^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 1) // SPDX-License-Identifier: GPL-2.0-only
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 2) /******************************************************************************
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 3) *******************************************************************************
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 4) **
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 5) ** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 6) **
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 7) **
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 8) *******************************************************************************
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 9) ******************************************************************************/
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 10)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 11) #include "dlm_internal.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 12) #include "member.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 13) #include "lock.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 14) #include "dir.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 15) #include "config.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 16) #include "requestqueue.h"
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 17)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 18) struct rq_entry {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 19) struct list_head list;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 20) uint32_t recover_seq;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 21) int nodeid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 22) struct dlm_message request;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 23) };
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 24)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 25) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 26) * Requests received while the lockspace is in recovery get added to the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 27) * request queue and processed when recovery is complete. This happens when
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 28) * the lockspace is suspended on some nodes before it is on others, or the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 29) * lockspace is enabled on some while still suspended on others.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 30) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 31)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 32) void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 33) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 34) struct rq_entry *e;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 35) int length = ms->m_header.h_length - sizeof(struct dlm_message);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 36)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 37) e = kmalloc(sizeof(struct rq_entry) + length, GFP_NOFS);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 38) if (!e) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 39) log_print("dlm_add_requestqueue: out of memory len %d", length);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 40) return;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 41) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 42)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 43) e->recover_seq = ls->ls_recover_seq & 0xFFFFFFFF;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 44) e->nodeid = nodeid;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 45) memcpy(&e->request, ms, ms->m_header.h_length);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 46)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 47) mutex_lock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 48) list_add_tail(&e->list, &ls->ls_requestqueue);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 49) mutex_unlock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 50) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 51)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 52) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 53) * Called by dlm_recoverd to process normal messages saved while recovery was
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 54) * happening. Normal locking has been enabled before this is called. dlm_recv
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 55) * upon receiving a message, will wait for all saved messages to be drained
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 56) * here before processing the message it got. If a new dlm_ls_stop() arrives
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 57) * while we're processing these saved messages, it may block trying to suspend
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 58) * dlm_recv if dlm_recv is waiting for us in dlm_wait_requestqueue. In that
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 59) * case, we don't abort since locking_stopped is still 0. If dlm_recv is not
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 60) * waiting for us, then this processing may be aborted due to locking_stopped.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 61) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 62)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 63) int dlm_process_requestqueue(struct dlm_ls *ls)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 64) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 65) struct rq_entry *e;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 66) struct dlm_message *ms;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 67) int error = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 68)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 69) mutex_lock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 70)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 71) for (;;) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 72) if (list_empty(&ls->ls_requestqueue)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 73) mutex_unlock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 74) error = 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 75) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 76) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 77) e = list_entry(ls->ls_requestqueue.next, struct rq_entry, list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 78) mutex_unlock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 79)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 80) ms = &e->request;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 81)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 82) log_limit(ls, "dlm_process_requestqueue msg %d from %d "
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 83) "lkid %x remid %x result %d seq %u",
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 84) ms->m_type, ms->m_header.h_nodeid,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 85) ms->m_lkid, ms->m_remid, ms->m_result,
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 86) e->recover_seq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 87)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 88) dlm_receive_message_saved(ls, &e->request, e->recover_seq);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 89)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 90) mutex_lock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 91) list_del(&e->list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 92) kfree(e);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 93)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 94) if (dlm_locking_stopped(ls)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 95) log_debug(ls, "process_requestqueue abort running");
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 96) mutex_unlock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 97) error = -EINTR;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 98) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 99) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 100) schedule();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 101) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 102)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 103) return error;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 104) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 105)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 106) /*
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 107) * After recovery is done, locking is resumed and dlm_recoverd takes all the
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 108) * saved requests and processes them as they would have been by dlm_recv. At
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 109) * the same time, dlm_recv will start receiving new requests from remote nodes.
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 110) * We want to delay dlm_recv processing new requests until dlm_recoverd has
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 111) * finished processing the old saved requests. We don't check for locking
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 112) * stopped here because dlm_ls_stop won't stop locking until it's suspended us
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 113) * (dlm_recv).
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 114) */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 115)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 116) void dlm_wait_requestqueue(struct dlm_ls *ls)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 117) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 118) for (;;) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 119) mutex_lock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 120) if (list_empty(&ls->ls_requestqueue))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 121) break;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 122) mutex_unlock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 123) schedule();
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 124) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 125) mutex_unlock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 126) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 127)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 128) static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 129) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 130) uint32_t type = ms->m_type;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 131)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 132) /* the ls is being cleaned up and freed by release_lockspace */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 133) if (!ls->ls_count)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 134) return 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 135)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 136) if (dlm_is_removed(ls, nodeid))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 137) return 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 138)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 139) /* directory operations are always purged because the directory is
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 140) always rebuilt during recovery and the lookups resent */
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 141)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 142) if (type == DLM_MSG_REMOVE ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 143) type == DLM_MSG_LOOKUP ||
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 144) type == DLM_MSG_LOOKUP_REPLY)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 145) return 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 146)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 147) if (!dlm_no_directory(ls))
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 148) return 0;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 149)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 150) return 1;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 151) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 152)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 153) void dlm_purge_requestqueue(struct dlm_ls *ls)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 154) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 155) struct dlm_message *ms;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 156) struct rq_entry *e, *safe;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 157)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 158) mutex_lock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 159) list_for_each_entry_safe(e, safe, &ls->ls_requestqueue, list) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 160) ms = &e->request;
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 161)
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 162) if (purge_request(ls, ms, e->nodeid)) {
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 163) list_del(&e->list);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 164) kfree(e);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 165) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 166) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 167) mutex_unlock(&ls->ls_requestqueue_mutex);
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 168) }
^8f3ce5b39 (kx 2023-10-28 12:00:06 +0300 169)