diff options
Diffstat (limited to 'fs/ocfs2/dlm/dlmdomain.c')
| -rw-r--r-- | fs/ocfs2/dlm/dlmdomain.c | 173 |
1 files changed, 131 insertions, 42 deletions
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c index 638d2ebb892b..63f8125824e8 100644 --- a/fs/ocfs2/dlm/dlmdomain.c +++ b/fs/ocfs2/dlm/dlmdomain.c @@ -33,6 +33,7 @@ #include <linux/spinlock.h> #include <linux/delay.h> #include <linux/err.h> +#include <linux/debugfs.h> #include "cluster/heartbeat.h" #include "cluster/nodemanager.h" @@ -40,8 +41,8 @@ #include "dlmapi.h" #include "dlmcommon.h" - #include "dlmdomain.h" +#include "dlmdebug.h" #include "dlmver.h" @@ -298,6 +299,8 @@ static int dlm_wait_on_domain_helper(const char *domain) static void dlm_free_ctxt_mem(struct dlm_ctxt *dlm) { + dlm_destroy_debugfs_subroot(dlm); + if (dlm->lockres_hash) dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES); @@ -395,6 +398,7 @@ static void dlm_destroy_dlm_worker(struct dlm_ctxt *dlm) static void dlm_complete_dlm_shutdown(struct dlm_ctxt *dlm) { dlm_unregister_domain_handlers(dlm); + dlm_debug_shutdown(dlm); dlm_complete_thread(dlm); dlm_complete_recovery_thread(dlm); dlm_destroy_dlm_worker(dlm); @@ -644,6 +648,7 @@ int dlm_shutting_down(struct dlm_ctxt *dlm) void dlm_unregister_domain(struct dlm_ctxt *dlm) { int leave = 0; + struct dlm_lock_resource *res; spin_lock(&dlm_domain_lock); BUG_ON(dlm->dlm_state != DLM_CTXT_JOINED); @@ -673,6 +678,15 @@ void dlm_unregister_domain(struct dlm_ctxt *dlm) msleep(500); mlog(0, "%s: more migration to do\n", dlm->name); } + + /* This list should be empty. If not, print remaining lockres */ + if (!list_empty(&dlm->tracking_list)) { + mlog(ML_ERROR, "Following lockres' are still on the " + "tracking list:\n"); + list_for_each_entry(res, &dlm->tracking_list, tracking) + dlm_print_one_lock_resource(res); + } + dlm_mark_domain_leaving(dlm); dlm_leave_domain(dlm); dlm_complete_dlm_shutdown(dlm); @@ -713,14 +727,46 @@ static int dlm_query_join_proto_check(char *proto_type, int node, return rc; } +/* + * struct dlm_query_join_packet is made up of four one-byte fields. They + * are effectively in big-endian order already. However, little-endian + * machines swap them before putting the packet on the wire (because + * query_join's response is a status, and that status is treated as a u32 + * on the wire). Thus, a big-endian and little-endian machines will treat + * this structure differently. + * + * The solution is to have little-endian machines swap the structure when + * converting from the structure to the u32 representation. This will + * result in the structure having the correct format on the wire no matter + * the host endian format. + */ +static void dlm_query_join_packet_to_wire(struct dlm_query_join_packet *packet, + u32 *wire) +{ + union dlm_query_join_response response; + + response.packet = *packet; + *wire = cpu_to_be32(response.intval); +} + +static void dlm_query_join_wire_to_packet(u32 wire, + struct dlm_query_join_packet *packet) +{ + union dlm_query_join_response response; + + response.intval = cpu_to_be32(wire); + *packet = response.packet; +} + static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, void **ret_data) { struct dlm_query_join_request *query; - union dlm_query_join_response response = { - .packet.code = JOIN_DISALLOW, + struct dlm_query_join_packet packet = { + .code = JOIN_DISALLOW, }; struct dlm_ctxt *dlm = NULL; + u32 response; u8 nodenum; query = (struct dlm_query_join_request *) msg->buf; @@ -737,11 +783,11 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, mlog(0, "node %u is not in our live map yet\n", query->node_idx); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; goto respond; } - response.packet.code = JOIN_OK_NO_MAP; + packet.code = JOIN_OK_NO_MAP; spin_lock(&dlm_domain_lock); dlm = __dlm_lookup_domain_full(query->domain, query->name_len); @@ -760,7 +806,7 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, mlog(0, "disallow join as node %u does not " "have node %u in its nodemap\n", query->node_idx, nodenum); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; goto unlock_respond; } } @@ -780,23 +826,23 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, /*If this is a brand new context and we * haven't started our join process yet, then * the other node won the race. */ - response.packet.code = JOIN_OK_NO_MAP; + packet.code = JOIN_OK_NO_MAP; } else if (dlm->joining_node != DLM_LOCK_RES_OWNER_UNKNOWN) { /* Disallow parallel joins. */ - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; } else if (dlm->reco.state & DLM_RECO_STATE_ACTIVE) { mlog(0, "node %u trying to join, but recovery " "is ongoing.\n", bit); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; } else if (test_bit(bit, dlm->recovery_map)) { mlog(0, "node %u trying to join, but it " "still needs recovery.\n", bit); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; } else if (test_bit(bit, dlm->domain_map)) { mlog(0, "node %u trying to join, but it " "is still in the domain! needs recovery?\n", bit); - response.packet.code = JOIN_DISALLOW; + packet.code = JOIN_DISALLOW; } else { /* Alright we're fully a part of this domain * so we keep some state as to who's joining @@ -807,19 +853,15 @@ static int dlm_query_join_handler(struct o2net_msg *msg, u32 len, void *data, if (dlm_query_join_proto_check("DLM", bit, &dlm->dlm_locking_proto, &query->dlm_proto)) { - response.packet.code = - JOIN_PROTOCOL_MISMATCH; + packet.code = JOIN_PROTOCOL_MISMATCH; } else if (dlm_query_join_proto_check("fs", bit, &dlm->fs_locking_proto, &query->fs_proto)) { - response.packet.code = - JOIN_PROTOCOL_MISMATCH; + packet.code = JOIN_PROTOCOL_MISMATCH; } else { - response.packet.dlm_minor = - query->dlm_proto.pv_minor; - response.packet.fs_minor = - query->fs_proto.pv_minor; - response.packet.code = JOIN_OK; + packet.dlm_minor = query->dlm_proto.pv_minor; + packet.fs_minor = query->fs_proto.pv_minor; + packet.code = JOIN_OK; __dlm_set_joining_node(dlm, query->node_idx); } } @@ -830,9 +872,10 @@ unlock_respond: spin_unlock(&dlm_domain_lock); respond: - mlog(0, "We respond with %u\n", response.packet.code); + mlog(0, "We respond with %u\n", packet.code); - return response.intval; + dlm_query_join_packet_to_wire(&packet, &response); + return response; } static int dlm_assert_joined_handler(struct o2net_msg *msg, u32 len, void *data, @@ -937,7 +980,7 @@ static int dlm_send_join_cancels(struct dlm_ctxt *dlm, sizeof(unsigned long))) { mlog(ML_ERROR, "map_size %u != BITS_TO_LONGS(O2NM_MAX_NODES) %u\n", - map_size, BITS_TO_LONGS(O2NM_MAX_NODES)); + map_size, (unsigned)BITS_TO_LONGS(O2NM_MAX_NODES)); return -EINVAL; } @@ -968,7 +1011,8 @@ static int dlm_request_join(struct dlm_ctxt *dlm, { int status; struct dlm_query_join_request join_msg; - union dlm_query_join_response join_resp; + struct dlm_query_join_packet packet; + u32 join_resp; mlog(0, "querying node %d\n", node); @@ -984,11 +1028,12 @@ static int dlm_request_join(struct dlm_ctxt *dlm, status = o2net_send_message(DLM_QUERY_JOIN_MSG, DLM_MOD_KEY, &join_msg, sizeof(join_msg), node, - &join_resp.intval); + &join_resp); if (status < 0 && status != -ENOPROTOOPT) { mlog_errno(status); goto bail; } + dlm_query_join_wire_to_packet(join_resp, &packet); /* -ENOPROTOOPT from the net code means the other side isn't listening for our message type -- that's fine, it means @@ -997,10 +1042,10 @@ static int dlm_request_join(struct dlm_ctxt *dlm, if (status == -ENOPROTOOPT) { status = 0; *response = JOIN_OK_NO_MAP; - } else if (join_resp.packet.code == JOIN_DISALLOW || - join_resp.packet.code == JOIN_OK_NO_MAP) { - *response = join_resp.packet.code; - } else if (join_resp.packet.code == JOIN_PROTOCOL_MISMATCH) { + } else if (packet.code == JOIN_DISALLOW || + packet.code == JOIN_OK_NO_MAP) { + *response = packet.code; + } else if (packet.code == JOIN_PROTOCOL_MISMATCH) { mlog(ML_NOTICE, "This node requested DLM locking protocol %u.%u and " "filesystem locking protocol %u.%u. At least one of " @@ -1012,14 +1057,12 @@ static int dlm_request_join(struct dlm_ctxt *dlm, dlm->fs_locking_proto.pv_minor, node); status = -EPROTO; - *response = join_resp.packet.code; - } else if (join_resp.packet.code == JOIN_OK) { - *response = join_resp.packet.code; + *response = packet.code; + } else if (packet.code == JOIN_OK) { + *response = packet.code; /* Use the same locking protocol as the remote node */ - dlm->dlm_locking_proto.pv_minor = - join_resp.packet.dlm_minor; - dlm->fs_locking_proto.pv_minor = - join_resp.packet.fs_minor; + dlm->dlm_locking_proto.pv_minor = packet.dlm_minor; + dlm->fs_locking_proto.pv_minor = packet.fs_minor; mlog(0, "Node %d responds JOIN_OK with DLM locking protocol " "%u.%u and fs locking protocol %u.%u\n", @@ -1031,11 +1074,11 @@ static int dlm_request_join(struct dlm_ctxt *dlm, } else { status = -EINVAL; mlog(ML_ERROR, "invalid response %d from node %u\n", - join_resp.packet.code, node); + packet.code, node); } mlog(0, "status %d, node %d response is %d\n", status, node, - *response); + *response); bail: return status; @@ -1376,6 +1419,12 @@ static int dlm_join_domain(struct dlm_ctxt *dlm) goto bail; } + status = dlm_debug_init(dlm); + if (status < 0) { + mlog_errno(status); + goto bail; + } + status = dlm_launch_thread(dlm); if (status < 0) { mlog_errno(status); @@ -1443,6 +1492,7 @@ bail: if (status) { dlm_unregister_domain_handlers(dlm); + dlm_debug_shutdown(dlm); dlm_complete_thread(dlm); dlm_complete_recovery_thread(dlm); dlm_destroy_dlm_worker(dlm); @@ -1455,6 +1505,7 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, u32 key) { int i; + int ret; struct dlm_ctxt *dlm = NULL; dlm = kzalloc(sizeof(*dlm), GFP_KERNEL); @@ -1487,6 +1538,15 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, dlm->key = key; dlm->node_num = o2nm_this_node(); + ret = dlm_create_debugfs_subroot(dlm); + if (ret < 0) { + dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES); + kfree(dlm->name); + kfree(dlm); + dlm = NULL; + goto leave; + } + spin_lock_init(&dlm->spinlock); spin_lock_init(&dlm->master_lock); spin_lock_init(&dlm->ast_lock); @@ -1497,6 +1557,7 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain, INIT_LIST_HEAD(&dlm->reco.node_data); INIT_LIST_HEAD(&dlm->purge_list); INIT_LIST_HEAD(&dlm->dlm_domain_handlers); + INIT_LIST_HEAD(&dlm->tracking_list); dlm->reco.state = 0; INIT_LIST_HEAD(&dlm->pending_asts); @@ -1787,21 +1848,49 @@ static int __init dlm_init(void) dlm_print_version(); status = dlm_init_mle_cache(); - if (status) - return -1; + if (status) { + mlog(ML_ERROR, "Could not create o2dlm_mle slabcache\n"); + goto error; + } + + status = dlm_init_master_caches(); + if (status) { + mlog(ML_ERROR, "Could not create o2dlm_lockres and " + "o2dlm_lockname slabcaches\n"); + goto error; + } + + status = dlm_init_lock_cache(); + if (status) { + mlog(ML_ERROR, "Count not create o2dlm_lock slabcache\n"); + goto error; + } status = dlm_register_net_handlers(); if (status) { - dlm_destroy_mle_cache(); - return -1; + mlog(ML_ERROR, "Unable to register network handlers\n"); + goto error; } + status = dlm_create_debugfs_root(); + if (status) + goto error; + return 0; +error: + dlm_unregister_net_handlers(); + dlm_destroy_lock_cache(); + dlm_destroy_master_caches(); + dlm_destroy_mle_cache(); + return -1; } static void __exit dlm_exit (void) { + dlm_destroy_debugfs_root(); dlm_unregister_net_handlers(); + dlm_destroy_lock_cache(); + dlm_destroy_master_caches(); dlm_destroy_mle_cache(); } |