rpc connection to the nfs4_pnfs_ds data server
- * Currently only supports IPv4 and IPv6 addresses
- */
-static int
-nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
-{
-	struct nfs_client *clp = ERR_PTR(-EIO);
-	struct nfs4_pnfs_ds_addr *da;
-	int status = 0;
-
-	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
-		mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor);
-
-	list_for_each_entry(da, &ds->ds_addrs, da_node) {
-		dprintk("%s: DS %s: trying address %s\n",
-			__func__, ds->ds_remotestr, da->da_remotestr);
-
-		clp = nfs4_set_ds_client(mds_srv->nfs_client,
-					(struct sockaddr *)&da->da_addr,
-					da->da_addrlen, IPPROTO_TCP,
-					dataserver_timeo, dataserver_retrans);
-		if (!IS_ERR(clp))
-			break;
-	}
-
-	if (IS_ERR(clp)) {
-		status = PTR_ERR(clp);
-		goto out;
-	}
-
-	status = nfs4_init_ds_session(clp, mds_srv->nfs_client->cl_lease_time);
-	if (status)
-		goto out_put;
-
-	smp_wmb();
-	ds->ds_clp = clp;
-	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
-out:
-	return status;
-out_put:
-	nfs_put_client(clp);
-	goto out;
-}
-
 void
 nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {

@@ -302,22 +257,7 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
 	return flseg->fh_array[i];
 }
 
-static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
-{
-	might_sleep();
-	wait_on_bit_action(&ds->ds_state, NFS4DS_CONNECTING,
-			   nfs_wait_bit_killable, TASK_KILLABLE);
-}
-
-static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
-{
-	smp_mb__before_atomic();
-	clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
-	smp_mb__after_atomic();
-	wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
-}
-
-
+/* Upon return, either ds is connected, or ds is NULL */
 struct nfs4_pnfs_ds *
 nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 {

@@ -325,6 +265,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_pnfs_ds *ds = dsaddr->ds_list[ds_idx];
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 	struct nfs4_pnfs_ds *ret = ds;
+	struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",

@@ -336,18 +277,9 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	if (ds->ds_clp)
 		goto out_test_devid;
 
-	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
-		struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
-		int err;
-
-		err = nfs4_ds_connect(s, ds);
-		if (err)
-			nfs4_mark_deviceid_unavailable(devid);
-		nfs4_clear_ds_conn_bit(ds);
-	} else {
-		/* Either ds is connected, or ds is NULL */
-		nfs4_wait_ds_connect(ds);
-	}
+	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+			     dataserver_retrans);
+
 out_test_devid:
 	if (filelayout_test_devid_unavailable(devid))
 		ret = NULL;

index 403d7bb..9a8937c 100644
@@ -312,6 +312,9 @@ void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
 void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
 struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
 				      gfp_t gfp_flags);
+void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+			  struct nfs4_deviceid_node *devid, unsigned int timeo,
+			  unsigned int retrans);
 struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
 						 struct xdr_stream *xdr,
 						 gfp_t gfp_flags);

93 lines not on this page · raw message

index 27bdd8c..5e4b0ce 100644
@@ -278,7 +278,8 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 		goto out_test_devid;
 
 	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
-			     dataserver_retrans);
+			     dataserver_retrans,
+			     s->nfs_client->cl_rpcclient->cl_auth->au_flavor);
 
 out_test_devid:
 	if (filelayout_test_devid_unavailable(devid))

index b6f34bf..1c366cd 100644
@@ -187,7 +187,8 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 					     const struct sockaddr *ds_addr,
 					     int ds_addrlen, int ds_proto,
 					     unsigned int ds_timeo,
-					     unsigned int ds_retrans);
+					     unsigned int ds_retrans,
+					     rpc_authflavor_t au_flavor);
 extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
 						struct inode *);
 #ifdef CONFIG_PROC_FS

index 706ad10..49a5202 100644
@@ -849,7 +849,8 @@ error:
  */
 struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 		const struct sockaddr *ds_addr, int ds_addrlen,
-		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans)
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
+		rpc_authflavor_t au_flavor)
 {
 	struct nfs_client_initdata cl_init = {
 		.addr = ds_addr,

@@ -874,7 +875,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 	 */
 	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
 	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
-			     mds_clp->cl_rpcclient->cl_auth->au_flavor);
+			     au_flavor);
 
 	dprintk("<-- %s %p\n", __func__, clp);
 	return clp;

index 9a8937c..2ea9e9a 100644
@@ -314,7 +314,7 @@ struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
 				      gfp_t gfp_flags);
 void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			  struct nfs4_deviceid_node *devid, unsigned int timeo,
-			  unsigned int retrans);
+			  unsigned int retrans, rpc_authflavor_t au_flavor);
 struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
 						 struct xdr_stream *xdr,
 						 gfp_t gfp_flags);

index 5a92e76..106ee08 100644
@@ -553,7 +553,8 @@ static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
 static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv,
 				 struct nfs4_pnfs_ds *ds,
 				 unsigned int timeo,
-				 unsigned int retrans)
+				 unsigned int retrans,
+				 rpc_authflavor_t au_flavor)
 {
 	struct nfs_client *clp = ERR_PTR(-EIO);
 	struct nfs4_pnfs_ds_addr *da;

@@ -569,7 +570,7 @@ static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv,
 		clp = nfs4_set_ds_client(mds_srv->nfs_client,
 					(struct sockaddr *)&da->da_addr,
 					da->da_addrlen, IPPROTO_TCP,
-					timeo, retrans);
+					timeo, retrans, au_flavor);
 		if (!IS_ERR(clp))
 			break;
 	}

@@ -600,12 +601,13 @@ out_put:
  */
 void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			  struct nfs4_deviceid_node *devid, unsigned int timeo,
-			  unsigned int retrans)
+			  unsigned int retrans, rpc_authflavor_t au_flavor)
 {
 	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
 		int err = 0;
 
-		err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo, retrans);
+		err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo,
+					    retrans, au_flavor);
 		if (err)
 			nfs4_mark_deviceid_unavailable(devid);
 		nfs4_clear_ds_conn_bit(ds);

index f97eea6..2896cb8 100644
@@ -33,13 +33,6 @@
 #include "../pnfs.h"
 
 /*
- * Default data server connection timeout and retrans vaules.
- * Set by module paramters dataserver_timeo and dataserver_retrans.
- */
-#define NFS4_DEF_DS_TIMEO   600 /* in tenths of a second */
-#define NFS4_DEF_DS_RETRANS 5
-
-/*
  * Field testing shows we need to support up to 4096 stripe indices.
  * We store each index as a u8 (u32 on the wire) to keep the memory footprint
  * reasonable. This in turn means we support a maximum of 256

@@ -48,9 +41,6 @@
 #define NFS4_PNFS_MAX_STRIPE_CNT 4096
 #define NFS4_PNFS_MAX_MULTI_CNT  256 /* 256 fit into a u8 stripe_index */
 
-/* error codes for internal use */
-#define NFS4ERR_RESET_TO_MDS   12001
-
 enum stripetype4 {
 	STRIPE_SPARSE = 1,
 	STRIPE_DENSE = 2

index 2ea9e9a..aef89b3 100644
@@ -77,6 +77,17 @@ enum pnfs_try_status {
 
 #define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4"
 
+/*
+ * Default data server connection timeout and retrans vaules.
+ * Set by module parameters dataserver_timeo and dataserver_retrans.
+ */
+#define NFS4_DEF_DS_TIMEO   600 /* in tenths of a second */
+#define NFS4_DEF_DS_RETRANS 5
+
+/* error codes for internal use */
+#define NFS4ERR_RESET_TO_MDS   12001
+#define NFS4ERR_RESET_TO_PNFS  12002
+
 enum {
 	NFS_LAYOUT_RO_FAILED = 0,	/* get ro layout failed stop trying */
 	NFS_LAYOUT_RW_FAILED,		/* get rw layout failed stop trying */

index 1c366cd..5467a08 100644
@@ -191,6 +191,10 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 					     rpc_authflavor_t au_flavor);
 extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
 						struct inode *);
+extern struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
+			const struct sockaddr *ds_addr, int ds_addrlen,
+			int ds_proto, unsigned int ds_timeo,
+			unsigned int ds_retrans, rpc_authflavor_t au_flavor);
 #ifdef CONFIG_PROC_FS
 extern int __init nfs_fs_proc_init(void);
 extern void nfs_fs_proc_exit(void);

index 333ae40..e134d65 100644
@@ -30,5 +30,7 @@ struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subver
 struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *,
 				     struct nfs_fattr *, rpc_authflavor_t);
 
+/* nfs3super.c */
+extern struct nfs_subversion nfs_v3;
 
 #endif /* __LINUX_FS_NFS_NFS3_FS_H */

index 8c1b437..52e2344 100644
@@ -64,3 +64,37 @@ struct nfs_server *nfs3_clone_server(struct nfs_server *source,
 		nfs_init_server_aclclient(server);
 	return server;
 }
+
+/*
+ * Set up a pNFS Data Server client over NFSv3.
+ *
+ * Return any existing nfs_client that matches server address,port,version
+ * and minorversion.
+ *
+ * For a new nfs_client, use a soft mount (default), a low retrans and a
+ * low timeout interval so that if a connection is lost, we retry through
+ * the MDS.
+ */
+struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
+		const struct sockaddr *ds_addr, int ds_addrlen,
+		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
+		rpc_authflavor_t au_flavor)
+{
+	struct nfs_client_initdata cl_init = {
+		.addr = ds_addr,
+		.addrlen = ds_addrlen,
+		.nfs_mod = &nfs_v3,
+		.proto = ds_proto,
+		.net = mds_clp->cl_net,
+	};
+	struct rpc_timeout ds_timeout;
+	struct nfs_client *clp;
+
+	/* Use the MDS nfs_client cl_ipaddr. */
+	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
+	clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr,
+			     au_flavor);
+
+	return clp;
+}
+EXPORT_SYMBOL_GPL(nfs3_set_ds_client);

index 6af29c2..5c4394e 100644
@@ -7,7 +7,7 @@
 #include "nfs3_fs.h"
 #include "nfs.h"
 
-static struct nfs_subversion nfs_v3 = {
+struct nfs_subversion nfs_v3 = {
 	.owner = THIS_MODULE,
 	.nfs_fs   = &nfs_fs_type,
 	.rpc_vers = &nfs_version3,

index ddea982..5e1273d 100644
@@ -77,10 +77,6 @@ struct nfs_client {
 	/* Client owner identifier */
 	const char *		cl_owner_id;
 
-	/* Our own IP address, as a null-terminated string.
-	 * This is used to generate the mv0 callback address.
-	 */
-	char			cl_ipaddr[48];
 	u32			cl_cb_ident;	/* v4.0 callback identifier */
 	const struct nfs4_minor_version_ops *cl_mvops;
 	unsigned long		cl_mig_gen;

@@ -108,6 +104,11 @@ struct nfs_client {
 #define NFS_SP4_MACH_CRED_COMMIT   6	/* COMMIT */
 #endif /* CONFIG_NFS_V4 */
 
+	/* Our own IP address, as a null-terminated string.
+	 * This is used to generate the mv0 callback address.
+	 */
+	char			cl_ipaddr[48];
+
 #ifdef CONFIG_NFS_FSCACHE
 	struct fscache_cookie	*fscache;	/* client index cache cookie */
 #endif

index 5e4b0ce..4f372e2 100644
@@ -278,7 +278,8 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 		goto out_test_devid;
 
 	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
-			     dataserver_retrans,
+			     dataserver_retrans, 4,
+			     s->nfs_client->cl_minorversion,
 			     s->nfs_client->cl_rpcclient->cl_auth->au_flavor);
 
 out_test_devid:

index 5467a08..9eebd93 100644
@@ -188,6 +188,7 @@ extern struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 					     int ds_addrlen, int ds_proto,
 					     unsigned int ds_timeo,
 					     unsigned int ds_retrans,
+					     u32 minor_version,
 					     rpc_authflavor_t au_flavor);
 extern struct rpc_clnt *nfs4_find_or_create_ds_client(struct nfs_client *,
 						struct inode *);

index 49a5202..8646af9 100644
@@ -850,14 +850,14 @@ error:
 struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp,
 		const struct sockaddr *ds_addr, int ds_addrlen,
 		int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans,
-		rpc_authflavor_t au_flavor)
+		u32 minor_version, rpc_authflavor_t au_flavor)
 {
 	struct nfs_client_initdata cl_init = {
 		.addr = ds_addr,
 		.addrlen = ds_addrlen,
 		.nfs_mod = &nfs_v4,
 		.proto = ds_proto,
-		.minorversion = mds_clp->cl_minorversion,
+		.minorversion = minor_version,
 		.net = mds_clp->cl_net,
 	};
 	struct rpc_timeout ds_timeout;

index aef89b3..70ffec1 100644
@@ -325,7 +325,8 @@ struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
 				      gfp_t gfp_flags);
 void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			  struct nfs4_deviceid_node *devid, unsigned int timeo,
-			  unsigned int retrans, rpc_authflavor_t au_flavor);
+			  unsigned int retrans, u32 versoin, u32 minor_version,
+			  rpc_authflavor_t au_flavor);
 struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
 						 struct xdr_stream *xdr,
 						 gfp_t gfp_flags);

index 106ee08..ad211a4 100644
@@ -554,6 +554,7 @@ static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv,
 				 struct nfs4_pnfs_ds *ds,
 				 unsigned int timeo,
 				 unsigned int retrans,
+				 u32 minor_version,
 				 rpc_authflavor_t au_flavor)
 {
 	struct nfs_client *clp = ERR_PTR(-EIO);

@@ -570,7 +571,8 @@ static int _nfs4_pnfs_ds_connect(struct nfs_server *mds_srv,
 		clp = nfs4_set_ds_client(mds_srv->nfs_client,
 					(struct sockaddr *)&da->da_addr,
 					da->da_addrlen, IPPROTO_TCP,
-					timeo, retrans, au_flavor);
+					timeo, retrans, minor_version,
+					au_flavor);
 		if (!IS_ERR(clp))
 			break;
 	}

@@ -601,13 +603,14 @@ out_put:
  */
 void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			  struct nfs4_deviceid_node *devid, unsigned int timeo,
-			  unsigned int retrans, rpc_authflavor_t au_flavor)
+			  unsigned int retrans, u32 version,
+			  u32 minor_version, rpc_authflavor_t au_flavor)
 {
 	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
 		int err = 0;
 
-		err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo,
-					    retrans, au_flavor);
+		err = _nfs4_pnfs_ds_connect(mds_srv, ds, timeo, retrans,
+					    minor_version, au_flavor);
 		if (err)
 			nfs4_mark_deviceid_unavailable(devid);
 		nfs4_clear_ds_conn_bit(ds);

index 6f340f0..48cea3c 100644
@@ -346,6 +346,9 @@ out:
 
 static void __exit exit_nfs_v4(void)
 {
+	/* Not called in the _init(), conditionally loaded */
+	nfs4_pnfs_v3_ds_connect_unload();
+
 	unregister_nfs_version(&nfs_v4);
 	nfs4_unregister_sysctl();
 	nfs_idmap_quit();

index 70ffec1..9ccaa50 100644
@@ -323,9 +323,10 @@ void pnfs_generic_write_commit_done(struct rpc_task *task, void *data);
 void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
 struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
 				      gfp_t gfp_flags);
+void nfs4_pnfs_v3_ds_connect_unload(void);
 void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			  struct nfs4_deviceid_node *devid, unsigned int timeo,
-			  unsigned int retrans, u32 versoin, u32 minor_version,
+			  unsigned int retrans, u32 version, u32 minor_version,
 			  rpc_authflavor_t au_flavor);
 struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
 						 struct xdr_stream *xdr,

112 lines not on this page · raw message

index bc36ed3..25c4896 100644
@@ -501,7 +501,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 	hdr->mds_offset = offset;
 
 	/* Perform an asynchronous read to ds */
-	nfs_initiate_pgio(ds_clnt, hdr,
+	nfs_initiate_pgio(ds_clnt, hdr, NFS_PROTO(hdr->inode),
 			    &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
 }

@@ -542,7 +542,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
 
 	/* Perform an asynchronous write */
-	nfs_initiate_pgio(ds_clnt, hdr,
+	nfs_initiate_pgio(ds_clnt, hdr, NFS_PROTO(hdr->inode),
 				    &filelayout_write_call_ops, sync,
 				    RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;

index 9eebd93..495c516 100644
@@ -249,6 +249,7 @@ void nfs_pgio_header_free(struct nfs_pgio_header *);
 void nfs_pgio_data_destroy(struct nfs_pgio_header *);
 int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
 int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_header *,
+		      const struct nfs_rpc_ops *,
 		      const struct rpc_call_ops *, int, int);
 void nfs_free_request(struct nfs_page *req);
 

index 2b5e769..35a2626 100644
@@ -597,6 +597,7 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
 }
 
 int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
+		      const struct nfs_rpc_ops *rpc_ops,
 		      const struct rpc_call_ops *call_ops, int how, int flags)
 {
 	struct rpc_task *task;

@@ -616,7 +617,7 @@ int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
 	};
 	int ret = 0;
 
-	hdr->rw_ops->rw_initiate(hdr, &msg, &task_setup_data, how);
+	hdr->rw_ops->rw_initiate(hdr, &msg, rpc_ops, &task_setup_data, how);
 
 	dprintk("NFS: %5u initiated pgio call "
 		"(req %s/%llu, %u bytes @ offset %llu)\n",

@@ -792,7 +793,8 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
 	ret = nfs_generic_pgio(desc, hdr);
 	if (ret == 0)
 		ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
-					hdr, desc->pg_rpc_callops,
+					hdr, NFS_PROTO(hdr->inode),
+					desc->pg_rpc_callops,
 					desc->pg_ioflags, 0);
 	return ret;
 }

index c91a479..092ab49 100644
@@ -168,13 +168,14 @@ out:
 
 static void nfs_initiate_read(struct nfs_pgio_header *hdr,
 			      struct rpc_message *msg,
+			      const struct nfs_rpc_ops *rpc_ops,
 			      struct rpc_task_setup *task_setup_data, int how)
 {
 	struct inode *inode = hdr->inode;
 	int swap_flags = IS_SWAPFILE(inode) ? NFS_RPC_SWAPFLAGS : 0;
 
 	task_setup_data->flags |= swap_flags;
-	NFS_PROTO(inode)->read_setup(hdr, msg);
+	rpc_ops->read_setup(hdr, msg);
 }
 
 static void

index af3af68..54d4857 100644
@@ -1240,15 +1240,15 @@ static int flush_task_priority(int how)
 
 static void nfs_initiate_write(struct nfs_pgio_header *hdr,
 			       struct rpc_message *msg,
+			       const struct nfs_rpc_ops *rpc_ops,
 			       struct rpc_task_setup *task_setup_data, int how)
 {
-	struct inode *inode = hdr->inode;
 	int priority = flush_task_priority(how);
 
 	task_setup_data->priority = priority;
-	NFS_PROTO(inode)->write_setup(hdr, msg);
+	rpc_ops->write_setup(hdr, msg);
 
-	nfs4_state_protect_write(NFS_SERVER(inode)->nfs_client,
+	nfs4_state_protect_write(NFS_SERVER(hdr->inode)->nfs_client,
 				 &task_setup_data->rpc_client, msg, hdr);
 }
 

index 6c3e06e..4c3aa80 100644
@@ -69,6 +69,7 @@ struct nfs_rw_ops {
 			struct inode *);
 	void (*rw_result)(struct rpc_task *, struct nfs_pgio_header *);
 	void (*rw_initiate)(struct nfs_pgio_header *, struct rpc_message *,
+			    const struct nfs_rpc_ops *,
 			    struct rpc_task_setup *, int);
 };
 

index 25c4896..e5a3c5b 100644
@@ -1055,7 +1055,7 @@ static int filelayout_initiate_commit(struct nfs_commit_data *data, int how)
 	fh = select_ds_fh_from_commit(lseg, data->ds_commit_index);
 	if (fh)
 		data->args.fh = fh;
-	return nfs_initiate_commit(ds_clnt, data,
+	return nfs_initiate_commit(ds_clnt, data, NFS_PROTO(data->inode),
 				   &filelayout_commit_call_ops, how,
 				   RPC_TASK_SOFTCONN);
 out_err:

index 495c516..331f11f 100644
@@ -434,6 +434,7 @@ extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
 extern void nfs_commit_prepare(struct rpc_task *task, void *calldata);
 extern int nfs_initiate_commit(struct rpc_clnt *clnt,
 			       struct nfs_commit_data *data,
+			       const struct nfs_rpc_ops *nfs_ops,
 			       const struct rpc_call_ops *call_ops,
 			       int how, int flags);
 extern void nfs_init_commit(struct nfs_commit_data *data,

index 23c851d..c87f664 100644
@@ -278,6 +278,7 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 		if (!data->lseg) {
 			nfs_init_commit(data, mds_pages, NULL, cinfo);
 			nfs_initiate_commit(NFS_CLIENT(inode), data,
+					    NFS_PROTO(data->inode),
 					    data->mds_ops, how, 0);
 		} else {
 			struct pnfs_commit_bucket *buckets;

index 54d4857..8800bd3 100644
@@ -1465,6 +1465,7 @@ void nfs_commitdata_release(struct nfs_commit_data *data)
 EXPORT_SYMBOL_GPL(nfs_commitdata_release);
 
 int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
+			const struct nfs_rpc_ops *nfs_ops,
 			const struct rpc_call_ops *call_ops,
 			int how, int flags)
 {

@@ -1486,7 +1487,7 @@ int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
 		.priority = priority,
 	};
 	/* Set up the initial task struct.  */
-	NFS_PROTO(data->inode)->commit_setup(data, &msg);
+	nfs_ops->commit_setup(data, &msg);
 
 	dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid);
 

@@ -1589,8 +1590,8 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 	/* Set up the argument struct */
 	nfs_init_commit(data, head, NULL, cinfo);
 	atomic_inc(&cinfo->mds->rpcs_out);
-	return nfs_initiate_commit(NFS_CLIENT(inode), data, data->mds_ops,
-				   how, 0);
+	return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
+				   data->mds_ops, how, 0);
  out_bad:
 	nfs_retry_commit(head, NULL, cinfo);
 	cinfo->completion_ops->error_cleanup(NFS_I(inode));

index a081787..90c4ffe 100644
@@ -443,6 +443,10 @@ extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_release_seqid(struct nfs_seqid *seqid);
 extern void nfs_free_seqid(struct nfs_seqid *seqid);
+extern int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
+				struct nfs4_sequence_args *args,
+				struct nfs4_sequence_res *res,
+				struct rpc_task *task);
 
 extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
 

index c347705..e98dda7 100644
@@ -495,12 +495,11 @@ static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args)
 	args->sa_privileged = 1;
 }
 
-static int nfs40_setup_sequence(const struct nfs_server *server,
-				struct nfs4_sequence_args *args,
-				struct nfs4_sequence_res *res,
-				struct rpc_task *task)
+int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
+			 struct nfs4_sequence_args *args,
+			 struct nfs4_sequence_res *res,
+			 struct rpc_task *task)
 {
-	struct nfs4_slot_table *tbl = server->nfs_client->cl_slot_tbl;
 	struct nfs4_slot *slot;
 
 	/* slot already allocated? */

@@ -535,6 +534,7 @@ out_sleep:
 	spin_unlock(&tbl->slot_tbl_lock);
 	return -EAGAIN;
 }
+EXPORT_SYMBOL_GPL(nfs40_setup_sequence);
 
 static int nfs40_sequence_done(struct rpc_task *task,
 			       struct nfs4_sequence_res *res)

@@ -777,7 +777,8 @@ static int nfs4_setup_sequence(const struct nfs_server *server,
 	int ret = 0;
 
 	if (!session)
-		return nfs40_setup_sequence(server, args, res, task);
+		return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
+					    args, res, task);
 
 	dprintk("--> %s clp %p session %p sr_slot %u\n",
 		__func__, session->clp, session, res->sr_slot ?

@@ -818,7 +819,8 @@ static int nfs4_setup_sequence(const struct nfs_server *server,
 			       struct nfs4_sequence_res *res,
 			       struct rpc_task *task)
 {
-	return nfs40_setup_sequence(server, args, res, task);
+	return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
+				    args, res, task);
 }
 
 static int nfs4_sequence_done(struct rpc_task *task,

@@ -1679,8 +1681,8 @@ static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_opendata *data = calldata;
 
-	nfs40_setup_sequence(data->o_arg.server, &data->c_arg.seq_args,
-				&data->c_res.seq_res, task);
+	nfs40_setup_sequence(data->o_arg.server->nfs_client->cl_slot_tbl,
+			     &data->c_arg.seq_args, &data->c_res.seq_res, task);
 }
 
 static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)

@@ -5974,8 +5976,8 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata
 {
 	struct nfs_release_lockowner_data *data = calldata;
 	struct nfs_server *server = data->server;
-	nfs40_setup_sequence(server, &data->args.seq_args,
-				&data->res.seq_res, task);
+	nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
+			     &data->args.seq_args, &data->res.seq_res, task);
 	data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
 	data->timestamp = jiffies;
 }

index 90c4ffe..b3c771e 100644
@@ -447,6 +447,8 @@ extern int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
 				struct nfs4_sequence_args *args,
 				struct nfs4_sequence_res *res,
 				struct rpc_task *task);
+extern int nfs4_sequence_done(struct rpc_task *task,
+			      struct nfs4_sequence_res *res);
 
 extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp);
 

index e98dda7..f358262 100644
@@ -694,8 +694,7 @@ out_retry:
 }
 EXPORT_SYMBOL_GPL(nfs41_sequence_done);
 
-static int nfs4_sequence_done(struct rpc_task *task,
-			       struct nfs4_sequence_res *res)
+int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
 	if (res->sr_slot == NULL)
 		return 1;

@@ -703,6 +702,7 @@ static int nfs4_sequence_done(struct rpc_task *task,
 		return nfs40_sequence_done(task, res);
 	return nfs41_sequence_done(task, res);
 }
+EXPORT_SYMBOL_GPL(nfs4_sequence_done);
 
 int nfs41_setup_sequence(struct nfs4_session *session,
 				struct nfs4_sequence_args *args,

@@ -823,11 +823,12 @@ static int nfs4_setup_sequence(const struct nfs_server *server,
 				    args, res, task);
 }
 
-static int nfs4_sequence_done(struct rpc_task *task,
-			       struct nfs4_sequence_res *res)
+int nfs4_sequence_done(struct rpc_task *task,
+		       struct nfs4_sequence_res *res)
 {
 	return nfs40_sequence_done(task, res);
 }
+EXPORT_SYMBOL_GPL(nfs4_sequence_done);
 
 #endif	/* !CONFIG_NFS_V4_1 */
 

index e5a3c5b..bfa8547 100644
@@ -501,8 +501,9 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 	hdr->mds_offset = offset;
 
 	/* Perform an asynchronous read to ds */
-	nfs_initiate_pgio(ds_clnt, hdr, NFS_PROTO(hdr->inode),
-			    &filelayout_read_call_ops, 0, RPC_TASK_SOFTCONN);
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+			  NFS_PROTO(hdr->inode), &filelayout_read_call_ops,
+			  0, RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
 }
 

@@ -542,9 +543,9 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	hdr->args.offset = filelayout_get_dserver_offset(lseg, offset);
 
 	/* Perform an asynchronous write */
-	nfs_initiate_pgio(ds_clnt, hdr, NFS_PROTO(hdr->inode),
-				    &filelayout_write_call_ops, sync,
-				    RPC_TASK_SOFTCONN);
+	nfs_initiate_pgio(ds_clnt, hdr, hdr->cred,
+			  NFS_PROTO(hdr->inode), &filelayout_write_call_ops,
+			  sync, RPC_TASK_SOFTCONN);
 	return PNFS_ATTEMPTED;
 }
 

index 331f11f..331b6e6 100644
@@ -248,9 +248,9 @@ struct nfs_pgio_header *nfs_pgio_header_alloc(const struct nfs_rw_ops *);
 void nfs_pgio_header_free(struct nfs_pgio_header *);
 void nfs_pgio_data_destroy(struct nfs_pgio_header *);
 int nfs_generic_pgio(struct nfs_pageio_descriptor *, struct nfs_pgio_header *);
-int nfs_initiate_pgio(struct rpc_clnt *, struct nfs_pgio_header *,
-		      const struct nfs_rpc_ops *,
-		      const struct rpc_call_ops *, int, int);
+int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
+		      struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
+		      const struct rpc_call_ops *call_ops, int how, int flags);
 void nfs_free_request(struct nfs_page *req);
 
 static inline void nfs_iocounter_init(struct nfs_io_counter *c)

index 35a2626..c4d1758 100644
@@ -597,14 +597,14 @@ static void nfs_pgio_prepare(struct rpc_task *task, void *calldata)
 }
 
 int nfs_initiate_pgio(struct rpc_clnt *clnt, struct nfs_pgio_header *hdr,
-		      const struct nfs_rpc_ops *rpc_ops,
+		      struct rpc_cred *cred, const struct nfs_rpc_ops *rpc_ops,
 		      const struct rpc_call_ops *call_ops, int how, int flags)
 {
 	struct rpc_task *task;
 	struct rpc_message msg = {
 		.rpc_argp = &hdr->args,
 		.rpc_resp = &hdr->res,
-		.rpc_cred = hdr->cred,
+		.rpc_cred = cred,
 	};
 	struct rpc_task_setup task_setup_data = {
 		.rpc_client = clnt,

@@ -793,7 +793,9 @@ static int nfs_generic_pg_pgios(struct nfs_pageio_descriptor *desc)
 	ret = nfs_generic_pgio(desc, hdr);
 	if (ret == 0)
 		ret = nfs_initiate_pgio(NFS_CLIENT(hdr->inode),
-					hdr, NFS_PROTO(hdr->inode),
+					hdr,
+					hdr->cred,
+					NFS_PROTO(hdr->inode),
 					desc->pg_rpc_callops,
 					desc->pg_ioflags, 0);
 	return ret;

index 524f9f8..78e557c 100644
@@ -800,6 +800,9 @@ static int nfs3_read_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
 
+	if (hdr->pgio_done_cb != NULL)
+		return hdr->pgio_done_cb(task, hdr);
+
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 

@@ -825,6 +828,9 @@ static int nfs3_write_done(struct rpc_task *task, struct nfs_pgio_header *hdr)
 {
 	struct inode *inode = hdr->inode;
 
+	if (hdr->pgio_done_cb != NULL)
+		return hdr->pgio_done_cb(task, hdr);
+
 	if (nfs3_async_handle_jukebox(task, inode))
 		return -EAGAIN;
 	if (task->tk_status >= 0)

@@ -845,6 +851,9 @@ static void nfs3_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commi
 
 static int nfs3_commit_done(struct rpc_task *task, struct nfs_commit_data *data)
 {
+	if (data->commit_done_cb != NULL)
+		return data->commit_done_cb(task, data);
+
 	if (nfs3_async_handle_jukebox(task, data->inode))
 		return -EAGAIN;
 	nfs_refresh_inode(data->inode, data->res.fattr);

index eecb5a7..89f2ca1 100644
@@ -79,6 +79,8 @@ struct rpc_clnt;
 struct rpc_iostats *	rpc_alloc_iostats(struct rpc_clnt *);
 void			rpc_count_iostats(const struct rpc_task *,
 					  struct rpc_iostats *);
+void			rpc_count_iostats_metrics(const struct rpc_task *,
+					  struct rpc_iostats *);
 void			rpc_print_iostats(struct seq_file *, struct rpc_clnt *);
 void			rpc_free_iostats(struct rpc_iostats *);
 

index 9711a15..2ecb994 100644
@@ -140,22 +140,20 @@ void rpc_free_iostats(struct rpc_iostats *stats)
 EXPORT_SYMBOL_GPL(rpc_free_iostats);
 
 /**
- * rpc_count_iostats - tally up per-task stats
+ * rpc_count_iostats_metrics - tally up per-task stats
  * @task: completed rpc_task
- * @stats: array of stat structures
+ * @op_metrics: stat structure for OP that will accumulate stats from @task
  */
-void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
+void rpc_count_iostats_metrics(const struct rpc_task *task,
+			       struct rpc_iostats *op_metrics)
 {
 	struct rpc_rqst *req = task->tk_rqstp;
-	struct rpc_iostats *op_metrics;
 	ktime_t delta, now;
 
-	if (!stats || !req)
+	if (!op_metrics || !req)
 		return;
 
 	now = ktime_get();
-	op_metrics = &stats[task->tk_msg.rpc_proc->p_statidx];
-
 	spin_lock(&op_metrics->om_lock);
 
 	op_metrics->om_ops++;

@@ -175,6 +173,20 @@ void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
 
 	spin_unlock(&op_metrics->om_lock);
 }
+EXPORT_SYMBOL_GPL(rpc_count_iostats_metrics);
+
+/**
+ * rpc_count_iostats - tally up per-task stats
+ * @task: completed rpc_task
+ * @stats: array of stat structures
+ *
+ * Uses the statidx from @task
+ */
+void rpc_count_iostats(const struct rpc_task *task, struct rpc_iostats *stats)
+{
+	rpc_count_iostats_metrics(task,
+				  &stats[task->tk_msg.rpc_proc->p_statidx]);
+}
 EXPORT_SYMBOL_GPL(rpc_count_iostats);
 
 static void _print_name(struct seq_file *seq, unsigned int op,

index 52e2344..9e9fa34 100644
@@ -1,5 +1,6 @@
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
+#include <linux/sunrpc/addr.h>
 #include "internal.h"
 #include "nfs3_fs.h"
 

@@ -89,6 +90,12 @@ struct nfs_client *nfs3_set_ds_client(struct nfs_client *mds_clp,
 	};
 	struct rpc_timeout ds_timeout;
 	struct nfs_client *clp;
+	char buf[INET6_ADDRSTRLEN + 1];
+
+	/* fake a hostname because lockd wants it */
+	if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
+		return ERR_PTR(-EINVAL);
+	cl_init.hostname = buf;
 
 	/* Use the MDS nfs_client cl_ipaddr. */
 	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);

index 0a5dda4..2d25670 100644
@@ -1966,6 +1966,7 @@ clear_layoutcommitting:
 	pnfs_clear_layoutcommitting(inode);
 	goto out;
 }
+EXPORT_SYMBOL_GPL(pnfs_layoutcommit_inode);
 
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void)
 {

index 2d25670..fa00b56 100644
@@ -1288,7 +1288,6 @@ pnfs_update_layout(struct inode *ino,
 	struct nfs_client *clp = server->nfs_client;
 	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg = NULL;
-	bool first;
 
 	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
 		goto out;

@@ -1321,16 +1320,15 @@ pnfs_update_layout(struct inode *ino,
 	if (pnfs_layoutgets_blocked(lo, 0))
 		goto out_unlock;
 	atomic_inc(&lo->plh_outstanding);
-
-	first = list_empty(&lo->plh_layouts) ? true : false;
 	spin_unlock(&ino->i_lock);
 
-	if (first) {
+	if (list_empty(&lo->plh_layouts)) {
 		/* The lo must be on the clp list if there is any
 		 * chance of a CB_LAYOUTRECALL(FILE) coming in.
 		 */
 		spin_lock(&clp->cl_lock);
-		list_add_tail(&lo->plh_layouts, &server->layouts);
+		if (list_empty(&lo->plh_layouts))
+			list_add_tail(&lo->plh_layouts, &server->layouts);
 		spin_unlock(&clp->cl_lock);
 	}
 

index fa00b56..7e1bac1 100644
@@ -1288,6 +1288,7 @@ pnfs_update_layout(struct inode *ino,
 	struct nfs_client *clp = server->nfs_client;
 	struct pnfs_layout_hdr *lo;
 	struct pnfs_layout_segment *lseg = NULL;
+	bool first;
 
 	if (!pnfs_enabled_sb(NFS_SERVER(ino)))
 		goto out;

@@ -1295,6 +1296,8 @@ pnfs_update_layout(struct inode *ino,
 	if (pnfs_within_mdsthreshold(ctx, ino, iomode))
 		goto out;
 
+lookup_again:
+	first = false;
 	spin_lock(&ino->i_lock);
 	lo = pnfs_find_alloc_layout(ino, ctx, gfp_flags);
 	if (lo == NULL) {

@@ -1312,10 +1315,27 @@ pnfs_update_layout(struct inode *ino,
 	if (pnfs_layout_io_test_failed(lo, iomode))
 		goto out_unlock;
 
-	/* Check to see if the layout for the given range already exists */
-	lseg = pnfs_find_lseg(lo, &arg);
-	if (lseg)
-		goto out_unlock;
+	first = list_empty(&lo->plh_segs);
+	if (first) {
+		/* The first layoutget for the file. Need to serialize per
+		 * RFC 5661 Errata 3208.
+		 */
+		if (test_and_set_bit(NFS_LAYOUT_FIRST_LAYOUTGET,
+				     &lo->plh_flags)) {
+			spin_unlock(&ino->i_lock);
+			wait_on_bit(&lo->plh_flags, NFS_LAYOUT_FIRST_LAYOUTGET,
+				    TASK_UNINTERRUPTIBLE);
+			pnfs_put_layout_hdr(lo);
+			goto lookup_again;
+		}
+	} else {
+		/* Check to see if the layout for the given range
+		 * already exists
+		 */
+		lseg = pnfs_find_lseg(lo, &arg);
+		if (lseg)
+			goto out_unlock;
+	}
 
 	if (pnfs_layoutgets_blocked(lo, 0))
 		goto out_unlock;

@@ -1343,6 +1363,13 @@ pnfs_update_layout(struct inode *ino,
 	lseg = send_layoutget(lo, ctx, &arg, gfp_flags);
 	atomic_dec(&lo->plh_outstanding);
 out_put_layout_hdr:
+	if (first) {
+		unsigned long *bitlock = &lo->plh_flags;
+
+		clear_bit_unlock(NFS_LAYOUT_FIRST_LAYOUTGET, bitlock);
+		smp_mb__after_atomic();
+		wake_up_bit(bitlock, NFS_LAYOUT_FIRST_LAYOUTGET);
+	}
 	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("%s: inode %s/%llu pNFS layout segment %s for "

index 9ccaa50..4993ba6 100644
@@ -95,6 +95,7 @@ enum {
 	NFS_LAYOUT_ROC,			/* some lseg had roc bit set */
 	NFS_LAYOUT_RETURN,		/* Return this layout ASAP */
 	NFS_LAYOUT_INVALID_STID,	/* layout stateid id is invalid */
+	NFS_LAYOUT_FIRST_LAYOUTGET,	/* Serialize first layoutget */
 };
 
 enum layoutdriver_policy_flags {

index 5f61b83..b4e03ed 100644
@@ -481,7 +481,8 @@ out_overflow:
  *		void;
  *	};
  */
-static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result)
+static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result,
+			   __u32 *op_status)
 {
 	enum nfs_stat status;
 	int error;

@@ -489,6 +490,8 @@ static int decode_attrstat(struct xdr_stream *xdr, struct nfs_fattr *result)
 	error = decode_stat(xdr, &status);
 	if (unlikely(error))
 		goto out;
+	if (op_status)
+		*op_status = status;
 	if (status != NFS_OK)
 		goto out_default;
 	error = decode_fattr(xdr, result);

@@ -808,7 +811,7 @@ out_default:
 static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr,
 				 struct nfs_fattr *result)
 {
-	return decode_attrstat(xdr, result);
+	return decode_attrstat(xdr, result, NULL);
 }
 
 static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr,

@@ -865,6 +868,7 @@ static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr,
 	error = decode_stat(xdr, &status);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS_OK)
 		goto out_default;
 	error = decode_fattr(xdr, result->fattr);

@@ -882,7 +886,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
 {
 	/* All NFSv2 writes are "file sync" writes */
 	result->verf->committed = NFS_FILE_SYNC;
-	return decode_attrstat(xdr, result->fattr);
+	return decode_attrstat(xdr, result->fattr, &result->op_status);
 }
 
 /**

index 8f4cbe7..2a932fd 100644
@@ -1636,6 +1636,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 	error = decode_post_op_attr(xdr, result->fattr);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
 	error = decode_read3resok(xdr, result);

@@ -1708,6 +1709,7 @@ static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
 	error = decode_wcc_data(xdr, result->fattr);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
 	error = decode_write3resok(xdr, result);

@@ -2323,6 +2325,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 	error = decode_wcc_data(xdr, result->fattr);
 	if (unlikely(error))
 		goto out;
+	result->op_status = status;
 	if (status != NFS3_OK)
 		goto out_status;
 	error = decode_writeverf3(xdr, &result->verf->verifier);

index cb4376b..7d8d7a4 100644
@@ -6567,6 +6567,7 @@ static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	int status;
 
 	status = decode_compound_hdr(xdr, &hdr);
+	res->op_status = hdr.status;
 	if (status)
 		goto out;
 	status = decode_sequence(xdr, &res->seq_res, rqstp);

@@ -6592,6 +6593,7 @@ static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	int status;
 
 	status = decode_compound_hdr(xdr, &hdr);
+	res->op_status = hdr.status;
 	if (status)
 		goto out;
 	status = decode_sequence(xdr, &res->seq_res, rqstp);

@@ -6621,6 +6623,7 @@ static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 	int status;
 
 	status = decode_compound_hdr(xdr, &hdr);
+	res->op_status = hdr.status;
 	if (status)
 		goto out;
 	status = decode_sequence(xdr, &res->seq_res, rqstp);

index 467c84e..962f461 100644
@@ -513,6 +513,7 @@ struct nfs_pgio_res {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs_fattr *	fattr;
 	__u32			count;
+	__u32			op_status;
 	int			eof;		/* used by read */
 	struct nfs_writeverf *	verf;		/* used by write */
 	const struct nfs_server *server;	/* used by write */

@@ -532,6 +533,7 @@ struct nfs_commitargs {
 
 struct nfs_commitres {
 	struct nfs4_sequence_res	seq_res;
+	__u32			op_status;
 	struct nfs_fattr	*fattr;
 	struct nfs_writeverf	*verf;
 	const struct nfs_server *server;

index 7d8d7a4..3c3ff63 100644
@@ -2012,7 +2012,7 @@ encode_layoutreturn(struct xdr_stream *xdr,
 	p = reserve_space(xdr, 16);
 	*p++ = cpu_to_be32(0);		/* reclaim. always 0 for now */
 	*p++ = cpu_to_be32(args->layout_type);
-	*p++ = cpu_to_be32(IOMODE_ANY);
+	*p++ = cpu_to_be32(args->iomode);
 	*p = cpu_to_be32(RETURN_FILE);
 	p = reserve_space(xdr, 16);
 	p = xdr_encode_hyper(p, 0);

index 7e1bac1..1b544c1 100644
@@ -914,6 +914,7 @@ _pnfs_return_layout(struct inode *ino)
 	lrp->args.stateid = stateid;
 	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
 	lrp->args.inode = ino;
+	lrp->args.iomode = IOMODE_ANY;
 	lrp->args.layout = lo;
 	lrp->clp = NFS_SERVER(ino)->nfs_client;
 	lrp->cred = lo->plh_lc_cred;

index 962f461..4fd7793 100644
@@ -293,6 +293,7 @@ struct nfs4_layoutreturn_args {
 	struct nfs4_sequence_args seq_args;
 	struct pnfs_layout_hdr *layout;
 	struct inode *inode;
+	enum pnfs_iomode iomode;
 	nfs4_stateid stateid;
 	__u32   layout_type;
 };

index 1b544c1..1b97209 100644
@@ -845,6 +845,38 @@ static void pnfs_clear_layoutcommit(struct inode *inode,
 	}
 }
 
+static int
+pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
+		       enum pnfs_iomode iomode)
+{
+	struct inode *ino = lo->plh_inode;
+	struct nfs4_layoutreturn *lrp;
+	int status = 0;
+
+	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
+	if (unlikely(lrp == NULL)) {
+		status = -ENOMEM;
+		spin_lock(&ino->i_lock);
+		lo->plh_block_lgets--;
+		spin_unlock(&ino->i_lock);
+		pnfs_put_layout_hdr(lo);
+		goto out;
+	}
+
+	lrp->args.stateid = stateid;
+	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
+	lrp->args.inode = ino;
+	lrp->args.iomode = iomode;
+	lrp->args.layout = lo;
+	lrp->clp = NFS_SERVER(ino)->nfs_client;
+	lrp->cred = lo->plh_lc_cred;
+
+	status = nfs4_proc_layoutreturn(lrp);
+out:
+	dprintk("<-- %s status: %d\n", __func__, status);
+	return status;
+}
+
 /*
  * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr
  * when the layout segment list is empty.

@@ -859,7 +891,6 @@ _pnfs_return_layout(struct inode *ino)
 	struct pnfs_layout_hdr *lo = NULL;
 	struct nfs_inode *nfsi = NFS_I(ino);
 	LIST_HEAD(tmp_list);
-	struct nfs4_layoutreturn *lrp;
 	nfs4_stateid stateid;
 	int status = 0, empty;
 

@@ -901,25 +932,7 @@ _pnfs_return_layout(struct inode *ino)
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
 
-	lrp = kzalloc(sizeof(*lrp), GFP_KERNEL);
-	if (unlikely(lrp == NULL)) {
-		status = -ENOMEM;
-		spin_lock(&ino->i_lock);
-		lo->plh_block_lgets--;
-		spin_unlock(&ino->i_lock);
-		pnfs_put_layout_hdr(lo);
-		goto out;
-	}
-
-	lrp->args.stateid = stateid;
-	lrp->args.layout_type = NFS_SERVER(ino)->pnfs_curr_ld->id;
-	lrp->args.inode = ino;
-	lrp->args.iomode = IOMODE_ANY;
-	lrp->args.layout = lo;
-	lrp->clp = NFS_SERVER(ino)->nfs_client;
-	lrp->cred = lo->plh_lc_cred;
-
-	status = nfs4_proc_layoutreturn(lrp);
+	status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY);
 out:
 	dprintk("<-- %s status: %d\n", __func__, status);
 	return status;

index 1b97209..0bd149b 100644
@@ -1479,6 +1479,61 @@ out_forget_reply:
 	goto out;
 }
 
+static void
+pnfs_mark_matching_lsegs_return(struct pnfs_layout_hdr *lo,
+				struct list_head *tmp_list,
+				struct pnfs_layout_range *return_range)
+{
+	struct pnfs_layout_segment *lseg, *next;
+
+	dprintk("%s:Begin lo %p\n", __func__, lo);
+
+	if (list_empty(&lo->plh_segs))
+		return;
+
+	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
+		if (should_free_lseg(&lseg->pls_range, return_range)) {
+			dprintk("%s: marking lseg %p iomode %d "
+				"offset %llu length %llu\n", __func__,
+				lseg, lseg->pls_range.iomode,
+				lseg->pls_range.offset,
+				lseg->pls_range.length);
+			set_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags);
+			mark_lseg_invalid(lseg, tmp_list);
+		}
+}
+
+void pnfs_error_mark_layout_for_return(struct inode *inode,
+				       struct pnfs_layout_segment *lseg)
+{
+	struct pnfs_layout_hdr *lo = NFS_I(inode)->layout;
+	int iomode = pnfs_iomode_to_fail_bit(lseg->pls_range.iomode);
+	struct pnfs_layout_range range = {
+		.iomode = lseg->pls_range.iomode,
+		.offset = 0,
+		.length = NFS4_MAX_UINT64,
+	};
+	LIST_HEAD(free_me);
+
+	spin_lock(&inode->i_lock);
+	/* set failure bit so that pnfs path will be retried later */
+	pnfs_layout_set_fail_bit(lo, iomode);
+	set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+	if (lo->plh_return_iomode == 0)
+		lo->plh_return_iomode = range.iomode;
+	else if (lo->plh_return_iomode != range.iomode)
+		lo->plh_return_iomode = IOMODE_ANY;
+	/*
+	 * mark all matching lsegs so that we are sure to have no live
+	 * segments at hand when sending layoutreturn. See pnfs_put_lseg()
+	 * for how it works.
+	 */
+	pnfs_mark_matching_lsegs_return(lo, &free_me, &range);
+	spin_unlock(&inode->i_lock);
+	pnfs_free_lseg_list(&free_me);
+}
+EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return);
+
 void
 pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {

index 4993ba6..f67382a 100644
@@ -38,6 +38,7 @@ enum {
 	NFS_LSEG_VALID = 0,	/* cleared when lseg is recalled/returned */
 	NFS_LSEG_ROC,		/* roc bit received from server */
 	NFS_LSEG_LAYOUTCOMMIT,	/* layoutcommit bit set for layoutcommit */
+	NFS_LSEG_LAYOUTRETURN,	/* layoutreturn bit set for layoutreturn */
 };
 
 /* Individual ip address */

@@ -184,6 +185,7 @@ struct pnfs_layout_hdr {
 	u32			plh_barrier; /* ignore lower seqids */
 	unsigned long		plh_retry_timestamp;
 	unsigned long		plh_flags;
+	enum pnfs_iomode	plh_return_iomode;
 	loff_t			plh_lwb; /* last write byte for layoutcommit */
 	struct rpc_cred		*plh_lc_cred; /* layoutcommit cred */
 	struct inode		*plh_inode;

@@ -274,6 +276,8 @@ void nfs4_deviceid_mark_client_invalid(struct nfs_client *clp);
 int pnfs_read_done_resend_to_mds(struct nfs_pgio_header *);
 int pnfs_write_done_resend_to_mds(struct nfs_pgio_header *);
 struct nfs4_threshold *pnfs_mdsthreshold_alloc(void);
+void pnfs_error_mark_layout_for_return(struct inode *inode,
+				       struct pnfs_layout_segment *lseg);
 
 /* nfs4_deviceid_flags */
 enum {

index f358262..1943284 100644
@@ -7540,6 +7540,7 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 		return;
 	if (pnfs_choose_layoutget_stateid(&lgp->args.stateid,
 					  NFS_I(lgp->args.inode)->layout,
+					  &lgp->args.range,
 					  lgp->args.ctx->state)) {
 		rpc_exit(task, NFS4_OK);
 	}

index 0bd149b..853b544 100644
@@ -740,25 +740,37 @@ pnfs_layout_stateid_blocked(const struct pnfs_layout_hdr *lo,
 	return !pnfs_seqid_is_newer(seqid, lo->plh_barrier);
 }
 
+static bool
+pnfs_layout_returning(const struct pnfs_layout_hdr *lo,
+		      struct pnfs_layout_range *range)
+{
+	return test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) &&
+		(lo->plh_return_iomode == IOMODE_ANY ||
+		 lo->plh_return_iomode == range->iomode);
+}
+
 /* lget is set to 1 if called from inside send_layoutget call chain */
 static bool
-pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo, int lget)
+pnfs_layoutgets_blocked(const struct pnfs_layout_hdr *lo,
+			struct pnfs_layout_range *range, int lget)
 {
 	return lo->plh_block_lgets ||
 		test_bit(NFS_LAYOUT_BULK_RECALL, &lo->plh_flags) ||
 		(list_empty(&lo->plh_segs) &&
-		 (atomic_read(&lo->plh_outstanding) > lget));
+		 (atomic_read(&lo->plh_outstanding) > lget)) ||
+		pnfs_layout_returning(lo, range);
 }
 
 int
 pnfs_choose_layoutget_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo,
+			      struct pnfs_layout_range *range,
 			      struct nfs4_state *open_state)
 {
 	int status = 0;
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
-	if (pnfs_layoutgets_blocked(lo, 1)) {
+	if (pnfs_layoutgets_blocked(lo, range, 1)) {
 		status = -EAGAIN;
 	} else if (!nfs4_valid_open_stateid(open_state)) {
 		status = -EBADF;

@@ -1192,6 +1204,7 @@ pnfs_find_lseg(struct pnfs_layout_hdr *lo,
 
 	list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
 		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags) &&
+		    !test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags) &&
 		    pnfs_lseg_range_match(&lseg->pls_range, range)) {
 			ret = pnfs_get_lseg(lseg);
 			break;

@@ -1351,7 +1364,7 @@ lookup_again:
 			goto out_unlock;
 	}
 
-	if (pnfs_layoutgets_blocked(lo, 0))
+	if (pnfs_layoutgets_blocked(lo, &arg, 0))
 		goto out_unlock;
 	atomic_inc(&lo->plh_outstanding);
 	spin_unlock(&ino->i_lock);

@@ -1432,7 +1445,7 @@ pnfs_layout_process(struct nfs4_layoutget *lgp)
 		goto out_forget_reply;
 	}
 
-	if (pnfs_layoutgets_blocked(lo, 1)) {
+	if (pnfs_layoutgets_blocked(lo, &lgp->args.range, 1)) {
 		dprintk("%s forget reply due to state\n", __func__);
 		goto out_forget_reply;
 	}

index f67382a..892678d 100644
@@ -249,6 +249,7 @@ void pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo,
 			     bool update_barrier);
 int pnfs_choose_layoutget_stateid(nfs4_stateid *dst,
 				  struct pnfs_layout_hdr *lo,
+				  struct pnfs_layout_range *range,
 				  struct nfs4_state *open_state);
 int pnfs_mark_matching_lsegs_invalid(struct pnfs_layout_hdr *lo,
 				struct list_head *tmp_list,

index 853b544..e9acfcf 100644
@@ -50,6 +50,10 @@ static DEFINE_SPINLOCK(pnfs_spinlock);
  */
 static LIST_HEAD(pnfs_modules_tbl);
 
+static int
+pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
+		       enum pnfs_iomode iomode);
+
 /* Return the registered pnfs layout driver module matching given id */
 static struct pnfs_layoutdriver_type *
 find_pnfs_driver_locked(u32 id)

@@ -337,6 +341,29 @@ pnfs_layout_remove_lseg(struct pnfs_layout_hdr *lo,
 	rpc_wake_up(&NFS_SERVER(inode)->roc_rpcwaitq);
 }
 
+/* Return true if layoutreturn is needed */
+static bool
+pnfs_layout_need_return(struct pnfs_layout_hdr *lo,
+			struct pnfs_layout_segment *lseg,
+			nfs4_stateid *stateid, enum pnfs_iomode *iomode)
+{
+	struct pnfs_layout_segment *s;
+
+	if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+		return false;
+
+	list_for_each_entry(s, &lo->plh_segs, pls_list)
+		if (test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+			return false;
+
+	*stateid = lo->plh_stateid;
+	*iomode = lo->plh_return_iomode;
+	/* decreased in pnfs_send_layoutreturn() */
+	lo->plh_block_lgets++;
+	lo->plh_return_iomode = 0;
+	return true;
+}
+
 void
 pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 {

@@ -352,11 +379,20 @@ pnfs_put_lseg(struct pnfs_layout_segment *lseg)
 	lo = lseg->pls_layout;
 	inode = lo->plh_inode;
 	if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
+		bool need_return;
+		nfs4_stateid stateid;
+		enum pnfs_iomode iomode;
+
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_remove_lseg(lo, lseg);
+		need_return = pnfs_layout_need_return(lo, lseg,
+						      &stateid, &iomode);
 		spin_unlock(&inode->i_lock);
 		pnfs_free_lseg(lseg);
-		pnfs_put_layout_hdr(lo);
+		if (need_return)
+			pnfs_send_layoutreturn(lo, stateid, iomode);
+		else
+			pnfs_put_layout_hdr(lo);
 	}
 }
 EXPORT_SYMBOL_GPL(pnfs_put_lseg);

index 1943284..e19b5db 100644
@@ -7796,6 +7796,7 @@ static void nfs4_layoutreturn_release(void *calldata)
 	spin_lock(&lo->plh_inode->i_lock);
 	if (lrp->res.lrs_present)
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+	clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
 	lo->plh_block_lgets--;
 	spin_unlock(&lo->plh_inode->i_lock);
 	pnfs_put_layout_hdr(lrp->args.layout);

index e9acfcf..63992c8 100644
@@ -921,6 +921,11 @@ pnfs_send_layoutreturn(struct pnfs_layout_hdr *lo, nfs4_stateid stateid,
 
 	status = nfs4_proc_layoutreturn(lrp);
 out:
+	if (status) {
+		spin_lock(&ino->i_lock);
+		clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+		spin_unlock(&ino->i_lock);
+	}
 	dprintk("<-- %s status: %d\n", __func__, status);
 	return status;
 }

index bfa8547..5d2eadc 100644
@@ -200,7 +200,7 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 		dprintk("%s DS connection error %d\n", __func__,
 			task->tk_status);
 		nfs4_mark_deviceid_unavailable(devid);
-		set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
+		pnfs_error_mark_layout_for_return(inode, lseg);
 		rpc_wake_up(&tbl->slot_tbl_waitq);
 		/* fall through */
 	default:

index c87f664..55bff41 100644
@@ -18,20 +18,10 @@
 
 #define NFSDBG_FACILITY		NFSDBG_PNFS
 
-static void pnfs_generic_fenceme(struct inode *inode,
-				 struct pnfs_layout_hdr *lo)
-{
-	if (!test_and_clear_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
-		return;
-	pnfs_return_layout(inode);
-}
-
 void pnfs_generic_rw_release(void *data)
 {
 	struct nfs_pgio_header *hdr = data;
-	struct pnfs_layout_hdr *lo = hdr->lseg->pls_layout;
 
-	pnfs_generic_fenceme(lo->plh_inode, lo);
 	nfs_put_client(hdr->ds_clp);
 	hdr->mds_ops->rpc_release(data);
 }

index c4d1758..1c03187 100644
@@ -1050,7 +1050,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
 EXPORT_SYMBOL_GPL(nfs_pageio_resend);
 
 /**
- * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor
+ * nfs_pageio_complete - Complete I/O then cleanup an nfs_pageio_descriptor
  * @desc: pointer to io descriptor
  */
 void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)

@@ -1062,6 +1062,9 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
 		if (!nfs_do_recoalesce(desc))
 			break;
 	}
+
+	if (desc->pg_ops->pg_cleanup)
+		desc->pg_ops->pg_cleanup(desc);
 }
 
 /**

index 4c3aa80..479c566 100644
@@ -58,6 +58,7 @@ struct nfs_pageio_ops {
 	size_t	(*pg_test)(struct nfs_pageio_descriptor *, struct nfs_page *,
 			   struct nfs_page *);
 	int	(*pg_doio)(struct nfs_pageio_descriptor *);
+	void	(*pg_cleanup)(struct nfs_pageio_descriptor *);
 };
 
 struct nfs_rw_ops {

index 77fec6a..1cac3c1 100644
@@ -860,12 +860,14 @@ static const struct nfs_pageio_ops bl_pg_read_ops = {
 	.pg_init = bl_pg_init_read,
 	.pg_test = bl_pg_test_read,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops bl_pg_write_ops = {
 	.pg_init = bl_pg_init_write,
 	.pg_test = bl_pg_test_write,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static struct pnfs_layoutdriver_type blocklayout_type = {

index 5d2eadc..2af32fc 100644
@@ -933,12 +933,14 @@ static const struct nfs_pageio_ops filelayout_pg_read_ops = {
 	.pg_init = filelayout_pg_init_read,
 	.pg_test = filelayout_pg_test,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops filelayout_pg_write_ops = {
 	.pg_init = filelayout_pg_init_write,
 	.pg_test = filelayout_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)

index 9e5bc42..d007780 100644
@@ -607,12 +607,14 @@ static const struct nfs_pageio_ops objio_pg_read_ops = {
 	.pg_init = objio_init_read,
 	.pg_test = objio_pg_test,
 	.pg_doio = pnfs_generic_pg_readpages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static const struct nfs_pageio_ops objio_pg_write_ops = {
 	.pg_init = objio_init_write,
 	.pg_test = objio_pg_test,
 	.pg_doio = pnfs_generic_pg_writepages,
+	.pg_cleanup = pnfs_generic_pg_cleanup,
 };
 
 static struct pnfs_layoutdriver_type objlayout_type = {

index 63992c8..2da2e77 100644
@@ -1631,6 +1631,16 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write);
 
+void
+pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *desc)
+{
+	if (desc->pg_lseg) {
+		pnfs_put_lseg(desc->pg_lseg);
+		desc->pg_lseg = NULL;
+	}
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_cleanup);
+
 /*
  * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
  * of bytes (maximum @req->wb_bytes) that can be coalesced.

@@ -1756,11 +1766,9 @@ pnfs_do_write(struct nfs_pageio_descriptor *desc,
 	struct pnfs_layout_segment *lseg = desc->pg_lseg;
 	enum pnfs_try_status trypnfs;
 
-	desc->pg_lseg = NULL;
 	trypnfs = pnfs_try_to_write_data(hdr, call_ops, lseg, how);
 	if (trypnfs == PNFS_NOT_ATTEMPTED)
 		pnfs_write_through_mds(desc, hdr);
-	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)

@@ -1779,17 +1787,13 @@ pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc)
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
 		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
 		return -ENOMEM;
 	}
 	nfs_pgheader_init(desc, hdr, pnfs_writehdr_free);
+
 	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	ret = nfs_generic_pgio(desc, hdr);
-	if (ret != 0) {
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
-	} else
+	if (!ret)
 		pnfs_do_write(desc, hdr, desc->pg_ioflags);
 	return ret;
 }

@@ -1874,11 +1878,9 @@ pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
 	struct pnfs_layout_segment *lseg = desc->pg_lseg;
 	enum pnfs_try_status trypnfs;
 
-	desc->pg_lseg = NULL;
 	trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg);
 	if (trypnfs == PNFS_NOT_ATTEMPTED)
 		pnfs_read_through_mds(desc, hdr);
-	pnfs_put_lseg(lseg);
 }
 
 static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)

@@ -1897,18 +1899,12 @@ pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc)
 	hdr = nfs_pgio_header_alloc(desc->pg_rw_ops);
 	if (!hdr) {
 		desc->pg_completion_ops->error_cleanup(&desc->pg_list);
-		ret = -ENOMEM;
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
-		return ret;
+		return -ENOMEM;
 	}
 	nfs_pgheader_init(desc, hdr, pnfs_readhdr_free);
 	hdr->lseg = pnfs_get_lseg(desc->pg_lseg);
 	ret = nfs_generic_pgio(desc, hdr);
-	if (ret != 0) {
-		pnfs_put_lseg(desc->pg_lseg);
-		desc->pg_lseg = NULL;
-	} else
+	if (!ret)
 		pnfs_do_read(desc, hdr);
 	return ret;
 }

index 892678d..00a0a4a 100644
@@ -230,6 +230,7 @@ void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *
 int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
 void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			        struct nfs_page *req, u64 wb_size);
+void pnfs_generic_pg_cleanup(struct nfs_pageio_descriptor *);
 int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc);
 size_t pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
 			    struct nfs_page *prev, struct nfs_page *req);

index 8800bd3..e997457 100644
@@ -473,13 +473,18 @@ try_again:
 	do {
 		/*
 		 * Subrequests are always contiguous, non overlapping
-		 * and in order. If not, it's a programming error.
+		 * and in order - but may be repeated (mirrored writes).
 		 */
-		WARN_ON_ONCE(subreq->wb_offset !=
-		     (head->wb_offset + total_bytes));
-
-		/* keep track of how many bytes this group covers */
-		total_bytes += subreq->wb_bytes;
+		if (subreq->wb_offset == (head->wb_offset + total_bytes)) {
+			/* keep track of how many bytes this group covers */
+			total_bytes += subreq->wb_bytes;
+		} else if (WARN_ON_ONCE(subreq->wb_offset < head->wb_offset ||
+			    ((subreq->wb_offset + subreq->wb_bytes) >
+			     (head->wb_offset + total_bytes)))) {
+			nfs_page_group_unlock(head);
+			spin_unlock(&inode->i_lock);
+			return ERR_PTR(-EIO);
+		}
 
 		if (!nfs_lock_request(subreq)) {
 			/* releases page group bit lock and

index 1df2594..4c7034b 100644
@@ -112,22 +112,22 @@ static inline int put_dreq(struct nfs_direct_req *dreq)
  * nfs_direct_select_verf - select the right verifier
  * @dreq - direct request possibly spanning multiple servers
  * @ds_clp - nfs_client of data server or NULL if MDS / non-pnfs
- * @ds_idx - index of data server in data server list, only valid if ds_clp set
+ * @commit_idx - commit bucket index for the DS
  *
  * returns the correct verifier to use given the role of the server
  */
 static struct nfs_writeverf *
 nfs_direct_select_verf(struct nfs_direct_req *dreq,
 		       struct nfs_client *ds_clp,
-		       int ds_idx)
+		       int commit_idx)
 {
 	struct nfs_writeverf *verfp = &dreq->verf;
 
 #ifdef CONFIG_NFS_V4_1
 	if (ds_clp) {
 		/* pNFS is in use, use the DS verf */
-		if (ds_idx >= 0 && ds_idx < dreq->ds_cinfo.nbuckets)
-			verfp = &dreq->ds_cinfo.buckets[ds_idx].direct_verf;
+		if (commit_idx >= 0 && commit_idx < dreq->ds_cinfo.nbuckets)
+			verfp = &dreq->ds_cinfo.buckets[commit_idx].direct_verf;
 		else
 			WARN_ON_ONCE(1);
 	}

@@ -148,8 +148,7 @@ static void nfs_direct_set_hdr_verf(struct nfs_direct_req *dreq,
 {
 	struct nfs_writeverf *verfp;
 
-	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
-				      hdr->ds_idx);
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx);
 	WARN_ON_ONCE(verfp->committed >= 0);
 	memcpy(verfp, &hdr->verf, sizeof(struct nfs_writeverf));
 	WARN_ON_ONCE(verfp->committed < 0);

@@ -169,8 +168,7 @@ static int nfs_direct_set_or_cmp_hdr_verf(struct nfs_direct_req *dreq,
 {
 	struct nfs_writeverf *verfp;
 
-	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp,
-					 hdr->ds_idx);
+	verfp = nfs_direct_select_verf(dreq, hdr->ds_clp, hdr->ds_commit_idx);
 	if (verfp->committed < 0) {
 		nfs_direct_set_hdr_verf(dreq, hdr);
 		return 0;

index 2af32fc..520cbc5 100644
@@ -492,7 +492,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 	/* No multipath support. Use first DS */
 	atomic_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
-	hdr->ds_idx = idx;
+	hdr->ds_commit_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
 		hdr->args.fh = fh;

@@ -536,7 +536,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	hdr->pgio_done_cb = filelayout_write_done_cb;
 	atomic_inc(&ds->ds_clp->cl_count);
 	hdr->ds_clp = ds->ds_clp;
-	hdr->ds_idx = idx;
+	hdr->ds_commit_idx = idx;
 	fh = nfs4_fl_select_ds_fh(lseg, j);
 	if (fh)
 		hdr->args.fh = fh;

index 4fd7793..5bc99f0 100644
@@ -1328,7 +1328,7 @@ struct nfs_pgio_header {
 	__u64			mds_offset;	/* Filelayout dense stripe */
 	struct nfs_page_array	page_array;
 	struct nfs_client	*ds_clp;	/* pNFS data server */
-	int			ds_idx;		/* ds index if ds_clp is set */
+	int			ds_commit_idx;	/* ds index if ds_clp is set */
 };
 
 struct nfs_mds_commit_info {

index 4c7034b..33ba86c 100644
@@ -655,7 +655,7 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 		nfs_list_remove_request(req);
 		if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES) {
 			/* Note the rewrite will go through mds */
-			nfs_mark_request_commit(req, NULL, &cinfo);
+			nfs_mark_request_commit(req, NULL, &cinfo, 0);
 		} else
 			nfs_release_request(req);
 		nfs_unlock_and_release_request(req);

@@ -754,7 +754,8 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 		nfs_list_remove_request(req);
 		if (request_commit) {
 			kref_get(&req->wb_kref);
-			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+			nfs_mark_request_commit(req, hdr->lseg, &cinfo,
+				hdr->ds_commit_idx);
 		}
 		nfs_unlock_and_release_request(req);
 	}

index 520cbc5..3c97694 100644
@@ -954,7 +954,8 @@ static u32 select_bucket_index(struct nfs4_filelayout_segment *fl, u32 j)
 static void
 filelayout_mark_request_commit(struct nfs_page *req,
 			       struct pnfs_layout_segment *lseg,
-			       struct nfs_commit_info *cinfo)
+			       struct nfs_commit_info *cinfo,
+			       u32 ds_commit_idx)
 
 {
 	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);

index 331b6e6..66b53ca 100644
@@ -448,13 +448,15 @@ int nfs_scan_commit(struct inode *inode, struct list_head *dst,
 		    struct nfs_commit_info *cinfo);
 void nfs_mark_request_commit(struct nfs_page *req,
 			     struct pnfs_layout_segment *lseg,
-			     struct nfs_commit_info *cinfo);
+			     struct nfs_commit_info *cinfo,
+			     u32 ds_commit_idx);
 int nfs_write_need_commit(struct nfs_pgio_header *);
 int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 			    int how, struct nfs_commit_info *cinfo);
 void nfs_retry_commit(struct list_head *page_list,
 		      struct pnfs_layout_segment *lseg,
-		      struct nfs_commit_info *cinfo);
+		      struct nfs_commit_info *cinfo,
+		      u32 ds_commit_idx);
 void nfs_commitdata_release(struct nfs_commit_data *data);
 void nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst,
 				 struct nfs_commit_info *cinfo);

index 00a0a4a..ff14de4 100644
@@ -137,7 +137,8 @@ struct pnfs_layoutdriver_type {
 	struct pnfs_ds_commit_info *(*get_ds_info) (struct inode *inode);
 	void (*mark_request_commit) (struct nfs_page *req,
 				     struct pnfs_layout_segment *lseg,
-				     struct nfs_commit_info *cinfo);
+				     struct nfs_commit_info *cinfo,
+				     u32 ds_commit_idx);
 	void (*clear_request_commit) (struct nfs_page *req,
 				      struct nfs_commit_info *cinfo);
 	int (*scan_commit_lists) (struct nfs_commit_info *cinfo,

@@ -389,14 +390,14 @@ pnfs_generic_mark_devid_invalid(struct nfs4_deviceid_node *node)
 
 static inline bool
 pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			 struct nfs_commit_info *cinfo)
+			 struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
 	struct inode *inode = req->wb_context->dentry->d_inode;
 	struct pnfs_layoutdriver_type *ld = NFS_SERVER(inode)->pnfs_curr_ld;
 
 	if (lseg == NULL || ld->mark_request_commit == NULL)
 		return false;
-	ld->mark_request_commit(req, lseg, cinfo);
+	ld->mark_request_commit(req, lseg, cinfo, ds_commit_idx);
 	return true;
 }
 

@@ -574,7 +575,7 @@ pnfs_get_ds_info(struct inode *inode)
 
 static inline bool
 pnfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			 struct nfs_commit_info *cinfo)
+			 struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
 	return false;
 }

index 55bff41..fdc4f65 100644
@@ -188,7 +188,7 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
 		bucket = &fl_cinfo->buckets[i];
 		if (list_empty(&bucket->committing))
 			continue;
-		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
+		nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo, i);
 		spin_lock(cinfo->lock);
 		freeme = bucket->clseg;
 		bucket->clseg = NULL;

@@ -247,7 +247,7 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 			list_add(&data->pages, &list);
 			nreq++;
 		} else {
-			nfs_retry_commit(mds_pages, NULL, cinfo);
+			nfs_retry_commit(mds_pages, NULL, cinfo, 0);
 			pnfs_generic_retry_commit(cinfo, 0);
 			cinfo->completion_ops->error_cleanup(NFS_I(inode));
 			return -ENOMEM;

index e997457..2bee165 100644
@@ -847,9 +847,9 @@ EXPORT_SYMBOL_GPL(nfs_init_cinfo);
  */
 void
 nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
-			struct nfs_commit_info *cinfo)
+			struct nfs_commit_info *cinfo, u32 ds_commit_idx)
 {
-	if (pnfs_mark_request_commit(req, lseg, cinfo))
+	if (pnfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx))
 		return;
 	nfs_request_add_commit_list(req, &cinfo->mds->list, cinfo);
 }

@@ -905,7 +905,8 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr)
 		}
 		if (nfs_write_need_commit(hdr)) {
 			memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
-			nfs_mark_request_commit(req, hdr->lseg, &cinfo);
+			nfs_mark_request_commit(req, hdr->lseg, &cinfo,
+				0);
 			goto next;
 		}
 remove_req:

@@ -1560,14 +1561,15 @@ EXPORT_SYMBOL_GPL(nfs_init_commit);
 
 void nfs_retry_commit(struct list_head *page_list,
 		      struct pnfs_layout_segment *lseg,
-		      struct nfs_commit_info *cinfo)
+		      struct nfs_commit_info *cinfo,
+		      u32 ds_commit_idx)
 {
 	struct nfs_page *req;
 
 	while (!list_empty(page_list)) {
 		req = nfs_list_entry(page_list->next);
 		nfs_list_remove_request(req);
-		nfs_mark_request_commit(req, lseg, cinfo);
+		nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx);
 		if (!cinfo->dreq) {
 			dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
 			dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info,

@@ -1598,7 +1600,7 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 	return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
 				   data->mds_ops, how, 0);
  out_bad:
-	nfs_retry_commit(head, NULL, cinfo);
+	nfs_retry_commit(head, NULL, cinfo, 0);
 	cinfo->completion_ops->error_cleanup(NFS_I(inode));
 	return -ENOMEM;
 }

index 33ba86c..2cf0b3d 100644
@@ -366,8 +366,14 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	spin_lock(&dreq->lock);
 	if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) && (hdr->good_bytes == 0))
 		dreq->error = hdr->error;
-	else
-		dreq->count += hdr->good_bytes;
+	else {
+		/*
+		 * FIXME: right now this only accounts for bytes written
+		 *        to the first mirror
+		 */
+		if (hdr->pgio_mirror_idx == 0)
+			dreq->count += hdr->good_bytes;
+	}
 	spin_unlock(&dreq->lock);
 
 	while (!list_empty(&hdr->pages)) {

@@ -730,7 +736,12 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 		dreq->error = hdr->error;
 	}
 	if (dreq->error == 0) {
-		dreq->count += hdr->good_bytes;
+		/*
+		 * FIXME: right now this only accounts for bytes written
+		 *        to the first mirror
+		 */
+		if (hdr->pgio_mirror_idx == 0)
+			dreq->count += hdr->good_bytes;
 		if (nfs_write_need_commit(hdr)) {
 			if (dreq->flags == NFS_ODIRECT_RESCHED_WRITES)
 				request_commit = true;

index 66b53ca..fff6465 100644
@@ -467,6 +467,7 @@ void nfs_init_cinfo(struct nfs_commit_info *cinfo,
 		    struct nfs_direct_req *dreq);
 int nfs_key_timeout_notify(struct file *filp, struct inode *inode);
 bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx);
+void nfs_pageio_stop_mirroring(struct nfs_pageio_descriptor *pgio);
 
 #ifdef CONFIG_MIGRATION
 extern int nfs_migrate_page(struct address_space *,

index d007780..9a5f2ee 100644
@@ -537,11 +537,12 @@ int objio_write_pagelist(struct nfs_pgio_header *hdr, int how)
 static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
 			  struct nfs_page *prev, struct nfs_page *req)
 {
+	struct nfs_pgio_mirror *mirror = &pgio->pg_mirrors[pgio->pg_mirror_idx];
 	unsigned int size;
 
 	size = pnfs_generic_pg_test(pgio, prev, req);
 
-	if (!size || pgio->pg_count + req->wb_bytes >
+	if (!size || mirror->pg_count + req->wb_bytes >
 	    (unsigned long)pgio->pg_layout_private)
 		return 0;
 

446 lines not on this page · raw message

index 2da2e77..5f7c422 100644
@@ -1646,8 +1646,8 @@ EXPORT_SYMBOL_GPL(pnfs_generic_pg_cleanup);
  * of bytes (maximum @req->wb_bytes) that can be coalesced.
  */
 size_t
-pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
-		     struct nfs_page *req)
+pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
+		     struct nfs_page *prev, struct nfs_page *req)
 {
 	unsigned int size;
 	u64 seg_end, req_start, seg_left;