1 files changed, 362 insertions, 221 deletions

diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c
index de5350f2b24..ed388aae968 100644
--- a/fs/nfs/nfs4filelayoutdev.c
+++ b/fs/nfs/nfs4filelayoutdev.c
@@ -37,30 +37,6 @@
 #define NFSDBG_FACILITY		NFSDBG_PNFS_LD
 
 /*
- * Device ID RCU cache. A device ID is unique per client ID and layout type.
- */
-#define NFS4_FL_DEVICE_ID_HASH_BITS	5
-#define NFS4_FL_DEVICE_ID_HASH_SIZE	(1 << NFS4_FL_DEVICE_ID_HASH_BITS)
-#define NFS4_FL_DEVICE_ID_HASH_MASK	(NFS4_FL_DEVICE_ID_HASH_SIZE - 1)
-
-static inline u32
-nfs4_fl_deviceid_hash(struct nfs4_deviceid *id)
-{
-	unsigned char *cptr = (unsigned char *)id->data;
-	unsigned int nbytes = NFS4_DEVICEID4_SIZE;
-	u32 x = 0;
-
-	while (nbytes--) {
-		x *= 37;
-		x += *cptr++;
-	}
-	return x & NFS4_FL_DEVICE_ID_HASH_MASK;
-}
-
-static struct hlist_head filelayout_deviceid_cache[NFS4_FL_DEVICE_ID_HASH_SIZE];
-static DEFINE_SPINLOCK(filelayout_deviceid_lock);
-
-/*
  * Data server cache
  *
  * Data servers can be mapped to different device ids.
@@ -80,75 +56,139 @@ print_ds(struct nfs4_pnfs_ds *ds)
 		printk("%s NULL device\n", __func__);
 		return;
 	}
-	printk("        ip_addr %x port %hu\n"
+	printk("        ds %s\n"
 		"        ref count %d\n"
 		"        client %p\n"
 		"        cl_exchange_flags %x\n",
-		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port),
+		ds->ds_remotestr,
 		atomic_read(&ds->ds_count), ds->ds_clp,
 		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
 }
 
-void
-print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr)
+static bool
+same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
 {
-	int i;
-
-	ifdebug(FACILITY) {
-		printk("%s dsaddr->ds_num %d\n", __func__,
-		       dsaddr->ds_num);
-		for (i = 0; i < dsaddr->ds_num; i++)
-			print_ds(dsaddr->ds_list[i]);
+	struct sockaddr_in *a, *b;
+	struct sockaddr_in6 *a6, *b6;
+
+	if (addr1->sa_family != addr2->sa_family)
+		return false;
+
+	switch (addr1->sa_family) {
+	case AF_INET:
+		a = (struct sockaddr_in *)addr1;
+		b = (struct sockaddr_in *)addr2;
+
+		if (a->sin_addr.s_addr == b->sin_addr.s_addr &&
+		    a->sin_port == b->sin_port)
+			return true;
+		break;
+
+	case AF_INET6:
+		a6 = (struct sockaddr_in6 *)addr1;
+		b6 = (struct sockaddr_in6 *)addr2;
+
+		/* LINKLOCAL addresses must have matching scope_id */
+		if (ipv6_addr_scope(&a6->sin6_addr) ==
+		    IPV6_ADDR_SCOPE_LINKLOCAL &&
+		    a6->sin6_scope_id != b6->sin6_scope_id)
+			return false;
+
+		if (ipv6_addr_equal(&a6->sin6_addr, &b6->sin6_addr) &&
+		    a6->sin6_port == b6->sin6_port)
+			return true;
+		break;
+
+	default:
+		dprintk("%s: unhandled address family: %u\n",
+			__func__, addr1->sa_family);
+		return false;
 	}
-}
 
-void print_deviceid(struct nfs4_deviceid *id)
-{
-	u32 *p = (u32 *)id;
-
-	dprintk("%s: device id= [%x%x%x%x]\n", __func__,
-		p[0], p[1], p[2], p[3]);
+	return false;
 }
 
-/* nfs4_ds_cache_lock is held */
+/*
+ * Lookup DS by addresses.  The first matching address returns true.
+ * nfs4_ds_cache_lock is held
+ */
 static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(u32 ip_addr, u32 port)
+_data_server_lookup_locked(struct list_head *dsaddrs)
 {
 	struct nfs4_pnfs_ds *ds;
-
-	dprintk("_data_server_lookup: ip_addr=%x port=%hu\n",
-			ntohl(ip_addr), ntohs(port));
-
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
-		if (ds->ds_ip_addr == ip_addr &&
-		    ds->ds_port == port) {
-			return ds;
+	struct nfs4_pnfs_ds_addr *da1, *da2;
+
+	list_for_each_entry(da1, dsaddrs, da_node) {
+		list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) {
+			list_for_each_entry(da2, &ds->ds_addrs, da_node) {
+				if (same_sockaddr(
+					(struct sockaddr *)&da1->da_addr,
+					(struct sockaddr *)&da2->da_addr))
+					return ds;
+			}
 		}
 	}
 	return NULL;
 }
 
 /*
+ * Compare two lists of addresses.
+ */
+static bool
+_data_server_match_all_addrs_locked(struct list_head *dsaddrs1,
+				    struct list_head *dsaddrs2)
+{
+	struct nfs4_pnfs_ds_addr *da1, *da2;
+	size_t count1 = 0,
+	       count2 = 0;
+
+	list_for_each_entry(da1, dsaddrs1, da_node)
+		count1++;
+
+	list_for_each_entry(da2, dsaddrs2, da_node) {
+		bool found = false;
+		count2++;
+		list_for_each_entry(da1, dsaddrs1, da_node) {
+			if (same_sockaddr((struct sockaddr *)&da1->da_addr,
+				(struct sockaddr *)&da2->da_addr)) {
+				found = true;
+				break;
+			}
+		}
+		if (!found)
+			return false;
+	}
+
+	return (count1 == count2);
+}
+
+/*
  * Create an rpc connection to the nfs4_pnfs_ds data server
- * Currently only support IPv4
+ * 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;
-	struct sockaddr_in sin;
+	struct nfs_client *clp = ERR_PTR(-EIO);
+	struct nfs4_pnfs_ds_addr *da;
 	int status = 0;
 
-	dprintk("--> %s ip:port %x:%hu au_flavor %d\n", __func__,
-		ntohl(ds->ds_ip_addr), ntohs(ds->ds_port),
+	dprintk("--> %s DS %s au_flavor %d\n", __func__, ds->ds_remotestr,
 		mds_srv->nfs_client->cl_rpcclient->cl_auth->au_flavor);
 
-	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = ds->ds_ip_addr;
-	sin.sin_port = ds->ds_port;
+	BUG_ON(list_empty(&ds->ds_addrs));
+
+	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);
+		if (!IS_ERR(clp))
+			break;
+	}
 
-	clp = nfs4_set_ds_client(mds_srv->nfs_client, (struct sockaddr *)&sin,
-				 sizeof(sin), IPPROTO_TCP);
 	if (IS_ERR(clp)) {
 		status = PTR_ERR(clp);
 		goto out;
@@ -160,8 +200,8 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 			goto out_put;
 		}
 		ds->ds_clp = clp;
-		dprintk("%s [existing] ip=%x, port=%hu\n", __func__,
-			ntohl(ds->ds_ip_addr), ntohs(ds->ds_port));
+		dprintk("%s [existing] server=%s\n", __func__,
+			ds->ds_remotestr);
 		goto out;
 	}
 
@@ -180,8 +220,7 @@ nfs4_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds)
 		goto out_put;
 
 	ds->ds_clp = clp;
-	dprintk("%s [new] ip=%x, port=%hu\n", __func__, ntohl(ds->ds_ip_addr),
-		ntohs(ds->ds_port));
+	dprintk("%s [new] addr: %s\n", __func__, ds->ds_remotestr);
 out:
 	return status;
 out_put:
@@ -192,22 +231,35 @@ out_put:
 static void
 destroy_ds(struct nfs4_pnfs_ds *ds)
 {
+	struct nfs4_pnfs_ds_addr *da;
+
 	dprintk("--> %s\n", __func__);
 	ifdebug(FACILITY)
 		print_ds(ds);
 
 	if (ds->ds_clp)
 		nfs_put_client(ds->ds_clp);
+
+	while (!list_empty(&ds->ds_addrs)) {
+		da = list_first_entry(&ds->ds_addrs,
+				      struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
+
+	kfree(ds->ds_remotestr);
 	kfree(ds);
 }
 
-static void
+void
 nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
 	struct nfs4_pnfs_ds *ds;
 	int i;
 
-	print_deviceid(&dsaddr->deviceid);
+	nfs4_print_deviceid(&dsaddr->id_node.deviceid);
 
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		ds = dsaddr->ds_list[i];
@@ -224,31 +276,96 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 	kfree(dsaddr);
 }
 
+/*
+ * Create a string with a human readable address and port to avoid
+ * complicated setup around many dprinks.
+ */
+static char *
+nfs4_pnfs_remotestr(struct list_head *dsaddrs, gfp_t gfp_flags)
+{
+	struct nfs4_pnfs_ds_addr *da;
+	char *remotestr;
+	size_t len;
+	char *p;
+
+	len = 3;        /* '{', '}' and eol */
+	list_for_each_entry(da, dsaddrs, da_node) {
+		len += strlen(da->da_remotestr) + 1;    /* string plus comma */
+	}
+
+	remotestr = kzalloc(len, gfp_flags);
+	if (!remotestr)
+		return NULL;
+
+	p = remotestr;
+	*(p++) = '{';
+	len--;
+	list_for_each_entry(da, dsaddrs, da_node) {
+		size_t ll = strlen(da->da_remotestr);
+
+		if (ll > len)
+			goto out_err;
+
+		memcpy(p, da->da_remotestr, ll);
+		p += ll;
+		len -= ll;
+
+		if (len < 1)
+			goto out_err;
+		(*p++) = ',';
+		len--;
+	}
+	if (len < 2)
+		goto out_err;
+	*(p++) = '}';
+	*p = '\0';
+	return remotestr;
+out_err:
+	kfree(remotestr);
+	return NULL;
+}
+
 static struct nfs4_pnfs_ds *
-nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port)
+nfs4_pnfs_ds_add(struct list_head *dsaddrs, gfp_t gfp_flags)
 {
-	struct nfs4_pnfs_ds *tmp_ds, *ds;
+	struct nfs4_pnfs_ds *tmp_ds, *ds = NULL;
+	char *remotestr;
+
+	if (list_empty(dsaddrs)) {
+		dprintk("%s: no addresses defined\n", __func__);
+		goto out;
+	}
 
-	ds = kzalloc(sizeof(*tmp_ds), GFP_KERNEL);
+	ds = kzalloc(sizeof(*ds), gfp_flags);
 	if (!ds)
 		goto out;
 
+	/* this is only used for debugging, so it's ok if its NULL */
+	remotestr = nfs4_pnfs_remotestr(dsaddrs, gfp_flags);
+
 	spin_lock(&nfs4_ds_cache_lock);
-	tmp_ds = _data_server_lookup_locked(ip_addr, port);
+	tmp_ds = _data_server_lookup_locked(dsaddrs);
 	if (tmp_ds == NULL) {
-		ds->ds_ip_addr = ip_addr;
-		ds->ds_port = port;
+		INIT_LIST_HEAD(&ds->ds_addrs);
+		list_splice_init(dsaddrs, &ds->ds_addrs);
+		ds->ds_remotestr = remotestr;
 		atomic_set(&ds->ds_count, 1);
 		INIT_LIST_HEAD(&ds->ds_node);
 		ds->ds_clp = NULL;
 		list_add(&ds->ds_node, &nfs4_data_server_cache);
-		dprintk("%s add new data server ip 0x%x\n", __func__,
-			ds->ds_ip_addr);
+		dprintk("%s add new data server %s\n", __func__,
+			ds->ds_remotestr);
 	} else {
+		if (!_data_server_match_all_addrs_locked(&tmp_ds->ds_addrs,
+							 dsaddrs)) {
+			dprintk("%s:  multipath address mismatch: %s != %s",
+				__func__, tmp_ds->ds_remotestr, remotestr);
+		}
+		kfree(remotestr);
 		kfree(ds);
 		atomic_inc(&tmp_ds->ds_count);
-		dprintk("%s data server found ip 0x%x, inc'ed ds_count to %d\n",
-			__func__, tmp_ds->ds_ip_addr,
+		dprintk("%s data server %s found, inc'ed ds_count to %d\n",
+			__func__, tmp_ds->ds_remotestr,
 			atomic_read(&tmp_ds->ds_count));
 		ds = tmp_ds;
 	}
@@ -258,18 +375,22 @@ out:
 }
 
 /*
- * Currently only support ipv4, and one multi-path address.
+ * Currently only supports ipv4, ipv6 and one multi-path address.
  */
-static struct nfs4_pnfs_ds *
-decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode)
+static struct nfs4_pnfs_ds_addr *
+decode_ds_addr(struct xdr_stream *streamp, gfp_t gfp_flags)
 {
-	struct nfs4_pnfs_ds *ds = NULL;
-	char *buf;
-	const char *ipend, *pstr;
-	u32 ip_addr, port;
-	int nlen, rlen, i;
+	struct nfs4_pnfs_ds_addr *da = NULL;
+	char *buf, *portstr;
+	u32 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);
@@ -281,69 +402,128 @@ decode_and_add_ds(struct xdr_stream *streamp, struct inode *inode)
 	if (unlikely(!p))
 		goto out_err;
 
-	/* Check that netid is "tcp" */
-	if (nlen != 3 ||  memcmp((char *)p, "tcp", 3)) {
-		dprintk("%s: ERROR: non ipv4 TCP r_netid\n", __func__);
+	netid = kmalloc(nlen+1, gfp_flags);
+	if (unlikely(!netid))
 		goto out_err;
-	}
 
-	/* r_addr */
+	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_err;
+		goto out_free_netid;
 	rlen = be32_to_cpup(p);
 
 	p = xdr_inline_decode(streamp, rlen);
 	if (unlikely(!p))
-		goto out_err;
+		goto out_free_netid;
 
-	/* ipv6 length plus port is legal */
-	if (rlen > INET6_ADDRSTRLEN + 8) {
+	/* 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_err;
+		goto out_free_netid;
 	}
-	buf = kmalloc(rlen + 1, GFP_KERNEL);
+	buf = kmalloc(rlen + 1, gfp_flags);
 	if (!buf) {
 		dprintk("%s: Not enough memory\n", __func__);
-		goto out_err;
+		goto out_free_netid;
 	}
 	buf[rlen] = '\0';
 	memcpy(buf, p, rlen);
 
-	/* replace the port dots with dashes for the in4_pton() delimiter*/
-	for (i = 0; i < 2; i++) {
-		char *res = strrchr(buf, '.');
-		if (!res) {
-			dprintk("%s: Failed finding expected dots in port\n",
-				__func__);
-			goto out_free;
-		}
-		*res = '-';
+	/* 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';
 
-	/* Currently only support ipv4 address */
-	if (in4_pton(buf, rlen, (u8 *)&ip_addr, '-', &ipend) == 0) {
-		dprintk("%s: Only ipv4 addresses supported\n", __func__);
-		goto out_free;
+	da = kzalloc(sizeof(*da), gfp_flags);
+	if (unlikely(!da))
+		goto out_free_buf;
+
+	INIT_LIST_HEAD(&da->da_node);
+
+	if (!rpc_pton(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;
 	}
 
-	/* port */
-	pstr = ipend;
-	sscanf(pstr, "-%d-%d", &tmp[0], &tmp[1]);
+	portstr++;
+	sscanf(portstr, "%d-%d", &tmp[0], &tmp[1]);
 	port = htons((tmp[0] << 8) | (tmp[1]));
 
-	ds = nfs4_pnfs_ds_add(inode, ip_addr, port);
-	dprintk("%s: Decoded address and port %s\n", __func__, buf);
-out_free:
+	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 ds;
+	return NULL;
 }
 
 /* Decode opaque device data and return the result */
 static struct nfs4_file_layout_dsaddr*
-decode_device(struct inode *ino, struct pnfs_device *pdev)
+decode_device(struct inode *ino, struct pnfs_device *pdev, gfp_t gfp_flags)
 {
 	int i;
 	u32 cnt, num;
@@ -353,20 +533,17 @@ decode_device(struct inode *ino, struct pnfs_device *pdev)
 	u8 max_stripe_index;
 	struct nfs4_file_layout_dsaddr *dsaddr = NULL;
 	struct xdr_stream stream;
-	struct xdr_buf buf = {
-		.pages = pdev->pages,
-		.page_len = pdev->pglen,
-		.buflen = pdev->pglen,
-		.len = pdev->pglen,
-	};
+	struct xdr_buf buf;
 	struct page *scratch;
+	struct list_head dsaddrs;
+	struct nfs4_pnfs_ds_addr *da;
 
 	/* set up xdr stream */
-	scratch = alloc_page(GFP_KERNEL);
+	scratch = alloc_page(gfp_flags);
 	if (!scratch)
 		goto out_err;
 
-	xdr_init_decode(&stream, &buf, NULL);
+	xdr_init_decode_pages(&stream, &buf, pdev->pages, pdev->pglen);
 	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
 
 	/* Get the stripe count (number of stripe index) */
@@ -384,7 +561,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev)
 	}
 
 	/* read stripe indices */
-	stripe_indices = kcalloc(cnt, sizeof(u8), GFP_KERNEL);
+	stripe_indices = kcalloc(cnt, sizeof(u8), gfp_flags);
 	if (!stripe_indices)
 		goto out_err_free_scratch;
 
@@ -423,7 +600,7 @@ decode_device(struct inode *ino, struct pnfs_device *pdev)
 
 	dsaddr = kzalloc(sizeof(*dsaddr) +
 			(sizeof(struct nfs4_pnfs_ds *) * (num - 1)),
-			GFP_KERNEL);
+			gfp_flags);
 	if (!dsaddr)
 		goto out_err_free_stripe_indices;
 
@@ -431,8 +608,12 @@ decode_device(struct inode *ino, struct pnfs_device *pdev)
 	dsaddr->stripe_indices = stripe_indices;
 	stripe_indices = NULL;
 	dsaddr->ds_num = num;
+	nfs4_init_deviceid_node(&dsaddr->id_node,
+				NFS_SERVER(ino)->pnfs_curr_ld,
+				NFS_SERVER(ino)->nfs_client,
+				&pdev->dev_id);
 
-	memcpy(&dsaddr->deviceid, &pdev->dev_id, sizeof(pdev->dev_id));
+	INIT_LIST_HEAD(&dsaddrs);
 
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		int j;
@@ -443,48 +624,43 @@ decode_device(struct inode *ino, struct pnfs_device *pdev)
 			goto out_err_free_deviceid;
 
 		mp_count = be32_to_cpup(p); /* multipath count */
-		if (mp_count > 1) {
-			printk(KERN_WARNING
-			       "%s: Multipath count %d not supported, "
-			       "skipping all greater than 1\n", __func__,
-				mp_count);
-		}
 		for (j = 0; j < mp_count; j++) {
-			if (j == 0) {
-				dsaddr->ds_list[i] = decode_and_add_ds(&stream,
-					ino);
-				if (dsaddr->ds_list[i] == NULL)
-					goto out_err_free_deviceid;
-			} else {
-				u32 len;
-				/* skip extra multipath */
-
-				/* read len, skip */
-				p = xdr_inline_decode(&stream, 4);
-				if (unlikely(!p))
-					goto out_err_free_deviceid;
-				len = be32_to_cpup(p);
-
-				p = xdr_inline_decode(&stream, len);
-				if (unlikely(!p))
-					goto out_err_free_deviceid;
-
-				/* read len, skip */
-				p = xdr_inline_decode(&stream, 4);
-				if (unlikely(!p))
-					goto out_err_free_deviceid;
-				len = be32_to_cpup(p);
-
-				p = xdr_inline_decode(&stream, len);
-				if (unlikely(!p))
-					goto out_err_free_deviceid;
-			}
+			da = decode_ds_addr(&stream, gfp_flags);
+			if (da)
+				list_add_tail(&da->da_node, &dsaddrs);
+		}
+		if (list_empty(&dsaddrs)) {
+			dprintk("%s: no suitable DS addresses found\n",
+				__func__);
+			goto out_err_free_deviceid;
+		}
+
+		dsaddr->ds_list[i] = nfs4_pnfs_ds_add(&dsaddrs, gfp_flags);
+		if (!dsaddr->ds_list[i])
+			goto out_err_drain_dsaddrs;
+
+		/* If DS was already in cache, free ds addrs */
+		while (!list_empty(&dsaddrs)) {
+			da = list_first_entry(&dsaddrs,
+					      struct nfs4_pnfs_ds_addr,
+					      da_node);
+			list_del_init(&da->da_node);
+			kfree(da->da_remotestr);
+			kfree(da);
 		}
 	}
 
 	__free_page(scratch);
 	return dsaddr;
 
+out_err_drain_dsaddrs:
+	while (!list_empty(&dsaddrs)) {
+		da = list_first_entry(&dsaddrs, struct nfs4_pnfs_ds_addr,
+				      da_node);
+		list_del_init(&da->da_node);
+		kfree(da->da_remotestr);
+		kfree(da);
+	}
 out_err_free_deviceid:
 	nfs4_fl_free_deviceid(dsaddr);
 	/* stripe_indicies was part of dsaddr */
@@ -503,32 +679,25 @@ out_err:
  * available devices.
  */
 static struct nfs4_file_layout_dsaddr *
-decode_and_add_device(struct inode *inode, struct pnfs_device *dev)
+decode_and_add_device(struct inode *inode, struct pnfs_device *dev, gfp_t gfp_flags)
 {
-	struct nfs4_file_layout_dsaddr *d, *new;
-	long hash;
+	struct nfs4_deviceid_node *d;
+	struct nfs4_file_layout_dsaddr *n, *new;
 
-	new = decode_device(inode, dev);
+	new = decode_device(inode, dev, gfp_flags);
 	if (!new) {
 		printk(KERN_WARNING "%s: Could not decode or add device\n",
 			__func__);
 		return NULL;
 	}
 
-	spin_lock(&filelayout_deviceid_lock);
-	d = nfs4_fl_find_get_deviceid(&new->deviceid);
-	if (d) {
-		spin_unlock(&filelayout_deviceid_lock);
+	d = nfs4_insert_deviceid_node(&new->id_node);
+	n = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	if (n != new) {
 		nfs4_fl_free_deviceid(new);
-		return d;
+		return n;
 	}
 
-	INIT_HLIST_NODE(&new->node);
-	atomic_set(&new->ref, 1);
-	hash = nfs4_fl_deviceid_hash(&new->deviceid);
-	hlist_add_head_rcu(&new->node, &filelayout_deviceid_cache[hash]);
-	spin_unlock(&filelayout_deviceid_lock);
-
 	return new;
 }
 
@@ -537,7 +706,7 @@ decode_and_add_device(struct inode *inode, struct pnfs_device *dev)
  * of available devices, and return it.
  */
 struct nfs4_file_layout_dsaddr *
-get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id)
+get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_flags)
 {
 	struct pnfs_device *pdev = NULL;
 	u32 max_resp_sz;
@@ -556,17 +725,17 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id)
 	dprintk("%s inode %p max_resp_sz %u max_pages %d\n",
 		__func__, inode, max_resp_sz, max_pages);
 
-	pdev = kzalloc(sizeof(struct pnfs_device), GFP_KERNEL);
+	pdev = kzalloc(sizeof(struct pnfs_device), gfp_flags);
 	if (pdev == NULL)
 		return NULL;
 
-	pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL);
+	pages = kzalloc(max_pages * sizeof(struct page *), gfp_flags);
 	if (pages == NULL) {
 		kfree(pdev);
 		return NULL;
 	}
 	for (i = 0; i < max_pages; i++) {
-		pages[i] = alloc_page(GFP_KERNEL);
+		pages[i] = alloc_page(gfp_flags);
 		if (!pages[i])
 			goto out_free;
 	}
@@ -587,7 +756,7 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id)
 	 * Found new device, need to decode it and then add it to the
 	 * list of known devices for this mountpoint.
 	 */
-	dsaddr = decode_and_add_device(inode, pdev);
+	dsaddr = decode_and_add_device(inode, pdev, gfp_flags);
 out_free:
 	for (i = 0; i < max_pages; i++)
 		__free_page(pages[i]);
@@ -600,35 +769,7 @@ out_free:
 void
 nfs4_fl_put_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
-	if (atomic_dec_and_lock(&dsaddr->ref, &filelayout_deviceid_lock)) {
-		hlist_del_rcu(&dsaddr->node);
-		spin_unlock(&filelayout_deviceid_lock);
-
-		synchronize_rcu();
-		nfs4_fl_free_deviceid(dsaddr);
-	}
-}
-
-struct nfs4_file_layout_dsaddr *
-nfs4_fl_find_get_deviceid(struct nfs4_deviceid *id)
-{
-	struct nfs4_file_layout_dsaddr *d;
-	struct hlist_node *n;
-	long hash = nfs4_fl_deviceid_hash(id);
-
-
-	rcu_read_lock();
-	hlist_for_each_entry_rcu(d, n, &filelayout_deviceid_cache[hash], node) {
-		if (!memcmp(&d->deviceid, id, sizeof(*id))) {
-			if (!atomic_inc_not_zero(&d->ref))
-				goto fail;
-			rcu_read_unlock();
-			return d;
-		}
-	}
-fail:
-	rcu_read_unlock();
-	return NULL;
+	nfs4_put_deviceid_node(&dsaddr->id_node);
 }
 
 /*
@@ -674,17 +815,17 @@ nfs4_fl_select_ds_fh(struct pnfs_layout_segment *lseg, u32 j)
 
 static void
 filelayout_mark_devid_negative(struct nfs4_file_layout_dsaddr *dsaddr,
-			       int err, u32 ds_addr)
+			       int err, const char *ds_remotestr)
 {
-	u32 *p = (u32 *)&dsaddr->deviceid;
+	u32 *p = (u32 *)&dsaddr->id_node.deviceid;
 
-	printk(KERN_ERR "NFS: data server %x connection error %d."
+	printk(KERN_ERR "NFS: data server %s connection error %d."
 		" Deviceid [%x%x%x%x] marked out of use.\n",
-		ds_addr, err, p[0], p[1], p[2], p[3]);
+		ds_remotestr, err, p[0], p[1], p[2], p[3]);
 
-	spin_lock(&filelayout_deviceid_lock);
+	spin_lock(&nfs4_ds_cache_lock);
 	dsaddr->flags |= NFS4_DEVICE_ID_NEG_ENTRY;
-	spin_unlock(&filelayout_deviceid_lock);
+	spin_unlock(&nfs4_ds_cache_lock);
 }
 
 struct nfs4_pnfs_ds *
@@ -711,7 +852,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 		err = nfs4_ds_connect(s, ds);
 		if (err) {
 			filelayout_mark_devid_negative(dsaddr, err,
-						       ntohl(ds->ds_ip_addr));
+						       ds->ds_remotestr);
 			return NULL;
 		}
 	}