afs: Fix server list handling

Fix server list handling in the following ways:

 (1) In afs_alloc_volume(), remove duplicate server list build code.  This
     was already done by afs_alloc_server_list() which afs_alloc_volume()
     previously called.  This just results in twice as many VL RPCs.

 (2) In afs_deliver_vl_get_entry_by_name_u(), use the number of server
     records indicated by ->nServers in the UVLDB record returned by the
     VL.GetEntryByNameU RPC call rather than scanning all NMAXNSERVERS
     slots.  Unused slots may contain garbage.

 (3) In afs_alloc_server_list(), don't stop converting a UVLDB record into
     a server list just because we can't look up one of the servers.  Just
     skip that server and go on to the next.  If we can't look up any of
     the servers then we'll fail at the end.

Without this patch, an attempt to view the umich.edu root cell using
something like "ls /afs/umich.edu" on a dynamic root (future patch) mount
or an autocell mount will result in ENOMEDIUM.  The failure is due to kafs
not stopping after nServers'worth of records have been read, but then
trying to access a server with a garbage UUID and getting an error, which
aborts the server list build.

Fixes: d2ddc776a458 ("afs: Overhaul volume and server record caching and fileserver rotation")
Reported-by: Jonathan Billings <jsbillings@jsbillings.org>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: stable@vger.kernel.org

3 files changed, 11 insertions, 48 deletions

diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index 0ab3f84..0f8dc4c 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -58,7 +58,8 @@ struct afs_server_list *afs_alloc_server_list(struct afs_cell *cell,
 		server = afs_lookup_server(cell, key, &vldb->fs_server[i]);
 		if (IS_ERR(server)) {
 			ret = PTR_ERR(server);
-			if (ret == -ENOENT)
+			if (ret == -ENOENT ||
+			    ret == -ENOMEDIUM)
 				continue;
 			goto error_2;
 		}
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index e372f89..5d8562f 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -23,7 +23,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	struct afs_uvldbentry__xdr *uvldb;
 	struct afs_vldb_entry *entry;
 	bool new_only = false;
-	u32 tmp;
+	u32 tmp, nr_servers;
 	int i, ret;
 
 	_enter("");
@@ -36,6 +36,10 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	uvldb = call->buffer;
 	entry = call->reply[0];
 
+	nr_servers = ntohl(uvldb->nServers);
+	if (nr_servers > AFS_NMAXNSERVERS)
+		nr_servers = AFS_NMAXNSERVERS;
+
 	for (i = 0; i < ARRAY_SIZE(uvldb->name) - 1; i++)
 		entry->name[i] = (u8)ntohl(uvldb->name[i]);
 	entry->name[i] = 0;
@@ -44,14 +48,14 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
 	/* If there is a new replication site that we can use, ignore all the
 	 * sites that aren't marked as new.
 	 */
-	for (i = 0; i < AFS_NMAXNSERVERS; i++) {
+	for (i = 0; i < nr_servers; i++) {
 		tmp = ntohl(uvldb->serverFlags[i]);
 		if (!(tmp & AFS_VLSF_DONTUSE) &&
 		    (tmp & AFS_VLSF_NEWREPSITE))
 			new_only = true;
 	}
 
-	for (i = 0; i < AFS_NMAXNSERVERS; i++) {
+	for (i = 0; i < nr_servers; i++) {
 		struct afs_uuid__xdr *xdr;
 		struct afs_uuid *uuid;
 		int j;
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 79db902..b517a58 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -26,9 +26,8 @@ static struct afs_volume *afs_alloc_volume(struct afs_mount_params *params,
 					   unsigned long type_mask)
 {
 	struct afs_server_list *slist;
-	struct afs_server *server;
 	struct afs_volume *volume;
-	int ret = -ENOMEM, nr_servers = 0, i, j;
+	int ret = -ENOMEM, nr_servers = 0, i;
 
 	for (i = 0; i < vldb->nr_servers; i++)
 		if (vldb->fs_mask[i] & type_mask)
@@ -58,49 +57,8 @@ static struct afs_volume *afs_alloc_volume(struct afs_mount_params *params,
 
 	refcount_set(&slist->usage, 1);
 	volume->servers = slist;
-
-	/* Make sure a records exists for each server this volume occupies. */
-	for (i = 0; i < nr_servers; i++) {
-		if (!(vldb->fs_mask[i] & type_mask))
-			continue;
-
-		server = afs_lookup_server(params->cell, params->key,
-					   &vldb->fs_server[i]);
-		if (IS_ERR(server)) {
-			ret = PTR_ERR(server);
-			if (ret == -ENOENT)
-				continue;
-			goto error_2;
-		}
-
-		/* Insertion-sort by server pointer */
-		for (j = 0; j < slist->nr_servers; j++)
-			if (slist->servers[j].server >= server)
-				break;
-		if (j < slist->nr_servers) {
-			if (slist->servers[j].server == server) {
-				afs_put_server(params->net, server);
-				continue;
-			}
-
-			memmove(slist->servers + j + 1,
-				slist->servers + j,
-				(slist->nr_servers - j) * sizeof(struct afs_server_entry));
-		}
-
-		slist->servers[j].server = server;
-		slist->nr_servers++;
-	}
-
-	if (slist->nr_servers == 0) {
-		ret = -EDESTADDRREQ;
-		goto error_2;
-	}
-
 	return volume;
 
-error_2:
-	afs_put_serverlist(params->net, slist);
 error_1:
 	afs_put_cell(params->net, volume->cell);
 	kfree(volume);
@@ -328,7 +286,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key)
 
 	/* See if the volume's server list got updated. */
 	new = afs_alloc_server_list(volume->cell, key,
-				      vldb, (1 << volume->type));
+				    vldb, (1 << volume->type));
 	if (IS_ERR(new)) {
 		ret = PTR_ERR(new);
 		goto error_vldb;