dlm: fix deadlock between dlm_send and dlm_controld

A deadlock sometimes occurs between dlm_controld closing
a lowcomms connection through configfs and dlm_send looking
up the address for a new connection in configfs.

dlm_controld does a configfs rmdir which calls
dlm_lowcomms_close which waits for dlm_send to
cancel work on the workqueues.

The dlm_send workqueue thread has called
tcp_connect_to_sock which calls dlm_nodeid_to_addr
which does a configfs lookup and blocks on a lock
held by dlm_controld in the rmdir path.

The solution here is to save the node addresses within
the lowcomms code so that the lowcomms workqueue does
not need to step through configfs to get a node address.

dlm_controld:
wait_for_completion+0x1d/0x20
__cancel_work_timer+0x1b3/0x1e0
cancel_work_sync+0x10/0x20
dlm_lowcomms_close+0x4c/0xb0 [dlm]
drop_comm+0x22/0x60 [dlm]
client_drop_item+0x26/0x50 [configfs]
configfs_rmdir+0x180/0x230 [configfs]
vfs_rmdir+0xbd/0xf0
do_rmdir+0x103/0x120
sys_rmdir+0x16/0x20

dlm_send:
mutex_lock+0x2b/0x50
get_comm+0x34/0x140 [dlm]
dlm_nodeid_to_addr+0x18/0xd0 [dlm]
tcp_connect_to_sock+0xf4/0x2d0 [dlm]
process_send_sockets+0x1d2/0x260 [dlm]
worker_thread+0x170/0x2a0

Signed-off-by: David Teigland <teigland@redhat.com>

1 files changed, 15 insertions, 64 deletions

diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 9ccf7346834a..a0387dd8b1f0 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -750,6 +750,7 @@ static ssize_t comm_local_write(struct dlm_comm *cm, const char *buf,
 static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len)
 {
         struct sockaddr_storage *addr;
+        int rv;
 
         if (len != sizeof(struct sockaddr_storage))
                 return -EINVAL;
@@ -762,6 +763,13 @@ static ssize_t comm_addr_write(struct dlm_comm *cm, const char *buf, size_t len)
                 return -ENOMEM;
 
         memcpy(addr, buf, len);
+
+        rv = dlm_lowcomms_addr(cm->nodeid, addr, len);
+        if (rv) {
+                kfree(addr);
+                return rv;
+        }
+
         cm->addr[cm->addr_count++] = addr;
         return len;
 }
@@ -878,34 +886,7 @@ static void put_space(struct dlm_space *sp)
         config_item_put(&sp->group.cg_item);
 }
 
-static int addr_compare(struct sockaddr_storage *x, struct sockaddr_storage *y)
-{
-        switch (x->ss_family) {
-        case AF_INET: {
-                struct sockaddr_in *sinx = (struct sockaddr_in *)x;
-                struct sockaddr_in *siny = (struct sockaddr_in *)y;
-                if (sinx->sin_addr.s_addr != siny->sin_addr.s_addr)
-                        return 0;
-                if (sinx->sin_port != siny->sin_port)
-                        return 0;
-                break;
-        }
-        case AF_INET6: {
-                struct sockaddr_in6 *sinx = (struct sockaddr_in6 *)x;
-                struct sockaddr_in6 *siny = (struct sockaddr_in6 *)y;
-                if (!ipv6_addr_equal(&sinx->sin6_addr, &siny->sin6_addr))
-                        return 0;
-                if (sinx->sin6_port != siny->sin6_port)
-                        return 0;
-                break;
-        }
-        default:
-                return 0;
-        }
-        return 1;
-}
-
-static struct dlm_comm *get_comm(int nodeid, struct sockaddr_storage *addr)
+static struct dlm_comm *get_comm(int nodeid)
 {
         struct config_item *i;
         struct dlm_comm *cm = NULL;
@@ -919,19 +900,11 @@ static struct dlm_comm *get_comm(int nodeid, struct sockaddr_storage *addr)
         list_for_each_entry(i, &comm_list->cg_children, ci_entry) {
                 cm = config_item_to_comm(i);
 
-                if (nodeid) {
-                        if (cm->nodeid != nodeid)
-                                continue;
-                        found = 1;
-                        config_item_get(i);
-                        break;
-                } else {
-                        if (!cm->addr_count || !addr_compare(cm->addr[0], addr))
-                                continue;
-                        found = 1;
-                        config_item_get(i);
-                        break;
-                }
+                if (cm->nodeid != nodeid)
+                        continue;
+                found = 1;
+                config_item_get(i);
+                break;
         }
         mutex_unlock(&clusters_root.subsys.su_mutex);
 
@@ -995,7 +968,7 @@ int dlm_config_nodes(char *lsname, struct dlm_config_node **nodes_out,
 
 int dlm_comm_seq(int nodeid, uint32_t *seq)
 {
-        struct dlm_comm *cm = get_comm(nodeid, NULL);
+        struct dlm_comm *cm = get_comm(nodeid);
         if (!cm)
                 return -EEXIST;
         *seq = cm->seq;
@@ -1003,28 +976,6 @@ int dlm_comm_seq(int nodeid, uint32_t *seq)
         return 0;
 }
 
-int dlm_nodeid_to_addr(int nodeid, struct sockaddr_storage *addr)
-{
-        struct dlm_comm *cm = get_comm(nodeid, NULL);
-        if (!cm)
-                return -EEXIST;
-        if (!cm->addr_count)
-                return -ENOENT;
-        memcpy(addr, cm->addr[0], sizeof(*addr));
-        put_comm(cm);
-        return 0;
-}
-
-int dlm_addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
-{
-        struct dlm_comm *cm = get_comm(0, addr);
-        if (!cm)
-                return -EEXIST;
-        *nodeid = cm->nodeid;
-        put_comm(cm);
-        return 0;
-}
-
 int dlm_our_nodeid(void)
 {
         return local_comm ? local_comm->nodeid : 0;