linux_dsm_epyc7002/fs/dlm/ast.c

317 lines
8.0 KiB
C
Raw Normal View History

/******************************************************************************
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
** Copyright (C) 2004-2010 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
** of the GNU General Public License v.2.
**
*******************************************************************************
******************************************************************************/
#include "dlm_internal.h"
#include "lock.h"
#include "user.h"
static uint64_t dlm_cb_seq;
static DEFINE_SPINLOCK(dlm_cb_seq_spin);
static void dlm_dump_lkb_callbacks(struct dlm_lkb *lkb)
{
int i;
log_print("last_bast %x %llu flags %x mode %d sb %d %x",
lkb->lkb_id,
(unsigned long long)lkb->lkb_last_bast.seq,
lkb->lkb_last_bast.flags,
lkb->lkb_last_bast.mode,
lkb->lkb_last_bast.sb_status,
lkb->lkb_last_bast.sb_flags);
log_print("last_cast %x %llu flags %x mode %d sb %d %x",
lkb->lkb_id,
(unsigned long long)lkb->lkb_last_cast.seq,
lkb->lkb_last_cast.flags,
lkb->lkb_last_cast.mode,
lkb->lkb_last_cast.sb_status,
lkb->lkb_last_cast.sb_flags);
for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
log_print("cb %x %llu flags %x mode %d sb %d %x",
lkb->lkb_id,
(unsigned long long)lkb->lkb_callbacks[i].seq,
lkb->lkb_callbacks[i].flags,
lkb->lkb_callbacks[i].mode,
lkb->lkb_callbacks[i].sb_status,
lkb->lkb_callbacks[i].sb_flags);
}
}
int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
int status, uint32_t sbflags, uint64_t seq)
{
struct dlm_ls *ls = lkb->lkb_resource->res_ls;
uint64_t prev_seq;
int prev_mode;
int i, rv;
for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
if (lkb->lkb_callbacks[i].seq)
continue;
/*
* Suppress some redundant basts here, do more on removal.
* Don't even add a bast if the callback just before it
* is a bast for the same mode or a more restrictive mode.
* (the addional > PR check is needed for PR/CW inversion)
*/
if ((i > 0) && (flags & DLM_CB_BAST) &&
(lkb->lkb_callbacks[i-1].flags & DLM_CB_BAST)) {
prev_seq = lkb->lkb_callbacks[i-1].seq;
prev_mode = lkb->lkb_callbacks[i-1].mode;
if ((prev_mode == mode) ||
(prev_mode > mode && prev_mode > DLM_LOCK_PR)) {
log_debug(ls, "skip %x add bast %llu mode %d "
"for bast %llu mode %d",
lkb->lkb_id,
(unsigned long long)seq,
mode,
(unsigned long long)prev_seq,
prev_mode);
rv = 0;
goto out;
}
}
lkb->lkb_callbacks[i].seq = seq;
lkb->lkb_callbacks[i].flags = flags;
lkb->lkb_callbacks[i].mode = mode;
lkb->lkb_callbacks[i].sb_status = status;
lkb->lkb_callbacks[i].sb_flags = (sbflags & 0x000000FF);
rv = 0;
break;
}
if (i == DLM_CALLBACKS_SIZE) {
log_error(ls, "no callbacks %x %llu flags %x mode %d sb %d %x",
lkb->lkb_id, (unsigned long long)seq,
flags, mode, status, sbflags);
dlm_dump_lkb_callbacks(lkb);
rv = -1;
goto out;
}
out:
return rv;
}
int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,
struct dlm_callback *cb, int *resid)
{
int i, rv;
*resid = 0;
if (!lkb->lkb_callbacks[0].seq) {
rv = -ENOENT;
goto out;
}
/* oldest undelivered cb is callbacks[0] */
memcpy(cb, &lkb->lkb_callbacks[0], sizeof(struct dlm_callback));
memset(&lkb->lkb_callbacks[0], 0, sizeof(struct dlm_callback));
/* shift others down */
for (i = 1; i < DLM_CALLBACKS_SIZE; i++) {
if (!lkb->lkb_callbacks[i].seq)
break;
memcpy(&lkb->lkb_callbacks[i-1], &lkb->lkb_callbacks[i],
sizeof(struct dlm_callback));
memset(&lkb->lkb_callbacks[i], 0, sizeof(struct dlm_callback));
(*resid)++;
}
/* if cb is a bast, it should be skipped if the blocking mode is
compatible with the last granted mode */
if ((cb->flags & DLM_CB_BAST) && lkb->lkb_last_cast.seq) {
if (dlm_modes_compat(cb->mode, lkb->lkb_last_cast.mode)) {
cb->flags |= DLM_CB_SKIP;
log_debug(ls, "skip %x bast %llu mode %d "
"for cast %llu mode %d",
lkb->lkb_id,
(unsigned long long)cb->seq,
cb->mode,
(unsigned long long)lkb->lkb_last_cast.seq,
lkb->lkb_last_cast.mode);
rv = 0;
goto out;
}
}
if (cb->flags & DLM_CB_CAST) {
memcpy(&lkb->lkb_last_cast, cb, sizeof(struct dlm_callback));
lkb->lkb_last_cast_time = ktime_get();
}
if (cb->flags & DLM_CB_BAST) {
memcpy(&lkb->lkb_last_bast, cb, sizeof(struct dlm_callback));
lkb->lkb_last_bast_time = ktime_get();
}
rv = 0;
out:
return rv;
}
void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
uint32_t sbflags)
{
struct dlm_ls *ls = lkb->lkb_resource->res_ls;
uint64_t new_seq, prev_seq;
int rv;
spin_lock(&dlm_cb_seq_spin);
new_seq = ++dlm_cb_seq;
spin_unlock(&dlm_cb_seq_spin);
if (lkb->lkb_flags & DLM_IFL_USER) {
dlm_user_add_ast(lkb, flags, mode, status, sbflags, new_seq);
return;
}
mutex_lock(&lkb->lkb_cb_mutex);
prev_seq = lkb->lkb_callbacks[0].seq;
rv = dlm_add_lkb_callback(lkb, flags, mode, status, sbflags, new_seq);
if (rv < 0)
goto out;
if (!prev_seq) {
kref_get(&lkb->lkb_ref);
if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) {
mutex_lock(&ls->ls_cb_mutex);
list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay);
mutex_unlock(&ls->ls_cb_mutex);
} else {
queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
}
}
out:
mutex_unlock(&lkb->lkb_cb_mutex);
}
void dlm_callback_work(struct work_struct *work)
{
struct dlm_lkb *lkb = container_of(work, struct dlm_lkb, lkb_cb_work);
struct dlm_ls *ls = lkb->lkb_resource->res_ls;
void (*castfn) (void *astparam);
void (*bastfn) (void *astparam, int mode);
struct dlm_callback callbacks[DLM_CALLBACKS_SIZE];
int i, rv, resid;
memset(&callbacks, 0, sizeof(callbacks));
mutex_lock(&lkb->lkb_cb_mutex);
if (!lkb->lkb_callbacks[0].seq) {
/* no callback work exists, shouldn't happen */
log_error(ls, "dlm_callback_work %x no work", lkb->lkb_id);
dlm_print_lkb(lkb);
dlm_dump_lkb_callbacks(lkb);
}
for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
rv = dlm_rem_lkb_callback(ls, lkb, &callbacks[i], &resid);
if (rv < 0)
break;
}
if (resid) {
/* cbs remain, loop should have removed all, shouldn't happen */
log_error(ls, "dlm_callback_work %x resid %d", lkb->lkb_id,
resid);
dlm_print_lkb(lkb);
dlm_dump_lkb_callbacks(lkb);
}
mutex_unlock(&lkb->lkb_cb_mutex);
castfn = lkb->lkb_astfn;
bastfn = lkb->lkb_bastfn;
for (i = 0; i < DLM_CALLBACKS_SIZE; i++) {
if (!callbacks[i].seq)
break;
if (callbacks[i].flags & DLM_CB_SKIP) {
continue;
} else if (callbacks[i].flags & DLM_CB_BAST) {
bastfn(lkb->lkb_astparam, callbacks[i].mode);
} else if (callbacks[i].flags & DLM_CB_CAST) {
lkb->lkb_lksb->sb_status = callbacks[i].sb_status;
lkb->lkb_lksb->sb_flags = callbacks[i].sb_flags;
castfn(lkb->lkb_astparam);
}
}
/* undo kref_get from dlm_add_callback, may cause lkb to be freed */
dlm_put_lkb(lkb);
}
int dlm_callback_start(struct dlm_ls *ls)
{
ls->ls_callback_wq = alloc_workqueue("dlm_callback",
WQ_UNBOUND |
WQ_MEM_RECLAIM |
WQ_NON_REENTRANT,
0);
if (!ls->ls_callback_wq) {
log_print("can't start dlm_callback workqueue");
return -ENOMEM;
}
return 0;
}
void dlm_callback_stop(struct dlm_ls *ls)
{
if (ls->ls_callback_wq)
destroy_workqueue(ls->ls_callback_wq);
}
void dlm_callback_suspend(struct dlm_ls *ls)
{
set_bit(LSFL_CB_DELAY, &ls->ls_flags);
if (ls->ls_callback_wq)
flush_workqueue(ls->ls_callback_wq);
}
void dlm_callback_resume(struct dlm_ls *ls)
{
struct dlm_lkb *lkb, *safe;
int count = 0;
clear_bit(LSFL_CB_DELAY, &ls->ls_flags);
if (!ls->ls_callback_wq)
return;
mutex_lock(&ls->ls_cb_mutex);
list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) {
list_del_init(&lkb->lkb_cb_list);
queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
count++;
}
mutex_unlock(&ls->ls_cb_mutex);
dlm: fixes for nodir mode The "nodir" mode (statically assign master nodes instead of using the resource directory) has always been highly experimental, and never seriously used. This commit fixes a number of problems, making nodir much more usable. - Major change to recovery: recover all locks and restart all in-progress operations after recovery. In some cases it's not possible to know which in-progess locks to recover, so recover all. (Most require recovery in nodir mode anyway since rehashing changes most master nodes.) - Change the way nodir mode is enabled, from a command line mount arg passed through gfs2, into a sysfs file managed by dlm_controld, consistent with the other config settings. - Allow recovering MSTCPY locks on an rsb that has not yet been turned into a master copy. - Ignore RCOM_LOCK and RCOM_LOCK_REPLY recovery messages from a previous, aborted recovery cycle. Base this on the local recovery status not being in the state where any nodes should be sending LOCK messages for the current recovery cycle. - Hold rsb lock around dlm_purge_mstcpy_locks() because it may run concurrently with dlm_recover_master_copy(). - Maintain highbast on process-copy lkb's (in addition to the master as is usual), because the lkb can switch back and forth between being a master and being a process copy as the master node changes in recovery. - When recovering MSTCPY locks, flag rsb's that have non-empty convert or waiting queues for granting at the end of recovery. (Rename flag from LOCKS_PURGED to RECOVER_GRANT and similar for the recovery function, because it's not only resources with purged locks that need grant a grant attempt.) - Replace a couple of unnecessary assertion panics with error messages. Signed-off-by: David Teigland <teigland@redhat.com>
2012-04-27 03:54:29 +07:00
if (count)
log_debug(ls, "dlm_callback_resume %d", count);
}