1 files changed, 12 insertions, 457 deletions

diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index bfecac781f19..4f372e224603 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -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"
@@ -42,183 +41,6 @@
 static unsigned int dataserver_timeo = NFS4_DEF_DS_TIMEO;
 static unsigned int dataserver_retrans = NFS4_DEF_DS_RETRANS;
 
-/*
- * Data server cache
- *
- * Data servers can be mapped to different device ids.
- * nfs4_pnfs_ds reference counting
- *   - set to 1 on allocation
- *   - incremented when a device id maps a data server already in the cache.
- *   - decremented when deviceid is removed from the cache.
- */
-static DEFINE_SPINLOCK(nfs4_ds_cache_lock);
-static LIST_HEAD(nfs4_data_server_cache);
-
-/* Debug routines */
-void
-print_ds(struct nfs4_pnfs_ds *ds)
-{
-	if (ds == NULL) {
-		printk("%s NULL device\n", __func__);
-		return;
-	}
-	printk("        ds %s\n"
-		"        ref count %d\n"
-		"        client %p\n"
-		"        cl_exchange_flags %x\n",
-		ds->ds_remotestr,
-		atomic_read(&ds->ds_count), ds->ds_clp,
-		ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0);
-}
-
-static bool
-same_sockaddr(struct sockaddr *addr1, struct sockaddr *addr2)
-{
-	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_src_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;
-	}
-
-	return false;
-}
-
-static bool
-_same_data_server_addrs_locked(const struct list_head *dsaddrs1,
-			       const struct list_head *dsaddrs2)
-{
-	struct nfs4_pnfs_ds_addr *da1, *da2;
-
-	/* step through both lists, comparing as we go */
-	for (da1 = list_first_entry(dsaddrs1, typeof(*da1), da_node),
-	     da2 = list_first_entry(dsaddrs2, typeof(*da2), da_node);
-	     da1 != NULL && da2 != NULL;
-	     da1 = list_entry(da1->da_node.next, typeof(*da1), da_node),
-	     da2 = list_entry(da2->da_node.next, typeof(*da2), da_node)) {
-		if (!same_sockaddr((struct sockaddr *)&da1->da_addr,
-				   (struct sockaddr *)&da2->da_addr))
-			return false;
-	}
-	if (da1 == NULL && da2 == NULL)
-		return true;
-
-	return false;
-}
-
-/*
- * Lookup DS by addresses.  nfs4_ds_cache_lock is held
- */
-static struct nfs4_pnfs_ds *
-_data_server_lookup_locked(const struct list_head *dsaddrs)
-{
-	struct nfs4_pnfs_ds *ds;
-
-	list_for_each_entry(ds, &nfs4_data_server_cache, ds_node)
-		if (_same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs))
-			return ds;
-	return NULL;
-}
-
-/*
- * 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;
-}
-
-static void
-destroy_ds(struct nfs4_pnfs_ds *ds)
-{
-	struct nfs4_pnfs_ds_addr *da;
-
-	dprintk("--> %s\n", __func__);
-	ifdebug(FACILITY)
-		print_ds(ds);
-
-	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);
-}
-
 void
 nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 {
@@ -229,259 +51,13 @@ nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr)
 
 	for (i = 0; i < dsaddr->ds_num; i++) {
 		ds = dsaddr->ds_list[i];
-		if (ds != NULL) {
-			if (atomic_dec_and_lock(&ds->ds_count,
-						&nfs4_ds_cache_lock)) {
-				list_del_init(&ds->ds_node);
-				spin_unlock(&nfs4_ds_cache_lock);
-				destroy_ds(ds);
-			}
-		}
+		if (ds != NULL)
+			nfs4_pnfs_ds_put(ds);
 	}
 	kfree(dsaddr->stripe_indices);
 	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 list_head *dsaddrs, gfp_t gfp_flags)
-{
-	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(*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(dsaddrs);
-	if (tmp_ds == NULL) {
-		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 %s\n", __func__,
-			ds->ds_remotestr);
-	} else {
-		kfree(remotestr);
-		kfree(ds);
-		atomic_inc(&tmp_ds->ds_count);
-		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;
-	}
-	spin_unlock(&nfs4_ds_cache_lock);
-out:
-	return ds;
-}
-
-/*
- * 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,
@@ -584,8 +160,8 @@ 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);
 		}
@@ -681,22 +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)
 {
@@ -704,29 +265,23 @@ 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",
 			__func__, ds_idx);
-		filelayout_mark_devid_invalid(devid);
+		pnfs_generic_mark_devid_invalid(devid);
 		goto out;
 	}
 	smp_rmb();
 	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, 4,
+			     s->nfs_client->cl_minorversion,
+			     s->nfs_client->cl_rpcclient->cl_auth->au_flavor);
+
 out_test_devid:
 	if (filelayout_test_devid_unavailable(devid))
 		ret = NULL;