* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/teigland/dlm: (21 commits)
dlm: static initialization improvements
dlm: clean ups
dlm: Sanity check namelen before copying it
dlm: keep cached master rsbs during recovery
dlm: change error message to debug
dlm: fix possible use-after-free
dlm: limit dir lookup loop
dlm: reject normal unlock when lock is waiting for lookup
dlm: validate messages before processing
dlm: reject messages from non-members
dlm: another call to confirm_master in receive_request_reply
dlm: recover locks waiting for overlap replies
dlm: clear ast_type when removing from astqueue
dlm: use fixed errno values in messages
dlm: swap bytes for rcom lock reply
dlm: align midcomms message buffer
dlm: close othercons
dlm: use dlm prefix on alloc and free functions
dlm: don't print common non-errors
dlm: proper prototypes
...
spin_unlock(&ls->ls_recover_list_lock);
if (!found)
- de = allocate_direntry(ls, len);
+ de = kzalloc(sizeof(struct dlm_direntry) + len, GFP_KERNEL);
return de;
}
de = list_entry(ls->ls_recover_list.next, struct dlm_direntry,
list);
list_del(&de->list);
- free_direntry(de);
+ kfree(de);
}
spin_unlock(&ls->ls_recover_list_lock);
}
}
list_del(&de->list);
- free_direntry(de);
+ kfree(de);
out:
write_unlock(&ls->ls_dirtbl[bucket].lock);
}
write_unlock(&ls->ls_dirtbl[bucket].lock);
- de = allocate_direntry(ls, namelen);
+ de = kzalloc(sizeof(struct dlm_direntry) + namelen, GFP_KERNEL);
if (!de)
return -ENOMEM;
write_lock(&ls->ls_dirtbl[bucket].lock);
tmp = search_bucket(ls, name, namelen, bucket);
if (tmp) {
- free_direntry(de);
+ kfree(de);
de = tmp;
} else {
list_add_tail(&de->list, &ls->ls_dirtbl[bucket].list);
return get_entry(ls, nodeid, name, namelen, r_nodeid);
}
-/* Copy the names of master rsb's into the buffer provided.
- Only select names whose dir node is the given nodeid. */
+static struct dlm_rsb *find_rsb_root(struct dlm_ls *ls, char *name, int len)
+{
+ struct dlm_rsb *r;
+
+ down_read(&ls->ls_root_sem);
+ list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+ if (len == r->res_length && !memcmp(name, r->res_name, len)) {
+ up_read(&ls->ls_root_sem);
+ return r;
+ }
+ }
+ up_read(&ls->ls_root_sem);
+ return NULL;
+}
+
+/* Find the rsb where we left off (or start again), then send rsb names
+ for rsb's we're master of and whose directory node matches the requesting
+ node. inbuf is the rsb name last sent, inlen is the name's length */
void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen,
char *outbuf, int outlen, int nodeid)
{
struct list_head *list;
- struct dlm_rsb *start_r = NULL, *r = NULL;
- int offset = 0, start_namelen, error, dir_nodeid;
- char *start_name;
+ struct dlm_rsb *r;
+ int offset = 0, dir_nodeid;
uint16_t be_namelen;
- /*
- * Find the rsb where we left off (or start again)
- */
-
- start_namelen = inlen;
- start_name = inbuf;
-
- if (start_namelen > 1) {
- /*
- * We could also use a find_rsb_root() function here that
- * searched the ls_root_list.
- */
- error = dlm_find_rsb(ls, start_name, start_namelen, R_MASTER,
- &start_r);
- DLM_ASSERT(!error && start_r,
- printk("error %d\n", error););
- DLM_ASSERT(!list_empty(&start_r->res_root_list),
- dlm_print_rsb(start_r););
- dlm_put_rsb(start_r);
- }
-
- /*
- * Send rsb names for rsb's we're master of and whose directory node
- * matches the requesting node.
- */
-
down_read(&ls->ls_root_sem);
- if (start_r)
- list = start_r->res_root_list.next;
- else
+
+ if (inlen > 1) {
+ r = find_rsb_root(ls, inbuf, inlen);
+ if (!r) {
+ inbuf[inlen - 1] = '\0';
+ log_error(ls, "copy_master_names from %d start %d %s",
+ nodeid, inlen, inbuf);
+ goto out;
+ }
+ list = r->res_root_list.next;
+ } else {
list = ls->ls_root_list.next;
+ }
for (offset = 0; list != &ls->ls_root_list; list = list->next) {
r = list_entry(list, struct dlm_rsb, res_root_list);
return (ls->ls_exflags & DLM_LSFL_NODIR) ? 1 : 0;
}
+int dlm_netlink_init(void);
+void dlm_netlink_exit(void);
+void dlm_timeout_warn(struct dlm_lkb *lkb);
+
+#ifdef CONFIG_DLM_DEBUG
+int dlm_register_debugfs(void);
+void dlm_unregister_debugfs(void);
+int dlm_create_debug_file(struct dlm_ls *ls);
+void dlm_delete_debug_file(struct dlm_ls *ls);
+#else
+static inline int dlm_register_debugfs(void) { return 0; }
+static inline void dlm_unregister_debugfs(void) { }
+static inline int dlm_create_debug_file(struct dlm_ls *ls) { return 0; }
+static inline void dlm_delete_debug_file(struct dlm_ls *ls) { }
+#endif
+
#endif /* __DLM_INTERNAL_DOT_H__ */
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 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
static int receive_extralen(struct dlm_message *ms);
static void do_purge(struct dlm_ls *ls, int nodeid, int pid);
static void del_timeout(struct dlm_lkb *lkb);
-void dlm_timeout_warn(struct dlm_lkb *lkb);
/*
* Lock compatibilty matrix - thanks Steve
{
struct dlm_rsb *r;
- r = allocate_rsb(ls, len);
+ r = dlm_allocate_rsb(ls, len);
if (!r)
return NULL;
error = _search_rsb(ls, name, namelen, bucket, 0, &tmp);
if (!error) {
write_unlock(&ls->ls_rsbtbl[bucket].lock);
- free_rsb(r);
+ dlm_free_rsb(r);
r = tmp;
goto out;
}
return error;
}
-int dlm_find_rsb(struct dlm_ls *ls, char *name, int namelen,
- unsigned int flags, struct dlm_rsb **r_ret)
-{
- return find_rsb(ls, name, namelen, flags, r_ret);
-}
-
/* This is only called to add a reference when the code already holds
a valid reference to the rsb, so there's no need for locking. */
list_move(&r->res_hashchain, &ls->ls_rsbtbl[r->res_bucket].toss);
r->res_toss_time = jiffies;
if (r->res_lvbptr) {
- free_lvb(r->res_lvbptr);
+ dlm_free_lvb(r->res_lvbptr);
r->res_lvbptr = NULL;
}
}
uint32_t lkid = 0;
uint16_t bucket;
- lkb = allocate_lkb(ls);
+ lkb = dlm_allocate_lkb(ls);
if (!lkb)
return -ENOMEM;
/* for local/process lkbs, lvbptr points to caller's lksb */
if (lkb->lkb_lvbptr && is_master_copy(lkb))
- free_lvb(lkb->lkb_lvbptr);
- free_lkb(lkb);
+ dlm_free_lvb(lkb->lkb_lvbptr);
+ dlm_free_lkb(lkb);
return 1;
} else {
write_unlock(&ls->ls_lkbtbl[bucket].lock);
if (is_master(r))
dir_remove(r);
- free_rsb(r);
+ dlm_free_rsb(r);
count++;
} else {
write_unlock(&ls->ls_rsbtbl[b].lock);
return;
if (!r->res_lvbptr)
- r->res_lvbptr = allocate_lvb(r->res_ls);
+ r->res_lvbptr = dlm_allocate_lvb(r->res_ls);
if (!r->res_lvbptr)
return;
return;
if (!r->res_lvbptr)
- r->res_lvbptr = allocate_lvb(r->res_ls);
+ r->res_lvbptr = dlm_allocate_lvb(r->res_ls);
if (!r->res_lvbptr)
return;
static int set_master(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
struct dlm_ls *ls = r->res_ls;
- int error, dir_nodeid, ret_nodeid, our_nodeid = dlm_our_nodeid();
+ int i, error, dir_nodeid, ret_nodeid, our_nodeid = dlm_our_nodeid();
if (rsb_flag(r, RSB_MASTER_UNCERTAIN)) {
rsb_clear_flag(r, RSB_MASTER_UNCERTAIN);
return 1;
}
- for (;;) {
+ for (i = 0; i < 2; i++) {
/* It's possible for dlm_scand to remove an old rsb for
this same resource from the toss list, us to create
a new one, look up the master locally, and find it
log_debug(ls, "dir_lookup error %d %s", error, r->res_name);
schedule();
}
+ if (error && error != -EEXIST)
+ return error;
if (ret_nodeid == our_nodeid) {
r->res_first_lkid = 0;
break;
case -EAGAIN:
- /* the remote master didn't queue our NOQUEUE request;
- make a waiting lkb the first_lkid */
+ case -EBADR:
+ case -ENOTBLK:
+ /* the remote request failed and won't be retried (it was
+ a NOQUEUE, or has been canceled/unlocked); make a waiting
+ lkb the first_lkid */
r->res_first_lkid = 0;
/* an lkb may be waiting for an rsb lookup to complete where the
lookup was initiated by another lock */
- if (args->flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)) {
- if (!list_empty(&lkb->lkb_rsb_lookup)) {
+ if (!list_empty(&lkb->lkb_rsb_lookup)) {
+ if (args->flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)) {
log_debug(ls, "unlock on rsb_lookup %x", lkb->lkb_id);
list_del_init(&lkb->lkb_rsb_lookup);
queue_cast(lkb->lkb_resource, lkb,
args->flags & DLM_LKF_CANCEL ?
-DLM_ECANCEL : -DLM_EUNLOCK);
unhold_lkb(lkb); /* undoes create_lkb() */
- rv = -EBUSY;
- goto out;
}
+ /* caller changes -EBUSY to 0 for CANCEL and FORCEUNLOCK */
+ rv = -EBUSY;
+ goto out;
}
/* cancel not allowed with another cancel/unlock in progress */
if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
if (!lkb->lkb_lvbptr)
- lkb->lkb_lvbptr = allocate_lvb(ls);
+ lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
if (!lkb->lkb_lvbptr)
return -ENOMEM;
len = receive_extralen(ms);
lkb->lkb_bastaddr = (void *) (long) (ms->m_asts & AST_BAST);
lkb->lkb_astaddr = (void *) (long) (ms->m_asts & AST_COMP);
- DLM_ASSERT(is_master_copy(lkb), dlm_print_lkb(lkb););
-
if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
/* lkb was just created so there won't be an lvb yet */
- lkb->lkb_lvbptr = allocate_lvb(ls);
+ lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
if (!lkb->lkb_lvbptr)
return -ENOMEM;
}
static int receive_convert_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
struct dlm_message *ms)
{
- if (lkb->lkb_nodeid != ms->m_header.h_nodeid) {
- log_error(ls, "convert_args nodeid %d %d lkid %x %x",
- lkb->lkb_nodeid, ms->m_header.h_nodeid,
- lkb->lkb_id, lkb->lkb_remid);
- return -EINVAL;
- }
-
- if (!is_master_copy(lkb))
- return -EINVAL;
-
if (lkb->lkb_status != DLM_LKSTS_GRANTED)
return -EBUSY;
static int receive_unlock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
struct dlm_message *ms)
{
- if (!is_master_copy(lkb))
- return -EINVAL;
if (receive_lvb(ls, lkb, ms))
return -ENOMEM;
return 0;
lkb->lkb_remid = ms->m_lkid;
}
+/* This is called after the rsb is locked so that we can safely inspect
+ fields in the lkb. */
+
+static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms)
+{
+ int from = ms->m_header.h_nodeid;
+ int error = 0;
+
+ switch (ms->m_type) {
+ case DLM_MSG_CONVERT:
+ case DLM_MSG_UNLOCK:
+ case DLM_MSG_CANCEL:
+ if (!is_master_copy(lkb) || lkb->lkb_nodeid != from)
+ error = -EINVAL;
+ break;
+
+ case DLM_MSG_CONVERT_REPLY:
+ case DLM_MSG_UNLOCK_REPLY:
+ case DLM_MSG_CANCEL_REPLY:
+ case DLM_MSG_GRANT:
+ case DLM_MSG_BAST:
+ if (!is_process_copy(lkb) || lkb->lkb_nodeid != from)
+ error = -EINVAL;
+ break;
+
+ case DLM_MSG_REQUEST_REPLY:
+ if (!is_process_copy(lkb))
+ error = -EINVAL;
+ else if (lkb->lkb_nodeid != -1 && lkb->lkb_nodeid != from)
+ error = -EINVAL;
+ break;
+
+ default:
+ error = -EINVAL;
+ }
+
+ if (error)
+ log_error(lkb->lkb_resource->res_ls,
+ "ignore invalid message %d from %d %x %x %x %d",
+ ms->m_type, from, lkb->lkb_id, lkb->lkb_remid,
+ lkb->lkb_flags, lkb->lkb_nodeid);
+ return error;
+}
+
static void receive_request(struct dlm_ls *ls, struct dlm_message *ms)
{
struct dlm_lkb *lkb;
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
receive_flags(lkb, ms);
error = receive_convert_args(ls, lkb, ms);
if (error)
- goto out;
+ goto out_reply;
reply = !down_conversion(lkb);
error = do_convert(r, lkb);
- out:
+ out_reply:
if (reply)
send_convert_reply(r, lkb, error);
-
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
receive_flags(lkb, ms);
error = receive_unlock_args(ls, lkb, ms);
if (error)
- goto out;
+ goto out_reply;
error = do_unlock(r, lkb);
- out:
+ out_reply:
send_unlock_reply(r, lkb, error);
-
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
error = do_cancel(r, lkb);
send_cancel_reply(r, lkb, error);
-
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_grant no lkb");
+ log_debug(ls, "receive_grant from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
r = lkb->lkb_resource;
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
receive_flags_reply(lkb, ms);
if (is_altmode(lkb))
munge_altmode(lkb, ms);
grant_lock_pc(r, lkb, ms);
queue_cast(r, lkb, 0);
-
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_bast no lkb");
+ log_debug(ls, "receive_bast from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
r = lkb->lkb_resource;
hold_rsb(r);
lock_rsb(r);
- queue_bast(r, lkb, ms->m_bastmode);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+ queue_bast(r, lkb, ms->m_bastmode);
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_request_reply no lkb");
+ log_debug(ls, "receive_request_reply from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
r = lkb->lkb_resource;
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
mstype = lkb->lkb_wait_type;
error = remove_from_waiters(lkb, DLM_MSG_REQUEST_REPLY);
if (error)
if (is_overlap(lkb)) {
/* we'll ignore error in cancel/unlock reply */
queue_cast_overlap(r, lkb);
+ confirm_master(r, result);
unhold_lkb(lkb); /* undoes create_lkb() */
} else
_request_lock(r, lkb);
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
/* stub reply can happen with waiters_mutex held */
error = remove_from_waiters_ms(lkb, ms);
if (error)
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_convert_reply no lkb");
+ log_debug(ls, "receive_convert_reply from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
_receive_convert_reply(lkb, ms);
dlm_put_lkb(lkb);
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
/* stub reply can happen with waiters_mutex held */
error = remove_from_waiters_ms(lkb, ms);
if (error)
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_unlock_reply no lkb");
+ log_debug(ls, "receive_unlock_reply from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
_receive_unlock_reply(lkb, ms);
dlm_put_lkb(lkb);
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
/* stub reply can happen with waiters_mutex held */
error = remove_from_waiters_ms(lkb, ms);
if (error)
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_cancel_reply no lkb");
+ log_debug(ls, "receive_cancel_reply from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
_receive_cancel_reply(lkb, ms);
dlm_put_lkb(lkb);
static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms)
{
+ if (!dlm_is_member(ls, ms->m_header.h_nodeid)) {
+ log_debug(ls, "ignore non-member message %d from %d %x %x %d",
+ ms->m_type, ms->m_header.h_nodeid, ms->m_lkid,
+ ms->m_remid, ms->m_result);
+ return;
+ }
+
switch (ms->m_type) {
/* messages sent to a master node */
ls = dlm_find_lockspace_global(hd->h_lockspace);
if (!ls) {
- log_print("invalid h_lockspace %x from %d cmd %d type %d",
- hd->h_lockspace, nodeid, hd->h_cmd, type);
+ if (dlm_config.ci_log_debug)
+ log_print("invalid lockspace %x from %d cmd %d type %d",
+ hd->h_lockspace, nodeid, hd->h_cmd, type);
if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS)
dlm_send_ls_not_ready(nodeid, rc);
ls->ls_stub_ms.m_type = DLM_MSG_CONVERT_REPLY;
ls->ls_stub_ms.m_result = -EINPROGRESS;
ls->ls_stub_ms.m_flags = lkb->lkb_flags;
+ ls->ls_stub_ms.m_header.h_nodeid = lkb->lkb_nodeid;
_receive_convert_reply(lkb, &ls->ls_stub_ms);
/* Same special case as in receive_rcom_lock_args() */
void dlm_recover_waiters_pre(struct dlm_ls *ls)
{
struct dlm_lkb *lkb, *safe;
+ int wait_type, stub_unlock_result, stub_cancel_result;
mutex_lock(&ls->ls_waiters_mutex);
if (!waiter_needs_recovery(ls, lkb))
continue;
- switch (lkb->lkb_wait_type) {
+ wait_type = lkb->lkb_wait_type;
+ stub_unlock_result = -DLM_EUNLOCK;
+ stub_cancel_result = -DLM_ECANCEL;
+
+ /* Main reply may have been received leaving a zero wait_type,
+ but a reply for the overlapping op may not have been
+ received. In that case we need to fake the appropriate
+ reply for the overlap op. */
+
+ if (!wait_type) {
+ if (is_overlap_cancel(lkb)) {
+ wait_type = DLM_MSG_CANCEL;
+ if (lkb->lkb_grmode == DLM_LOCK_IV)
+ stub_cancel_result = 0;
+ }
+ if (is_overlap_unlock(lkb)) {
+ wait_type = DLM_MSG_UNLOCK;
+ if (lkb->lkb_grmode == DLM_LOCK_IV)
+ stub_unlock_result = -ENOENT;
+ }
+
+ log_debug(ls, "rwpre overlap %x %x %d %d %d",
+ lkb->lkb_id, lkb->lkb_flags, wait_type,
+ stub_cancel_result, stub_unlock_result);
+ }
+
+ switch (wait_type) {
case DLM_MSG_REQUEST:
lkb->lkb_flags |= DLM_IFL_RESEND;
case DLM_MSG_UNLOCK:
hold_lkb(lkb);
ls->ls_stub_ms.m_type = DLM_MSG_UNLOCK_REPLY;
- ls->ls_stub_ms.m_result = -DLM_EUNLOCK;
+ ls->ls_stub_ms.m_result = stub_unlock_result;
ls->ls_stub_ms.m_flags = lkb->lkb_flags;
+ ls->ls_stub_ms.m_header.h_nodeid = lkb->lkb_nodeid;
_receive_unlock_reply(lkb, &ls->ls_stub_ms);
dlm_put_lkb(lkb);
break;
case DLM_MSG_CANCEL:
hold_lkb(lkb);
ls->ls_stub_ms.m_type = DLM_MSG_CANCEL_REPLY;
- ls->ls_stub_ms.m_result = -DLM_ECANCEL;
+ ls->ls_stub_ms.m_result = stub_cancel_result;
ls->ls_stub_ms.m_flags = lkb->lkb_flags;
+ ls->ls_stub_ms.m_header.h_nodeid = lkb->lkb_nodeid;
_receive_cancel_reply(lkb, &ls->ls_stub_ms);
dlm_put_lkb(lkb);
break;
default:
- log_error(ls, "invalid lkb wait_type %d",
- lkb->lkb_wait_type);
+ log_error(ls, "invalid lkb wait_type %d %d",
+ lkb->lkb_wait_type, wait_type);
}
schedule();
}
lkb->lkb_astaddr = (void *) (long) (rl->rl_asts & AST_COMP);
if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
- lkb->lkb_lvbptr = allocate_lvb(ls);
+ lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
if (!lkb->lkb_lvbptr)
return -ENOMEM;
lvblen = rc->rc_header.h_length - sizeof(struct dlm_rcom) -
put_rsb(r);
out:
if (error)
- log_print("recover_master_copy %d %x", error, rl->rl_lkid);
+ log_debug(ls, "recover_master_copy %d %x", error, rl->rl_lkid);
rl->rl_result = error;
return error;
}
}
}
- /* After ua is attached to lkb it will be freed by free_lkb().
+ /* After ua is attached to lkb it will be freed by dlm_free_lkb().
When DLM_IFL_USER is set, the dlm knows that this is a userspace
lock and that lkb_astparam is the dlm_user_args structure. */
}
list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_astqueue) {
+ lkb->lkb_ast_type = 0;
list_del(&lkb->lkb_astqueue);
dlm_put_lkb(lkb);
}
void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms);
void dlm_receive_buffer(struct dlm_header *hd, int nodeid);
int dlm_modes_compat(int mode1, int mode2);
-int dlm_find_rsb(struct dlm_ls *ls, char *name, int namelen,
- unsigned int flags, struct dlm_rsb **r_ret);
void dlm_put_rsb(struct dlm_rsb *r);
void dlm_hold_rsb(struct dlm_rsb *r);
int dlm_put_lkb(struct dlm_lkb *lkb);
#include "recover.h"
#include "requestqueue.h"
-#ifdef CONFIG_DLM_DEBUG
-int dlm_create_debug_file(struct dlm_ls *ls);
-void dlm_delete_debug_file(struct dlm_ls *ls);
-#else
-static inline int dlm_create_debug_file(struct dlm_ls *ls) { return 0; }
-static inline void dlm_delete_debug_file(struct dlm_ls *ls) { }
-#endif
-
static int ls_count;
static struct mutex ls_lock;
static struct list_head lslist;
dlm_del_ast(lkb);
if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY)
- free_lvb(lkb->lkb_lvbptr);
+ dlm_free_lvb(lkb->lkb_lvbptr);
- free_lkb(lkb);
+ dlm_free_lkb(lkb);
}
}
dlm_astd_resume();
res_hashchain);
list_del(&rsb->res_hashchain);
- free_rsb(rsb);
+ dlm_free_rsb(rsb);
}
head = &ls->ls_rsbtbl[i].toss;
rsb = list_entry(head->next, struct dlm_rsb,
res_hashchain);
list_del(&rsb->res_hashchain);
- free_rsb(rsb);
+ dlm_free_rsb(rsb);
}
}
static void tcp_connect_to_sock(struct connection *con)
{
int result = -EHOSTUNREACH;
- struct sockaddr_storage saddr;
+ struct sockaddr_storage saddr, src_addr;
int addr_len;
struct socket *sock;
con->connect_action = tcp_connect_to_sock;
add_sock(sock, con);
+ /* Bind to our cluster-known address connecting to avoid
+ routing problems */
+ memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr));
+ make_sockaddr(&src_addr, 0, &addr_len);
+ result = sock->ops->bind(sock, (struct sockaddr *) &src_addr,
+ addr_len);
+ if (result < 0) {
+ log_print("could not bind for connect: %d", result);
+ /* This *may* not indicate a critical error */
+ }
+
make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len);
log_print("connecting to %d", con->nodeid);
con = __nodeid2con(i, 0);
if (con) {
close_connection(con, true);
+ if (con->othercon)
+ kmem_cache_free(con_cache, con->othercon);
kmem_cache_free(con_cache, con);
}
}
#include "memory.h"
#include "config.h"
-#ifdef CONFIG_DLM_DEBUG
-int dlm_register_debugfs(void);
-void dlm_unregister_debugfs(void);
-#else
-static inline int dlm_register_debugfs(void) { return 0; }
-static inline void dlm_unregister_debugfs(void) { }
-#endif
-int dlm_netlink_init(void);
-void dlm_netlink_exit(void);
-
static int __init init_dlm(void)
{
int error;
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 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
ls->ls_num_nodes--;
}
-static int dlm_is_member(struct dlm_ls *ls, int nodeid)
+int dlm_is_member(struct dlm_ls *ls, int nodeid)
{
struct dlm_member *memb;
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 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
void dlm_clear_members_gone(struct dlm_ls *ls);
int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv,int *neg_out);
int dlm_is_removed(struct dlm_ls *ls, int nodeid);
+int dlm_is_member(struct dlm_ls *ls, int nodeid);
#endif /* __MEMBER_DOT_H__ */
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2004-2007 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
kmem_cache_destroy(lkb_cache);
}
-char *allocate_lvb(struct dlm_ls *ls)
+char *dlm_allocate_lvb(struct dlm_ls *ls)
{
char *p;
return p;
}
-void free_lvb(char *p)
+void dlm_free_lvb(char *p)
{
kfree(p);
}
/* FIXME: have some minimal space built-in to rsb for the name and
kmalloc a separate name if needed, like dentries are done */
-struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen)
+struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls, int namelen)
{
struct dlm_rsb *r;
return r;
}
-void free_rsb(struct dlm_rsb *r)
+void dlm_free_rsb(struct dlm_rsb *r)
{
if (r->res_lvbptr)
- free_lvb(r->res_lvbptr);
+ dlm_free_lvb(r->res_lvbptr);
kfree(r);
}
-struct dlm_lkb *allocate_lkb(struct dlm_ls *ls)
+struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls)
{
struct dlm_lkb *lkb;
return lkb;
}
-void free_lkb(struct dlm_lkb *lkb)
+void dlm_free_lkb(struct dlm_lkb *lkb)
{
if (lkb->lkb_flags & DLM_IFL_USER) {
struct dlm_user_args *ua;
kmem_cache_free(lkb_cache, lkb);
}
-struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen)
-{
- struct dlm_direntry *de;
-
- DLM_ASSERT(namelen <= DLM_RESNAME_MAXLEN,
- printk("namelen = %d\n", namelen););
-
- de = kzalloc(sizeof(*de) + namelen, GFP_KERNEL);
- return de;
-}
-
-void free_direntry(struct dlm_direntry *de)
-{
- kfree(de);
-}
-
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2004-2007 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
int dlm_memory_init(void);
void dlm_memory_exit(void);
-struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen);
-void free_rsb(struct dlm_rsb *r);
-struct dlm_lkb *allocate_lkb(struct dlm_ls *ls);
-void free_lkb(struct dlm_lkb *l);
-struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen);
-void free_direntry(struct dlm_direntry *de);
-char *allocate_lvb(struct dlm_ls *ls);
-void free_lvb(char *l);
+struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls, int namelen);
+void dlm_free_rsb(struct dlm_rsb *r);
+struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls);
+void dlm_free_lkb(struct dlm_lkb *l);
+char *dlm_allocate_lvb(struct dlm_ls *ls);
+void dlm_free_lvb(char *l);
#endif /* __MEMORY_DOT_H__ */
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2004-2008 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
int dlm_process_incoming_buffer(int nodeid, const void *base,
unsigned offset, unsigned len, unsigned limit)
{
- unsigned char __tmp[DLM_INBUF_LEN];
- struct dlm_header *msg = (struct dlm_header *) __tmp;
+ union {
+ unsigned char __buf[DLM_INBUF_LEN];
+ /* this is to force proper alignment on some arches */
+ struct dlm_header dlm;
+ } __tmp;
+ struct dlm_header *msg = &__tmp.dlm;
int ret = 0;
int err = 0;
uint16_t msglen;
in the buffer on the stack (which should work for most
ordinary messages). */
- if (msglen > sizeof(__tmp) &&
- msg == (struct dlm_header *) __tmp) {
+ if (msglen > DLM_INBUF_LEN && msg == &__tmp.dlm) {
msg = kmalloc(dlm_config.ci_buffer_size, GFP_KERNEL);
if (msg == NULL)
return ret;
dlm_receive_buffer(msg, nodeid);
}
- if (msg != (struct dlm_header *) __tmp)
+ if (msg != &__tmp.dlm)
kfree(msg);
return err ? err : ret;
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 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
spin_unlock(&ls->ls_rcom_spin);
}
-static void receive_rcom_status_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
-{
- receive_sync_reply(ls, rc_in);
-}
-
int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len)
{
struct dlm_rcom *rc;
send_rcom(ls, mh, rc);
}
-static void receive_rcom_names_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
-{
- receive_sync_reply(ls, rc_in);
-}
-
int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid)
{
struct dlm_rcom *rc;
send_rcom(ls, mh, rc);
}
-static void receive_rcom_lock_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
-{
- dlm_recover_process_copy(ls, rc_in);
-}
-
/* If the lockspace doesn't exist then still send a status message
back; it's possible that it just doesn't have its global_id yet. */
break;
case DLM_RCOM_STATUS_REPLY:
- receive_rcom_status_reply(ls, rc);
+ receive_sync_reply(ls, rc);
break;
case DLM_RCOM_NAMES_REPLY:
- receive_rcom_names_reply(ls, rc);
+ receive_sync_reply(ls, rc);
break;
case DLM_RCOM_LOOKUP_REPLY:
break;
case DLM_RCOM_LOCK_REPLY:
- receive_rcom_lock_reply(ls, rc);
+ dlm_recover_process_copy(ls, rc);
break;
default:
- DLM_ASSERT(0, printk("rc_type=%x\n", rc->rc_type););
+ log_error(ls, "receive_rcom bad type %d", rc->rc_type);
}
out:
return;
goto out;
if (!r->res_lvbptr) {
- r->res_lvbptr = allocate_lvb(r->res_ls);
+ r->res_lvbptr = dlm_allocate_lvb(r->res_ls);
if (!r->res_lvbptr)
goto out;
}
list_add(&r->res_root_list, &ls->ls_root_list);
dlm_hold_rsb(r);
}
+
+ /* If we're using a directory, add tossed rsbs to the root
+ list; they'll have entries created in the new directory,
+ but no other recovery steps should do anything with them. */
+
+ if (dlm_no_directory(ls)) {
+ read_unlock(&ls->ls_rsbtbl[i].lock);
+ continue;
+ }
+
+ list_for_each_entry(r, &ls->ls_rsbtbl[i].toss, res_hashchain) {
+ list_add(&r->res_root_list, &ls->ls_root_list);
+ dlm_hold_rsb(r);
+ }
read_unlock(&ls->ls_rsbtbl[i].lock);
}
out:
up_write(&ls->ls_root_sem);
}
+/* If not using a directory, clear the entire toss list, there's no benefit to
+ caching the master value since it's fixed. If we are using a dir, keep the
+ rsb's we're the master of. Recovery will add them to the root list and from
+ there they'll be entered in the rebuilt directory. */
+
void dlm_clear_toss_list(struct dlm_ls *ls)
{
struct dlm_rsb *r, *safe;
write_lock(&ls->ls_rsbtbl[i].lock);
list_for_each_entry_safe(r, safe, &ls->ls_rsbtbl[i].toss,
res_hashchain) {
- list_del(&r->res_hashchain);
- free_rsb(r);
+ if (dlm_no_directory(ls) || !is_master(r)) {
+ list_del(&r->res_hashchain);
+ dlm_free_rsb(r);
+ }
}
write_unlock(&ls->ls_rsbtbl[i].lock);
}
dlm_astd_resume();
/*
- * This list of root rsb's will be the basis of most of the recovery
- * routines.
+ * Free non-master tossed rsb's. Master rsb's are kept on toss
+ * list and put on root list to be included in resdir recovery.
*/
- dlm_create_root_list(ls);
+ dlm_clear_toss_list(ls);
/*
- * Free all the tossed rsb's so we don't have to recover them.
+ * This list of root rsb's will be the basis of most of the recovery
+ * routines.
*/
- dlm_clear_toss_list(ls);
+ dlm_create_root_list(ls);
/*
* Add or remove nodes from the lockspace's ls_nodes list.
#include "lvb_table.h"
#include "user.h"
-static const char *name_prefix="dlm";
-static struct miscdevice ctl_device;
+static const char name_prefix[] = "dlm";
static const struct file_operations device_fops;
#ifdef CONFIG_COMPAT
};
static void compat_input(struct dlm_write_request *kb,
- struct dlm_write_request32 *kb32)
+ struct dlm_write_request32 *kb32,
+ int max_namelen)
{
kb->version[0] = kb32->version[0];
kb->version[1] = kb32->version[1];
kb->i.lock.bastaddr = (void *)(long)kb32->i.lock.bastaddr;
kb->i.lock.lksb = (void *)(long)kb32->i.lock.lksb;
memcpy(kb->i.lock.lvb, kb32->i.lock.lvb, DLM_USER_LVB_LEN);
- memcpy(kb->i.lock.name, kb32->i.lock.name, kb->i.lock.namelen);
+ if (kb->i.lock.namelen <= max_namelen)
+ memcpy(kb->i.lock.name, kb32->i.lock.name,
+ kb->i.lock.namelen);
+ else
+ kb->i.lock.namelen = max_namelen;
}
}
spin_unlock(&proc->asts_spin);
if (eol) {
- spin_lock(&ua->proc->locks_spin);
+ spin_lock(&proc->locks_spin);
if (!list_empty(&lkb->lkb_ownqueue)) {
list_del_init(&lkb->lkb_ownqueue);
dlm_put_lkb(lkb);
}
- spin_unlock(&ua->proc->locks_spin);
+ spin_unlock(&proc->locks_spin);
}
out:
mutex_unlock(&ls->ls_clear_proc_locks);
if (proc)
set_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags);
- compat_input(kbuf, k32buf);
+ compat_input(kbuf, k32buf,
+ count - sizeof(struct dlm_write_request32));
kfree(k32buf);
}
#endif
.owner = THIS_MODULE,
};
+static struct miscdevice ctl_device = {
+ .name = "dlm-control",
+ .fops = &ctl_device_fops,
+ .minor = MISC_DYNAMIC_MINOR,
+};
+
int dlm_user_init(void)
{
int error;
- ctl_device.name = "dlm-control";
- ctl_device.fops = &ctl_device_fops;
- ctl_device.minor = MISC_DYNAMIC_MINOR;
-
error = misc_register(&ctl_device);
if (error)
log_print("misc_register failed for control device");
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 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
#include "rcom.h"
#include "util.h"
+#define DLM_ERRNO_EDEADLK 35
+#define DLM_ERRNO_EBADR 53
+#define DLM_ERRNO_EBADSLT 57
+#define DLM_ERRNO_EPROTO 71
+#define DLM_ERRNO_EOPNOTSUPP 95
+#define DLM_ERRNO_ETIMEDOUT 110
+#define DLM_ERRNO_EINPROGRESS 115
+
static void header_out(struct dlm_header *hd)
{
hd->h_version = cpu_to_le32(hd->h_version);
hd->h_length = le16_to_cpu(hd->h_length);
}
-void dlm_message_out(struct dlm_message *ms)
+/* higher errno values are inconsistent across architectures, so select
+ one set of values for on the wire */
+
+static int to_dlm_errno(int err)
+{
+ switch (err) {
+ case -EDEADLK:
+ return -DLM_ERRNO_EDEADLK;
+ case -EBADR:
+ return -DLM_ERRNO_EBADR;
+ case -EBADSLT:
+ return -DLM_ERRNO_EBADSLT;
+ case -EPROTO:
+ return -DLM_ERRNO_EPROTO;
+ case -EOPNOTSUPP:
+ return -DLM_ERRNO_EOPNOTSUPP;
+ case -ETIMEDOUT:
+ return -DLM_ERRNO_ETIMEDOUT;
+ case -EINPROGRESS:
+ return -DLM_ERRNO_EINPROGRESS;
+ }
+ return err;
+}
+
+static int from_dlm_errno(int err)
{
- struct dlm_header *hd = (struct dlm_header *) ms;
+ switch (err) {
+ case -DLM_ERRNO_EDEADLK:
+ return -EDEADLK;
+ case -DLM_ERRNO_EBADR:
+ return -EBADR;
+ case -DLM_ERRNO_EBADSLT:
+ return -EBADSLT;
+ case -DLM_ERRNO_EPROTO:
+ return -EPROTO;
+ case -DLM_ERRNO_EOPNOTSUPP:
+ return -EOPNOTSUPP;
+ case -DLM_ERRNO_ETIMEDOUT:
+ return -ETIMEDOUT;
+ case -DLM_ERRNO_EINPROGRESS:
+ return -EINPROGRESS;
+ }
+ return err;
+}
- header_out(hd);
+void dlm_message_out(struct dlm_message *ms)
+{
+ header_out(&ms->m_header);
ms->m_type = cpu_to_le32(ms->m_type);
ms->m_nodeid = cpu_to_le32(ms->m_nodeid);
ms->m_rqmode = cpu_to_le32(ms->m_rqmode);
ms->m_bastmode = cpu_to_le32(ms->m_bastmode);
ms->m_asts = cpu_to_le32(ms->m_asts);
- ms->m_result = cpu_to_le32(ms->m_result);
+ ms->m_result = cpu_to_le32(to_dlm_errno(ms->m_result));
}
void dlm_message_in(struct dlm_message *ms)
{
- struct dlm_header *hd = (struct dlm_header *) ms;
-
- header_in(hd);
+ header_in(&ms->m_header);
ms->m_type = le32_to_cpu(ms->m_type);
ms->m_nodeid = le32_to_cpu(ms->m_nodeid);
ms->m_rqmode = le32_to_cpu(ms->m_rqmode);
ms->m_bastmode = le32_to_cpu(ms->m_bastmode);
ms->m_asts = le32_to_cpu(ms->m_asts);
- ms->m_result = le32_to_cpu(ms->m_result);
+ ms->m_result = from_dlm_errno(le32_to_cpu(ms->m_result));
}
static void rcom_lock_out(struct rcom_lock *rl)
void dlm_rcom_out(struct dlm_rcom *rc)
{
- struct dlm_header *hd = (struct dlm_header *) rc;
int type = rc->rc_type;
- header_out(hd);
+ header_out(&rc->rc_header);
rc->rc_type = cpu_to_le32(rc->rc_type);
rc->rc_result = cpu_to_le32(rc->rc_result);
rc->rc_seq = cpu_to_le64(rc->rc_seq);
rc->rc_seq_reply = cpu_to_le64(rc->rc_seq_reply);
- if (type == DLM_RCOM_LOCK)
+ if ((type == DLM_RCOM_LOCK) || (type == DLM_RCOM_LOCK_REPLY))
rcom_lock_out((struct rcom_lock *) rc->rc_buf);
else if (type == DLM_RCOM_STATUS_REPLY)
void dlm_rcom_in(struct dlm_rcom *rc)
{
- struct dlm_header *hd = (struct dlm_header *) rc;
+ int type;
- header_in(hd);
+ header_in(&rc->rc_header);
rc->rc_type = le32_to_cpu(rc->rc_type);
rc->rc_result = le32_to_cpu(rc->rc_result);
rc->rc_seq = le64_to_cpu(rc->rc_seq);
rc->rc_seq_reply = le64_to_cpu(rc->rc_seq_reply);
- if (rc->rc_type == DLM_RCOM_LOCK)
+ type = rc->rc_type;
+
+ if ((type == DLM_RCOM_LOCK) || (type == DLM_RCOM_LOCK_REPLY))
rcom_lock_in((struct rcom_lock *) rc->rc_buf);
- else if (rc->rc_type == DLM_RCOM_STATUS_REPLY)
+ else if (type == DLM_RCOM_STATUS_REPLY)
rcom_config_in((struct rcom_config *) rc->rc_buf);
}
git.samba.org / sfrench / cifs-2.6.git / commitdiff