* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-nmw: (34 commits)
[GFS2] Uncomment sprintf_symbol calling code
[DLM] lowcomms style
[GFS2] printk warning fixes
[GFS2] Patch to fix mmap of stuffed files
[GFS2] use lib/parser for parsing mount options
[DLM] Lowcomms nodeid range & initialisation fixes
[DLM] Fix dlm_lowcoms_stop hang
[DLM] fix mode munging
[GFS2] lockdump improvements
[GFS2] Patch to detect corrupt number of dir entries in leaf and/or inode blocks
[GFS2] bz 236008: Kernel gpf doing cat /debugfs/gfs2/xxx (lock dump)
[DLM] fs/dlm/ast.c should #include "ast.h"
[DLM] Consolidate transport protocols
[DLM] Remove redundant assignment
[GFS2] Fix bz 234168 (ignoring rgrp flags)
[DLM] change lkid format
[DLM] interface for purge (2/2)
[DLM] add orphan purging code (1/2)
[DLM] split create_message function
[GFS2] Set drop_count to 0 (off) by default
...
config DLM
tristate "Distributed Lock Manager (DLM)"
- depends on SYSFS && (IPV6 || IPV6=n)
+ depends on IPV6 || IPV6=n
select CONFIGFS_FS
- select IP_SCTP if DLM_SCTP
+ select IP_SCTP
help
- A general purpose distributed lock manager for kernel or userspace
- applications.
-
-choice
- prompt "Select DLM communications protocol"
- depends on DLM
- default DLM_TCP
- help
- The DLM Can use TCP or SCTP for it's network communications.
- SCTP supports multi-homed operations whereas TCP doesn't.
- However, SCTP seems to have stability problems at the moment.
-
-config DLM_TCP
- bool "TCP/IP"
-
-config DLM_SCTP
- bool "SCTP"
-
-endchoice
+ A general purpose distributed lock manager for kernel or userspace
+ applications.
config DLM_DEBUG
bool "DLM debugging"
depends on DLM
help
- Under the debugfs mount point, the name of each lockspace will
- appear as a file in the "dlm" directory. The output is the
- list of resource and locks the local node knows about.
+ Under the debugfs mount point, the name of each lockspace will
+ appear as a file in the "dlm" directory. The output is the
+ list of resource and locks the local node knows about.
endmenu
member.o \
memory.o \
midcomms.o \
+ lowcomms.o \
rcom.o \
recover.o \
recoverd.o \
requestqueue.o \
user.o \
- util.o
+ util.o
dlm-$(CONFIG_DLM_DEBUG) += debug_fs.o
-dlm-$(CONFIG_DLM_TCP) += lowcomms-tcp.o
-
-dlm-$(CONFIG_DLM_SCTP) += lowcomms-sctp.o
\ No newline at end of file
#include "dlm_internal.h"
#include "lock.h"
#include "user.h"
+#include "ast.h"
#define WAKE_ASTS 0
*******************************************************************************
**
** 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
unsigned int cl_toss_secs;
unsigned int cl_scan_secs;
unsigned int cl_log_debug;
+ unsigned int cl_protocol;
};
enum {
CLUSTER_ATTR_TOSS_SECS,
CLUSTER_ATTR_SCAN_SECS,
CLUSTER_ATTR_LOG_DEBUG,
+ CLUSTER_ATTR_PROTOCOL,
};
struct cluster_attribute {
CLUSTER_ATTR(toss_secs, 1);
CLUSTER_ATTR(scan_secs, 1);
CLUSTER_ATTR(log_debug, 0);
+CLUSTER_ATTR(protocol, 0);
static struct configfs_attribute *cluster_attrs[] = {
[CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port.attr,
[CLUSTER_ATTR_TOSS_SECS] = &cluster_attr_toss_secs.attr,
[CLUSTER_ATTR_SCAN_SECS] = &cluster_attr_scan_secs.attr,
[CLUSTER_ATTR_LOG_DEBUG] = &cluster_attr_log_debug.attr,
+ [CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol.attr,
NULL,
};
#define DEFAULT_TOSS_SECS 10
#define DEFAULT_SCAN_SECS 5
#define DEFAULT_LOG_DEBUG 0
+#define DEFAULT_PROTOCOL 0
struct dlm_config_info dlm_config = {
.ci_tcp_port = DEFAULT_TCP_PORT,
.ci_recover_timer = DEFAULT_RECOVER_TIMER,
.ci_toss_secs = DEFAULT_TOSS_SECS,
.ci_scan_secs = DEFAULT_SCAN_SECS,
- .ci_log_debug = DEFAULT_LOG_DEBUG
+ .ci_log_debug = DEFAULT_LOG_DEBUG,
+ .ci_protocol = DEFAULT_PROTOCOL
};
*******************************************************************************
**
** 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 ci_toss_secs;
int ci_scan_secs;
int ci_log_debug;
+ int ci_protocol;
};
extern struct dlm_config_info dlm_config;
*******************************************************************************
**
** 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
#define DLM_IFL_MSTCPY 0x00010000
#define DLM_IFL_RESEND 0x00020000
#define DLM_IFL_DEAD 0x00040000
+#define DLM_IFL_OVERLAP_UNLOCK 0x00080000
+#define DLM_IFL_OVERLAP_CANCEL 0x00100000
+#define DLM_IFL_ENDOFLIFE 0x00200000
#define DLM_IFL_USER 0x00000001
#define DLM_IFL_ORPHAN 0x00000002
int8_t lkb_grmode; /* granted lock mode */
int8_t lkb_bastmode; /* requested mode */
int8_t lkb_highbast; /* highest mode bast sent for */
-
int8_t lkb_wait_type; /* type of reply waiting for */
+ int8_t lkb_wait_count;
int8_t lkb_ast_type; /* type of ast queued for */
struct list_head lkb_idtbl_list; /* lockspace lkbtbl */
#define DLM_MSG_LOOKUP 11
#define DLM_MSG_REMOVE 12
#define DLM_MSG_LOOKUP_REPLY 13
+#define DLM_MSG_PURGE 14
struct dlm_message {
struct dlm_header m_header;
struct mutex ls_waiters_mutex;
struct list_head ls_waiters; /* lkbs needing a reply */
+ struct mutex ls_orphans_mutex;
+ struct list_head ls_orphans;
+
struct list_head ls_nodes; /* current nodes in ls */
struct list_head ls_nodes_gone; /* dead node list, recovery */
int ls_num_nodes; /* number of nodes in ls */
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2007 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
static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
struct dlm_message *ms);
static int receive_extralen(struct dlm_message *ms);
+static void do_purge(struct dlm_ls *ls, int nodeid, int pid);
/*
* Lock compatibilty matrix - thanks Steve
return (lkb->lkb_sbflags & DLM_SBF_DEMOTED);
}
+static inline int is_altmode(struct dlm_lkb *lkb)
+{
+ return (lkb->lkb_sbflags & DLM_SBF_ALTMODE);
+}
+
+static inline int is_granted(struct dlm_lkb *lkb)
+{
+ return (lkb->lkb_status == DLM_LKSTS_GRANTED);
+}
+
static inline int is_remote(struct dlm_rsb *r)
{
DLM_ASSERT(r->res_nodeid >= 0, dlm_print_rsb(r););
return (!middle_conversion(lkb) && lkb->lkb_rqmode < lkb->lkb_grmode);
}
+static inline int is_overlap_unlock(struct dlm_lkb *lkb)
+{
+ return lkb->lkb_flags & DLM_IFL_OVERLAP_UNLOCK;
+}
+
+static inline int is_overlap_cancel(struct dlm_lkb *lkb)
+{
+ return lkb->lkb_flags & DLM_IFL_OVERLAP_CANCEL;
+}
+
+static inline int is_overlap(struct dlm_lkb *lkb)
+{
+ return (lkb->lkb_flags & (DLM_IFL_OVERLAP_UNLOCK |
+ DLM_IFL_OVERLAP_CANCEL));
+}
+
static void queue_cast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv)
{
if (is_master_copy(lkb))
dlm_add_ast(lkb, AST_COMP);
}
+static inline void queue_cast_overlap(struct dlm_rsb *r, struct dlm_lkb *lkb)
+{
+ queue_cast(r, lkb,
+ is_overlap_unlock(lkb) ? -DLM_EUNLOCK : -DLM_ECANCEL);
+}
+
static void queue_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rqmode)
{
if (is_master_copy(lkb))
lkb->lkb_grmode = DLM_LOCK_IV;
kref_init(&lkb->lkb_ref);
INIT_LIST_HEAD(&lkb->lkb_ownqueue);
+ INIT_LIST_HEAD(&lkb->lkb_rsb_lookup);
get_random_bytes(&bucket, sizeof(bucket));
bucket &= (ls->ls_lkbtbl_size - 1);
/* counter can roll over so we must verify lkid is not in use */
while (lkid == 0) {
- lkid = bucket | (ls->ls_lkbtbl[bucket].counter++ << 16);
+ lkid = (bucket << 16) | ls->ls_lkbtbl[bucket].counter++;
list_for_each_entry(tmp, &ls->ls_lkbtbl[bucket].list,
lkb_idtbl_list) {
static struct dlm_lkb *__find_lkb(struct dlm_ls *ls, uint32_t lkid)
{
- uint16_t bucket = lkid & 0xFFFF;
struct dlm_lkb *lkb;
+ uint16_t bucket = (lkid >> 16);
list_for_each_entry(lkb, &ls->ls_lkbtbl[bucket].list, lkb_idtbl_list) {
if (lkb->lkb_id == lkid)
static int find_lkb(struct dlm_ls *ls, uint32_t lkid, struct dlm_lkb **lkb_ret)
{
struct dlm_lkb *lkb;
- uint16_t bucket = lkid & 0xFFFF;
+ uint16_t bucket = (lkid >> 16);
if (bucket >= ls->ls_lkbtbl_size)
return -EBADSLT;
static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb)
{
- uint16_t bucket = lkb->lkb_id & 0xFFFF;
+ uint16_t bucket = (lkb->lkb_id >> 16);
write_lock(&ls->ls_lkbtbl[bucket].lock);
if (kref_put(&lkb->lkb_ref, kill_lkb)) {
unhold_lkb(lkb);
}
+static int msg_reply_type(int mstype)
+{
+ switch (mstype) {
+ case DLM_MSG_REQUEST:
+ return DLM_MSG_REQUEST_REPLY;
+ case DLM_MSG_CONVERT:
+ return DLM_MSG_CONVERT_REPLY;
+ case DLM_MSG_UNLOCK:
+ return DLM_MSG_UNLOCK_REPLY;
+ case DLM_MSG_CANCEL:
+ return DLM_MSG_CANCEL_REPLY;
+ case DLM_MSG_LOOKUP:
+ return DLM_MSG_LOOKUP_REPLY;
+ }
+ return -1;
+}
+
/* add/remove lkb from global waiters list of lkb's waiting for
a reply from a remote node */
-static void add_to_waiters(struct dlm_lkb *lkb, int mstype)
+static int add_to_waiters(struct dlm_lkb *lkb, int mstype)
{
struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+ int error = 0;
mutex_lock(&ls->ls_waiters_mutex);
- if (lkb->lkb_wait_type) {
- log_print("add_to_waiters error %d", lkb->lkb_wait_type);
+
+ if (is_overlap_unlock(lkb) ||
+ (is_overlap_cancel(lkb) && (mstype == DLM_MSG_CANCEL))) {
+ error = -EINVAL;
+ goto out;
+ }
+
+ if (lkb->lkb_wait_type || is_overlap_cancel(lkb)) {
+ switch (mstype) {
+ case DLM_MSG_UNLOCK:
+ lkb->lkb_flags |= DLM_IFL_OVERLAP_UNLOCK;
+ break;
+ case DLM_MSG_CANCEL:
+ lkb->lkb_flags |= DLM_IFL_OVERLAP_CANCEL;
+ break;
+ default:
+ error = -EBUSY;
+ goto out;
+ }
+ lkb->lkb_wait_count++;
+ hold_lkb(lkb);
+
+ log_debug(ls, "add overlap %x cur %d new %d count %d flags %x",
+ lkb->lkb_id, lkb->lkb_wait_type, mstype,
+ lkb->lkb_wait_count, lkb->lkb_flags);
goto out;
}
+
+ DLM_ASSERT(!lkb->lkb_wait_count,
+ dlm_print_lkb(lkb);
+ printk("wait_count %d\n", lkb->lkb_wait_count););
+
+ lkb->lkb_wait_count++;
lkb->lkb_wait_type = mstype;
- kref_get(&lkb->lkb_ref);
+ hold_lkb(lkb);
list_add(&lkb->lkb_wait_reply, &ls->ls_waiters);
out:
+ if (error)
+ log_error(ls, "add_to_waiters %x error %d flags %x %d %d %s",
+ lkb->lkb_id, error, lkb->lkb_flags, mstype,
+ lkb->lkb_wait_type, lkb->lkb_resource->res_name);
mutex_unlock(&ls->ls_waiters_mutex);
+ return error;
}
/* We clear the RESEND flag because we might be taking an lkb off the waiters
request reply on the requestqueue) between dlm_recover_waiters_pre() which
set RESEND and dlm_recover_waiters_post() */
-static int _remove_from_waiters(struct dlm_lkb *lkb)
+static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype)
{
- int error = 0;
+ struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+ int overlap_done = 0;
- if (!lkb->lkb_wait_type) {
- log_print("remove_from_waiters error");
- error = -EINVAL;
- goto out;
+ if (is_overlap_unlock(lkb) && (mstype == DLM_MSG_UNLOCK_REPLY)) {
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
+ overlap_done = 1;
+ goto out_del;
+ }
+
+ if (is_overlap_cancel(lkb) && (mstype == DLM_MSG_CANCEL_REPLY)) {
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
+ overlap_done = 1;
+ goto out_del;
+ }
+
+ /* N.B. type of reply may not always correspond to type of original
+ msg due to lookup->request optimization, verify others? */
+
+ if (lkb->lkb_wait_type) {
+ lkb->lkb_wait_type = 0;
+ goto out_del;
+ }
+
+ log_error(ls, "remove_from_waiters lkid %x flags %x types %d %d",
+ lkb->lkb_id, lkb->lkb_flags, mstype, lkb->lkb_wait_type);
+ return -1;
+
+ out_del:
+ /* the force-unlock/cancel has completed and we haven't recvd a reply
+ to the op that was in progress prior to the unlock/cancel; we
+ give up on any reply to the earlier op. FIXME: not sure when/how
+ this would happen */
+
+ if (overlap_done && lkb->lkb_wait_type) {
+ log_error(ls, "remove_from_waiters %x reply %d give up on %d",
+ lkb->lkb_id, mstype, lkb->lkb_wait_type);
+ lkb->lkb_wait_count--;
+ lkb->lkb_wait_type = 0;
}
- lkb->lkb_wait_type = 0;
+
+ DLM_ASSERT(lkb->lkb_wait_count, dlm_print_lkb(lkb););
+
lkb->lkb_flags &= ~DLM_IFL_RESEND;
- list_del(&lkb->lkb_wait_reply);
+ lkb->lkb_wait_count--;
+ if (!lkb->lkb_wait_count)
+ list_del_init(&lkb->lkb_wait_reply);
unhold_lkb(lkb);
- out:
- return error;
+ return 0;
}
-static int remove_from_waiters(struct dlm_lkb *lkb)
+static int remove_from_waiters(struct dlm_lkb *lkb, int mstype)
{
struct dlm_ls *ls = lkb->lkb_resource->res_ls;
int error;
mutex_lock(&ls->ls_waiters_mutex);
- error = _remove_from_waiters(lkb);
+ error = _remove_from_waiters(lkb, mstype);
mutex_unlock(&ls->ls_waiters_mutex);
return error;
}
+/* Handles situations where we might be processing a "fake" or "stub" reply in
+ which we can't try to take waiters_mutex again. */
+
+static int remove_from_waiters_ms(struct dlm_lkb *lkb, struct dlm_message *ms)
+{
+ struct dlm_ls *ls = lkb->lkb_resource->res_ls;
+ int error;
+
+ if (ms != &ls->ls_stub_ms)
+ mutex_lock(&ls->ls_waiters_mutex);
+ error = _remove_from_waiters(lkb, ms->m_type);
+ if (ms != &ls->ls_stub_ms)
+ mutex_unlock(&ls->ls_waiters_mutex);
+ return error;
+}
+
static void dir_remove(struct dlm_rsb *r)
{
int to_nodeid;
_remove_lock(r, lkb);
}
-static void revert_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
+/* returns: 0 did nothing
+ 1 moved lock to granted
+ -1 removed lock */
+
+static int revert_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
+ int rv = 0;
+
lkb->lkb_rqmode = DLM_LOCK_IV;
switch (lkb->lkb_status) {
break;
case DLM_LKSTS_CONVERT:
move_lkb(r, lkb, DLM_LKSTS_GRANTED);
+ rv = 1;
break;
case DLM_LKSTS_WAITING:
del_lkb(r, lkb);
/* this unhold undoes the original ref from create_lkb()
so this leads to the lkb being freed */
unhold_lkb(lkb);
+ rv = -1;
break;
default:
log_print("invalid status for revert %d", lkb->lkb_status);
}
+ return rv;
}
-static void revert_lock_pc(struct dlm_rsb *r, struct dlm_lkb *lkb)
+static int revert_lock_pc(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
- revert_lock(r, lkb);
+ return revert_lock(r, lkb);
}
static void _grant_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
queue_cast(r, lkb, 0);
}
+/* The special CONVDEADLK, ALTPR and ALTCW flags allow the master to
+ change the granted/requested modes. We're munging things accordingly in
+ the process copy.
+ CONVDEADLK: our grmode may have been forced down to NL to resolve a
+ conversion deadlock
+ ALTPR/ALTCW: our rqmode may have been changed to PR or CW to become
+ compatible with other granted locks */
+
+static void munge_demoted(struct dlm_lkb *lkb, struct dlm_message *ms)
+{
+ if (ms->m_type != DLM_MSG_CONVERT_REPLY) {
+ log_print("munge_demoted %x invalid reply type %d",
+ lkb->lkb_id, ms->m_type);
+ return;
+ }
+
+ if (lkb->lkb_rqmode == DLM_LOCK_IV || lkb->lkb_grmode == DLM_LOCK_IV) {
+ log_print("munge_demoted %x invalid modes gr %d rq %d",
+ lkb->lkb_id, lkb->lkb_grmode, lkb->lkb_rqmode);
+ return;
+ }
+
+ lkb->lkb_grmode = DLM_LOCK_NL;
+}
+
+static void munge_altmode(struct dlm_lkb *lkb, struct dlm_message *ms)
+{
+ if (ms->m_type != DLM_MSG_REQUEST_REPLY &&
+ ms->m_type != DLM_MSG_GRANT) {
+ log_print("munge_altmode %x invalid reply type %d",
+ lkb->lkb_id, ms->m_type);
+ return;
+ }
+
+ if (lkb->lkb_exflags & DLM_LKF_ALTPR)
+ lkb->lkb_rqmode = DLM_LOCK_PR;
+ else if (lkb->lkb_exflags & DLM_LKF_ALTCW)
+ lkb->lkb_rqmode = DLM_LOCK_CW;
+ else {
+ log_print("munge_altmode invalid exflags %x", lkb->lkb_exflags);
+ dlm_print_lkb(lkb);
+ }
+}
+
static inline int first_in_list(struct dlm_lkb *lkb, struct list_head *head)
{
struct dlm_lkb *first = list_entry(head->next, struct dlm_lkb,
struct dlm_lkb *lkb, *safe;
list_for_each_entry_safe(lkb, safe, &r->res_lookup, lkb_rsb_lookup) {
- list_del(&lkb->lkb_rsb_lookup);
+ list_del_init(&lkb->lkb_rsb_lookup);
_request_lock(r, lkb);
schedule();
}
if (!list_empty(&r->res_lookup)) {
lkb = list_entry(r->res_lookup.next, struct dlm_lkb,
lkb_rsb_lookup);
- list_del(&lkb->lkb_rsb_lookup);
+ list_del_init(&lkb->lkb_rsb_lookup);
r->res_first_lkid = lkb->lkb_id;
_request_lock(r, lkb);
} else
DLM_LKF_FORCEUNLOCK))
return -EINVAL;
+ if (flags & DLM_LKF_CANCEL && flags & DLM_LKF_FORCEUNLOCK)
+ return -EINVAL;
+
args->flags = flags;
args->astparam = (long) astarg;
return 0;
if (lkb->lkb_wait_type)
goto out;
+
+ if (is_overlap(lkb))
+ goto out;
}
lkb->lkb_exflags = args->flags;
return rv;
}
+/* when dlm_unlock() sees -EBUSY with CANCEL/FORCEUNLOCK it returns 0
+ for success */
+
+/* note: it's valid for lkb_nodeid/res_nodeid to be -1 when we get here
+ because there may be a lookup in progress and it's valid to do
+ cancel/unlockf on it */
+
static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
{
+ struct dlm_ls *ls = lkb->lkb_resource->res_ls;
int rv = -EINVAL;
- if (lkb->lkb_flags & DLM_IFL_MSTCPY)
+ if (lkb->lkb_flags & DLM_IFL_MSTCPY) {
+ log_error(ls, "unlock on MSTCPY %x", lkb->lkb_id);
+ dlm_print_lkb(lkb);
goto out;
+ }
- if (args->flags & DLM_LKF_FORCEUNLOCK)
- goto out_ok;
+ /* an lkb may still exist even though the lock is EOL'ed due to a
+ cancel, unlock or failed noqueue request; an app can't use these
+ locks; return same error as if the lkid had not been found at all */
- if (args->flags & DLM_LKF_CANCEL &&
- lkb->lkb_status == DLM_LKSTS_GRANTED)
+ if (lkb->lkb_flags & DLM_IFL_ENDOFLIFE) {
+ log_debug(ls, "unlock on ENDOFLIFE %x", lkb->lkb_id);
+ rv = -ENOENT;
goto out;
+ }
- if (!(args->flags & DLM_LKF_CANCEL) &&
- lkb->lkb_status != DLM_LKSTS_GRANTED)
- goto out;
+ /* 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)) {
+ 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;
+ }
+ }
+
+ /* cancel not allowed with another cancel/unlock in progress */
+
+ if (args->flags & DLM_LKF_CANCEL) {
+ if (lkb->lkb_exflags & DLM_LKF_CANCEL)
+ goto out;
+
+ if (is_overlap(lkb))
+ goto out;
+
+ if (lkb->lkb_flags & DLM_IFL_RESEND) {
+ lkb->lkb_flags |= DLM_IFL_OVERLAP_CANCEL;
+ rv = -EBUSY;
+ goto out;
+ }
+
+ switch (lkb->lkb_wait_type) {
+ case DLM_MSG_LOOKUP:
+ case DLM_MSG_REQUEST:
+ lkb->lkb_flags |= DLM_IFL_OVERLAP_CANCEL;
+ rv = -EBUSY;
+ goto out;
+ case DLM_MSG_UNLOCK:
+ case DLM_MSG_CANCEL:
+ goto out;
+ }
+ /* add_to_waiters() will set OVERLAP_CANCEL */
+ goto out_ok;
+ }
+
+ /* do we need to allow a force-unlock if there's a normal unlock
+ already in progress? in what conditions could the normal unlock
+ fail such that we'd want to send a force-unlock to be sure? */
+
+ if (args->flags & DLM_LKF_FORCEUNLOCK) {
+ if (lkb->lkb_exflags & DLM_LKF_FORCEUNLOCK)
+ goto out;
+
+ if (is_overlap_unlock(lkb))
+ goto out;
+ if (lkb->lkb_flags & DLM_IFL_RESEND) {
+ lkb->lkb_flags |= DLM_IFL_OVERLAP_UNLOCK;
+ rv = -EBUSY;
+ goto out;
+ }
+
+ switch (lkb->lkb_wait_type) {
+ case DLM_MSG_LOOKUP:
+ case DLM_MSG_REQUEST:
+ lkb->lkb_flags |= DLM_IFL_OVERLAP_UNLOCK;
+ rv = -EBUSY;
+ goto out;
+ case DLM_MSG_UNLOCK:
+ goto out;
+ }
+ /* add_to_waiters() will set OVERLAP_UNLOCK */
+ goto out_ok;
+ }
+
+ /* normal unlock not allowed if there's any op in progress */
rv = -EBUSY;
- if (lkb->lkb_wait_type)
+ if (lkb->lkb_wait_type || lkb->lkb_wait_count)
goto out;
out_ok:
- lkb->lkb_exflags = args->flags;
+ /* an overlapping op shouldn't blow away exflags from other op */
+ lkb->lkb_exflags |= args->flags;
lkb->lkb_sbflags = 0;
lkb->lkb_astparam = args->astparam;
-
rv = 0;
out:
+ if (rv)
+ log_debug(ls, "validate_unlock_args %d %x %x %x %x %d %s", rv,
+ lkb->lkb_id, lkb->lkb_flags, lkb->lkb_exflags,
+ args->flags, lkb->lkb_wait_type,
+ lkb->lkb_resource->res_name);
return rv;
}
goto out;
}
- if (can_be_queued(lkb)) {
- if (is_demoted(lkb))
+ /* is_demoted() means the can_be_granted() above set the grmode
+ to NL, and left us on the granted queue. This auto-demotion
+ (due to CONVDEADLK) might mean other locks, and/or this lock, are
+ now grantable. We have to try to grant other converting locks
+ before we try again to grant this one. */
+
+ if (is_demoted(lkb)) {
+ grant_pending_convert(r, DLM_LOCK_IV);
+ if (_can_be_granted(r, lkb, 1)) {
+ grant_lock(r, lkb);
+ queue_cast(r, lkb, 0);
grant_pending_locks(r);
+ goto out;
+ }
+ /* else fall through and move to convert queue */
+ }
+
+ if (can_be_queued(lkb)) {
error = -EINPROGRESS;
del_lkb(r, lkb);
add_lkb(r, lkb, DLM_LKSTS_CONVERT);
return -DLM_EUNLOCK;
}
-/* FIXME: if revert_lock() finds that the lkb is granted, we should
- skip the queue_cast(ECANCEL). It indicates that the request/convert
- completed (and queued a normal ast) just before the cancel; we don't
- want to clobber the sb_result for the normal ast with ECANCEL. */
+/* returns: 0 did nothing, -DLM_ECANCEL canceled lock */
static int do_cancel(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
- revert_lock(r, lkb);
- queue_cast(r, lkb, -DLM_ECANCEL);
- grant_pending_locks(r);
- return -DLM_ECANCEL;
+ int error;
+
+ error = revert_lock(r, lkb);
+ if (error) {
+ queue_cast(r, lkb, -DLM_ECANCEL);
+ grant_pending_locks(r);
+ return -DLM_ECANCEL;
+ }
+ return 0;
}
/*
if (error == -DLM_EUNLOCK || error == -DLM_ECANCEL)
error = 0;
+ if (error == -EBUSY && (flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)))
+ error = 0;
out_put:
dlm_put_lkb(lkb);
out:
* receive_lookup_reply send_lookup_reply
*/
-static int create_message(struct dlm_rsb *r, struct dlm_lkb *lkb,
- int to_nodeid, int mstype,
- struct dlm_message **ms_ret,
- struct dlm_mhandle **mh_ret)
+static int _create_message(struct dlm_ls *ls, int mb_len,
+ int to_nodeid, int mstype,
+ struct dlm_message **ms_ret,
+ struct dlm_mhandle **mh_ret)
{
struct dlm_message *ms;
struct dlm_mhandle *mh;
char *mb;
- int mb_len = sizeof(struct dlm_message);
-
- switch (mstype) {
- case DLM_MSG_REQUEST:
- case DLM_MSG_LOOKUP:
- case DLM_MSG_REMOVE:
- mb_len += r->res_length;
- break;
- case DLM_MSG_CONVERT:
- case DLM_MSG_UNLOCK:
- case DLM_MSG_REQUEST_REPLY:
- case DLM_MSG_CONVERT_REPLY:
- case DLM_MSG_GRANT:
- if (lkb && lkb->lkb_lvbptr)
- mb_len += r->res_ls->ls_lvblen;
- break;
- }
/* get_buffer gives us a message handle (mh) that we need to
pass into lowcomms_commit and a message buffer (mb) that we
ms = (struct dlm_message *) mb;
ms->m_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
- ms->m_header.h_lockspace = r->res_ls->ls_global_id;
+ ms->m_header.h_lockspace = ls->ls_global_id;
ms->m_header.h_nodeid = dlm_our_nodeid();
ms->m_header.h_length = mb_len;
ms->m_header.h_cmd = DLM_MSG;
return 0;
}
+static int create_message(struct dlm_rsb *r, struct dlm_lkb *lkb,
+ int to_nodeid, int mstype,
+ struct dlm_message **ms_ret,
+ struct dlm_mhandle **mh_ret)
+{
+ int mb_len = sizeof(struct dlm_message);
+
+ switch (mstype) {
+ case DLM_MSG_REQUEST:
+ case DLM_MSG_LOOKUP:
+ case DLM_MSG_REMOVE:
+ mb_len += r->res_length;
+ break;
+ case DLM_MSG_CONVERT:
+ case DLM_MSG_UNLOCK:
+ case DLM_MSG_REQUEST_REPLY:
+ case DLM_MSG_CONVERT_REPLY:
+ case DLM_MSG_GRANT:
+ if (lkb && lkb->lkb_lvbptr)
+ mb_len += r->res_ls->ls_lvblen;
+ break;
+ }
+
+ return _create_message(r->res_ls, mb_len, to_nodeid, mstype,
+ ms_ret, mh_ret);
+}
+
/* further lowcomms enhancements or alternate implementations may make
the return value from this function useful at some point */
struct dlm_mhandle *mh;
int to_nodeid, error;
- add_to_waiters(lkb, mstype);
+ error = add_to_waiters(lkb, mstype);
+ if (error)
+ return error;
to_nodeid = r->res_nodeid;
return 0;
fail:
- remove_from_waiters(lkb);
+ remove_from_waiters(lkb, msg_reply_type(mstype));
return error;
}
/* down conversions go without a reply from the master */
if (!error && down_conversion(lkb)) {
- remove_from_waiters(lkb);
+ remove_from_waiters(lkb, DLM_MSG_CONVERT_REPLY);
+ r->res_ls->ls_stub_ms.m_type = DLM_MSG_CONVERT_REPLY;
r->res_ls->ls_stub_ms.m_result = 0;
r->res_ls->ls_stub_ms.m_flags = lkb->lkb_flags;
__receive_convert_reply(r, lkb, &r->res_ls->ls_stub_ms);
struct dlm_mhandle *mh;
int to_nodeid, error;
- add_to_waiters(lkb, DLM_MSG_LOOKUP);
+ error = add_to_waiters(lkb, DLM_MSG_LOOKUP);
+ if (error)
+ return error;
to_nodeid = dlm_dir_nodeid(r);
return 0;
fail:
- remove_from_waiters(lkb);
+ remove_from_waiters(lkb, DLM_MSG_LOOKUP_REPLY);
return error;
}
lock_rsb(r);
receive_flags_reply(lkb, ms);
+ if (is_altmode(lkb))
+ munge_altmode(lkb, ms);
grant_lock_pc(r, lkb, ms);
queue_cast(r, lkb, 0);
dlm_dir_remove_entry(ls, from_nodeid, ms->m_extra, len);
}
+static void receive_purge(struct dlm_ls *ls, struct dlm_message *ms)
+{
+ do_purge(ls, ms->m_nodeid, ms->m_pid);
+}
+
static void receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms)
{
struct dlm_lkb *lkb;
struct dlm_rsb *r;
- int error, mstype;
+ int error, mstype, result;
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
}
DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
- mstype = lkb->lkb_wait_type;
- error = remove_from_waiters(lkb);
- if (error) {
- log_error(ls, "receive_request_reply not on waiters");
- goto out;
- }
-
- /* this is the value returned from do_request() on the master */
- error = ms->m_result;
-
r = lkb->lkb_resource;
hold_rsb(r);
lock_rsb(r);
+ mstype = lkb->lkb_wait_type;
+ error = remove_from_waiters(lkb, DLM_MSG_REQUEST_REPLY);
+ if (error)
+ goto out;
+
/* Optimization: the dir node was also the master, so it took our
lookup as a request and sent request reply instead of lookup reply */
if (mstype == DLM_MSG_LOOKUP) {
lkb->lkb_nodeid = r->res_nodeid;
}
- switch (error) {
+ /* this is the value returned from do_request() on the master */
+ result = ms->m_result;
+
+ switch (result) {
case -EAGAIN:
- /* request would block (be queued) on remote master;
- the unhold undoes the original ref from create_lkb()
- so it leads to the lkb being freed */
+ /* request would block (be queued) on remote master */
queue_cast(r, lkb, -EAGAIN);
confirm_master(r, -EAGAIN);
- unhold_lkb(lkb);
+ unhold_lkb(lkb); /* undoes create_lkb() */
break;
case -EINPROGRESS:
/* request was queued or granted on remote master */
receive_flags_reply(lkb, ms);
lkb->lkb_remid = ms->m_lkid;
- if (error)
+ if (is_altmode(lkb))
+ munge_altmode(lkb, ms);
+ if (result)
add_lkb(r, lkb, DLM_LKSTS_WAITING);
else {
grant_lock_pc(r, lkb, ms);
queue_cast(r, lkb, 0);
}
- confirm_master(r, error);
+ confirm_master(r, result);
break;
case -EBADR:
case -ENOTBLK:
/* find_rsb failed to find rsb or rsb wasn't master */
+ log_debug(ls, "receive_request_reply %x %x master diff %d %d",
+ lkb->lkb_id, lkb->lkb_flags, r->res_nodeid, result);
r->res_nodeid = -1;
lkb->lkb_nodeid = -1;
- _request_lock(r, lkb);
+
+ if (is_overlap(lkb)) {
+ /* we'll ignore error in cancel/unlock reply */
+ queue_cast_overlap(r, lkb);
+ unhold_lkb(lkb); /* undoes create_lkb() */
+ } else
+ _request_lock(r, lkb);
break;
default:
- log_error(ls, "receive_request_reply error %d", error);
+ log_error(ls, "receive_request_reply %x error %d",
+ lkb->lkb_id, result);
}
+ if (is_overlap_unlock(lkb) && (result == 0 || result == -EINPROGRESS)) {
+ log_debug(ls, "receive_request_reply %x result %d unlock",
+ lkb->lkb_id, result);
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
+ send_unlock(r, lkb);
+ } else if (is_overlap_cancel(lkb) && (result == -EINPROGRESS)) {
+ log_debug(ls, "receive_request_reply %x cancel", lkb->lkb_id);
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
+ send_cancel(r, lkb);
+ } else {
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
+ }
+ out:
unlock_rsb(r);
put_rsb(r);
- out:
dlm_put_lkb(lkb);
}
static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
struct dlm_message *ms)
{
- int error = ms->m_result;
-
/* this is the value returned from do_convert() on the master */
-
- switch (error) {
+ switch (ms->m_result) {
case -EAGAIN:
/* convert would block (be queued) on remote master */
queue_cast(r, lkb, -EAGAIN);
case -EINPROGRESS:
/* convert was queued on remote master */
+ receive_flags_reply(lkb, ms);
+ if (is_demoted(lkb))
+ munge_demoted(lkb, ms);
del_lkb(r, lkb);
add_lkb(r, lkb, DLM_LKSTS_CONVERT);
break;
case 0:
/* convert was granted on remote master */
receive_flags_reply(lkb, ms);
+ if (is_demoted(lkb))
+ munge_demoted(lkb, ms);
grant_lock_pc(r, lkb, ms);
queue_cast(r, lkb, 0);
break;
default:
- log_error(r->res_ls, "receive_convert_reply error %d", error);
+ log_error(r->res_ls, "receive_convert_reply %x error %d",
+ lkb->lkb_id, ms->m_result);
}
}
static void _receive_convert_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
{
struct dlm_rsb *r = lkb->lkb_resource;
+ int error;
hold_rsb(r);
lock_rsb(r);
- __receive_convert_reply(r, lkb, ms);
+ /* stub reply can happen with waiters_mutex held */
+ error = remove_from_waiters_ms(lkb, ms);
+ if (error)
+ goto out;
+ __receive_convert_reply(r, lkb, ms);
+ out:
unlock_rsb(r);
put_rsb(r);
}
}
DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
- error = remove_from_waiters(lkb);
- if (error) {
- log_error(ls, "receive_convert_reply not on waiters");
- goto out;
- }
-
_receive_convert_reply(lkb, ms);
- out:
dlm_put_lkb(lkb);
}
static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
{
struct dlm_rsb *r = lkb->lkb_resource;
- int error = ms->m_result;
+ int error;
hold_rsb(r);
lock_rsb(r);
+ /* stub reply can happen with waiters_mutex held */
+ error = remove_from_waiters_ms(lkb, ms);
+ if (error)
+ goto out;
+
/* this is the value returned from do_unlock() on the master */
- switch (error) {
+ switch (ms->m_result) {
case -DLM_EUNLOCK:
receive_flags_reply(lkb, ms);
remove_lock_pc(r, lkb);
queue_cast(r, lkb, -DLM_EUNLOCK);
break;
+ case -ENOENT:
+ break;
default:
- log_error(r->res_ls, "receive_unlock_reply error %d", error);
+ log_error(r->res_ls, "receive_unlock_reply %x error %d",
+ lkb->lkb_id, ms->m_result);
}
-
+ out:
unlock_rsb(r);
put_rsb(r);
}
}
DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
- error = remove_from_waiters(lkb);
- if (error) {
- log_error(ls, "receive_unlock_reply not on waiters");
- goto out;
- }
-
_receive_unlock_reply(lkb, ms);
- out:
dlm_put_lkb(lkb);
}
static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
{
struct dlm_rsb *r = lkb->lkb_resource;
- int error = ms->m_result;
+ int error;
hold_rsb(r);
lock_rsb(r);
+ /* stub reply can happen with waiters_mutex held */
+ error = remove_from_waiters_ms(lkb, ms);
+ if (error)
+ goto out;
+
/* this is the value returned from do_cancel() on the master */
- switch (error) {
+ switch (ms->m_result) {
case -DLM_ECANCEL:
receive_flags_reply(lkb, ms);
revert_lock_pc(r, lkb);
- queue_cast(r, lkb, -DLM_ECANCEL);
+ if (ms->m_result)
+ queue_cast(r, lkb, -DLM_ECANCEL);
+ break;
+ case 0:
break;
default:
- log_error(r->res_ls, "receive_cancel_reply error %d", error);
+ log_error(r->res_ls, "receive_cancel_reply %x error %d",
+ lkb->lkb_id, ms->m_result);
}
-
+ out:
unlock_rsb(r);
put_rsb(r);
}
}
DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
- error = remove_from_waiters(lkb);
- if (error) {
- log_error(ls, "receive_cancel_reply not on waiters");
- goto out;
- }
-
_receive_cancel_reply(lkb, ms);
- out:
dlm_put_lkb(lkb);
}
return;
}
- error = remove_from_waiters(lkb);
- if (error) {
- log_error(ls, "receive_lookup_reply not on waiters");
- goto out;
- }
-
- /* this is the value returned by dlm_dir_lookup on dir node
+ /* ms->m_result is the value returned by dlm_dir_lookup on dir node
FIXME: will a non-zero error ever be returned? */
- error = ms->m_result;
r = lkb->lkb_resource;
hold_rsb(r);
lock_rsb(r);
+ error = remove_from_waiters(lkb, DLM_MSG_LOOKUP_REPLY);
+ if (error)
+ goto out;
+
ret_nodeid = ms->m_nodeid;
if (ret_nodeid == dlm_our_nodeid()) {
r->res_nodeid = 0;
r->res_nodeid = ret_nodeid;
}
+ if (is_overlap(lkb)) {
+ log_debug(ls, "receive_lookup_reply %x unlock %x",
+ lkb->lkb_id, lkb->lkb_flags);
+ queue_cast_overlap(r, lkb);
+ unhold_lkb(lkb); /* undoes create_lkb() */
+ goto out_list;
+ }
+
_request_lock(r, lkb);
+ out_list:
if (!ret_nodeid)
process_lookup_list(r);
-
+ out:
unlock_rsb(r);
put_rsb(r);
- out:
dlm_put_lkb(lkb);
}
receive_lookup_reply(ls, ms);
break;
+ /* other messages */
+
+ case DLM_MSG_PURGE:
+ receive_purge(ls, ms);
+ break;
+
default:
log_error(ls, "unknown message type %d", ms->m_type);
}
{
if (middle_conversion(lkb)) {
hold_lkb(lkb);
+ 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;
- _remove_from_waiters(lkb);
_receive_convert_reply(lkb, &ls->ls_stub_ms);
/* Same special case as in receive_rcom_lock_args() */
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_flags = lkb->lkb_flags;
- _remove_from_waiters(lkb);
_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_flags = lkb->lkb_flags;
- _remove_from_waiters(lkb);
_receive_cancel_reply(lkb, &ls->ls_stub_ms);
dlm_put_lkb(lkb);
break;
mutex_unlock(&ls->ls_waiters_mutex);
}
-static int remove_resend_waiter(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
+static struct dlm_lkb *find_resend_waiter(struct dlm_ls *ls)
{
struct dlm_lkb *lkb;
- int rv = 0;
+ int found = 0;
mutex_lock(&ls->ls_waiters_mutex);
list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
if (lkb->lkb_flags & DLM_IFL_RESEND) {
- rv = lkb->lkb_wait_type;
- _remove_from_waiters(lkb);
- lkb->lkb_flags &= ~DLM_IFL_RESEND;
+ hold_lkb(lkb);
+ found = 1;
break;
}
}
mutex_unlock(&ls->ls_waiters_mutex);
- if (!rv)
+ if (!found)
lkb = NULL;
- *lkb_ret = lkb;
- return rv;
+ return lkb;
}
/* Deal with lookups and lkb's marked RESEND from _pre. We may now be the
master or dir-node for r. Processing the lkb may result in it being placed
back on waiters. */
+/* We do this after normal locking has been enabled and any saved messages
+ (in requestqueue) have been processed. We should be confident that at
+ this point we won't get or process a reply to any of these waiting
+ operations. But, new ops may be coming in on the rsbs/locks here from
+ userspace or remotely. */
+
+/* there may have been an overlap unlock/cancel prior to recovery or after
+ recovery. if before, the lkb may still have a pos wait_count; if after, the
+ overlap flag would just have been set and nothing new sent. we can be
+ confident here than any replies to either the initial op or overlap ops
+ prior to recovery have been received. */
+
int dlm_recover_waiters_post(struct dlm_ls *ls)
{
struct dlm_lkb *lkb;
struct dlm_rsb *r;
- int error = 0, mstype;
+ int error = 0, mstype, err, oc, ou;
while (1) {
if (dlm_locking_stopped(ls)) {
break;
}
- mstype = remove_resend_waiter(ls, &lkb);
- if (!mstype)
+ lkb = find_resend_waiter(ls);
+ if (!lkb)
break;
r = lkb->lkb_resource;
+ hold_rsb(r);
+ lock_rsb(r);
+
+ mstype = lkb->lkb_wait_type;
+ oc = is_overlap_cancel(lkb);
+ ou = is_overlap_unlock(lkb);
+ err = 0;
log_debug(ls, "recover_waiters_post %x type %d flags %x %s",
lkb->lkb_id, mstype, lkb->lkb_flags, r->res_name);
- switch (mstype) {
-
- case DLM_MSG_LOOKUP:
- hold_rsb(r);
- lock_rsb(r);
- _request_lock(r, lkb);
- if (is_master(r))
- confirm_master(r, 0);
- unlock_rsb(r);
- put_rsb(r);
- break;
-
- case DLM_MSG_REQUEST:
- hold_rsb(r);
- lock_rsb(r);
- _request_lock(r, lkb);
- if (is_master(r))
- confirm_master(r, 0);
- unlock_rsb(r);
- put_rsb(r);
- break;
-
- case DLM_MSG_CONVERT:
- hold_rsb(r);
- lock_rsb(r);
- _convert_lock(r, lkb);
- unlock_rsb(r);
- put_rsb(r);
- break;
-
- default:
- log_error(ls, "recover_waiters_post type %d", mstype);
+ /* At this point we assume that we won't get a reply to any
+ previous op or overlap op on this lock. First, do a big
+ remove_from_waiters() for all previous ops. */
+
+ lkb->lkb_flags &= ~DLM_IFL_RESEND;
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
+ lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
+ lkb->lkb_wait_type = 0;
+ lkb->lkb_wait_count = 0;
+ mutex_lock(&ls->ls_waiters_mutex);
+ list_del_init(&lkb->lkb_wait_reply);
+ mutex_unlock(&ls->ls_waiters_mutex);
+ unhold_lkb(lkb); /* for waiters list */
+
+ if (oc || ou) {
+ /* do an unlock or cancel instead of resending */
+ switch (mstype) {
+ case DLM_MSG_LOOKUP:
+ case DLM_MSG_REQUEST:
+ queue_cast(r, lkb, ou ? -DLM_EUNLOCK :
+ -DLM_ECANCEL);
+ unhold_lkb(lkb); /* undoes create_lkb() */
+ break;
+ case DLM_MSG_CONVERT:
+ if (oc) {
+ queue_cast(r, lkb, -DLM_ECANCEL);
+ } else {
+ lkb->lkb_exflags |= DLM_LKF_FORCEUNLOCK;
+ _unlock_lock(r, lkb);
+ }
+ break;
+ default:
+ err = 1;
+ }
+ } else {
+ switch (mstype) {
+ case DLM_MSG_LOOKUP:
+ case DLM_MSG_REQUEST:
+ _request_lock(r, lkb);
+ if (is_master(r))
+ confirm_master(r, 0);
+ break;
+ case DLM_MSG_CONVERT:
+ _convert_lock(r, lkb);
+ break;
+ default:
+ err = 1;
+ }
}
+
+ if (err)
+ log_error(ls, "recover_waiters_post %x %d %x %d %d",
+ lkb->lkb_id, mstype, lkb->lkb_flags, oc, ou);
+ unlock_rsb(r);
+ put_rsb(r);
+ dlm_put_lkb(lkb);
}
return error;
/* add this new lkb to the per-process list of locks */
spin_lock(&ua->proc->locks_spin);
- kref_get(&lkb->lkb_ref);
+ hold_lkb(lkb);
list_add_tail(&lkb->lkb_ownqueue, &ua->proc->locks);
spin_unlock(&ua->proc->locks_spin);
out:
if (error == -DLM_EUNLOCK)
error = 0;
+ /* from validate_unlock_args() */
+ if (error == -EBUSY && (flags & DLM_LKF_FORCEUNLOCK))
+ error = 0;
if (error)
goto out_put;
dlm_put_lkb(lkb);
out:
unlock_recovery(ls);
+ kfree(ua_tmp);
return error;
}
if (error == -DLM_ECANCEL)
error = 0;
- if (error)
- goto out_put;
-
- /* this lkb was removed from the WAITING queue */
- if (lkb->lkb_grmode == DLM_LOCK_IV) {
- spin_lock(&ua->proc->locks_spin);
- list_move(&lkb->lkb_ownqueue, &ua->proc->unlocking);
- spin_unlock(&ua->proc->locks_spin);
- }
+ /* from validate_unlock_args() */
+ if (error == -EBUSY)
+ error = 0;
out_put:
dlm_put_lkb(lkb);
out:
unlock_recovery(ls);
+ kfree(ua_tmp);
return error;
}
+/* lkb's that are removed from the waiters list by revert are just left on the
+ orphans list with the granted orphan locks, to be freed by purge */
+
static int orphan_proc_lock(struct dlm_ls *ls, struct dlm_lkb *lkb)
{
struct dlm_user_args *ua = (struct dlm_user_args *)lkb->lkb_astparam;
+ struct dlm_args args;
+ int error;
- if (ua->lksb.sb_lvbptr)
- kfree(ua->lksb.sb_lvbptr);
- kfree(ua);
- lkb->lkb_astparam = (long)NULL;
+ hold_lkb(lkb);
+ mutex_lock(&ls->ls_orphans_mutex);
+ list_add_tail(&lkb->lkb_ownqueue, &ls->ls_orphans);
+ mutex_unlock(&ls->ls_orphans_mutex);
- /* TODO: propogate to master if needed */
- return 0;
+ set_unlock_args(0, ua, &args);
+
+ error = cancel_lock(ls, lkb, &args);
+ if (error == -DLM_ECANCEL)
+ error = 0;
+ return error;
}
/* The force flag allows the unlock to go ahead even if the lkb isn't granted.
struct dlm_args args;
int error;
- /* FIXME: we need to handle the case where the lkb is in limbo
- while the rsb is being looked up, currently we assert in
- _unlock_lock/is_remote because rsb nodeid is -1. */
-
set_unlock_args(DLM_LKF_FORCEUNLOCK, ua, &args);
error = unlock_lock(ls, lkb, &args);
return error;
}
+/* We have to release clear_proc_locks mutex before calling unlock_proc_lock()
+ (which does lock_rsb) due to deadlock with receiving a message that does
+ lock_rsb followed by dlm_user_add_ast() */
+
+static struct dlm_lkb *del_proc_lock(struct dlm_ls *ls,
+ struct dlm_user_proc *proc)
+{
+ struct dlm_lkb *lkb = NULL;
+
+ mutex_lock(&ls->ls_clear_proc_locks);
+ if (list_empty(&proc->locks))
+ goto out;
+
+ lkb = list_entry(proc->locks.next, struct dlm_lkb, lkb_ownqueue);
+ list_del_init(&lkb->lkb_ownqueue);
+
+ if (lkb->lkb_exflags & DLM_LKF_PERSISTENT)
+ lkb->lkb_flags |= DLM_IFL_ORPHAN;
+ else
+ lkb->lkb_flags |= DLM_IFL_DEAD;
+ out:
+ mutex_unlock(&ls->ls_clear_proc_locks);
+ return lkb;
+}
+
/* The ls_clear_proc_locks mutex protects against dlm_user_add_asts() which
1) references lkb->ua which we free here and 2) adds lkbs to proc->asts,
which we clear here. */
struct dlm_lkb *lkb, *safe;
lock_recovery(ls);
- mutex_lock(&ls->ls_clear_proc_locks);
- list_for_each_entry_safe(lkb, safe, &proc->locks, lkb_ownqueue) {
- list_del_init(&lkb->lkb_ownqueue);
-
- if (lkb->lkb_exflags & DLM_LKF_PERSISTENT) {
- lkb->lkb_flags |= DLM_IFL_ORPHAN;
+ while (1) {
+ lkb = del_proc_lock(ls, proc);
+ if (!lkb)
+ break;
+ if (lkb->lkb_exflags & DLM_LKF_PERSISTENT)
orphan_proc_lock(ls, lkb);
- } else {
- lkb->lkb_flags |= DLM_IFL_DEAD;
+ else
unlock_proc_lock(ls, lkb);
- }
/* this removes the reference for the proc->locks list
added by dlm_user_request, it may result in the lkb
dlm_put_lkb(lkb);
}
+ mutex_lock(&ls->ls_clear_proc_locks);
+
/* in-progress unlocks */
list_for_each_entry_safe(lkb, safe, &proc->unlocking, lkb_ownqueue) {
list_del_init(&lkb->lkb_ownqueue);
unlock_recovery(ls);
}
+static void purge_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
+{
+ struct dlm_lkb *lkb, *safe;
+
+ while (1) {
+ lkb = NULL;
+ spin_lock(&proc->locks_spin);
+ if (!list_empty(&proc->locks)) {
+ lkb = list_entry(proc->locks.next, struct dlm_lkb,
+ lkb_ownqueue);
+ list_del_init(&lkb->lkb_ownqueue);
+ }
+ spin_unlock(&proc->locks_spin);
+
+ if (!lkb)
+ break;
+
+ lkb->lkb_flags |= DLM_IFL_DEAD;
+ unlock_proc_lock(ls, lkb);
+ dlm_put_lkb(lkb); /* ref from proc->locks list */
+ }
+
+ spin_lock(&proc->locks_spin);
+ list_for_each_entry_safe(lkb, safe, &proc->unlocking, lkb_ownqueue) {
+ list_del_init(&lkb->lkb_ownqueue);
+ lkb->lkb_flags |= DLM_IFL_DEAD;
+ dlm_put_lkb(lkb);
+ }
+ spin_unlock(&proc->locks_spin);
+
+ spin_lock(&proc->asts_spin);
+ list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_astqueue) {
+ list_del(&lkb->lkb_astqueue);
+ dlm_put_lkb(lkb);
+ }
+ spin_unlock(&proc->asts_spin);
+}
+
+/* pid of 0 means purge all orphans */
+
+static void do_purge(struct dlm_ls *ls, int nodeid, int pid)
+{
+ struct dlm_lkb *lkb, *safe;
+
+ mutex_lock(&ls->ls_orphans_mutex);
+ list_for_each_entry_safe(lkb, safe, &ls->ls_orphans, lkb_ownqueue) {
+ if (pid && lkb->lkb_ownpid != pid)
+ continue;
+ unlock_proc_lock(ls, lkb);
+ list_del_init(&lkb->lkb_ownqueue);
+ dlm_put_lkb(lkb);
+ }
+ mutex_unlock(&ls->ls_orphans_mutex);
+}
+
+static int send_purge(struct dlm_ls *ls, int nodeid, int pid)
+{
+ struct dlm_message *ms;
+ struct dlm_mhandle *mh;
+ int error;
+
+ error = _create_message(ls, sizeof(struct dlm_message), nodeid,
+ DLM_MSG_PURGE, &ms, &mh);
+ if (error)
+ return error;
+ ms->m_nodeid = nodeid;
+ ms->m_pid = pid;
+
+ return send_message(mh, ms);
+}
+
+int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,
+ int nodeid, int pid)
+{
+ int error = 0;
+
+ if (nodeid != dlm_our_nodeid()) {
+ error = send_purge(ls, nodeid, pid);
+ } else {
+ lock_recovery(ls);
+ if (pid == current->pid)
+ purge_proc_locks(ls, proc);
+ else
+ do_purge(ls, nodeid, pid);
+ unlock_recovery(ls);
+ }
+ return error;
+}
+
uint32_t flags, uint32_t lkid, char *lvb_in);
int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
uint32_t flags, uint32_t lkid);
+int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,
+ int nodeid, int pid);
void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc);
static inline int is_master(struct dlm_rsb *r)
*******************************************************************************
**
** 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
INIT_LIST_HEAD(&ls->ls_waiters);
mutex_init(&ls->ls_waiters_mutex);
+ INIT_LIST_HEAD(&ls->ls_orphans);
+ mutex_init(&ls->ls_orphans_mutex);
INIT_LIST_HEAD(&ls->ls_nodes);
INIT_LIST_HEAD(&ls->ls_nodes_gone);
+++ /dev/null
-/******************************************************************************
-*******************************************************************************
-**
-** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2006 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.
-**
-*******************************************************************************
-******************************************************************************/
-
-/*
- * lowcomms.c
- *
- * This is the "low-level" comms layer.
- *
- * It is responsible for sending/receiving messages
- * from other nodes in the cluster.
- *
- * Cluster nodes are referred to by their nodeids. nodeids are
- * simply 32 bit numbers to the locking module - if they need to
- * be expanded for the cluster infrastructure then that is it's
- * responsibility. It is this layer's
- * responsibility to resolve these into IP address or
- * whatever it needs for inter-node communication.
- *
- * The comms level is two kernel threads that deal mainly with
- * the receiving of messages from other nodes and passing them
- * up to the mid-level comms layer (which understands the
- * message format) for execution by the locking core, and
- * a send thread which does all the setting up of connections
- * to remote nodes and the sending of data. Threads are not allowed
- * to send their own data because it may cause them to wait in times
- * of high load. Also, this way, the sending thread can collect together
- * messages bound for one node and send them in one block.
- *
- * I don't see any problem with the recv thread executing the locking
- * code on behalf of remote processes as the locking code is
- * short, efficient and never (well, hardly ever) waits.
- *
- */
-
-#include <asm/ioctls.h>
-#include <net/sock.h>
-#include <net/tcp.h>
-#include <net/sctp/user.h>
-#include <linux/pagemap.h>
-#include <linux/socket.h>
-#include <linux/idr.h>
-
-#include "dlm_internal.h"
-#include "lowcomms.h"
-#include "config.h"
-#include "midcomms.h"
-
-static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT];
-static int dlm_local_count;
-static int dlm_local_nodeid;
-
-/* One of these per connected node */
-
-#define NI_INIT_PENDING 1
-#define NI_WRITE_PENDING 2
-
-struct nodeinfo {
- spinlock_t lock;
- sctp_assoc_t assoc_id;
- unsigned long flags;
- struct list_head write_list; /* nodes with pending writes */
- struct list_head writequeue; /* outgoing writequeue_entries */
- spinlock_t writequeue_lock;
- int nodeid;
- struct work_struct swork; /* Send workqueue */
- struct work_struct lwork; /* Locking workqueue */
-};
-
-static DEFINE_IDR(nodeinfo_idr);
-static DECLARE_RWSEM(nodeinfo_lock);
-static int max_nodeid;
-
-struct cbuf {
- unsigned int base;
- unsigned int len;
- unsigned int mask;
-};
-
-/* Just the one of these, now. But this struct keeps
- the connection-specific variables together */
-
-#define CF_READ_PENDING 1
-
-struct connection {
- struct socket *sock;
- unsigned long flags;
- struct page *rx_page;
- atomic_t waiting_requests;
- struct cbuf cb;
- int eagain_flag;
- struct work_struct work; /* Send workqueue */
-};
-
-/* An entry waiting to be sent */
-
-struct writequeue_entry {
- struct list_head list;
- struct page *page;
- int offset;
- int len;
- int end;
- int users;
- struct nodeinfo *ni;
-};
-
-static void cbuf_add(struct cbuf *cb, int n)
-{
- cb->len += n;
-}
-
-static int cbuf_data(struct cbuf *cb)
-{
- return ((cb->base + cb->len) & cb->mask);
-}
-
-static void cbuf_init(struct cbuf *cb, int size)
-{
- cb->base = cb->len = 0;
- cb->mask = size-1;
-}
-
-static void cbuf_eat(struct cbuf *cb, int n)
-{
- cb->len -= n;
- cb->base += n;
- cb->base &= cb->mask;
-}
-
-/* List of nodes which have writes pending */
-static LIST_HEAD(write_nodes);
-static DEFINE_SPINLOCK(write_nodes_lock);
-
-
-/* Maximum number of incoming messages to process before
- * doing a schedule()
- */
-#define MAX_RX_MSG_COUNT 25
-
-/* Work queues */
-static struct workqueue_struct *recv_workqueue;
-static struct workqueue_struct *send_workqueue;
-static struct workqueue_struct *lock_workqueue;
-
-/* The SCTP connection */
-static struct connection sctp_con;
-
-static void process_send_sockets(struct work_struct *work);
-static void process_recv_sockets(struct work_struct *work);
-static void process_lock_request(struct work_struct *work);
-
-static int nodeid_to_addr(int nodeid, struct sockaddr *retaddr)
-{
- struct sockaddr_storage addr;
- int error;
-
- if (!dlm_local_count)
- return -1;
-
- error = dlm_nodeid_to_addr(nodeid, &addr);
- if (error)
- return error;
-
- if (dlm_local_addr[0]->ss_family == AF_INET) {
- struct sockaddr_in *in4 = (struct sockaddr_in *) &addr;
- struct sockaddr_in *ret4 = (struct sockaddr_in *) retaddr;
- ret4->sin_addr.s_addr = in4->sin_addr.s_addr;
- } else {
- struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) &addr;
- struct sockaddr_in6 *ret6 = (struct sockaddr_in6 *) retaddr;
- memcpy(&ret6->sin6_addr, &in6->sin6_addr,
- sizeof(in6->sin6_addr));
- }
-
- return 0;
-}
-
-/* If alloc is 0 here we will not attempt to allocate a new
- nodeinfo struct */
-static struct nodeinfo *nodeid2nodeinfo(int nodeid, gfp_t alloc)
-{
- struct nodeinfo *ni;
- int r;
- int n;
-
- down_read(&nodeinfo_lock);
- ni = idr_find(&nodeinfo_idr, nodeid);
- up_read(&nodeinfo_lock);
-
- if (ni || !alloc)
- return ni;
-
- down_write(&nodeinfo_lock);
-
- ni = idr_find(&nodeinfo_idr, nodeid);
- if (ni)
- goto out_up;
-
- r = idr_pre_get(&nodeinfo_idr, alloc);
- if (!r)
- goto out_up;
-
- ni = kmalloc(sizeof(struct nodeinfo), alloc);
- if (!ni)
- goto out_up;
-
- r = idr_get_new_above(&nodeinfo_idr, ni, nodeid, &n);
- if (r) {
- kfree(ni);
- ni = NULL;
- goto out_up;
- }
- if (n != nodeid) {
- idr_remove(&nodeinfo_idr, n);
- kfree(ni);
- ni = NULL;
- goto out_up;
- }
- memset(ni, 0, sizeof(struct nodeinfo));
- spin_lock_init(&ni->lock);
- INIT_LIST_HEAD(&ni->writequeue);
- spin_lock_init(&ni->writequeue_lock);
- INIT_WORK(&ni->lwork, process_lock_request);
- INIT_WORK(&ni->swork, process_send_sockets);
- ni->nodeid = nodeid;
-
- if (nodeid > max_nodeid)
- max_nodeid = nodeid;
-out_up:
- up_write(&nodeinfo_lock);
-
- return ni;
-}
-
-/* Don't call this too often... */
-static struct nodeinfo *assoc2nodeinfo(sctp_assoc_t assoc)
-{
- int i;
- struct nodeinfo *ni;
-
- for (i=1; i<=max_nodeid; i++) {
- ni = nodeid2nodeinfo(i, 0);
- if (ni && ni->assoc_id == assoc)
- return ni;
- }
- return NULL;
-}
-
-/* Data or notification available on socket */
-static void lowcomms_data_ready(struct sock *sk, int count_unused)
-{
- if (test_and_set_bit(CF_READ_PENDING, &sctp_con.flags))
- queue_work(recv_workqueue, &sctp_con.work);
-}
-
-
-/* Add the port number to an IP6 or 4 sockaddr and return the address length.
- Also padd out the struct with zeros to make comparisons meaningful */
-
-static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port,
- int *addr_len)
-{
- struct sockaddr_in *local4_addr;
- struct sockaddr_in6 *local6_addr;
-
- if (!dlm_local_count)
- return;
-
- if (!port) {
- if (dlm_local_addr[0]->ss_family == AF_INET) {
- local4_addr = (struct sockaddr_in *)dlm_local_addr[0];
- port = be16_to_cpu(local4_addr->sin_port);
- } else {
- local6_addr = (struct sockaddr_in6 *)dlm_local_addr[0];
- port = be16_to_cpu(local6_addr->sin6_port);
- }
- }
-
- saddr->ss_family = dlm_local_addr[0]->ss_family;
- if (dlm_local_addr[0]->ss_family == AF_INET) {
- struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr;
- in4_addr->sin_port = cpu_to_be16(port);
- memset(&in4_addr->sin_zero, 0, sizeof(in4_addr->sin_zero));
- memset(in4_addr+1, 0, sizeof(struct sockaddr_storage) -
- sizeof(struct sockaddr_in));
- *addr_len = sizeof(struct sockaddr_in);
- } else {
- struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)saddr;
- in6_addr->sin6_port = cpu_to_be16(port);
- memset(in6_addr+1, 0, sizeof(struct sockaddr_storage) -
- sizeof(struct sockaddr_in6));
- *addr_len = sizeof(struct sockaddr_in6);
- }
-}
-
-/* Close the connection and tidy up */
-static void close_connection(void)
-{
- if (sctp_con.sock) {
- sock_release(sctp_con.sock);
- sctp_con.sock = NULL;
- }
-
- if (sctp_con.rx_page) {
- __free_page(sctp_con.rx_page);
- sctp_con.rx_page = NULL;
- }
-}
-
-/* We only send shutdown messages to nodes that are not part of the cluster */
-static void send_shutdown(sctp_assoc_t associd)
-{
- static char outcmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
- struct msghdr outmessage;
- struct cmsghdr *cmsg;
- struct sctp_sndrcvinfo *sinfo;
- int ret;
-
- outmessage.msg_name = NULL;
- outmessage.msg_namelen = 0;
- outmessage.msg_control = outcmsg;
- outmessage.msg_controllen = sizeof(outcmsg);
- outmessage.msg_flags = MSG_EOR;
-
- cmsg = CMSG_FIRSTHDR(&outmessage);
- cmsg->cmsg_level = IPPROTO_SCTP;
- cmsg->cmsg_type = SCTP_SNDRCV;
- cmsg->cmsg_len = CMSG_LEN(sizeof(struct sctp_sndrcvinfo));
- outmessage.msg_controllen = cmsg->cmsg_len;
- sinfo = CMSG_DATA(cmsg);
- memset(sinfo, 0x00, sizeof(struct sctp_sndrcvinfo));
-
- sinfo->sinfo_flags |= MSG_EOF;
- sinfo->sinfo_assoc_id = associd;
-
- ret = kernel_sendmsg(sctp_con.sock, &outmessage, NULL, 0, 0);
-
- if (ret != 0)
- log_print("send EOF to node failed: %d", ret);
-}
-
-
-/* INIT failed but we don't know which node...
- restart INIT on all pending nodes */
-static void init_failed(void)
-{
- int i;
- struct nodeinfo *ni;
-
- for (i=1; i<=max_nodeid; i++) {
- ni = nodeid2nodeinfo(i, 0);
- if (!ni)
- continue;
-
- if (test_and_clear_bit(NI_INIT_PENDING, &ni->flags)) {
- ni->assoc_id = 0;
- if (!test_and_set_bit(NI_WRITE_PENDING, &ni->flags)) {
- spin_lock_bh(&write_nodes_lock);
- list_add_tail(&ni->write_list, &write_nodes);
- spin_unlock_bh(&write_nodes_lock);
- queue_work(send_workqueue, &ni->swork);
- }
- }
- }
-}
-
-/* Something happened to an association */
-static void process_sctp_notification(struct msghdr *msg, char *buf)
-{
- union sctp_notification *sn = (union sctp_notification *)buf;
-
- if (sn->sn_header.sn_type == SCTP_ASSOC_CHANGE) {
- switch (sn->sn_assoc_change.sac_state) {
-
- case SCTP_COMM_UP:
- case SCTP_RESTART:
- {
- /* Check that the new node is in the lockspace */
- struct sctp_prim prim;
- mm_segment_t fs;
- int nodeid;
- int prim_len, ret;
- int addr_len;
- struct nodeinfo *ni;
-
- /* This seems to happen when we received a connection
- * too early... or something... anyway, it happens but
- * we always seem to get a real message too, see
- * receive_from_sock */
-
- if ((int)sn->sn_assoc_change.sac_assoc_id <= 0) {
- log_print("COMM_UP for invalid assoc ID %d",
- (int)sn->sn_assoc_change.sac_assoc_id);
- init_failed();
- return;
- }
- memset(&prim, 0, sizeof(struct sctp_prim));
- prim_len = sizeof(struct sctp_prim);
- prim.ssp_assoc_id = sn->sn_assoc_change.sac_assoc_id;
-
- fs = get_fs();
- set_fs(get_ds());
- ret = sctp_con.sock->ops->getsockopt(sctp_con.sock,
- IPPROTO_SCTP,
- SCTP_PRIMARY_ADDR,
- (char*)&prim,
- &prim_len);
- set_fs(fs);
- if (ret < 0) {
- struct nodeinfo *ni;
-
- log_print("getsockopt/sctp_primary_addr on "
- "new assoc %d failed : %d",
- (int)sn->sn_assoc_change.sac_assoc_id,
- ret);
-
- /* Retry INIT later */
- ni = assoc2nodeinfo(sn->sn_assoc_change.sac_assoc_id);
- if (ni)
- clear_bit(NI_INIT_PENDING, &ni->flags);
- return;
- }
- make_sockaddr(&prim.ssp_addr, 0, &addr_len);
- if (dlm_addr_to_nodeid(&prim.ssp_addr, &nodeid)) {
- log_print("reject connect from unknown addr");
- send_shutdown(prim.ssp_assoc_id);
- return;
- }
-
- ni = nodeid2nodeinfo(nodeid, GFP_KERNEL);
- if (!ni)
- return;
-
- /* Save the assoc ID */
- ni->assoc_id = sn->sn_assoc_change.sac_assoc_id;
-
- log_print("got new/restarted association %d nodeid %d",
- (int)sn->sn_assoc_change.sac_assoc_id, nodeid);
-
- /* Send any pending writes */
- clear_bit(NI_INIT_PENDING, &ni->flags);
- if (!test_and_set_bit(NI_WRITE_PENDING, &ni->flags)) {
- spin_lock_bh(&write_nodes_lock);
- list_add_tail(&ni->write_list, &write_nodes);
- spin_unlock_bh(&write_nodes_lock);
- queue_work(send_workqueue, &ni->swork);
- }
- }
- break;
-
- case SCTP_COMM_LOST:
- case SCTP_SHUTDOWN_COMP:
- {
- struct nodeinfo *ni;
-
- ni = assoc2nodeinfo(sn->sn_assoc_change.sac_assoc_id);
- if (ni) {
- spin_lock(&ni->lock);
- ni->assoc_id = 0;
- spin_unlock(&ni->lock);
- }
- }
- break;
-
- /* We don't know which INIT failed, so clear the PENDING flags
- * on them all. if assoc_id is zero then it will then try
- * again */
-
- case SCTP_CANT_STR_ASSOC:
- {
- log_print("Can't start SCTP association - retrying");
- init_failed();
- }
- break;
-
- default:
- log_print("unexpected SCTP assoc change id=%d state=%d",
- (int)sn->sn_assoc_change.sac_assoc_id,
- sn->sn_assoc_change.sac_state);
- }
- }
-}
-
-/* Data received from remote end */
-static int receive_from_sock(void)
-{
- int ret = 0;
- struct msghdr msg;
- struct kvec iov[2];
- unsigned len;
- int r;
- struct sctp_sndrcvinfo *sinfo;
- struct cmsghdr *cmsg;
- struct nodeinfo *ni;
-
- /* These two are marginally too big for stack allocation, but this
- * function is (currently) only called by dlm_recvd so static should be
- * OK.
- */
- static struct sockaddr_storage msgname;
- static char incmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
-
- if (sctp_con.sock == NULL)
- goto out;
-
- if (sctp_con.rx_page == NULL) {
- /*
- * This doesn't need to be atomic, but I think it should
- * improve performance if it is.
- */
- sctp_con.rx_page = alloc_page(GFP_ATOMIC);
- if (sctp_con.rx_page == NULL)
- goto out_resched;
- cbuf_init(&sctp_con.cb, PAGE_CACHE_SIZE);
- }
-
- memset(&incmsg, 0, sizeof(incmsg));
- memset(&msgname, 0, sizeof(msgname));
-
- msg.msg_name = &msgname;
- msg.msg_namelen = sizeof(msgname);
- msg.msg_flags = 0;
- msg.msg_control = incmsg;
- msg.msg_controllen = sizeof(incmsg);
- msg.msg_iovlen = 1;
-
- /* I don't see why this circular buffer stuff is necessary for SCTP
- * which is a packet-based protocol, but the whole thing breaks under
- * load without it! The overhead is minimal (and is in the TCP lowcomms
- * anyway, of course) so I'll leave it in until I can figure out what's
- * really happening.
- */
-
- /*
- * iov[0] is the bit of the circular buffer between the current end
- * point (cb.base + cb.len) and the end of the buffer.
- */
- iov[0].iov_len = sctp_con.cb.base - cbuf_data(&sctp_con.cb);
- iov[0].iov_base = page_address(sctp_con.rx_page) +
- cbuf_data(&sctp_con.cb);
- iov[1].iov_len = 0;
-
- /*
- * iov[1] is the bit of the circular buffer between the start of the
- * buffer and the start of the currently used section (cb.base)
- */
- if (cbuf_data(&sctp_con.cb) >= sctp_con.cb.base) {
- iov[0].iov_len = PAGE_CACHE_SIZE - cbuf_data(&sctp_con.cb);
- iov[1].iov_len = sctp_con.cb.base;
- iov[1].iov_base = page_address(sctp_con.rx_page);
- msg.msg_iovlen = 2;
- }
- len = iov[0].iov_len + iov[1].iov_len;
-
- r = ret = kernel_recvmsg(sctp_con.sock, &msg, iov, msg.msg_iovlen, len,
- MSG_NOSIGNAL | MSG_DONTWAIT);
- if (ret <= 0)
- goto out_close;
-
- msg.msg_control = incmsg;
- msg.msg_controllen = sizeof(incmsg);
- cmsg = CMSG_FIRSTHDR(&msg);
- sinfo = CMSG_DATA(cmsg);
-
- if (msg.msg_flags & MSG_NOTIFICATION) {
- process_sctp_notification(&msg, page_address(sctp_con.rx_page));
- return 0;
- }
-
- /* Is this a new association ? */
- ni = nodeid2nodeinfo(le32_to_cpu(sinfo->sinfo_ppid), GFP_KERNEL);
- if (ni) {
- ni->assoc_id = sinfo->sinfo_assoc_id;
- if (test_and_clear_bit(NI_INIT_PENDING, &ni->flags)) {
-
- if (!test_and_set_bit(NI_WRITE_PENDING, &ni->flags)) {
- spin_lock_bh(&write_nodes_lock);
- list_add_tail(&ni->write_list, &write_nodes);
- spin_unlock_bh(&write_nodes_lock);
- queue_work(send_workqueue, &ni->swork);
- }
- }
- }
-
- /* INIT sends a message with length of 1 - ignore it */
- if (r == 1)
- return 0;
-
- cbuf_add(&sctp_con.cb, ret);
- // PJC: TODO: Add to node's workqueue....can we ??
- ret = dlm_process_incoming_buffer(cpu_to_le32(sinfo->sinfo_ppid),
- page_address(sctp_con.rx_page),
- sctp_con.cb.base, sctp_con.cb.len,
- PAGE_CACHE_SIZE);
- if (ret < 0)
- goto out_close;
- cbuf_eat(&sctp_con.cb, ret);
-
-out:
- ret = 0;
- goto out_ret;
-
-out_resched:
- lowcomms_data_ready(sctp_con.sock->sk, 0);
- ret = 0;
- cond_resched();
- goto out_ret;
-
-out_close:
- if (ret != -EAGAIN)
- log_print("error reading from sctp socket: %d", ret);
-out_ret:
- return ret;
-}
-
-/* Bind to an IP address. SCTP allows multiple address so it can do multi-homing */
-static int add_bind_addr(struct sockaddr_storage *addr, int addr_len, int num)
-{
- mm_segment_t fs;
- int result = 0;
-
- fs = get_fs();
- set_fs(get_ds());
- if (num == 1)
- result = sctp_con.sock->ops->bind(sctp_con.sock,
- (struct sockaddr *) addr,
- addr_len);
- else
- result = sctp_con.sock->ops->setsockopt(sctp_con.sock, SOL_SCTP,
- SCTP_SOCKOPT_BINDX_ADD,
- (char *)addr, addr_len);
- set_fs(fs);
-
- if (result < 0)
- log_print("Can't bind to port %d addr number %d",
- dlm_config.ci_tcp_port, num);
-
- return result;
-}
-
-static void init_local(void)
-{
- struct sockaddr_storage sas, *addr;
- int i;
-
- dlm_local_nodeid = dlm_our_nodeid();
-
- for (i = 0; i < DLM_MAX_ADDR_COUNT - 1; i++) {
- if (dlm_our_addr(&sas, i))
- break;
-
- addr = kmalloc(sizeof(*addr), GFP_KERNEL);
- if (!addr)
- break;
- memcpy(addr, &sas, sizeof(*addr));
- dlm_local_addr[dlm_local_count++] = addr;
- }
-}
-
-/* Initialise SCTP socket and bind to all interfaces */
-static int init_sock(void)
-{
- mm_segment_t fs;
- struct socket *sock = NULL;
- struct sockaddr_storage localaddr;
- struct sctp_event_subscribe subscribe;
- int result = -EINVAL, num = 1, i, addr_len;
-
- if (!dlm_local_count) {
- init_local();
- if (!dlm_local_count) {
- log_print("no local IP address has been set");
- goto out;
- }
- }
-
- result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_SEQPACKET,
- IPPROTO_SCTP, &sock);
- if (result < 0) {
- log_print("Can't create comms socket, check SCTP is loaded");
- goto out;
- }
-
- /* Listen for events */
- memset(&subscribe, 0, sizeof(subscribe));
- subscribe.sctp_data_io_event = 1;
- subscribe.sctp_association_event = 1;
- subscribe.sctp_send_failure_event = 1;
- subscribe.sctp_shutdown_event = 1;
- subscribe.sctp_partial_delivery_event = 1;
-
- fs = get_fs();
- set_fs(get_ds());
- result = sock->ops->setsockopt(sock, SOL_SCTP, SCTP_EVENTS,
- (char *)&subscribe, sizeof(subscribe));
- set_fs(fs);
-
- if (result < 0) {
- log_print("Failed to set SCTP_EVENTS on socket: result=%d",
- result);
- goto create_delsock;
- }
-
- /* Init con struct */
- sock->sk->sk_user_data = &sctp_con;
- sctp_con.sock = sock;
- sctp_con.sock->sk->sk_data_ready = lowcomms_data_ready;
-
- /* Bind to all interfaces. */
- for (i = 0; i < dlm_local_count; i++) {
- memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr));
- make_sockaddr(&localaddr, dlm_config.ci_tcp_port, &addr_len);
-
- result = add_bind_addr(&localaddr, addr_len, num);
- if (result)
- goto create_delsock;
- ++num;
- }
-
- result = sock->ops->listen(sock, 5);
- if (result < 0) {
- log_print("Can't set socket listening");
- goto create_delsock;
- }
-
- return 0;
-
-create_delsock:
- sock_release(sock);
- sctp_con.sock = NULL;
-out:
- return result;
-}
-
-
-static struct writequeue_entry *new_writequeue_entry(gfp_t allocation)
-{
- struct writequeue_entry *entry;
-
- entry = kmalloc(sizeof(struct writequeue_entry), allocation);
- if (!entry)
- return NULL;
-
- entry->page = alloc_page(allocation);
- if (!entry->page) {
- kfree(entry);
- return NULL;
- }
-
- entry->offset = 0;
- entry->len = 0;
- entry->end = 0;
- entry->users = 0;
-
- return entry;
-}
-
-void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc)
-{
- struct writequeue_entry *e;
- int offset = 0;
- int users = 0;
- struct nodeinfo *ni;
-
- ni = nodeid2nodeinfo(nodeid, allocation);
- if (!ni)
- return NULL;
-
- spin_lock(&ni->writequeue_lock);
- e = list_entry(ni->writequeue.prev, struct writequeue_entry, list);
- if ((&e->list == &ni->writequeue) ||
- (PAGE_CACHE_SIZE - e->end < len)) {
- e = NULL;
- } else {
- offset = e->end;
- e->end += len;
- users = e->users++;
- }
- spin_unlock(&ni->writequeue_lock);
-
- if (e) {
- got_one:
- if (users == 0)
- kmap(e->page);
- *ppc = page_address(e->page) + offset;
- return e;
- }
-
- e = new_writequeue_entry(allocation);
- if (e) {
- spin_lock(&ni->writequeue_lock);
- offset = e->end;
- e->end += len;
- e->ni = ni;
- users = e->users++;
- list_add_tail(&e->list, &ni->writequeue);
- spin_unlock(&ni->writequeue_lock);
- goto got_one;
- }
- return NULL;
-}
-
-void dlm_lowcomms_commit_buffer(void *arg)
-{
- struct writequeue_entry *e = (struct writequeue_entry *) arg;
- int users;
- struct nodeinfo *ni = e->ni;
-
- spin_lock(&ni->writequeue_lock);
- users = --e->users;
- if (users)
- goto out;
- e->len = e->end - e->offset;
- kunmap(e->page);
- spin_unlock(&ni->writequeue_lock);
-
- if (!test_and_set_bit(NI_WRITE_PENDING, &ni->flags)) {
- spin_lock_bh(&write_nodes_lock);
- list_add_tail(&ni->write_list, &write_nodes);
- spin_unlock_bh(&write_nodes_lock);
-
- queue_work(send_workqueue, &ni->swork);
- }
- return;
-
-out:
- spin_unlock(&ni->writequeue_lock);
- return;
-}
-
-static void free_entry(struct writequeue_entry *e)
-{
- __free_page(e->page);
- kfree(e);
-}
-
-/* Initiate an SCTP association. In theory we could just use sendmsg() on
- the first IP address and it should work, but this allows us to set up the
- association before sending any valuable data that we can't afford to lose.
- It also keeps the send path clean as it can now always use the association ID */
-static void initiate_association(int nodeid)
-{
- struct sockaddr_storage rem_addr;
- static char outcmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
- struct msghdr outmessage;
- struct cmsghdr *cmsg;
- struct sctp_sndrcvinfo *sinfo;
- int ret;
- int addrlen;
- char buf[1];
- struct kvec iov[1];
- struct nodeinfo *ni;
-
- log_print("Initiating association with node %d", nodeid);
-
- ni = nodeid2nodeinfo(nodeid, GFP_KERNEL);
- if (!ni)
- return;
-
- if (nodeid_to_addr(nodeid, (struct sockaddr *)&rem_addr)) {
- log_print("no address for nodeid %d", nodeid);
- return;
- }
-
- make_sockaddr(&rem_addr, dlm_config.ci_tcp_port, &addrlen);
-
- outmessage.msg_name = &rem_addr;
- outmessage.msg_namelen = addrlen;
- outmessage.msg_control = outcmsg;
- outmessage.msg_controllen = sizeof(outcmsg);
- outmessage.msg_flags = MSG_EOR;
-
- iov[0].iov_base = buf;
- iov[0].iov_len = 1;
-
- /* Real INIT messages seem to cause trouble. Just send a 1 byte message
- we can afford to lose */
- cmsg = CMSG_FIRSTHDR(&outmessage);
- cmsg->cmsg_level = IPPROTO_SCTP;
- cmsg->cmsg_type = SCTP_SNDRCV;
- cmsg->cmsg_len = CMSG_LEN(sizeof(struct sctp_sndrcvinfo));
- sinfo = CMSG_DATA(cmsg);
- memset(sinfo, 0x00, sizeof(struct sctp_sndrcvinfo));
- sinfo->sinfo_ppid = cpu_to_le32(dlm_local_nodeid);
-
- outmessage.msg_controllen = cmsg->cmsg_len;
- ret = kernel_sendmsg(sctp_con.sock, &outmessage, iov, 1, 1);
- if (ret < 0) {
- log_print("send INIT to node failed: %d", ret);
- /* Try again later */
- clear_bit(NI_INIT_PENDING, &ni->flags);
- }
-}
-
-/* Send a message */
-static void send_to_sock(struct nodeinfo *ni)
-{
- int ret = 0;
- struct writequeue_entry *e;
- int len, offset;
- struct msghdr outmsg;
- static char outcmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
- struct cmsghdr *cmsg;
- struct sctp_sndrcvinfo *sinfo;
- struct kvec iov;
-
- /* See if we need to init an association before we start
- sending precious messages */
- spin_lock(&ni->lock);
- if (!ni->assoc_id && !test_and_set_bit(NI_INIT_PENDING, &ni->flags)) {
- spin_unlock(&ni->lock);
- initiate_association(ni->nodeid);
- return;
- }
- spin_unlock(&ni->lock);
-
- outmsg.msg_name = NULL; /* We use assoc_id */
- outmsg.msg_namelen = 0;
- outmsg.msg_control = outcmsg;
- outmsg.msg_controllen = sizeof(outcmsg);
- outmsg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL | MSG_EOR;
-
- cmsg = CMSG_FIRSTHDR(&outmsg);
- cmsg->cmsg_level = IPPROTO_SCTP;
- cmsg->cmsg_type = SCTP_SNDRCV;
- cmsg->cmsg_len = CMSG_LEN(sizeof(struct sctp_sndrcvinfo));
- sinfo = CMSG_DATA(cmsg);
- memset(sinfo, 0x00, sizeof(struct sctp_sndrcvinfo));
- sinfo->sinfo_ppid = cpu_to_le32(dlm_local_nodeid);
- sinfo->sinfo_assoc_id = ni->assoc_id;
- outmsg.msg_controllen = cmsg->cmsg_len;
-
- spin_lock(&ni->writequeue_lock);
- for (;;) {
- if (list_empty(&ni->writequeue))
- break;
- e = list_entry(ni->writequeue.next, struct writequeue_entry,
- list);
- len = e->len;
- offset = e->offset;
- BUG_ON(len == 0 && e->users == 0);
- spin_unlock(&ni->writequeue_lock);
- kmap(e->page);
-
- ret = 0;
- if (len) {
- iov.iov_base = page_address(e->page)+offset;
- iov.iov_len = len;
-
- ret = kernel_sendmsg(sctp_con.sock, &outmsg, &iov, 1,
- len);
- if (ret == -EAGAIN) {
- sctp_con.eagain_flag = 1;
- goto out;
- } else if (ret < 0)
- goto send_error;
- } else {
- /* Don't starve people filling buffers */
- cond_resched();
- }
-
- spin_lock(&ni->writequeue_lock);
- e->offset += ret;
- e->len -= ret;
-
- if (e->len == 0 && e->users == 0) {
- list_del(&e->list);
- kunmap(e->page);
- free_entry(e);
- continue;
- }
- }
- spin_unlock(&ni->writequeue_lock);
-out:
- return;
-
-send_error:
- log_print("Error sending to node %d %d", ni->nodeid, ret);
- spin_lock(&ni->lock);
- if (!test_and_set_bit(NI_INIT_PENDING, &ni->flags)) {
- ni->assoc_id = 0;
- spin_unlock(&ni->lock);
- initiate_association(ni->nodeid);
- } else
- spin_unlock(&ni->lock);
-
- return;
-}
-
-/* Try to send any messages that are pending */
-static void process_output_queue(void)
-{
- struct list_head *list;
- struct list_head *temp;
-
- spin_lock_bh(&write_nodes_lock);
- list_for_each_safe(list, temp, &write_nodes) {
- struct nodeinfo *ni =
- list_entry(list, struct nodeinfo, write_list);
- clear_bit(NI_WRITE_PENDING, &ni->flags);
- list_del(&ni->write_list);
-
- spin_unlock_bh(&write_nodes_lock);
-
- send_to_sock(ni);
- spin_lock_bh(&write_nodes_lock);
- }
- spin_unlock_bh(&write_nodes_lock);
-}
-
-/* Called after we've had -EAGAIN and been woken up */
-static void refill_write_queue(void)
-{
- int i;
-
- for (i=1; i<=max_nodeid; i++) {
- struct nodeinfo *ni = nodeid2nodeinfo(i, 0);
-
- if (ni) {
- if (!test_and_set_bit(NI_WRITE_PENDING, &ni->flags)) {
- spin_lock_bh(&write_nodes_lock);
- list_add_tail(&ni->write_list, &write_nodes);
- spin_unlock_bh(&write_nodes_lock);
- }
- }
- }
-}
-
-static void clean_one_writequeue(struct nodeinfo *ni)
-{
- struct list_head *list;
- struct list_head *temp;
-
- spin_lock(&ni->writequeue_lock);
- list_for_each_safe(list, temp, &ni->writequeue) {
- struct writequeue_entry *e =
- list_entry(list, struct writequeue_entry, list);
- list_del(&e->list);
- free_entry(e);
- }
- spin_unlock(&ni->writequeue_lock);
-}
-
-static void clean_writequeues(void)
-{
- int i;
-
- for (i=1; i<=max_nodeid; i++) {
- struct nodeinfo *ni = nodeid2nodeinfo(i, 0);
- if (ni)
- clean_one_writequeue(ni);
- }
-}
-
-
-static void dealloc_nodeinfo(void)
-{
- int i;
-
- for (i=1; i<=max_nodeid; i++) {
- struct nodeinfo *ni = nodeid2nodeinfo(i, 0);
- if (ni) {
- idr_remove(&nodeinfo_idr, i);
- kfree(ni);
- }
- }
-}
-
-int dlm_lowcomms_close(int nodeid)
-{
- struct nodeinfo *ni;
-
- ni = nodeid2nodeinfo(nodeid, 0);
- if (!ni)
- return -1;
-
- spin_lock(&ni->lock);
- if (ni->assoc_id) {
- ni->assoc_id = 0;
- /* Don't send shutdown here, sctp will just queue it
- till the node comes back up! */
- }
- spin_unlock(&ni->lock);
-
- clean_one_writequeue(ni);
- clear_bit(NI_INIT_PENDING, &ni->flags);
- return 0;
-}
-
-// PJC: The work queue function for receiving.
-static void process_recv_sockets(struct work_struct *work)
-{
- if (test_and_clear_bit(CF_READ_PENDING, &sctp_con.flags)) {
- int ret;
- int count = 0;
-
- do {
- ret = receive_from_sock();
-
- /* Don't starve out everyone else */
- if (++count >= MAX_RX_MSG_COUNT) {
- cond_resched();
- count = 0;
- }
- } while (!kthread_should_stop() && ret >=0);
- }
- cond_resched();
-}
-
-// PJC: the work queue function for sending
-static void process_send_sockets(struct work_struct *work)
-{
- if (sctp_con.eagain_flag) {
- sctp_con.eagain_flag = 0;
- refill_write_queue();
- }
- process_output_queue();
-}
-
-// PJC: Process lock requests from a particular node.
-// TODO: can we optimise this out on UP ??
-static void process_lock_request(struct work_struct *work)
-{
-}
-
-static void daemons_stop(void)
-{
- destroy_workqueue(recv_workqueue);
- destroy_workqueue(send_workqueue);
- destroy_workqueue(lock_workqueue);
-}
-
-static int daemons_start(void)
-{
- int error;
- recv_workqueue = create_workqueue("dlm_recv");
- error = IS_ERR(recv_workqueue);
- if (error) {
- log_print("can't start dlm_recv %d", error);
- return error;
- }
-
- send_workqueue = create_singlethread_workqueue("dlm_send");
- error = IS_ERR(send_workqueue);
- if (error) {
- log_print("can't start dlm_send %d", error);
- destroy_workqueue(recv_workqueue);
- return error;
- }
-
- lock_workqueue = create_workqueue("dlm_rlock");
- error = IS_ERR(lock_workqueue);
- if (error) {
- log_print("can't start dlm_rlock %d", error);
- destroy_workqueue(send_workqueue);
- destroy_workqueue(recv_workqueue);
- return error;
- }
-
- return 0;
-}
-
-/*
- * This is quite likely to sleep...
- */
-int dlm_lowcomms_start(void)
-{
- int error;
-
- INIT_WORK(&sctp_con.work, process_recv_sockets);
-
- error = init_sock();
- if (error)
- goto fail_sock;
- error = daemons_start();
- if (error)
- goto fail_sock;
- return 0;
-
-fail_sock:
- close_connection();
- return error;
-}
-
-void dlm_lowcomms_stop(void)
-{
- int i;
-
- sctp_con.flags = 0x7;
- daemons_stop();
- clean_writequeues();
- close_connection();
- dealloc_nodeinfo();
- max_nodeid = 0;
-
- dlm_local_count = 0;
- dlm_local_nodeid = 0;
-
- for (i = 0; i < dlm_local_count; i++)
- kfree(dlm_local_addr[i]);
-}
+++ /dev/null
-/******************************************************************************
-*******************************************************************************
-**
-** Copyright (C) Sistina Software, Inc. 1997-2003 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
-** of the GNU General Public License v.2.
-**
-*******************************************************************************
-******************************************************************************/
-
-/*
- * lowcomms.c
- *
- * This is the "low-level" comms layer.
- *
- * It is responsible for sending/receiving messages
- * from other nodes in the cluster.
- *
- * Cluster nodes are referred to by their nodeids. nodeids are
- * simply 32 bit numbers to the locking module - if they need to
- * be expanded for the cluster infrastructure then that is it's
- * responsibility. It is this layer's
- * responsibility to resolve these into IP address or
- * whatever it needs for inter-node communication.
- *
- * The comms level is two kernel threads that deal mainly with
- * the receiving of messages from other nodes and passing them
- * up to the mid-level comms layer (which understands the
- * message format) for execution by the locking core, and
- * a send thread which does all the setting up of connections
- * to remote nodes and the sending of data. Threads are not allowed
- * to send their own data because it may cause them to wait in times
- * of high load. Also, this way, the sending thread can collect together
- * messages bound for one node and send them in one block.
- *
- * I don't see any problem with the recv thread executing the locking
- * code on behalf of remote processes as the locking code is
- * short, efficient and never waits.
- *
- */
-
-
-#include <asm/ioctls.h>
-#include <net/sock.h>
-#include <net/tcp.h>
-#include <linux/pagemap.h>
-
-#include "dlm_internal.h"
-#include "lowcomms.h"
-#include "midcomms.h"
-#include "config.h"
-
-struct cbuf {
- unsigned int base;
- unsigned int len;
- unsigned int mask;
-};
-
-#define NODE_INCREMENT 32
-static void cbuf_add(struct cbuf *cb, int n)
-{
- cb->len += n;
-}
-
-static int cbuf_data(struct cbuf *cb)
-{
- return ((cb->base + cb->len) & cb->mask);
-}
-
-static void cbuf_init(struct cbuf *cb, int size)
-{
- cb->base = cb->len = 0;
- cb->mask = size-1;
-}
-
-static void cbuf_eat(struct cbuf *cb, int n)
-{
- cb->len -= n;
- cb->base += n;
- cb->base &= cb->mask;
-}
-
-static bool cbuf_empty(struct cbuf *cb)
-{
- return cb->len == 0;
-}
-
-/* Maximum number of incoming messages to process before
- doing a cond_resched()
-*/
-#define MAX_RX_MSG_COUNT 25
-
-struct connection {
- struct socket *sock; /* NULL if not connected */
- uint32_t nodeid; /* So we know who we are in the list */
- struct mutex sock_mutex;
- unsigned long flags; /* bit 1,2 = We are on the read/write lists */
-#define CF_READ_PENDING 1
-#define CF_WRITE_PENDING 2
-#define CF_CONNECT_PENDING 3
-#define CF_IS_OTHERCON 4
- struct list_head writequeue; /* List of outgoing writequeue_entries */
- struct list_head listenlist; /* List of allocated listening sockets */
- spinlock_t writequeue_lock;
- int (*rx_action) (struct connection *); /* What to do when active */
- struct page *rx_page;
- struct cbuf cb;
- int retries;
-#define MAX_CONNECT_RETRIES 3
- struct connection *othercon;
- struct work_struct rwork; /* Receive workqueue */
- struct work_struct swork; /* Send workqueue */
-};
-#define sock2con(x) ((struct connection *)(x)->sk_user_data)
-
-/* An entry waiting to be sent */
-struct writequeue_entry {
- struct list_head list;
- struct page *page;
- int offset;
- int len;
- int end;
- int users;
- struct connection *con;
-};
-
-static struct sockaddr_storage dlm_local_addr;
-
-/* Work queues */
-static struct workqueue_struct *recv_workqueue;
-static struct workqueue_struct *send_workqueue;
-
-/* An array of pointers to connections, indexed by NODEID */
-static struct connection **connections;
-static DECLARE_MUTEX(connections_lock);
-static struct kmem_cache *con_cache;
-static int conn_array_size;
-
-static void process_recv_sockets(struct work_struct *work);
-static void process_send_sockets(struct work_struct *work);
-
-static struct connection *nodeid2con(int nodeid, gfp_t allocation)
-{
- struct connection *con = NULL;
-
- down(&connections_lock);
- if (nodeid >= conn_array_size) {
- int new_size = nodeid + NODE_INCREMENT;
- struct connection **new_conns;
-
- new_conns = kzalloc(sizeof(struct connection *) *
- new_size, allocation);
- if (!new_conns)
- goto finish;
-
- memcpy(new_conns, connections, sizeof(struct connection *) * conn_array_size);
- conn_array_size = new_size;
- kfree(connections);
- connections = new_conns;
-
- }
-
- con = connections[nodeid];
- if (con == NULL && allocation) {
- con = kmem_cache_zalloc(con_cache, allocation);
- if (!con)
- goto finish;
-
- con->nodeid = nodeid;
- mutex_init(&con->sock_mutex);
- INIT_LIST_HEAD(&con->writequeue);
- spin_lock_init(&con->writequeue_lock);
- INIT_WORK(&con->swork, process_send_sockets);
- INIT_WORK(&con->rwork, process_recv_sockets);
-
- connections[nodeid] = con;
- }
-
-finish:
- up(&connections_lock);
- return con;
-}
-
-/* Data available on socket or listen socket received a connect */
-static void lowcomms_data_ready(struct sock *sk, int count_unused)
-{
- struct connection *con = sock2con(sk);
-
- if (!test_and_set_bit(CF_READ_PENDING, &con->flags))
- queue_work(recv_workqueue, &con->rwork);
-}
-
-static void lowcomms_write_space(struct sock *sk)
-{
- struct connection *con = sock2con(sk);
-
- if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags))
- queue_work(send_workqueue, &con->swork);
-}
-
-static inline void lowcomms_connect_sock(struct connection *con)
-{
- if (!test_and_set_bit(CF_CONNECT_PENDING, &con->flags))
- queue_work(send_workqueue, &con->swork);
-}
-
-static void lowcomms_state_change(struct sock *sk)
-{
- if (sk->sk_state == TCP_ESTABLISHED)
- lowcomms_write_space(sk);
-}
-
-/* Make a socket active */
-static int add_sock(struct socket *sock, struct connection *con)
-{
- con->sock = sock;
-
- /* Install a data_ready callback */
- con->sock->sk->sk_data_ready = lowcomms_data_ready;
- con->sock->sk->sk_write_space = lowcomms_write_space;
- con->sock->sk->sk_state_change = lowcomms_state_change;
-
- return 0;
-}
-
-/* Add the port number to an IP6 or 4 sockaddr and return the address
- length */
-static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port,
- int *addr_len)
-{
- saddr->ss_family = dlm_local_addr.ss_family;
- if (saddr->ss_family == AF_INET) {
- struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr;
- in4_addr->sin_port = cpu_to_be16(port);
- *addr_len = sizeof(struct sockaddr_in);
- } else {
- struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)saddr;
- in6_addr->sin6_port = cpu_to_be16(port);
- *addr_len = sizeof(struct sockaddr_in6);
- }
-}
-
-/* Close a remote connection and tidy up */
-static void close_connection(struct connection *con, bool and_other)
-{
- mutex_lock(&con->sock_mutex);
-
- if (con->sock) {
- sock_release(con->sock);
- con->sock = NULL;
- }
- if (con->othercon && and_other) {
- /* Will only re-enter once. */
- close_connection(con->othercon, false);
- }
- if (con->rx_page) {
- __free_page(con->rx_page);
- con->rx_page = NULL;
- }
- con->retries = 0;
- mutex_unlock(&con->sock_mutex);
-}
-
-/* Data received from remote end */
-static int receive_from_sock(struct connection *con)
-{
- int ret = 0;
- struct msghdr msg = {};
- struct kvec iov[2];
- unsigned len;
- int r;
- int call_again_soon = 0;
- int nvec;
-
- mutex_lock(&con->sock_mutex);
-
- if (con->sock == NULL) {
- ret = -EAGAIN;
- goto out_close;
- }
-
- if (con->rx_page == NULL) {
- /*
- * This doesn't need to be atomic, but I think it should
- * improve performance if it is.
- */
- con->rx_page = alloc_page(GFP_ATOMIC);
- if (con->rx_page == NULL)
- goto out_resched;
- cbuf_init(&con->cb, PAGE_CACHE_SIZE);
- }
-
- /*
- * iov[0] is the bit of the circular buffer between the current end
- * point (cb.base + cb.len) and the end of the buffer.
- */
- iov[0].iov_len = con->cb.base - cbuf_data(&con->cb);
- iov[0].iov_base = page_address(con->rx_page) + cbuf_data(&con->cb);
- nvec = 1;
-
- /*
- * iov[1] is the bit of the circular buffer between the start of the
- * buffer and the start of the currently used section (cb.base)
- */
- if (cbuf_data(&con->cb) >= con->cb.base) {
- iov[0].iov_len = PAGE_CACHE_SIZE - cbuf_data(&con->cb);
- iov[1].iov_len = con->cb.base;
- iov[1].iov_base = page_address(con->rx_page);
- nvec = 2;
- }
- len = iov[0].iov_len + iov[1].iov_len;
-
- r = ret = kernel_recvmsg(con->sock, &msg, iov, nvec, len,
- MSG_DONTWAIT | MSG_NOSIGNAL);
-
- if (ret <= 0)
- goto out_close;
- if (ret == -EAGAIN)
- goto out_resched;
-
- if (ret == len)
- call_again_soon = 1;
- cbuf_add(&con->cb, ret);
- ret = dlm_process_incoming_buffer(con->nodeid,
- page_address(con->rx_page),
- con->cb.base, con->cb.len,
- PAGE_CACHE_SIZE);
- if (ret == -EBADMSG) {
- printk(KERN_INFO "dlm: lowcomms: addr=%p, base=%u, len=%u, "
- "iov_len=%u, iov_base[0]=%p, read=%d\n",
- page_address(con->rx_page), con->cb.base, con->cb.len,
- len, iov[0].iov_base, r);
- }
- if (ret < 0)
- goto out_close;
- cbuf_eat(&con->cb, ret);
-
- if (cbuf_empty(&con->cb) && !call_again_soon) {
- __free_page(con->rx_page);
- con->rx_page = NULL;
- }
-
- if (call_again_soon)
- goto out_resched;
- mutex_unlock(&con->sock_mutex);
- return 0;
-
-out_resched:
- if (!test_and_set_bit(CF_READ_PENDING, &con->flags))
- queue_work(recv_workqueue, &con->rwork);
- mutex_unlock(&con->sock_mutex);
- return -EAGAIN;
-
-out_close:
- mutex_unlock(&con->sock_mutex);
- if (ret != -EAGAIN && !test_bit(CF_IS_OTHERCON, &con->flags)) {
- close_connection(con, false);
- /* Reconnect when there is something to send */
- }
- /* Don't return success if we really got EOF */
- if (ret == 0)
- ret = -EAGAIN;
-
- return ret;
-}
-
-/* Listening socket is busy, accept a connection */
-static int accept_from_sock(struct connection *con)
-{
- int result;
- struct sockaddr_storage peeraddr;
- struct socket *newsock;
- int len;
- int nodeid;
- struct connection *newcon;
- struct connection *addcon;
-
- memset(&peeraddr, 0, sizeof(peeraddr));
- result = sock_create_kern(dlm_local_addr.ss_family, SOCK_STREAM,
- IPPROTO_TCP, &newsock);
- if (result < 0)
- return -ENOMEM;
-
- mutex_lock_nested(&con->sock_mutex, 0);
-
- result = -ENOTCONN;
- if (con->sock == NULL)
- goto accept_err;
-
- newsock->type = con->sock->type;
- newsock->ops = con->sock->ops;
-
- result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK);
- if (result < 0)
- goto accept_err;
-
- /* Get the connected socket's peer */
- memset(&peeraddr, 0, sizeof(peeraddr));
- if (newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr,
- &len, 2)) {
- result = -ECONNABORTED;
- goto accept_err;
- }
-
- /* Get the new node's NODEID */
- make_sockaddr(&peeraddr, 0, &len);
- if (dlm_addr_to_nodeid(&peeraddr, &nodeid)) {
- printk("dlm: connect from non cluster node\n");
- sock_release(newsock);
- mutex_unlock(&con->sock_mutex);
- return -1;
- }
-
- log_print("got connection from %d", nodeid);
-
- /* Check to see if we already have a connection to this node. This
- * could happen if the two nodes initiate a connection at roughly
- * the same time and the connections cross on the wire.
- * TEMPORARY FIX:
- * In this case we store the incoming one in "othercon"
- */
- newcon = nodeid2con(nodeid, GFP_KERNEL);
- if (!newcon) {
- result = -ENOMEM;
- goto accept_err;
- }
- mutex_lock_nested(&newcon->sock_mutex, 1);
- if (newcon->sock) {
- struct connection *othercon = newcon->othercon;
-
- if (!othercon) {
- othercon = kmem_cache_zalloc(con_cache, GFP_KERNEL);
- if (!othercon) {
- printk("dlm: failed to allocate incoming socket\n");
- mutex_unlock(&newcon->sock_mutex);
- result = -ENOMEM;
- goto accept_err;
- }
- othercon->nodeid = nodeid;
- othercon->rx_action = receive_from_sock;
- mutex_init(&othercon->sock_mutex);
- INIT_WORK(&othercon->swork, process_send_sockets);
- INIT_WORK(&othercon->rwork, process_recv_sockets);
- set_bit(CF_IS_OTHERCON, &othercon->flags);
- newcon->othercon = othercon;
- }
- othercon->sock = newsock;
- newsock->sk->sk_user_data = othercon;
- add_sock(newsock, othercon);
- addcon = othercon;
- }
- else {
- newsock->sk->sk_user_data = newcon;
- newcon->rx_action = receive_from_sock;
- add_sock(newsock, newcon);
- addcon = newcon;
- }
-
- mutex_unlock(&newcon->sock_mutex);
-
- /*
- * Add it to the active queue in case we got data
- * beween processing the accept adding the socket
- * to the read_sockets list
- */
- if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags))
- queue_work(recv_workqueue, &addcon->rwork);
- mutex_unlock(&con->sock_mutex);
-
- return 0;
-
-accept_err:
- mutex_unlock(&con->sock_mutex);
- sock_release(newsock);
-
- if (result != -EAGAIN)
- printk("dlm: error accepting connection from node: %d\n", result);
- return result;
-}
-
-/* Connect a new socket to its peer */
-static void connect_to_sock(struct connection *con)
-{
- int result = -EHOSTUNREACH;
- struct sockaddr_storage saddr;
- int addr_len;
- struct socket *sock;
-
- if (con->nodeid == 0) {
- log_print("attempt to connect sock 0 foiled");
- return;
- }
-
- mutex_lock(&con->sock_mutex);
- if (con->retries++ > MAX_CONNECT_RETRIES)
- goto out;
-
- /* Some odd races can cause double-connects, ignore them */
- if (con->sock) {
- result = 0;
- goto out;
- }
-
- /* Create a socket to communicate with */
- result = sock_create_kern(dlm_local_addr.ss_family, SOCK_STREAM,
- IPPROTO_TCP, &sock);
- if (result < 0)
- goto out_err;
-
- memset(&saddr, 0, sizeof(saddr));
- if (dlm_nodeid_to_addr(con->nodeid, &saddr))
- goto out_err;
-
- sock->sk->sk_user_data = con;
- con->rx_action = receive_from_sock;
-
- make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len);
-
- add_sock(sock, con);
-
- log_print("connecting to %d", con->nodeid);
- result =
- sock->ops->connect(sock, (struct sockaddr *)&saddr, addr_len,
- O_NONBLOCK);
- if (result == -EINPROGRESS)
- result = 0;
- if (result == 0)
- goto out;
-
-out_err:
- if (con->sock) {
- sock_release(con->sock);
- con->sock = NULL;
- }
- /*
- * Some errors are fatal and this list might need adjusting. For other
- * errors we try again until the max number of retries is reached.
- */
- if (result != -EHOSTUNREACH && result != -ENETUNREACH &&
- result != -ENETDOWN && result != EINVAL
- && result != -EPROTONOSUPPORT) {
- lowcomms_connect_sock(con);
- result = 0;
- }
-out:
- mutex_unlock(&con->sock_mutex);
- return;
-}
-
-static struct socket *create_listen_sock(struct connection *con,
- struct sockaddr_storage *saddr)
-{
- struct socket *sock = NULL;
- mm_segment_t fs;
- int result = 0;
- int one = 1;
- int addr_len;
-
- if (dlm_local_addr.ss_family == AF_INET)
- addr_len = sizeof(struct sockaddr_in);
- else
- addr_len = sizeof(struct sockaddr_in6);
-
- /* Create a socket to communicate with */
- result = sock_create_kern(dlm_local_addr.ss_family, SOCK_STREAM, IPPROTO_TCP, &sock);
- if (result < 0) {
- printk("dlm: Can't create listening comms socket\n");
- goto create_out;
- }
-
- fs = get_fs();
- set_fs(get_ds());
- result = sock_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
- (char *)&one, sizeof(one));
- set_fs(fs);
- if (result < 0) {
- printk("dlm: Failed to set SO_REUSEADDR on socket: result=%d\n",
- result);
- }
- sock->sk->sk_user_data = con;
- con->rx_action = accept_from_sock;
- con->sock = sock;
-
- /* Bind to our port */
- make_sockaddr(saddr, dlm_config.ci_tcp_port, &addr_len);
- result = sock->ops->bind(sock, (struct sockaddr *) saddr, addr_len);
- if (result < 0) {
- printk("dlm: Can't bind to port %d\n", dlm_config.ci_tcp_port);
- sock_release(sock);
- sock = NULL;
- con->sock = NULL;
- goto create_out;
- }
-
- fs = get_fs();
- set_fs(get_ds());
-
- result = sock_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
- (char *)&one, sizeof(one));
- set_fs(fs);
- if (result < 0) {
- printk("dlm: Set keepalive failed: %d\n", result);
- }
-
- result = sock->ops->listen(sock, 5);
- if (result < 0) {
- printk("dlm: Can't listen on port %d\n", dlm_config.ci_tcp_port);
- sock_release(sock);
- sock = NULL;
- goto create_out;
- }
-
-create_out:
- return sock;
-}
-
-
-/* Listen on all interfaces */
-static int listen_for_all(void)
-{
- struct socket *sock = NULL;
- struct connection *con = nodeid2con(0, GFP_KERNEL);
- int result = -EINVAL;
-
- /* We don't support multi-homed hosts */
- set_bit(CF_IS_OTHERCON, &con->flags);
-
- sock = create_listen_sock(con, &dlm_local_addr);
- if (sock) {
- add_sock(sock, con);
- result = 0;
- }
- else {
- result = -EADDRINUSE;
- }
-
- return result;
-}
-
-
-
-static struct writequeue_entry *new_writequeue_entry(struct connection *con,
- gfp_t allocation)
-{
- struct writequeue_entry *entry;
-
- entry = kmalloc(sizeof(struct writequeue_entry), allocation);
- if (!entry)
- return NULL;
-
- entry->page = alloc_page(allocation);
- if (!entry->page) {
- kfree(entry);
- return NULL;
- }
-
- entry->offset = 0;
- entry->len = 0;
- entry->end = 0;
- entry->users = 0;
- entry->con = con;
-
- return entry;
-}
-
-void *dlm_lowcomms_get_buffer(int nodeid, int len,
- gfp_t allocation, char **ppc)
-{
- struct connection *con;
- struct writequeue_entry *e;
- int offset = 0;
- int users = 0;
-
- con = nodeid2con(nodeid, allocation);
- if (!con)
- return NULL;
-
- spin_lock(&con->writequeue_lock);
- e = list_entry(con->writequeue.prev, struct writequeue_entry, list);
- if ((&e->list == &con->writequeue) ||
- (PAGE_CACHE_SIZE - e->end < len)) {
- e = NULL;
- } else {
- offset = e->end;
- e->end += len;
- users = e->users++;
- }
- spin_unlock(&con->writequeue_lock);
-
- if (e) {
- got_one:
- if (users == 0)
- kmap(e->page);
- *ppc = page_address(e->page) + offset;
- return e;
- }
-
- e = new_writequeue_entry(con, allocation);
- if (e) {
- spin_lock(&con->writequeue_lock);
- offset = e->end;
- e->end += len;
- users = e->users++;
- list_add_tail(&e->list, &con->writequeue);
- spin_unlock(&con->writequeue_lock);
- goto got_one;
- }
- return NULL;
-}
-
-void dlm_lowcomms_commit_buffer(void *mh)
-{
- struct writequeue_entry *e = (struct writequeue_entry *)mh;
- struct connection *con = e->con;
- int users;
-
- spin_lock(&con->writequeue_lock);
- users = --e->users;
- if (users)
- goto out;
- e->len = e->end - e->offset;
- kunmap(e->page);
- spin_unlock(&con->writequeue_lock);
-
- if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags)) {
- queue_work(send_workqueue, &con->swork);
- }
- return;
-
-out:
- spin_unlock(&con->writequeue_lock);
- return;
-}
-
-static void free_entry(struct writequeue_entry *e)
-{
- __free_page(e->page);
- kfree(e);
-}
-
-/* Send a message */
-static void send_to_sock(struct connection *con)
-{
- int ret = 0;
- ssize_t(*sendpage) (struct socket *, struct page *, int, size_t, int);
- const int msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
- struct writequeue_entry *e;
- int len, offset;
-
- mutex_lock(&con->sock_mutex);
- if (con->sock == NULL)
- goto out_connect;
-
- sendpage = con->sock->ops->sendpage;
-
- spin_lock(&con->writequeue_lock);
- for (;;) {
- e = list_entry(con->writequeue.next, struct writequeue_entry,
- list);
- if ((struct list_head *) e == &con->writequeue)
- break;
-
- len = e->len;
- offset = e->offset;
- BUG_ON(len == 0 && e->users == 0);
- spin_unlock(&con->writequeue_lock);
- kmap(e->page);
-
- ret = 0;
- if (len) {
- ret = sendpage(con->sock, e->page, offset, len,
- msg_flags);
- if (ret == -EAGAIN || ret == 0)
- goto out;
- if (ret <= 0)
- goto send_error;
- }
- else {
- /* Don't starve people filling buffers */
- cond_resched();
- }
-
- spin_lock(&con->writequeue_lock);
- e->offset += ret;
- e->len -= ret;
-
- if (e->len == 0 && e->users == 0) {
- list_del(&e->list);
- kunmap(e->page);
- free_entry(e);
- continue;
- }
- }
- spin_unlock(&con->writequeue_lock);
-out:
- mutex_unlock(&con->sock_mutex);
- return;
-
-send_error:
- mutex_unlock(&con->sock_mutex);
- close_connection(con, false);
- lowcomms_connect_sock(con);
- return;
-
-out_connect:
- mutex_unlock(&con->sock_mutex);
- connect_to_sock(con);
- return;
-}
-
-static void clean_one_writequeue(struct connection *con)
-{
- struct list_head *list;
- struct list_head *temp;
-
- spin_lock(&con->writequeue_lock);
- list_for_each_safe(list, temp, &con->writequeue) {
- struct writequeue_entry *e =
- list_entry(list, struct writequeue_entry, list);
- list_del(&e->list);
- free_entry(e);
- }
- spin_unlock(&con->writequeue_lock);
-}
-
-/* Called from recovery when it knows that a node has
- left the cluster */
-int dlm_lowcomms_close(int nodeid)
-{
- struct connection *con;
-
- if (!connections)
- goto out;
-
- log_print("closing connection to node %d", nodeid);
- con = nodeid2con(nodeid, 0);
- if (con) {
- clean_one_writequeue(con);
- close_connection(con, true);
- }
- return 0;
-
-out:
- return -1;
-}
-
-/* Look for activity on active sockets */
-static void process_recv_sockets(struct work_struct *work)
-{
- struct connection *con = container_of(work, struct connection, rwork);
- int err;
-
- clear_bit(CF_READ_PENDING, &con->flags);
- do {
- err = con->rx_action(con);
- } while (!err);
-}
-
-
-static void process_send_sockets(struct work_struct *work)
-{
- struct connection *con = container_of(work, struct connection, swork);
-
- if (test_and_clear_bit(CF_CONNECT_PENDING, &con->flags)) {
- connect_to_sock(con);
- }
-
- clear_bit(CF_WRITE_PENDING, &con->flags);
- send_to_sock(con);
-}
-
-
-/* Discard all entries on the write queues */
-static void clean_writequeues(void)
-{
- int nodeid;
-
- for (nodeid = 1; nodeid < conn_array_size; nodeid++) {
- struct connection *con = nodeid2con(nodeid, 0);
-
- if (con)
- clean_one_writequeue(con);
- }
-}
-
-static void work_stop(void)
-{
- destroy_workqueue(recv_workqueue);
- destroy_workqueue(send_workqueue);
-}
-
-static int work_start(void)
-{
- int error;
- recv_workqueue = create_workqueue("dlm_recv");
- error = IS_ERR(recv_workqueue);
- if (error) {
- log_print("can't start dlm_recv %d", error);
- return error;
- }
-
- send_workqueue = create_singlethread_workqueue("dlm_send");
- error = IS_ERR(send_workqueue);
- if (error) {
- log_print("can't start dlm_send %d", error);
- destroy_workqueue(recv_workqueue);
- return error;
- }
-
- return 0;
-}
-
-void dlm_lowcomms_stop(void)
-{
- int i;
-
- /* Set all the flags to prevent any
- socket activity.
- */
- for (i = 0; i < conn_array_size; i++) {
- if (connections[i])
- connections[i]->flags |= 0xFF;
- }
-
- work_stop();
- clean_writequeues();
-
- for (i = 0; i < conn_array_size; i++) {
- if (connections[i]) {
- close_connection(connections[i], true);
- if (connections[i]->othercon)
- kmem_cache_free(con_cache, connections[i]->othercon);
- kmem_cache_free(con_cache, connections[i]);
- }
- }
-
- kfree(connections);
- connections = NULL;
-
- kmem_cache_destroy(con_cache);
-}
-
-/* This is quite likely to sleep... */
-int dlm_lowcomms_start(void)
-{
- int error = 0;
-
- error = -ENOMEM;
- connections = kzalloc(sizeof(struct connection *) *
- NODE_INCREMENT, GFP_KERNEL);
- if (!connections)
- goto out;
-
- conn_array_size = NODE_INCREMENT;
-
- if (dlm_our_addr(&dlm_local_addr, 0)) {
- log_print("no local IP address has been set");
- goto fail_free_conn;
- }
- if (!dlm_our_addr(&dlm_local_addr, 1)) {
- log_print("This dlm comms module does not support multi-homed clustering");
- goto fail_free_conn;
- }
-
- con_cache = kmem_cache_create("dlm_conn", sizeof(struct connection),
- __alignof__(struct connection), 0,
- NULL, NULL);
- if (!con_cache)
- goto fail_free_conn;
-
-
- /* Start listening */
- error = listen_for_all();
- if (error)
- goto fail_unlisten;
-
- error = work_start();
- if (error)
- goto fail_unlisten;
-
- return 0;
-
-fail_unlisten:
- close_connection(connections[0], false);
- kmem_cache_free(con_cache, connections[0]);
- kmem_cache_destroy(con_cache);
-
-fail_free_conn:
- kfree(connections);
-
-out:
- return error;
-}
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only. This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
--- /dev/null
+/******************************************************************************
+*******************************************************************************
+**
+** Copyright (C) Sistina Software, Inc. 1997-2003 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
+** of the GNU General Public License v.2.
+**
+*******************************************************************************
+******************************************************************************/
+
+/*
+ * lowcomms.c
+ *
+ * This is the "low-level" comms layer.
+ *
+ * It is responsible for sending/receiving messages
+ * from other nodes in the cluster.
+ *
+ * Cluster nodes are referred to by their nodeids. nodeids are
+ * simply 32 bit numbers to the locking module - if they need to
+ * be expanded for the cluster infrastructure then that is it's
+ * responsibility. It is this layer's
+ * responsibility to resolve these into IP address or
+ * whatever it needs for inter-node communication.
+ *
+ * The comms level is two kernel threads that deal mainly with
+ * the receiving of messages from other nodes and passing them
+ * up to the mid-level comms layer (which understands the
+ * message format) for execution by the locking core, and
+ * a send thread which does all the setting up of connections
+ * to remote nodes and the sending of data. Threads are not allowed
+ * to send their own data because it may cause them to wait in times
+ * of high load. Also, this way, the sending thread can collect together
+ * messages bound for one node and send them in one block.
+ *
+ * lowcomms will choose to use wither TCP or SCTP as its transport layer
+ * depending on the configuration variable 'protocol'. This should be set
+ * to 0 (default) for TCP or 1 for SCTP. It shouldbe configured using a
+ * cluster-wide mechanism as it must be the same on all nodes of the cluster
+ * for the DLM to function.
+ *
+ */
+
+#include <asm/ioctls.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <linux/pagemap.h>
+#include <linux/idr.h>
+#include <linux/file.h>
+#include <linux/sctp.h>
+#include <net/sctp/user.h>
+
+#include "dlm_internal.h"
+#include "lowcomms.h"
+#include "midcomms.h"
+#include "config.h"
+
+#define NEEDED_RMEM (4*1024*1024)
+
+struct cbuf {
+ unsigned int base;
+ unsigned int len;
+ unsigned int mask;
+};
+
+static void cbuf_add(struct cbuf *cb, int n)
+{
+ cb->len += n;
+}
+
+static int cbuf_data(struct cbuf *cb)
+{
+ return ((cb->base + cb->len) & cb->mask);
+}
+
+static void cbuf_init(struct cbuf *cb, int size)
+{
+ cb->base = cb->len = 0;
+ cb->mask = size-1;
+}
+
+static void cbuf_eat(struct cbuf *cb, int n)
+{
+ cb->len -= n;
+ cb->base += n;
+ cb->base &= cb->mask;
+}
+
+static bool cbuf_empty(struct cbuf *cb)
+{
+ return cb->len == 0;
+}
+
+struct connection {
+ struct socket *sock; /* NULL if not connected */
+ uint32_t nodeid; /* So we know who we are in the list */
+ struct mutex sock_mutex;
+ unsigned long flags;
+#define CF_READ_PENDING 1
+#define CF_WRITE_PENDING 2
+#define CF_CONNECT_PENDING 3
+#define CF_INIT_PENDING 4
+#define CF_IS_OTHERCON 5
+ struct list_head writequeue; /* List of outgoing writequeue_entries */
+ spinlock_t writequeue_lock;
+ int (*rx_action) (struct connection *); /* What to do when active */
+ void (*connect_action) (struct connection *); /* What to do to connect */
+ struct page *rx_page;
+ struct cbuf cb;
+ int retries;
+#define MAX_CONNECT_RETRIES 3
+ int sctp_assoc;
+ struct connection *othercon;
+ struct work_struct rwork; /* Receive workqueue */
+ struct work_struct swork; /* Send workqueue */
+};
+#define sock2con(x) ((struct connection *)(x)->sk_user_data)
+
+/* An entry waiting to be sent */
+struct writequeue_entry {
+ struct list_head list;
+ struct page *page;
+ int offset;
+ int len;
+ int end;
+ int users;
+ struct connection *con;
+};
+
+static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT];
+static int dlm_local_count;
+
+/* Work queues */
+static struct workqueue_struct *recv_workqueue;
+static struct workqueue_struct *send_workqueue;
+
+static DEFINE_IDR(connections_idr);
+static DECLARE_MUTEX(connections_lock);
+static int max_nodeid;
+static struct kmem_cache *con_cache;
+
+static void process_recv_sockets(struct work_struct *work);
+static void process_send_sockets(struct work_struct *work);
+
+/*
+ * If 'allocation' is zero then we don't attempt to create a new
+ * connection structure for this node.
+ */
+static struct connection *__nodeid2con(int nodeid, gfp_t alloc)
+{
+ struct connection *con = NULL;
+ int r;
+ int n;
+
+ con = idr_find(&connections_idr, nodeid);
+ if (con || !alloc)
+ return con;
+
+ r = idr_pre_get(&connections_idr, alloc);
+ if (!r)
+ return NULL;
+
+ con = kmem_cache_zalloc(con_cache, alloc);
+ if (!con)
+ return NULL;
+
+ r = idr_get_new_above(&connections_idr, con, nodeid, &n);
+ if (r) {
+ kmem_cache_free(con_cache, con);
+ return NULL;
+ }
+
+ if (n != nodeid) {
+ idr_remove(&connections_idr, n);
+ kmem_cache_free(con_cache, con);
+ return NULL;
+ }
+
+ con->nodeid = nodeid;
+ mutex_init(&con->sock_mutex);
+ INIT_LIST_HEAD(&con->writequeue);
+ spin_lock_init(&con->writequeue_lock);
+ INIT_WORK(&con->swork, process_send_sockets);
+ INIT_WORK(&con->rwork, process_recv_sockets);
+
+ /* Setup action pointers for child sockets */
+ if (con->nodeid) {
+ struct connection *zerocon = idr_find(&connections_idr, 0);
+
+ con->connect_action = zerocon->connect_action;
+ if (!con->rx_action)
+ con->rx_action = zerocon->rx_action;
+ }
+
+ if (nodeid > max_nodeid)
+ max_nodeid = nodeid;
+
+ return con;
+}
+
+static struct connection *nodeid2con(int nodeid, gfp_t allocation)
+{
+ struct connection *con;
+
+ down(&connections_lock);
+ con = __nodeid2con(nodeid, allocation);
+ up(&connections_lock);
+
+ return con;
+}
+
+/* This is a bit drastic, but only called when things go wrong */
+static struct connection *assoc2con(int assoc_id)
+{
+ int i;
+ struct connection *con;
+
+ down(&connections_lock);
+ for (i=0; i<=max_nodeid; i++) {
+ con = __nodeid2con(i, 0);
+ if (con && con->sctp_assoc == assoc_id) {
+ up(&connections_lock);
+ return con;
+ }
+ }
+ up(&connections_lock);
+ return NULL;
+}
+
+static int nodeid_to_addr(int nodeid, struct sockaddr *retaddr)
+{
+ struct sockaddr_storage addr;
+ int error;
+
+ if (!dlm_local_count)
+ return -1;
+
+ error = dlm_nodeid_to_addr(nodeid, &addr);
+ if (error)
+ return error;
+
+ if (dlm_local_addr[0]->ss_family == AF_INET) {
+ struct sockaddr_in *in4 = (struct sockaddr_in *) &addr;
+ struct sockaddr_in *ret4 = (struct sockaddr_in *) retaddr;
+ ret4->sin_addr.s_addr = in4->sin_addr.s_addr;
+ } else {
+ struct sockaddr_in6 *in6 = (struct sockaddr_in6 *) &addr;
+ struct sockaddr_in6 *ret6 = (struct sockaddr_in6 *) retaddr;
+ memcpy(&ret6->sin6_addr, &in6->sin6_addr,
+ sizeof(in6->sin6_addr));
+ }
+
+ return 0;
+}
+
+/* Data available on socket or listen socket received a connect */
+static void lowcomms_data_ready(struct sock *sk, int count_unused)
+{
+ struct connection *con = sock2con(sk);
+ if (!test_and_set_bit(CF_READ_PENDING, &con->flags))
+ queue_work(recv_workqueue, &con->rwork);
+}
+
+static void lowcomms_write_space(struct sock *sk)
+{
+ struct connection *con = sock2con(sk);
+
+ if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags))
+ queue_work(send_workqueue, &con->swork);
+}
+
+static inline void lowcomms_connect_sock(struct connection *con)
+{
+ if (!test_and_set_bit(CF_CONNECT_PENDING, &con->flags))
+ queue_work(send_workqueue, &con->swork);
+}
+
+static void lowcomms_state_change(struct sock *sk)
+{
+ if (sk->sk_state == TCP_ESTABLISHED)
+ lowcomms_write_space(sk);
+}
+
+/* Make a socket active */
+static int add_sock(struct socket *sock, struct connection *con)
+{
+ con->sock = sock;
+
+ /* Install a data_ready callback */
+ con->sock->sk->sk_data_ready = lowcomms_data_ready;
+ con->sock->sk->sk_write_space = lowcomms_write_space;
+ con->sock->sk->sk_state_change = lowcomms_state_change;
+ con->sock->sk->sk_user_data = con;
+ return 0;
+}
+
+/* Add the port number to an IPv6 or 4 sockaddr and return the address
+ length */
+static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port,
+ int *addr_len)
+{
+ saddr->ss_family = dlm_local_addr[0]->ss_family;
+ if (saddr->ss_family == AF_INET) {
+ struct sockaddr_in *in4_addr = (struct sockaddr_in *)saddr;
+ in4_addr->sin_port = cpu_to_be16(port);
+ *addr_len = sizeof(struct sockaddr_in);
+ memset(&in4_addr->sin_zero, 0, sizeof(in4_addr->sin_zero));
+ } else {
+ struct sockaddr_in6 *in6_addr = (struct sockaddr_in6 *)saddr;
+ in6_addr->sin6_port = cpu_to_be16(port);
+ *addr_len = sizeof(struct sockaddr_in6);
+ }
+}
+
+/* Close a remote connection and tidy up */
+static void close_connection(struct connection *con, bool and_other)
+{
+ mutex_lock(&con->sock_mutex);
+
+ if (con->sock) {
+ sock_release(con->sock);
+ con->sock = NULL;
+ }
+ if (con->othercon && and_other) {
+ /* Will only re-enter once. */
+ close_connection(con->othercon, false);
+ }
+ if (con->rx_page) {
+ __free_page(con->rx_page);
+ con->rx_page = NULL;
+ }
+ con->retries = 0;
+ mutex_unlock(&con->sock_mutex);
+}
+
+/* We only send shutdown messages to nodes that are not part of the cluster */
+static void sctp_send_shutdown(sctp_assoc_t associd)
+{
+ static char outcmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
+ struct msghdr outmessage;
+ struct cmsghdr *cmsg;
+ struct sctp_sndrcvinfo *sinfo;
+ int ret;
+ struct connection *con;
+
+ con = nodeid2con(0,0);
+ BUG_ON(con == NULL);
+
+ outmessage.msg_name = NULL;
+ outmessage.msg_namelen = 0;
+ outmessage.msg_control = outcmsg;
+ outmessage.msg_controllen = sizeof(outcmsg);
+ outmessage.msg_flags = MSG_EOR;
+
+ cmsg = CMSG_FIRSTHDR(&outmessage);
+ cmsg->cmsg_level = IPPROTO_SCTP;
+ cmsg->cmsg_type = SCTP_SNDRCV;
+ cmsg->cmsg_len = CMSG_LEN(sizeof(struct sctp_sndrcvinfo));
+ outmessage.msg_controllen = cmsg->cmsg_len;
+ sinfo = CMSG_DATA(cmsg);
+ memset(sinfo, 0x00, sizeof(struct sctp_sndrcvinfo));
+
+ sinfo->sinfo_flags |= MSG_EOF;
+ sinfo->sinfo_assoc_id = associd;
+
+ ret = kernel_sendmsg(con->sock, &outmessage, NULL, 0, 0);
+
+ if (ret != 0)
+ log_print("send EOF to node failed: %d", ret);
+}
+
+/* INIT failed but we don't know which node...
+ restart INIT on all pending nodes */
+static void sctp_init_failed(void)
+{
+ int i;
+ struct connection *con;
+
+ down(&connections_lock);
+ for (i=1; i<=max_nodeid; i++) {
+ con = __nodeid2con(i, 0);
+ if (!con)
+ continue;
+ con->sctp_assoc = 0;
+ if (test_and_clear_bit(CF_CONNECT_PENDING, &con->flags)) {
+ if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags)) {
+ queue_work(send_workqueue, &con->swork);
+ }
+ }
+ }
+ up(&connections_lock);
+}
+
+/* Something happened to an association */
+static void process_sctp_notification(struct connection *con,
+ struct msghdr *msg, char *buf)
+{
+ union sctp_notification *sn = (union sctp_notification *)buf;
+
+ if (sn->sn_header.sn_type == SCTP_ASSOC_CHANGE) {
+ switch (sn->sn_assoc_change.sac_state) {
+
+ case SCTP_COMM_UP:
+ case SCTP_RESTART:
+ {
+ /* Check that the new node is in the lockspace */
+ struct sctp_prim prim;
+ int nodeid;
+ int prim_len, ret;
+ int addr_len;
+ struct connection *new_con;
+ struct file *file;
+ sctp_peeloff_arg_t parg;
+ int parglen = sizeof(parg);
+
+ /*
+ * We get this before any data for an association.
+ * We verify that the node is in the cluster and
+ * then peel off a socket for it.
+ */
+ if ((int)sn->sn_assoc_change.sac_assoc_id <= 0) {
+ log_print("COMM_UP for invalid assoc ID %d",
+ (int)sn->sn_assoc_change.sac_assoc_id);
+ sctp_init_failed();
+ return;
+ }
+ memset(&prim, 0, sizeof(struct sctp_prim));
+ prim_len = sizeof(struct sctp_prim);
+ prim.ssp_assoc_id = sn->sn_assoc_change.sac_assoc_id;
+
+ ret = kernel_getsockopt(con->sock,
+ IPPROTO_SCTP,
+ SCTP_PRIMARY_ADDR,
+ (char*)&prim,
+ &prim_len);
+ if (ret < 0) {
+ log_print("getsockopt/sctp_primary_addr on "
+ "new assoc %d failed : %d",
+ (int)sn->sn_assoc_change.sac_assoc_id,
+ ret);
+
+ /* Retry INIT later */
+ new_con = assoc2con(sn->sn_assoc_change.sac_assoc_id);
+ if (new_con)
+ clear_bit(CF_CONNECT_PENDING, &con->flags);
+ return;
+ }
+ make_sockaddr(&prim.ssp_addr, 0, &addr_len);
+ if (dlm_addr_to_nodeid(&prim.ssp_addr, &nodeid)) {
+ int i;
+ unsigned char *b=(unsigned char *)&prim.ssp_addr;
+ log_print("reject connect from unknown addr");
+ for (i=0; i<sizeof(struct sockaddr_storage);i++)
+ printk("%02x ", b[i]);
+ printk("\n");
+ sctp_send_shutdown(prim.ssp_assoc_id);
+ return;
+ }
+
+ new_con = nodeid2con(nodeid, GFP_KERNEL);
+ if (!new_con)
+ return;
+
+ /* Peel off a new sock */
+ parg.associd = sn->sn_assoc_change.sac_assoc_id;
+ ret = kernel_getsockopt(con->sock, IPPROTO_SCTP,
+ SCTP_SOCKOPT_PEELOFF,
+ (void *)&parg, &parglen);
+ if (ret) {
+ log_print("Can't peel off a socket for "
+ "connection %d to node %d: err=%d\n",
+ parg.associd, nodeid, ret);
+ }
+ file = fget(parg.sd);
+ new_con->sock = SOCKET_I(file->f_dentry->d_inode);
+ add_sock(new_con->sock, new_con);
+ fput(file);
+ put_unused_fd(parg.sd);
+
+ log_print("got new/restarted association %d nodeid %d",
+ (int)sn->sn_assoc_change.sac_assoc_id, nodeid);
+
+ /* Send any pending writes */
+ clear_bit(CF_CONNECT_PENDING, &new_con->flags);
+ clear_bit(CF_INIT_PENDING, &con->flags);
+ if (!test_and_set_bit(CF_WRITE_PENDING, &new_con->flags)) {
+ queue_work(send_workqueue, &new_con->swork);
+ }
+ if (!test_and_set_bit(CF_READ_PENDING, &new_con->flags))
+ queue_work(recv_workqueue, &new_con->rwork);
+ }
+ break;
+
+ case SCTP_COMM_LOST:
+ case SCTP_SHUTDOWN_COMP:
+ {
+ con = assoc2con(sn->sn_assoc_change.sac_assoc_id);
+ if (con) {
+ con->sctp_assoc = 0;
+ }
+ }
+ break;
+
+ /* We don't know which INIT failed, so clear the PENDING flags
+ * on them all. if assoc_id is zero then it will then try
+ * again */
+
+ case SCTP_CANT_STR_ASSOC:
+ {
+ log_print("Can't start SCTP association - retrying");
+ sctp_init_failed();
+ }
+ break;
+
+ default:
+ log_print("unexpected SCTP assoc change id=%d state=%d",
+ (int)sn->sn_assoc_change.sac_assoc_id,
+ sn->sn_assoc_change.sac_state);
+ }
+ }
+}
+
+/* Data received from remote end */
+static int receive_from_sock(struct connection *con)
+{
+ int ret = 0;
+ struct msghdr msg = {};
+ struct kvec iov[2];
+ unsigned len;
+ int r;
+ int call_again_soon = 0;
+ int nvec;
+ char incmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
+
+ mutex_lock(&con->sock_mutex);
+
+ if (con->sock == NULL) {
+ ret = -EAGAIN;
+ goto out_close;
+ }
+
+ if (con->rx_page == NULL) {
+ /*
+ * This doesn't need to be atomic, but I think it should
+ * improve performance if it is.
+ */
+ con->rx_page = alloc_page(GFP_ATOMIC);
+ if (con->rx_page == NULL)
+ goto out_resched;
+ cbuf_init(&con->cb, PAGE_CACHE_SIZE);
+ }
+
+ /* Only SCTP needs these really */
+ memset(&incmsg, 0, sizeof(incmsg));
+ msg.msg_control = incmsg;
+ msg.msg_controllen = sizeof(incmsg);
+
+ /*
+ * iov[0] is the bit of the circular buffer between the current end
+ * point (cb.base + cb.len) and the end of the buffer.
+ */
+ iov[0].iov_len = con->cb.base - cbuf_data(&con->cb);
+ iov[0].iov_base = page_address(con->rx_page) + cbuf_data(&con->cb);
+ iov[1].iov_len = 0;
+ nvec = 1;
+
+ /*
+ * iov[1] is the bit of the circular buffer between the start of the
+ * buffer and the start of the currently used section (cb.base)
+ */
+ if (cbuf_data(&con->cb) >= con->cb.base) {
+ iov[0].iov_len = PAGE_CACHE_SIZE - cbuf_data(&con->cb);
+ iov[1].iov_len = con->cb.base;
+ iov[1].iov_base = page_address(con->rx_page);
+ nvec = 2;
+ }
+ len = iov[0].iov_len + iov[1].iov_len;
+
+ r = ret = kernel_recvmsg(con->sock, &msg, iov, nvec, len,
+ MSG_DONTWAIT | MSG_NOSIGNAL);
+ if (ret <= 0)
+ goto out_close;
+
+ /* Process SCTP notifications */
+ if (msg.msg_flags & MSG_NOTIFICATION) {
+ msg.msg_control = incmsg;
+ msg.msg_controllen = sizeof(incmsg);
+
+ process_sctp_notification(con, &msg,
+ page_address(con->rx_page) + con->cb.base);
+ mutex_unlock(&con->sock_mutex);
+ return 0;
+ }
+ BUG_ON(con->nodeid == 0);
+
+ if (ret == len)
+ call_again_soon = 1;
+ cbuf_add(&con->cb, ret);
+ ret = dlm_process_incoming_buffer(con->nodeid,
+ page_address(con->rx_page),
+ con->cb.base, con->cb.len,
+ PAGE_CACHE_SIZE);
+ if (ret == -EBADMSG) {
+ log_print("lowcomms: addr=%p, base=%u, len=%u, "
+ "iov_len=%u, iov_base[0]=%p, read=%d",
+ page_address(con->rx_page), con->cb.base, con->cb.len,
+ len, iov[0].iov_base, r);
+ }
+ if (ret < 0)
+ goto out_close;
+ cbuf_eat(&con->cb, ret);
+
+ if (cbuf_empty(&con->cb) && !call_again_soon) {
+ __free_page(con->rx_page);
+ con->rx_page = NULL;
+ }
+
+ if (call_again_soon)
+ goto out_resched;
+ mutex_unlock(&con->sock_mutex);
+ return 0;
+
+out_resched:
+ if (!test_and_set_bit(CF_READ_PENDING, &con->flags))
+ queue_work(recv_workqueue, &con->rwork);
+ mutex_unlock(&con->sock_mutex);
+ return -EAGAIN;
+
+out_close:
+ mutex_unlock(&con->sock_mutex);
+ if (ret != -EAGAIN && !test_bit(CF_IS_OTHERCON, &con->flags)) {
+ close_connection(con, false);
+ /* Reconnect when there is something to send */
+ }
+ /* Don't return success if we really got EOF */
+ if (ret == 0)
+ ret = -EAGAIN;
+
+ return ret;
+}
+
+/* Listening socket is busy, accept a connection */
+static int tcp_accept_from_sock(struct connection *con)
+{
+ int result;
+ struct sockaddr_storage peeraddr;
+ struct socket *newsock;
+ int len;
+ int nodeid;
+ struct connection *newcon;
+ struct connection *addcon;
+
+ memset(&peeraddr, 0, sizeof(peeraddr));
+ result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_STREAM,
+ IPPROTO_TCP, &newsock);
+ if (result < 0)
+ return -ENOMEM;
+
+ mutex_lock_nested(&con->sock_mutex, 0);
+
+ result = -ENOTCONN;
+ if (con->sock == NULL)
+ goto accept_err;
+
+ newsock->type = con->sock->type;
+ newsock->ops = con->sock->ops;
+
+ result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK);
+ if (result < 0)
+ goto accept_err;
+
+ /* Get the connected socket's peer */
+ memset(&peeraddr, 0, sizeof(peeraddr));
+ if (newsock->ops->getname(newsock, (struct sockaddr *)&peeraddr,
+ &len, 2)) {
+ result = -ECONNABORTED;
+ goto accept_err;
+ }
+
+ /* Get the new node's NODEID */
+ make_sockaddr(&peeraddr, 0, &len);
+ if (dlm_addr_to_nodeid(&peeraddr, &nodeid)) {
+ log_print("connect from non cluster node");
+ sock_release(newsock);
+ mutex_unlock(&con->sock_mutex);
+ return -1;
+ }
+
+ log_print("got connection from %d", nodeid);
+
+ /* Check to see if we already have a connection to this node. This
+ * could happen if the two nodes initiate a connection at roughly
+ * the same time and the connections cross on the wire.
+ * In this case we store the incoming one in "othercon"
+ */
+ newcon = nodeid2con(nodeid, GFP_KERNEL);
+ if (!newcon) {
+ result = -ENOMEM;
+ goto accept_err;
+ }
+ mutex_lock_nested(&newcon->sock_mutex, 1);
+ if (newcon->sock) {
+ struct connection *othercon = newcon->othercon;
+
+ if (!othercon) {
+ othercon = kmem_cache_zalloc(con_cache, GFP_KERNEL);
+ if (!othercon) {
+ log_print("failed to allocate incoming socket");
+ mutex_unlock(&newcon->sock_mutex);
+ result = -ENOMEM;
+ goto accept_err;
+ }
+ othercon->nodeid = nodeid;
+ othercon->rx_action = receive_from_sock;
+ mutex_init(&othercon->sock_mutex);
+ INIT_WORK(&othercon->swork, process_send_sockets);
+ INIT_WORK(&othercon->rwork, process_recv_sockets);
+ set_bit(CF_IS_OTHERCON, &othercon->flags);
+ newcon->othercon = othercon;
+ }
+ othercon->sock = newsock;
+ newsock->sk->sk_user_data = othercon;
+ add_sock(newsock, othercon);
+ addcon = othercon;
+ }
+ else {
+ newsock->sk->sk_user_data = newcon;
+ newcon->rx_action = receive_from_sock;
+ add_sock(newsock, newcon);
+ addcon = newcon;
+ }
+
+ mutex_unlock(&newcon->sock_mutex);
+
+ /*
+ * Add it to the active queue in case we got data
+ * beween processing the accept adding the socket
+ * to the read_sockets list
+ */
+ if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags))
+ queue_work(recv_workqueue, &addcon->rwork);
+ mutex_unlock(&con->sock_mutex);
+
+ return 0;
+
+accept_err:
+ mutex_unlock(&con->sock_mutex);
+ sock_release(newsock);
+
+ if (result != -EAGAIN)
+ log_print("error accepting connection from node: %d", result);
+ return result;
+}
+
+static void free_entry(struct writequeue_entry *e)
+{
+ __free_page(e->page);
+ kfree(e);
+}
+
+/* Initiate an SCTP association.
+ This is a special case of send_to_sock() in that we don't yet have a
+ peeled-off socket for this association, so we use the listening socket
+ and add the primary IP address of the remote node.
+ */
+static void sctp_init_assoc(struct connection *con)
+{
+ struct sockaddr_storage rem_addr;
+ char outcmsg[CMSG_SPACE(sizeof(struct sctp_sndrcvinfo))];
+ struct msghdr outmessage;
+ struct cmsghdr *cmsg;
+ struct sctp_sndrcvinfo *sinfo;
+ struct connection *base_con;
+ struct writequeue_entry *e;
+ int len, offset;
+ int ret;
+ int addrlen;
+ struct kvec iov[1];
+
+ if (test_and_set_bit(CF_INIT_PENDING, &con->flags))
+ return;
+
+ if (con->retries++ > MAX_CONNECT_RETRIES)
+ return;
+
+ log_print("Initiating association with node %d", con->nodeid);
+
+ if (nodeid_to_addr(con->nodeid, (struct sockaddr *)&rem_addr)) {
+ log_print("no address for nodeid %d", con->nodeid);
+ return;
+ }
+ base_con = nodeid2con(0, 0);
+ BUG_ON(base_con == NULL);
+
+ make_sockaddr(&rem_addr, dlm_config.ci_tcp_port, &addrlen);
+
+ outmessage.msg_name = &rem_addr;
+ outmessage.msg_namelen = addrlen;
+ outmessage.msg_control = outcmsg;
+ outmessage.msg_controllen = sizeof(outcmsg);
+ outmessage.msg_flags = MSG_EOR;
+
+ spin_lock(&con->writequeue_lock);
+ e = list_entry(con->writequeue.next, struct writequeue_entry,
+ list);
+
+ BUG_ON((struct list_head *) e == &con->writequeue);
+
+ len = e->len;
+ offset = e->offset;
+ spin_unlock(&con->writequeue_lock);
+ kmap(e->page);
+
+ /* Send the first block off the write queue */
+ iov[0].iov_base = page_address(e->page)+offset;
+ iov[0].iov_len = len;
+
+ cmsg = CMSG_FIRSTHDR(&outmessage);
+ cmsg->cmsg_level = IPPROTO_SCTP;
+ cmsg->cmsg_type = SCTP_SNDRCV;
+ cmsg->cmsg_len = CMSG_LEN(sizeof(struct sctp_sndrcvinfo));
+ sinfo = CMSG_DATA(cmsg);
+ memset(sinfo, 0x00, sizeof(struct sctp_sndrcvinfo));
+ sinfo->sinfo_ppid = cpu_to_le32(dlm_our_nodeid());
+ outmessage.msg_controllen = cmsg->cmsg_len;
+
+ ret = kernel_sendmsg(base_con->sock, &outmessage, iov, 1, len);
+ if (ret < 0) {
+ log_print("Send first packet to node %d failed: %d",
+ con->nodeid, ret);
+
+ /* Try again later */
+ clear_bit(CF_CONNECT_PENDING, &con->flags);
+ clear_bit(CF_INIT_PENDING, &con->flags);
+ }
+ else {
+ spin_lock(&con->writequeue_lock);
+ e->offset += ret;
+ e->len -= ret;
+
+ if (e->len == 0 && e->users == 0) {
+ list_del(&e->list);
+ kunmap(e->page);
+ free_entry(e);
+ }
+ spin_unlock(&con->writequeue_lock);
+ }
+}
+
+/* Connect a new socket to its peer */
+static void tcp_connect_to_sock(struct connection *con)
+{
+ int result = -EHOSTUNREACH;
+ struct sockaddr_storage saddr;
+ int addr_len;
+ struct socket *sock;
+
+ if (con->nodeid == 0) {
+ log_print("attempt to connect sock 0 foiled");
+ return;
+ }
+
+ mutex_lock(&con->sock_mutex);
+ if (con->retries++ > MAX_CONNECT_RETRIES)
+ goto out;
+
+ /* Some odd races can cause double-connects, ignore them */
+ if (con->sock) {
+ result = 0;
+ goto out;
+ }
+
+ /* Create a socket to communicate with */
+ result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_STREAM,
+ IPPROTO_TCP, &sock);
+ if (result < 0)
+ goto out_err;
+
+ memset(&saddr, 0, sizeof(saddr));
+ if (dlm_nodeid_to_addr(con->nodeid, &saddr))
+ goto out_err;
+
+ sock->sk->sk_user_data = con;
+ con->rx_action = receive_from_sock;
+ con->connect_action = tcp_connect_to_sock;
+ add_sock(sock, con);
+
+ make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len);
+
+ log_print("connecting to %d", con->nodeid);
+ result =
+ sock->ops->connect(sock, (struct sockaddr *)&saddr, addr_len,
+ O_NONBLOCK);
+ if (result == -EINPROGRESS)
+ result = 0;
+ if (result == 0)
+ goto out;
+
+out_err:
+ if (con->sock) {
+ sock_release(con->sock);
+ con->sock = NULL;
+ }
+ /*
+ * Some errors are fatal and this list might need adjusting. For other
+ * errors we try again until the max number of retries is reached.
+ */
+ if (result != -EHOSTUNREACH && result != -ENETUNREACH &&
+ result != -ENETDOWN && result != EINVAL
+ && result != -EPROTONOSUPPORT) {
+ lowcomms_connect_sock(con);
+ result = 0;
+ }
+out:
+ mutex_unlock(&con->sock_mutex);
+ return;
+}
+
+static struct socket *tcp_create_listen_sock(struct connection *con,
+ struct sockaddr_storage *saddr)
+{
+ struct socket *sock = NULL;
+ int result = 0;
+ int one = 1;
+ int addr_len;
+
+ if (dlm_local_addr[0]->ss_family == AF_INET)
+ addr_len = sizeof(struct sockaddr_in);
+ else
+ addr_len = sizeof(struct sockaddr_in6);
+
+ /* Create a socket to communicate with */
+ result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_STREAM,
+ IPPROTO_TCP, &sock);
+ if (result < 0) {
+ log_print("Can't create listening comms socket");
+ goto create_out;
+ }
+
+ result = kernel_setsockopt(sock, SOL_SOCKET, SO_REUSEADDR,
+ (char *)&one, sizeof(one));
+
+ if (result < 0) {
+ log_print("Failed to set SO_REUSEADDR on socket: %d", result);
+ }
+ sock->sk->sk_user_data = con;
+ con->rx_action = tcp_accept_from_sock;
+ con->connect_action = tcp_connect_to_sock;
+ con->sock = sock;
+
+ /* Bind to our port */
+ make_sockaddr(saddr, dlm_config.ci_tcp_port, &addr_len);
+ result = sock->ops->bind(sock, (struct sockaddr *) saddr, addr_len);
+ if (result < 0) {
+ log_print("Can't bind to port %d", dlm_config.ci_tcp_port);
+ sock_release(sock);
+ sock = NULL;
+ con->sock = NULL;
+ goto create_out;
+ }
+ result = kernel_setsockopt(sock, SOL_SOCKET, SO_KEEPALIVE,
+ (char *)&one, sizeof(one));
+ if (result < 0) {
+ log_print("Set keepalive failed: %d", result);
+ }
+
+ result = sock->ops->listen(sock, 5);
+ if (result < 0) {
+ log_print("Can't listen on port %d", dlm_config.ci_tcp_port);
+ sock_release(sock);
+ sock = NULL;
+ goto create_out;
+ }
+
+create_out:
+ return sock;
+}
+
+/* Get local addresses */
+static void init_local(void)
+{
+ struct sockaddr_storage sas, *addr;
+ int i;
+
+ dlm_local_count = 0;
+ for (i = 0; i < DLM_MAX_ADDR_COUNT - 1; i++) {
+ if (dlm_our_addr(&sas, i))
+ break;
+
+ addr = kmalloc(sizeof(*addr), GFP_KERNEL);
+ if (!addr)
+ break;
+ memcpy(addr, &sas, sizeof(*addr));
+ dlm_local_addr[dlm_local_count++] = addr;
+ }
+}
+
+/* Bind to an IP address. SCTP allows multiple address so it can do
+ multi-homing */
+static int add_sctp_bind_addr(struct connection *sctp_con,
+ struct sockaddr_storage *addr,
+ int addr_len, int num)
+{
+ int result = 0;
+
+ if (num == 1)
+ result = kernel_bind(sctp_con->sock,
+ (struct sockaddr *) addr,
+ addr_len);
+ else
+ result = kernel_setsockopt(sctp_con->sock, SOL_SCTP,
+ SCTP_SOCKOPT_BINDX_ADD,
+ (char *)addr, addr_len);
+
+ if (result < 0)
+ log_print("Can't bind to port %d addr number %d",
+ dlm_config.ci_tcp_port, num);
+
+ return result;
+}
+
+/* Initialise SCTP socket and bind to all interfaces */
+static int sctp_listen_for_all(void)
+{
+ struct socket *sock = NULL;
+ struct sockaddr_storage localaddr;
+ struct sctp_event_subscribe subscribe;
+ int result = -EINVAL, num = 1, i, addr_len;
+ struct connection *con = nodeid2con(0, GFP_KERNEL);
+ int bufsize = NEEDED_RMEM;
+
+ if (!con)
+ return -ENOMEM;
+
+ log_print("Using SCTP for communications");
+
+ result = sock_create_kern(dlm_local_addr[0]->ss_family, SOCK_SEQPACKET,
+ IPPROTO_SCTP, &sock);
+ if (result < 0) {
+ log_print("Can't create comms socket, check SCTP is loaded");
+ goto out;
+ }
+
+ /* Listen for events */
+ memset(&subscribe, 0, sizeof(subscribe));
+ subscribe.sctp_data_io_event = 1;
+ subscribe.sctp_association_event = 1;
+ subscribe.sctp_send_failure_event = 1;
+ subscribe.sctp_shutdown_event = 1;
+ subscribe.sctp_partial_delivery_event = 1;
+
+ result = kernel_setsockopt(sock, SOL_SOCKET, SO_RCVBUF,
+ (char *)&bufsize, sizeof(bufsize));
+ if (result)
+ log_print("Error increasing buffer space on socket %d", result);
+
+ result = kernel_setsockopt(sock, SOL_SCTP, SCTP_EVENTS,
+ (char *)&subscribe, sizeof(subscribe));
+ if (result < 0) {
+ log_print("Failed to set SCTP_EVENTS on socket: result=%d",
+ result);
+ goto create_delsock;
+ }
+
+ /* Init con struct */
+ sock->sk->sk_user_data = con;
+ con->sock = sock;
+ con->sock->sk->sk_data_ready = lowcomms_data_ready;
+ con->rx_action = receive_from_sock;
+ con->connect_action = sctp_init_assoc;
+
+ /* Bind to all interfaces. */
+ for (i = 0; i < dlm_local_count; i++) {
+ memcpy(&localaddr, dlm_local_addr[i], sizeof(localaddr));
+ make_sockaddr(&localaddr, dlm_config.ci_tcp_port, &addr_len);
+
+ result = add_sctp_bind_addr(con, &localaddr, addr_len, num);
+ if (result)
+ goto create_delsock;
+ ++num;
+ }
+
+ result = sock->ops->listen(sock, 5);
+ if (result < 0) {
+ log_print("Can't set socket listening");
+ goto create_delsock;
+ }
+
+ return 0;
+
+create_delsock:
+ sock_release(sock);
+ con->sock = NULL;
+out:
+ return result;
+}
+
+static int tcp_listen_for_all(void)
+{
+ struct socket *sock = NULL;
+ struct connection *con = nodeid2con(0, GFP_KERNEL);
+ int result = -EINVAL;
+
+ if (!con)
+ return -ENOMEM;
+
+ /* We don't support multi-homed hosts */
+ if (dlm_local_addr[1] != NULL) {
+ log_print("TCP protocol can't handle multi-homed hosts, "
+ "try SCTP");
+ return -EINVAL;
+ }
+
+ log_print("Using TCP for communications");
+
+ set_bit(CF_IS_OTHERCON, &con->flags);
+
+ sock = tcp_create_listen_sock(con, dlm_local_addr[0]);
+ if (sock) {
+ add_sock(sock, con);
+ result = 0;
+ }
+ else {
+ result = -EADDRINUSE;
+ }
+
+ return result;
+}
+
+
+
+static struct writequeue_entry *new_writequeue_entry(struct connection *con,
+ gfp_t allocation)
+{
+ struct writequeue_entry *entry;
+
+ entry = kmalloc(sizeof(struct writequeue_entry), allocation);
+ if (!entry)
+ return NULL;
+
+ entry->page = alloc_page(allocation);
+ if (!entry->page) {
+ kfree(entry);
+ return NULL;
+ }
+
+ entry->offset = 0;
+ entry->len = 0;
+ entry->end = 0;
+ entry->users = 0;
+ entry->con = con;
+
+ return entry;
+}
+
+void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc)
+{
+ struct connection *con;
+ struct writequeue_entry *e;
+ int offset = 0;
+ int users = 0;
+
+ con = nodeid2con(nodeid, allocation);
+ if (!con)
+ return NULL;
+
+ spin_lock(&con->writequeue_lock);
+ e = list_entry(con->writequeue.prev, struct writequeue_entry, list);
+ if ((&e->list == &con->writequeue) ||
+ (PAGE_CACHE_SIZE - e->end < len)) {
+ e = NULL;
+ } else {
+ offset = e->end;
+ e->end += len;
+ users = e->users++;
+ }
+ spin_unlock(&con->writequeue_lock);
+
+ if (e) {
+ got_one:
+ if (users == 0)
+ kmap(e->page);
+ *ppc = page_address(e->page) + offset;
+ return e;
+ }
+
+ e = new_writequeue_entry(con, allocation);
+ if (e) {
+ spin_lock(&con->writequeue_lock);
+ offset = e->end;
+ e->end += len;
+ users = e->users++;
+ list_add_tail(&e->list, &con->writequeue);
+ spin_unlock(&con->writequeue_lock);
+ goto got_one;
+ }
+ return NULL;
+}
+
+void dlm_lowcomms_commit_buffer(void *mh)
+{
+ struct writequeue_entry *e = (struct writequeue_entry *)mh;
+ struct connection *con = e->con;
+ int users;
+
+ spin_lock(&con->writequeue_lock);
+ users = --e->users;
+ if (users)
+ goto out;
+ e->len = e->end - e->offset;
+ kunmap(e->page);
+ spin_unlock(&con->writequeue_lock);
+
+ if (!test_and_set_bit(CF_WRITE_PENDING, &con->flags)) {
+ queue_work(send_workqueue, &con->swork);
+ }
+ return;
+
+out:
+ spin_unlock(&con->writequeue_lock);
+ return;
+}
+
+/* Send a message */
+static void send_to_sock(struct connection *con)
+{
+ int ret = 0;
+ ssize_t(*sendpage) (struct socket *, struct page *, int, size_t, int);
+ const int msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
+ struct writequeue_entry *e;
+ int len, offset;
+
+ mutex_lock(&con->sock_mutex);
+ if (con->sock == NULL)
+ goto out_connect;
+
+ sendpage = con->sock->ops->sendpage;
+
+ spin_lock(&con->writequeue_lock);
+ for (;;) {
+ e = list_entry(con->writequeue.next, struct writequeue_entry,
+ list);
+ if ((struct list_head *) e == &con->writequeue)
+ break;
+
+ len = e->len;
+ offset = e->offset;
+ BUG_ON(len == 0 && e->users == 0);
+ spin_unlock(&con->writequeue_lock);
+ kmap(e->page);
+
+ ret = 0;
+ if (len) {
+ ret = sendpage(con->sock, e->page, offset, len,
+ msg_flags);
+ if (ret == -EAGAIN || ret == 0)
+ goto out;
+ if (ret <= 0)
+ goto send_error;
+ } else {
+ /* Don't starve people filling buffers */
+ cond_resched();
+ }
+
+ spin_lock(&con->writequeue_lock);
+ e->offset += ret;
+ e->len -= ret;
+
+ if (e->len == 0 && e->users == 0) {
+ list_del(&e->list);
+ kunmap(e->page);
+ free_entry(e);
+ continue;
+ }
+ }
+ spin_unlock(&con->writequeue_lock);
+out:
+ mutex_unlock(&con->sock_mutex);
+ return;
+
+send_error:
+ mutex_unlock(&con->sock_mutex);
+ close_connection(con, false);
+ lowcomms_connect_sock(con);
+ return;
+
+out_connect:
+ mutex_unlock(&con->sock_mutex);
+ if (!test_bit(CF_INIT_PENDING, &con->flags))
+ lowcomms_connect_sock(con);
+ return;
+}
+
+static void clean_one_writequeue(struct connection *con)
+{
+ struct list_head *list;
+ struct list_head *temp;
+
+ spin_lock(&con->writequeue_lock);
+ list_for_each_safe(list, temp, &con->writequeue) {
+ struct writequeue_entry *e =
+ list_entry(list, struct writequeue_entry, list);
+ list_del(&e->list);
+ free_entry(e);
+ }
+ spin_unlock(&con->writequeue_lock);
+}
+
+/* Called from recovery when it knows that a node has
+ left the cluster */
+int dlm_lowcomms_close(int nodeid)
+{
+ struct connection *con;
+
+ log_print("closing connection to node %d", nodeid);
+ con = nodeid2con(nodeid, 0);
+ if (con) {
+ clean_one_writequeue(con);
+ close_connection(con, true);
+ }
+ return 0;
+}
+
+/* Receive workqueue function */
+static void process_recv_sockets(struct work_struct *work)
+{
+ struct connection *con = container_of(work, struct connection, rwork);
+ int err;
+
+ clear_bit(CF_READ_PENDING, &con->flags);
+ do {
+ err = con->rx_action(con);
+ } while (!err);
+}
+
+/* Send workqueue function */
+static void process_send_sockets(struct work_struct *work)
+{
+ struct connection *con = container_of(work, struct connection, swork);
+
+ if (test_and_clear_bit(CF_CONNECT_PENDING, &con->flags)) {
+ con->connect_action(con);
+ }
+ clear_bit(CF_WRITE_PENDING, &con->flags);
+ send_to_sock(con);
+}
+
+
+/* Discard all entries on the write queues */
+static void clean_writequeues(void)
+{
+ int nodeid;
+
+ for (nodeid = 1; nodeid <= max_nodeid; nodeid++) {
+ struct connection *con = __nodeid2con(nodeid, 0);
+
+ if (con)
+ clean_one_writequeue(con);
+ }
+}
+
+static void work_stop(void)
+{
+ destroy_workqueue(recv_workqueue);
+ destroy_workqueue(send_workqueue);
+}
+
+static int work_start(void)
+{
+ int error;
+ recv_workqueue = create_workqueue("dlm_recv");
+ error = IS_ERR(recv_workqueue);
+ if (error) {
+ log_print("can't start dlm_recv %d", error);
+ return error;
+ }
+
+ send_workqueue = create_singlethread_workqueue("dlm_send");
+ error = IS_ERR(send_workqueue);
+ if (error) {
+ log_print("can't start dlm_send %d", error);
+ destroy_workqueue(recv_workqueue);
+ return error;
+ }
+
+ return 0;
+}
+
+void dlm_lowcomms_stop(void)
+{
+ int i;
+ struct connection *con;
+
+ /* Set all the flags to prevent any
+ socket activity.
+ */
+ down(&connections_lock);
+ for (i = 0; i <= max_nodeid; i++) {
+ con = __nodeid2con(i, 0);
+ if (con)
+ con->flags |= 0xFF;
+ }
+ up(&connections_lock);
+
+ work_stop();
+
+ down(&connections_lock);
+ clean_writequeues();
+
+ for (i = 0; i <= max_nodeid; i++) {
+ 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);
+ }
+ }
+ max_nodeid = 0;
+ up(&connections_lock);
+ kmem_cache_destroy(con_cache);
+ idr_init(&connections_idr);
+}
+
+int dlm_lowcomms_start(void)
+{
+ int error = -EINVAL;
+ struct connection *con;
+
+ init_local();
+ if (!dlm_local_count) {
+ error = -ENOTCONN;
+ log_print("no local IP address has been set");
+ goto out;
+ }
+
+ error = -ENOMEM;
+ con_cache = kmem_cache_create("dlm_conn", sizeof(struct connection),
+ __alignof__(struct connection), 0,
+ NULL, NULL);
+ if (!con_cache)
+ goto out;
+
+ /* Set some sysctl minima */
+ if (sysctl_rmem_max < NEEDED_RMEM)
+ sysctl_rmem_max = NEEDED_RMEM;
+
+ /* Start listening */
+ if (dlm_config.ci_protocol == 0)
+ error = tcp_listen_for_all();
+ else
+ error = sctp_listen_for_all();
+ if (error)
+ goto fail_unlisten;
+
+ error = work_start();
+ if (error)
+ goto fail_unlisten;
+
+ return 0;
+
+fail_unlisten:
+ con = nodeid2con(0,0);
+ if (con) {
+ close_connection(con, false);
+ kmem_cache_free(con_cache, con);
+ }
+ kmem_cache_destroy(con_cache);
+
+out:
+ return error;
+}
/*
- * Copyright (C) 2006 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2006-2007 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
union {
struct dlm_lock_params32 lock;
struct dlm_lspace_params lspace;
+ struct dlm_purge_params purge;
} i;
};
kb->i.lspace.flags = kb32->i.lspace.flags;
kb->i.lspace.minor = kb32->i.lspace.minor;
strcpy(kb->i.lspace.name, kb32->i.lspace.name);
+ } else if (kb->cmd == DLM_USER_PURGE) {
+ kb->i.purge.nodeid = kb32->i.purge.nodeid;
+ kb->i.purge.pid = kb32->i.purge.pid;
} else {
kb->i.lock.mode = kb32->i.lock.mode;
kb->i.lock.namelen = kb32->i.lock.namelen;
static void compat_output(struct dlm_lock_result *res,
struct dlm_lock_result32 *res32)
{
- res32->length = res->length - (sizeof(struct dlm_lock_result) -
- sizeof(struct dlm_lock_result32));
res32->user_astaddr = (__u32)(long)res->user_astaddr;
res32->user_astparam = (__u32)(long)res->user_astparam;
res32->user_lksb = (__u32)(long)res->user_lksb;
}
#endif
+/* we could possibly check if the cancel of an orphan has resulted in the lkb
+ being removed and then remove that lkb from the orphans list and free it */
void dlm_user_add_ast(struct dlm_lkb *lkb, int type)
{
struct dlm_ls *ls;
struct dlm_user_args *ua;
struct dlm_user_proc *proc;
- int remove_ownqueue = 0;
+ int eol = 0, ast_type;
- /* dlm_clear_proc_locks() sets ORPHAN/DEAD flag on each
- lkb before dealing with it. We need to check this
- flag before taking ls_clear_proc_locks mutex because if
- it's set, dlm_clear_proc_locks() holds the mutex. */
-
- if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD)) {
- /* log_print("user_add_ast skip1 %x", lkb->lkb_flags); */
+ if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD))
return;
- }
ls = lkb->lkb_resource->res_ls;
mutex_lock(&ls->ls_clear_proc_locks);
/* If ORPHAN/DEAD flag is set, it means the process is dead so an ast
can't be delivered. For ORPHAN's, dlm_clear_proc_locks() freed
- lkb->ua so we can't try to use it. */
+ lkb->ua so we can't try to use it. This second check is necessary
+ for cases where a completion ast is received for an operation that
+ began before clear_proc_locks did its cancel/unlock. */
- if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD)) {
- /* log_print("user_add_ast skip2 %x", lkb->lkb_flags); */
+ if (lkb->lkb_flags & (DLM_IFL_ORPHAN | DLM_IFL_DEAD))
goto out;
- }
DLM_ASSERT(lkb->lkb_astparam, dlm_print_lkb(lkb););
ua = (struct dlm_user_args *)lkb->lkb_astparam;
goto out;
spin_lock(&proc->asts_spin);
- if (!(lkb->lkb_ast_type & (AST_COMP | AST_BAST))) {
+
+ ast_type = lkb->lkb_ast_type;
+ lkb->lkb_ast_type |= type;
+
+ if (!ast_type) {
kref_get(&lkb->lkb_ref);
list_add_tail(&lkb->lkb_astqueue, &proc->asts);
- lkb->lkb_ast_type |= type;
wake_up_interruptible(&proc->wait);
}
-
- /* noqueue requests that fail may need to be removed from the
- proc's locks list, there should be a better way of detecting
- this situation than checking all these things... */
-
- if (type == AST_COMP && lkb->lkb_grmode == DLM_LOCK_IV &&
- ua->lksb.sb_status == -EAGAIN && !list_empty(&lkb->lkb_ownqueue))
- remove_ownqueue = 1;
-
- /* unlocks or cancels of waiting requests need to be removed from the
- proc's unlocking list, again there must be a better way... */
-
- if (ua->lksb.sb_status == -DLM_EUNLOCK ||
+ if (type == AST_COMP && (ast_type & AST_COMP))
+ log_debug(ls, "ast overlap %x status %x %x",
+ lkb->lkb_id, ua->lksb.sb_status, lkb->lkb_flags);
+
+ /* Figure out if this lock is at the end of its life and no longer
+ available for the application to use. The lkb still exists until
+ the final ast is read. A lock becomes EOL in three situations:
+ 1. a noqueue request fails with EAGAIN
+ 2. an unlock completes with EUNLOCK
+ 3. a cancel of a waiting request completes with ECANCEL
+ An EOL lock needs to be removed from the process's list of locks.
+ And we can't allow any new operation on an EOL lock. This is
+ not related to the lifetime of the lkb struct which is managed
+ entirely by refcount. */
+
+ if (type == AST_COMP &&
+ lkb->lkb_grmode == DLM_LOCK_IV &&
+ ua->lksb.sb_status == -EAGAIN)
+ eol = 1;
+ else if (ua->lksb.sb_status == -DLM_EUNLOCK ||
(ua->lksb.sb_status == -DLM_ECANCEL &&
lkb->lkb_grmode == DLM_LOCK_IV))
- remove_ownqueue = 1;
+ eol = 1;
+ if (eol) {
+ lkb->lkb_ast_type &= ~AST_BAST;
+ lkb->lkb_flags |= DLM_IFL_ENDOFLIFE;
+ }
/* We want to copy the lvb to userspace when the completion
ast is read if the status is 0, the lock has an lvb and
spin_unlock(&proc->asts_spin);
- if (remove_ownqueue) {
+ if (eol) {
spin_lock(&ua->proc->locks_spin);
- list_del_init(&lkb->lkb_ownqueue);
+ if (!list_empty(&lkb->lkb_ownqueue)) {
+ list_del_init(&lkb->lkb_ownqueue);
+ dlm_put_lkb(lkb);
+ }
spin_unlock(&ua->proc->locks_spin);
- dlm_put_lkb(lkb);
}
out:
mutex_unlock(&ls->ls_clear_proc_locks);
return error;
}
-static int device_create_lockspace(struct dlm_lspace_params *params)
+static int create_misc_device(struct dlm_ls *ls, char *name)
{
- dlm_lockspace_t *lockspace;
- struct dlm_ls *ls;
int error, len;
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- error = dlm_new_lockspace(params->name, strlen(params->name),
- &lockspace, 0, DLM_USER_LVB_LEN);
- if (error)
- return error;
-
- ls = dlm_find_lockspace_local(lockspace);
- if (!ls)
- return -ENOENT;
-
error = -ENOMEM;
- len = strlen(params->name) + strlen(name_prefix) + 2;
+ len = strlen(name) + strlen(name_prefix) + 2;
ls->ls_device.name = kzalloc(len, GFP_KERNEL);
if (!ls->ls_device.name)
goto fail;
+
snprintf((char *)ls->ls_device.name, len, "%s_%s", name_prefix,
- params->name);
+ name);
ls->ls_device.fops = &device_fops;
ls->ls_device.minor = MISC_DYNAMIC_MINOR;
error = misc_register(&ls->ls_device);
if (error) {
kfree(ls->ls_device.name);
- goto fail;
}
+fail:
+ return error;
+}
+
+static int device_user_purge(struct dlm_user_proc *proc,
+ struct dlm_purge_params *params)
+{
+ struct dlm_ls *ls;
+ int error;
+
+ ls = dlm_find_lockspace_local(proc->lockspace);
+ if (!ls)
+ return -ENOENT;
+
+ error = dlm_user_purge(ls, proc, params->nodeid, params->pid);
- error = ls->ls_device.minor;
dlm_put_lockspace(ls);
return error;
+}
+
+static int device_create_lockspace(struct dlm_lspace_params *params)
+{
+ dlm_lockspace_t *lockspace;
+ struct dlm_ls *ls;
+ int error;
- fail:
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ error = dlm_new_lockspace(params->name, strlen(params->name),
+ &lockspace, 0, DLM_USER_LVB_LEN);
+ if (error)
+ return error;
+
+ ls = dlm_find_lockspace_local(lockspace);
+ if (!ls)
+ return -ENOENT;
+
+ error = create_misc_device(ls, params->name);
dlm_put_lockspace(ls);
- dlm_release_lockspace(lockspace, 0);
+
+ if (error)
+ dlm_release_lockspace(lockspace, 0);
+ else
+ error = ls->ls_device.minor;
+
return error;
}
if (!ls)
return -ENOENT;
+ /* Deregister the misc device first, so we don't have
+ * a device that's not attached to a lockspace. If
+ * dlm_release_lockspace fails then we can recreate it
+ */
error = misc_deregister(&ls->ls_device);
if (error) {
dlm_put_lockspace(ls);
dlm_put_lockspace(ls);
error = dlm_release_lockspace(lockspace, force);
+ if (error)
+ create_misc_device(ls, ls->ls_name);
out:
return error;
}
error = device_remove_lockspace(&kbuf->i.lspace);
break;
+ case DLM_USER_PURGE:
+ if (!proc) {
+ log_print("no locking on control device");
+ goto out_sig;
+ }
+ error = device_user_purge(proc, &kbuf->i.purge);
+ break;
+
default:
log_print("Unknown command passed to DLM device : %d\n",
kbuf->cmd);
u64 leaf_no)
{
struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
struct buffer_head *bh;
struct gfs2_leaf *lf;
- unsigned entries = 0;
+ unsigned entries = 0, entries2 = 0;
unsigned leaves = 0;
const struct gfs2_dirent **darr, *dent;
struct dirent_gather g;
return 0;
error = -ENOMEM;
- larr = vmalloc((leaves + entries) * sizeof(void *));
+ /*
+ * The extra 99 entries are not normally used, but are a buffer
+ * zone in case the number of entries in the leaf is corrupt.
+ * 99 is the maximum number of entries that can fit in a single
+ * leaf block.
+ */
+ larr = vmalloc((leaves + entries + 99) * sizeof(void *));
if (!larr)
goto out;
darr = (const struct gfs2_dirent **)(larr + leaves);
lf = (struct gfs2_leaf *)bh->b_data;
lfn = be64_to_cpu(lf->lf_next);
if (lf->lf_entries) {
+ entries2 += be16_to_cpu(lf->lf_entries);
dent = gfs2_dirent_scan(inode, bh->b_data, bh->b_size,
gfs2_dirent_gather, NULL, &g);
error = PTR_ERR(dent);
- if (IS_ERR(dent)) {
+ if (IS_ERR(dent))
+ goto out_kfree;
+ if (entries2 != g.offset) {
+ fs_warn(sdp, "Number of entries corrupt in dir "
+ "leaf %llu, entries2 (%u) != "
+ "g.offset (%u)\n",
+ (unsigned long long)bh->b_blocknr,
+ entries2, g.offset);
+
+ error = -EIO;
goto out_kfree;
}
error = 0;
}
} while(lfn);
+ BUG_ON(entries2 != entries);
error = do_filldir_main(ip, offset, opaque, filldir, darr,
entries, copied);
out_kfree:
filldir_t filldir)
{
struct gfs2_inode *dip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
struct dirent_gather g;
const struct gfs2_dirent **darr, *dent;
struct buffer_head *dibh;
return error;
error = -ENOMEM;
- darr = kmalloc(dip->i_di.di_entries * sizeof(struct gfs2_dirent *),
- GFP_KERNEL);
+ /* 96 is max number of dirents which can be stuffed into an inode */
+ darr = kmalloc(96 * sizeof(struct gfs2_dirent *), GFP_KERNEL);
if (darr) {
g.pdent = darr;
g.offset = 0;
error = PTR_ERR(dent);
goto out;
}
+ if (dip->i_di.di_entries != g.offset) {
+ fs_warn(sdp, "Number of entries corrupt in dir %llu, "
+ "ip->i_di.di_entries (%u) != g.offset (%u)\n",
+ (unsigned long long)dip->i_num.no_addr,
+ dip->i_di.di_entries,
+ g.offset);
+ error = -EIO;
+ goto out;
+ }
error = do_filldir_main(dip, offset, opaque, filldir, darr,
dip->i_di.di_entries, &copied);
out:
#include <linux/module.h>
#include <linux/rwsem.h>
#include <asm/uaccess.h>
+#include <linux/seq_file.h>
+#include <linux/debugfs.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
#include "gfs2.h"
#include "incore.h"
struct hlist_head hb_list;
};
+struct glock_iter {
+ int hash; /* hash bucket index */
+ struct gfs2_sbd *sdp; /* incore superblock */
+ struct gfs2_glock *gl; /* current glock struct */
+ struct hlist_head *hb_list; /* current hash bucket ptr */
+ struct seq_file *seq; /* sequence file for debugfs */
+ char string[512]; /* scratch space */
+};
+
typedef void (*glock_examiner) (struct gfs2_glock * gl);
static int gfs2_dump_lockstate(struct gfs2_sbd *sdp);
-static int dump_glock(struct gfs2_glock *gl);
-static int dump_inode(struct gfs2_inode *ip);
-static void gfs2_glock_xmote_th(struct gfs2_holder *gh);
+static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl);
+static void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh);
static void gfs2_glock_drop_th(struct gfs2_glock *gl);
static DECLARE_RWSEM(gfs2_umount_flush_sem);
+static struct dentry *gfs2_root;
#define GFS2_GL_HASH_SHIFT 15
#define GFS2_GL_HASH_SIZE (1 << GFS2_GL_HASH_SHIFT)
#define GFS2_GL_HASH_MASK (GFS2_GL_HASH_SIZE - 1)
static struct gfs2_gl_hash_bucket gl_hash_table[GFS2_GL_HASH_SIZE];
+static struct dentry *gfs2_root;
/*
* Despite what you might think, the numbers below are not arbitrary :-)
gfs2_assert(sdp, list_empty(&gl->gl_reclaim));
gfs2_assert(sdp, list_empty(&gl->gl_holders));
gfs2_assert(sdp, list_empty(&gl->gl_waiters1));
- gfs2_assert(sdp, list_empty(&gl->gl_waiters2));
gfs2_assert(sdp, list_empty(&gl->gl_waiters3));
glock_free(gl);
rv = 1;
atomic_set(&gl->gl_ref, 1);
gl->gl_state = LM_ST_UNLOCKED;
gl->gl_hash = hash;
- gl->gl_owner = NULL;
+ gl->gl_owner_pid = 0;
gl->gl_ip = 0;
gl->gl_ops = glops;
gl->gl_req_gh = NULL;
INIT_LIST_HEAD(&gh->gh_list);
gh->gh_gl = gl;
gh->gh_ip = (unsigned long)__builtin_return_address(0);
- gh->gh_owner = current;
+ gh->gh_owner_pid = current->pid;
gh->gh_state = state;
gh->gh_flags = flags;
gh->gh_error = 0;
{
gh->gh_state = state;
gh->gh_flags = flags;
- gh->gh_iflags &= 1 << HIF_ALLOCED;
+ gh->gh_iflags = 0;
gh->gh_ip = (unsigned long)__builtin_return_address(0);
}
gh->gh_ip = 0;
}
-/**
- * gfs2_holder_get - get a struct gfs2_holder structure
- * @gl: the glock
- * @state: the state we're requesting
- * @flags: the modifier flags
- * @gfp_flags:
- *
- * Figure out how big an impact this function has. Either:
- * 1) Replace it with a cache of structures hanging off the struct gfs2_sbd
- * 2) Leave it like it is
- *
- * Returns: the holder structure, NULL on ENOMEM
- */
-
-static struct gfs2_holder *gfs2_holder_get(struct gfs2_glock *gl,
- unsigned int state,
- int flags, gfp_t gfp_flags)
-{
- struct gfs2_holder *gh;
-
- gh = kmalloc(sizeof(struct gfs2_holder), gfp_flags);
- if (!gh)
- return NULL;
-
- gfs2_holder_init(gl, state, flags, gh);
- set_bit(HIF_ALLOCED, &gh->gh_iflags);
- gh->gh_ip = (unsigned long)__builtin_return_address(0);
- return gh;
-}
-
-/**
- * gfs2_holder_put - get rid of a struct gfs2_holder structure
- * @gh: the holder structure
- *
- */
-
-static void gfs2_holder_put(struct gfs2_holder *gh)
+static void gfs2_holder_wake(struct gfs2_holder *gh)
{
- gfs2_holder_uninit(gh);
- kfree(gh);
-}
-
-static void gfs2_holder_dispose_or_wake(struct gfs2_holder *gh)
-{
- if (test_bit(HIF_DEALLOC, &gh->gh_iflags)) {
- gfs2_holder_put(gh);
- return;
- }
clear_bit(HIF_WAIT, &gh->gh_iflags);
smp_mb();
wake_up_bit(&gh->gh_iflags, HIF_WAIT);
gfs2_reclaim_glock(sdp);
}
- gfs2_glock_xmote_th(gh);
+ gfs2_glock_xmote_th(gh->gh_gl, gh);
spin_lock(&gl->gl_spin);
}
return 1;
gh->gh_error = 0;
set_bit(HIF_HOLDER, &gh->gh_iflags);
- gfs2_holder_dispose_or_wake(gh);
+ gfs2_holder_wake(gh);
return 0;
}
* Returns: 1 if the queue is blocked
*/
-static int rq_demote(struct gfs2_holder *gh)
+static int rq_demote(struct gfs2_glock *gl)
{
- struct gfs2_glock *gl = gh->gh_gl;
-
if (!list_empty(&gl->gl_holders))
return 1;
- if (gl->gl_state == gh->gh_state || gl->gl_state == LM_ST_UNLOCKED) {
- list_del_init(&gh->gh_list);
- gh->gh_error = 0;
- spin_unlock(&gl->gl_spin);
- gfs2_holder_dispose_or_wake(gh);
- spin_lock(&gl->gl_spin);
- } else {
- gl->gl_req_gh = gh;
- set_bit(GLF_LOCK, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
-
- if (gh->gh_state == LM_ST_UNLOCKED ||
- gl->gl_state != LM_ST_EXCLUSIVE)
- gfs2_glock_drop_th(gl);
- else
- gfs2_glock_xmote_th(gh);
-
- spin_lock(&gl->gl_spin);
+ if (gl->gl_state == gl->gl_demote_state ||
+ gl->gl_state == LM_ST_UNLOCKED) {
+ clear_bit(GLF_DEMOTE, &gl->gl_flags);
+ return 0;
}
+ set_bit(GLF_LOCK, &gl->gl_flags);
+ spin_unlock(&gl->gl_spin);
+ if (gl->gl_demote_state == LM_ST_UNLOCKED ||
+ gl->gl_state != LM_ST_EXCLUSIVE)
+ gfs2_glock_drop_th(gl);
+ else
+ gfs2_glock_xmote_th(gl, NULL);
+ spin_lock(&gl->gl_spin);
return 0;
}
else
gfs2_assert_warn(gl->gl_sbd, 0);
- } else if (!list_empty(&gl->gl_waiters2) &&
- !test_bit(GLF_SKIP_WAITERS2, &gl->gl_flags)) {
- gh = list_entry(gl->gl_waiters2.next,
- struct gfs2_holder, gh_list);
-
- if (test_bit(HIF_DEMOTE, &gh->gh_iflags))
- blocked = rq_demote(gh);
- else
- gfs2_assert_warn(gl->gl_sbd, 0);
-
+ } else if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
+ blocked = rq_demote(gl);
} else if (!list_empty(&gl->gl_waiters3)) {
gh = list_entry(gl->gl_waiters3.next,
struct gfs2_holder, gh_list);
if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
list_add_tail(&gh.gh_list, &gl->gl_waiters1);
} else {
- gl->gl_owner = current;
+ gl->gl_owner_pid = current->pid;
gl->gl_ip = (unsigned long)__builtin_return_address(0);
clear_bit(HIF_WAIT, &gh.gh_iflags);
smp_mb();
if (test_and_set_bit(GLF_LOCK, &gl->gl_flags)) {
acquired = 0;
} else {
- gl->gl_owner = current;
+ gl->gl_owner_pid = current->pid;
gl->gl_ip = (unsigned long)__builtin_return_address(0);
}
spin_unlock(&gl->gl_spin);
{
spin_lock(&gl->gl_spin);
clear_bit(GLF_LOCK, &gl->gl_flags);
- gl->gl_owner = NULL;
+ gl->gl_owner_pid = 0;
gl->gl_ip = 0;
run_queue(gl);
BUG_ON(!spin_is_locked(&gl->gl_spin));
}
/**
- * handle_callback - add a demote request to a lock's queue
+ * handle_callback - process a demote request
* @gl: the glock
* @state: the state the caller wants us to change to
*
- * Note: This may fail sliently if we are out of memory.
+ * There are only two requests that we are going to see in actual
+ * practise: LM_ST_SHARED and LM_ST_UNLOCKED
*/
static void handle_callback(struct gfs2_glock *gl, unsigned int state)
{
- struct gfs2_holder *gh, *new_gh = NULL;
-
-restart:
spin_lock(&gl->gl_spin);
-
- list_for_each_entry(gh, &gl->gl_waiters2, gh_list) {
- if (test_bit(HIF_DEMOTE, &gh->gh_iflags) &&
- gl->gl_req_gh != gh) {
- if (gh->gh_state != state)
- gh->gh_state = LM_ST_UNLOCKED;
- goto out;
- }
- }
-
- if (new_gh) {
- list_add_tail(&new_gh->gh_list, &gl->gl_waiters2);
- new_gh = NULL;
- } else {
- spin_unlock(&gl->gl_spin);
-
- new_gh = gfs2_holder_get(gl, state, LM_FLAG_TRY, GFP_NOFS);
- if (!new_gh)
- return;
- set_bit(HIF_DEMOTE, &new_gh->gh_iflags);
- set_bit(HIF_DEALLOC, &new_gh->gh_iflags);
- set_bit(HIF_WAIT, &new_gh->gh_iflags);
-
- goto restart;
+ if (test_and_set_bit(GLF_DEMOTE, &gl->gl_flags) == 0) {
+ gl->gl_demote_state = state;
+ gl->gl_demote_time = jiffies;
+ } else if (gl->gl_demote_state != LM_ST_UNLOCKED) {
+ gl->gl_demote_state = state;
}
-
-out:
spin_unlock(&gl->gl_spin);
-
- if (new_gh)
- gfs2_holder_put(new_gh);
}
/**
/* Deal with each possible exit condition */
- if (!gh)
+ if (!gh) {
gl->gl_stamp = jiffies;
- else if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
+ if (ret & LM_OUT_CANCELED)
+ op_done = 0;
+ else
+ clear_bit(GLF_DEMOTE, &gl->gl_flags);
+ } else {
spin_lock(&gl->gl_spin);
list_del_init(&gh->gh_list);
gh->gh_error = -EIO;
- spin_unlock(&gl->gl_spin);
- } else if (test_bit(HIF_DEMOTE, &gh->gh_iflags)) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
- if (gl->gl_state == gh->gh_state ||
- gl->gl_state == LM_ST_UNLOCKED) {
+ if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+ goto out;
+ gh->gh_error = GLR_CANCELED;
+ if (ret & LM_OUT_CANCELED)
+ goto out;
+ if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
+ list_add_tail(&gh->gh_list, &gl->gl_holders);
gh->gh_error = 0;
- } else {
- if (gfs2_assert_warn(sdp, gh->gh_flags &
- (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) == -1)
- fs_warn(sdp, "ret = 0x%.8X\n", ret);
- gh->gh_error = GLR_TRYFAILED;
+ set_bit(HIF_HOLDER, &gh->gh_iflags);
+ set_bit(HIF_FIRST, &gh->gh_iflags);
+ op_done = 0;
+ goto out;
}
- spin_unlock(&gl->gl_spin);
-
- if (ret & LM_OUT_CANCELED)
- handle_callback(gl, LM_ST_UNLOCKED);
-
- } else if (ret & LM_OUT_CANCELED) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
- gh->gh_error = GLR_CANCELED;
- spin_unlock(&gl->gl_spin);
-
- } else if (relaxed_state_ok(gl->gl_state, gh->gh_state, gh->gh_flags)) {
- spin_lock(&gl->gl_spin);
- list_move_tail(&gh->gh_list, &gl->gl_holders);
- gh->gh_error = 0;
- set_bit(HIF_HOLDER, &gh->gh_iflags);
- spin_unlock(&gl->gl_spin);
-
- set_bit(HIF_FIRST, &gh->gh_iflags);
-
- op_done = 0;
-
- } else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)) {
- spin_lock(&gl->gl_spin);
- list_del_init(&gh->gh_list);
gh->gh_error = GLR_TRYFAILED;
- spin_unlock(&gl->gl_spin);
-
- } else {
+ if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
+ goto out;
+ gh->gh_error = -EINVAL;
if (gfs2_assert_withdraw(sdp, 0) == -1)
fs_err(sdp, "ret = 0x%.8X\n", ret);
+out:
+ spin_unlock(&gl->gl_spin);
}
if (glops->go_xmote_bh)
gfs2_glock_put(gl);
if (gh)
- gfs2_holder_dispose_or_wake(gh);
+ gfs2_holder_wake(gh);
}
/**
*
*/
-void gfs2_glock_xmote_th(struct gfs2_holder *gh)
+void gfs2_glock_xmote_th(struct gfs2_glock *gl, struct gfs2_holder *gh)
{
- struct gfs2_glock *gl = gh->gh_gl;
struct gfs2_sbd *sdp = gl->gl_sbd;
- int flags = gh->gh_flags;
- unsigned state = gh->gh_state;
+ int flags = gh ? gh->gh_flags : 0;
+ unsigned state = gh ? gh->gh_state : gl->gl_demote_state;
const struct gfs2_glock_operations *glops = gl->gl_ops;
int lck_flags = flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB |
LM_FLAG_NOEXP | LM_FLAG_ANY |
gfs2_assert_warn(sdp, !ret);
state_change(gl, LM_ST_UNLOCKED);
+ clear_bit(GLF_DEMOTE, &gl->gl_flags);
if (glops->go_inval)
glops->go_inval(gl, DIO_METADATA);
gfs2_glock_put(gl);
if (gh)
- gfs2_holder_dispose_or_wake(gh);
+ gfs2_holder_wake(gh);
}
/**
}
static inline struct gfs2_holder *
-find_holder_by_owner(struct list_head *head, struct task_struct *owner)
+find_holder_by_owner(struct list_head *head, pid_t pid)
{
struct gfs2_holder *gh;
list_for_each_entry(gh, head, gh_list) {
- if (gh->gh_owner == owner)
+ if (gh->gh_owner_pid == pid)
return gh;
}
return NULL;
}
+static void print_dbg(struct glock_iter *gi, const char *fmt, ...)
+{
+ va_list args;
+
+ va_start(args, fmt);
+ if (gi) {
+ vsprintf(gi->string, fmt, args);
+ seq_printf(gi->seq, gi->string);
+ }
+ else
+ vprintk(fmt, args);
+ va_end(args);
+}
+
/**
* add_to_queue - Add a holder to the wait queue (but look for recursion)
* @gh: the holder structure to add
struct gfs2_glock *gl = gh->gh_gl;
struct gfs2_holder *existing;
- BUG_ON(!gh->gh_owner);
+ BUG_ON(!gh->gh_owner_pid);
if (test_and_set_bit(HIF_WAIT, &gh->gh_iflags))
BUG();
- existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner);
+ existing = find_holder_by_owner(&gl->gl_holders, gh->gh_owner_pid);
if (existing) {
print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
- printk(KERN_INFO "pid : %d\n", existing->gh_owner->pid);
+ printk(KERN_INFO "pid : %d\n", existing->gh_owner_pid);
printk(KERN_INFO "lock type : %d lock state : %d\n",
existing->gh_gl->gl_name.ln_type, existing->gh_gl->gl_state);
print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
- printk(KERN_INFO "pid : %d\n", gh->gh_owner->pid);
+ printk(KERN_INFO "pid : %d\n", gh->gh_owner_pid);
printk(KERN_INFO "lock type : %d lock state : %d\n",
gl->gl_name.ln_type, gl->gl_state);
BUG();
}
- existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner);
+ existing = find_holder_by_owner(&gl->gl_waiters3, gh->gh_owner_pid);
if (existing) {
print_symbol(KERN_WARNING "original: %s\n", existing->gh_ip);
print_symbol(KERN_WARNING "new: %s\n", gh->gh_ip);
if (glops->go_unlock)
glops->go_unlock(gh);
- gl->gl_stamp = jiffies;
-
spin_lock(&gl->gl_spin);
+ gl->gl_stamp = jiffies;
}
clear_bit(GLF_LOCK, &gl->gl_flags);
* Diagnostic routines to help debug distributed deadlock
*/
+static void gfs2_print_symbol(struct glock_iter *gi, const char *fmt,
+ unsigned long address)
+{
+ char buffer[KSYM_SYMBOL_LEN];
+
+ sprint_symbol(buffer, address);
+ print_dbg(gi, fmt, buffer);
+}
+
/**
* dump_holder - print information about a glock holder
* @str: a string naming the type of holder
* Returns: 0 on success, -ENOBUFS when we run out of space
*/
-static int dump_holder(char *str, struct gfs2_holder *gh)
+static int dump_holder(struct glock_iter *gi, char *str,
+ struct gfs2_holder *gh)
{
unsigned int x;
- int error = -ENOBUFS;
-
- printk(KERN_INFO " %s\n", str);
- printk(KERN_INFO " owner = %ld\n",
- (gh->gh_owner) ? (long)gh->gh_owner->pid : -1);
- printk(KERN_INFO " gh_state = %u\n", gh->gh_state);
- printk(KERN_INFO " gh_flags =");
+ struct task_struct *gh_owner;
+
+ print_dbg(gi, " %s\n", str);
+ if (gh->gh_owner_pid) {
+ print_dbg(gi, " owner = %ld ", (long)gh->gh_owner_pid);
+ gh_owner = find_task_by_pid(gh->gh_owner_pid);
+ if (gh_owner)
+ print_dbg(gi, "(%s)\n", gh_owner->comm);
+ else
+ print_dbg(gi, "(ended)\n");
+ } else
+ print_dbg(gi, " owner = -1\n");
+ print_dbg(gi, " gh_state = %u\n", gh->gh_state);
+ print_dbg(gi, " gh_flags =");
for (x = 0; x < 32; x++)
if (gh->gh_flags & (1 << x))
- printk(" %u", x);
- printk(" \n");
- printk(KERN_INFO " error = %d\n", gh->gh_error);
- printk(KERN_INFO " gh_iflags =");
+ print_dbg(gi, " %u", x);
+ print_dbg(gi, " \n");
+ print_dbg(gi, " error = %d\n", gh->gh_error);
+ print_dbg(gi, " gh_iflags =");
for (x = 0; x < 32; x++)
if (test_bit(x, &gh->gh_iflags))
- printk(" %u", x);
- printk(" \n");
- print_symbol(KERN_INFO " initialized at: %s\n", gh->gh_ip);
-
- error = 0;
+ print_dbg(gi, " %u", x);
+ print_dbg(gi, " \n");
+ gfs2_print_symbol(gi, " initialized at: %s\n", gh->gh_ip);
- return error;
+ return 0;
}
/**
* Returns: 0 on success, -ENOBUFS when we run out of space
*/
-static int dump_inode(struct gfs2_inode *ip)
+static int dump_inode(struct glock_iter *gi, struct gfs2_inode *ip)
{
unsigned int x;
- int error = -ENOBUFS;
- printk(KERN_INFO " Inode:\n");
- printk(KERN_INFO " num = %llu %llu\n",
- (unsigned long long)ip->i_num.no_formal_ino,
- (unsigned long long)ip->i_num.no_addr);
- printk(KERN_INFO " type = %u\n", IF2DT(ip->i_inode.i_mode));
- printk(KERN_INFO " i_flags =");
+ print_dbg(gi, " Inode:\n");
+ print_dbg(gi, " num = %llu/%llu\n",
+ ip->i_num.no_formal_ino, ip->i_num.no_addr);
+ print_dbg(gi, " type = %u\n", IF2DT(ip->i_inode.i_mode));
+ print_dbg(gi, " i_flags =");
for (x = 0; x < 32; x++)
if (test_bit(x, &ip->i_flags))
- printk(" %u", x);
- printk(" \n");
-
- error = 0;
-
- return error;
+ print_dbg(gi, " %u", x);
+ print_dbg(gi, " \n");
+ return 0;
}
/**
* Returns: 0 on success, -ENOBUFS when we run out of space
*/
-static int dump_glock(struct gfs2_glock *gl)
+static int dump_glock(struct glock_iter *gi, struct gfs2_glock *gl)
{
struct gfs2_holder *gh;
unsigned int x;
int error = -ENOBUFS;
+ struct task_struct *gl_owner;
spin_lock(&gl->gl_spin);
- printk(KERN_INFO "Glock 0x%p (%u, %llu)\n", gl, gl->gl_name.ln_type,
- (unsigned long long)gl->gl_name.ln_number);
- printk(KERN_INFO " gl_flags =");
+ print_dbg(gi, "Glock 0x%p (%u, %llu)\n", gl, gl->gl_name.ln_type,
+ (unsigned long long)gl->gl_name.ln_number);
+ print_dbg(gi, " gl_flags =");
for (x = 0; x < 32; x++) {
if (test_bit(x, &gl->gl_flags))
- printk(" %u", x);
+ print_dbg(gi, " %u", x);
}
- printk(" \n");
- printk(KERN_INFO " gl_ref = %d\n", atomic_read(&gl->gl_ref));
- printk(KERN_INFO " gl_state = %u\n", gl->gl_state);
- printk(KERN_INFO " gl_owner = %s\n", gl->gl_owner->comm);
- print_symbol(KERN_INFO " gl_ip = %s\n", gl->gl_ip);
- printk(KERN_INFO " req_gh = %s\n", (gl->gl_req_gh) ? "yes" : "no");
- printk(KERN_INFO " req_bh = %s\n", (gl->gl_req_bh) ? "yes" : "no");
- printk(KERN_INFO " lvb_count = %d\n", atomic_read(&gl->gl_lvb_count));
- printk(KERN_INFO " object = %s\n", (gl->gl_object) ? "yes" : "no");
- printk(KERN_INFO " le = %s\n",
+ if (!test_bit(GLF_LOCK, &gl->gl_flags))
+ print_dbg(gi, " (unlocked)");
+ print_dbg(gi, " \n");
+ print_dbg(gi, " gl_ref = %d\n", atomic_read(&gl->gl_ref));
+ print_dbg(gi, " gl_state = %u\n", gl->gl_state);
+ if (gl->gl_owner_pid) {
+ gl_owner = find_task_by_pid(gl->gl_owner_pid);
+ if (gl_owner)
+ print_dbg(gi, " gl_owner = pid %d (%s)\n",
+ gl->gl_owner_pid, gl_owner->comm);
+ else
+ print_dbg(gi, " gl_owner = %d (ended)\n",
+ gl->gl_owner_pid);
+ } else
+ print_dbg(gi, " gl_owner = -1\n");
+ print_dbg(gi, " gl_ip = %lu\n", gl->gl_ip);
+ print_dbg(gi, " req_gh = %s\n", (gl->gl_req_gh) ? "yes" : "no");
+ print_dbg(gi, " req_bh = %s\n", (gl->gl_req_bh) ? "yes" : "no");
+ print_dbg(gi, " lvb_count = %d\n", atomic_read(&gl->gl_lvb_count));
+ print_dbg(gi, " object = %s\n", (gl->gl_object) ? "yes" : "no");
+ print_dbg(gi, " le = %s\n",
(list_empty(&gl->gl_le.le_list)) ? "no" : "yes");
- printk(KERN_INFO " reclaim = %s\n",
- (list_empty(&gl->gl_reclaim)) ? "no" : "yes");
+ print_dbg(gi, " reclaim = %s\n",
+ (list_empty(&gl->gl_reclaim)) ? "no" : "yes");
if (gl->gl_aspace)
- printk(KERN_INFO " aspace = 0x%p nrpages = %lu\n", gl->gl_aspace,
- gl->gl_aspace->i_mapping->nrpages);
+ print_dbg(gi, " aspace = 0x%p nrpages = %lu\n", gl->gl_aspace,
+ gl->gl_aspace->i_mapping->nrpages);
else
- printk(KERN_INFO " aspace = no\n");
- printk(KERN_INFO " ail = %d\n", atomic_read(&gl->gl_ail_count));
+ print_dbg(gi, " aspace = no\n");
+ print_dbg(gi, " ail = %d\n", atomic_read(&gl->gl_ail_count));
if (gl->gl_req_gh) {
- error = dump_holder("Request", gl->gl_req_gh);
+ error = dump_holder(gi, "Request", gl->gl_req_gh);
if (error)
goto out;
}
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
- error = dump_holder("Holder", gh);
+ error = dump_holder(gi, "Holder", gh);
if (error)
goto out;
}
list_for_each_entry(gh, &gl->gl_waiters1, gh_list) {
- error = dump_holder("Waiter1", gh);
- if (error)
- goto out;
- }
- list_for_each_entry(gh, &gl->gl_waiters2, gh_list) {
- error = dump_holder("Waiter2", gh);
+ error = dump_holder(gi, "Waiter1", gh);
if (error)
goto out;
}
list_for_each_entry(gh, &gl->gl_waiters3, gh_list) {
- error = dump_holder("Waiter3", gh);
+ error = dump_holder(gi, "Waiter3", gh);
if (error)
goto out;
}
+ if (test_bit(GLF_DEMOTE, &gl->gl_flags)) {
+ print_dbg(gi, " Demotion req to state %u (%llu uS ago)\n",
+ gl->gl_demote_state,
+ (u64)(jiffies - gl->gl_demote_time)*(1000000/HZ));
+ }
if (gl->gl_ops == &gfs2_inode_glops && gl->gl_object) {
if (!test_bit(GLF_LOCK, &gl->gl_flags) &&
- list_empty(&gl->gl_holders)) {
- error = dump_inode(gl->gl_object);
+ list_empty(&gl->gl_holders)) {
+ error = dump_inode(gi, gl->gl_object);
if (error)
goto out;
} else {
error = -ENOBUFS;
- printk(KERN_INFO " Inode: busy\n");
+ print_dbg(gi, " Inode: busy\n");
}
}
if (gl->gl_sbd != sdp)
continue;
- error = dump_glock(gl);
+ error = dump_glock(NULL, gl);
if (error)
break;
}
return 0;
}
+static int gfs2_glock_iter_next(struct glock_iter *gi)
+{
+ read_lock(gl_lock_addr(gi->hash));
+ while (1) {
+ if (!gi->hb_list) { /* If we don't have a hash bucket yet */
+ gi->hb_list = &gl_hash_table[gi->hash].hb_list;
+ if (hlist_empty(gi->hb_list)) {
+ read_unlock(gl_lock_addr(gi->hash));
+ gi->hash++;
+ read_lock(gl_lock_addr(gi->hash));
+ gi->hb_list = NULL;
+ if (gi->hash >= GFS2_GL_HASH_SIZE) {
+ read_unlock(gl_lock_addr(gi->hash));
+ return 1;
+ }
+ else
+ continue;
+ }
+ if (!hlist_empty(gi->hb_list)) {
+ gi->gl = list_entry(gi->hb_list->first,
+ struct gfs2_glock,
+ gl_list);
+ }
+ } else {
+ if (gi->gl->gl_list.next == NULL) {
+ read_unlock(gl_lock_addr(gi->hash));
+ gi->hash++;
+ read_lock(gl_lock_addr(gi->hash));
+ gi->hb_list = NULL;
+ continue;
+ }
+ gi->gl = list_entry(gi->gl->gl_list.next,
+ struct gfs2_glock, gl_list);
+ }
+ if (gi->gl)
+ break;
+ }
+ read_unlock(gl_lock_addr(gi->hash));
+ return 0;
+}
+
+static void gfs2_glock_iter_free(struct glock_iter *gi)
+{
+ kfree(gi);
+}
+
+static struct glock_iter *gfs2_glock_iter_init(struct gfs2_sbd *sdp)
+{
+ struct glock_iter *gi;
+
+ gi = kmalloc(sizeof (*gi), GFP_KERNEL);
+ if (!gi)
+ return NULL;
+
+ gi->sdp = sdp;
+ gi->hash = 0;
+ gi->gl = NULL;
+ gi->hb_list = NULL;
+ gi->seq = NULL;
+ memset(gi->string, 0, sizeof(gi->string));
+
+ if (gfs2_glock_iter_next(gi)) {
+ gfs2_glock_iter_free(gi);
+ return NULL;
+ }
+
+ return gi;
+}
+
+static void *gfs2_glock_seq_start(struct seq_file *file, loff_t *pos)
+{
+ struct glock_iter *gi;
+ loff_t n = *pos;
+
+ gi = gfs2_glock_iter_init(file->private);
+ if (!gi)
+ return NULL;
+
+ while (n--) {
+ if (gfs2_glock_iter_next(gi)) {
+ gfs2_glock_iter_free(gi);
+ return NULL;
+ }
+ }
+
+ return gi;
+}
+
+static void *gfs2_glock_seq_next(struct seq_file *file, void *iter_ptr,
+ loff_t *pos)
+{
+ struct glock_iter *gi = iter_ptr;
+
+ (*pos)++;
+
+ if (gfs2_glock_iter_next(gi)) {
+ gfs2_glock_iter_free(gi);
+ return NULL;
+ }
+
+ return gi;
+}
+
+static void gfs2_glock_seq_stop(struct seq_file *file, void *iter_ptr)
+{
+ /* nothing for now */
+}
+
+static int gfs2_glock_seq_show(struct seq_file *file, void *iter_ptr)
+{
+ struct glock_iter *gi = iter_ptr;
+
+ gi->seq = file;
+ dump_glock(gi, gi->gl);
+
+ return 0;
+}
+
+static struct seq_operations gfs2_glock_seq_ops = {
+ .start = gfs2_glock_seq_start,
+ .next = gfs2_glock_seq_next,
+ .stop = gfs2_glock_seq_stop,
+ .show = gfs2_glock_seq_show,
+};
+
+static int gfs2_debugfs_open(struct inode *inode, struct file *file)
+{
+ struct seq_file *seq;
+ int ret;
+
+ ret = seq_open(file, &gfs2_glock_seq_ops);
+ if (ret)
+ return ret;
+
+ seq = file->private_data;
+ seq->private = inode->i_private;
+
+ return 0;
+}
+
+static const struct file_operations gfs2_debug_fops = {
+ .owner = THIS_MODULE,
+ .open = gfs2_debugfs_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release
+};
+
+int gfs2_create_debugfs_file(struct gfs2_sbd *sdp)
+{
+ sdp->debugfs_dir = debugfs_create_dir(sdp->sd_table_name, gfs2_root);
+ if (!sdp->debugfs_dir)
+ return -ENOMEM;
+ sdp->debugfs_dentry_glocks = debugfs_create_file("glocks",
+ S_IFREG | S_IRUGO,
+ sdp->debugfs_dir, sdp,
+ &gfs2_debug_fops);
+ if (!sdp->debugfs_dentry_glocks)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp)
+{
+ if (sdp && sdp->debugfs_dir) {
+ if (sdp->debugfs_dentry_glocks) {
+ debugfs_remove(sdp->debugfs_dentry_glocks);
+ sdp->debugfs_dentry_glocks = NULL;
+ }
+ debugfs_remove(sdp->debugfs_dir);
+ sdp->debugfs_dir = NULL;
+ }
+}
+
+int gfs2_register_debugfs(void)
+{
+ gfs2_root = debugfs_create_dir("gfs2", NULL);
+ return gfs2_root ? 0 : -ENOMEM;
+}
+
+void gfs2_unregister_debugfs(void)
+{
+ debugfs_remove(gfs2_root);
+ gfs2_root = NULL;
+}
/* Look in glock's list of holders for one with current task as owner */
spin_lock(&gl->gl_spin);
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
- if (gh->gh_owner == current) {
+ if (gh->gh_owner_pid == current->pid) {
locked = 1;
break;
}
{
int ret;
spin_lock(&gl->gl_spin);
- ret = !list_empty(&gl->gl_waiters2) || !list_empty(&gl->gl_waiters3);
+ ret = test_bit(GLF_DEMOTE, &gl->gl_flags) || !list_empty(&gl->gl_waiters3);
spin_unlock(&gl->gl_spin);
return ret;
}
void gfs2_gl_hash_clear(struct gfs2_sbd *sdp, int wait);
int __init gfs2_glock_init(void);
+int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
+void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
+int gfs2_register_debugfs(void);
+void gfs2_unregister_debugfs(void);
#endif /* __GLOCK_DOT_H__ */
/* Actions */
HIF_MUTEX = 0,
HIF_PROMOTE = 1,
- HIF_DEMOTE = 2,
/* States */
- HIF_ALLOCED = 4,
- HIF_DEALLOC = 5,
HIF_HOLDER = 6,
HIF_FIRST = 7,
HIF_ABORTED = 9,
struct list_head gh_list;
struct gfs2_glock *gh_gl;
- struct task_struct *gh_owner;
+ pid_t gh_owner_pid;
unsigned int gh_state;
unsigned gh_flags;
enum {
GLF_LOCK = 1,
GLF_STICKY = 2,
+ GLF_DEMOTE = 3,
GLF_DIRTY = 5,
- GLF_SKIP_WAITERS2 = 6,
};
struct gfs2_glock {
unsigned int gl_state;
unsigned int gl_hash;
- struct task_struct *gl_owner;
+ unsigned int gl_demote_state; /* state requested by remote node */
+ unsigned long gl_demote_time; /* time of first demote request */
+ pid_t gl_owner_pid;
unsigned long gl_ip;
struct list_head gl_holders;
struct list_head gl_waiters1; /* HIF_MUTEX */
- struct list_head gl_waiters2; /* HIF_DEMOTE */
struct list_head gl_waiters3; /* HIF_PROMOTE */
const struct gfs2_glock_operations *gl_ops;
unsigned long sd_last_warning;
struct vfsmount *sd_gfs2mnt;
+ struct dentry *debugfs_dir; /* debugfs directory */
+ struct dentry *debugfs_dentry_glocks; /* for debugfs */
};
#endif /* __INCORE_DOT_H__ */
/* make_strname - convert GFS lock numbers to a string */
-static inline void make_strname(struct lm_lockname *lockname,
+static inline void make_strname(const struct lm_lockname *lockname,
struct gdlm_strname *str)
{
sprintf(str->name, "%8x%16llx", lockname->ln_type,
return -ENOMEM;
lp->lockname = *name;
+ make_strname(name, &lp->strname);
lp->ls = ls;
lp->cur = DLM_LOCK_IV;
lp->lvb = NULL;
unsigned int gdlm_do_lock(struct gdlm_lock *lp)
{
struct gdlm_ls *ls = lp->ls;
- struct gdlm_strname str;
int error, bast = 1;
/*
if (test_bit(LFL_NOBAST, &lp->flags))
bast = 0;
- make_strname(&lp->lockname, &str);
-
set_bit(LFL_ACTIVE, &lp->flags);
log_debug("lk %x,%llx id %x %d,%d %x", lp->lockname.ln_type,
lp->cur, lp->req, lp->lkf);
error = dlm_lock(ls->dlm_lockspace, lp->req, &lp->lksb, lp->lkf,
- str.name, str.namelen, 0, gdlm_ast, lp,
- bast ? gdlm_bast : NULL);
+ lp->strname.name, lp->strname.namelen, 0, gdlm_ast,
+ lp, bast ? gdlm_bast : NULL);
if ((error == -EAGAIN) && (lp->lkf & DLM_LKF_NOQUEUE)) {
lp->lksb.sb_status = -EAGAIN;
}
if (error) {
- log_debug("%s: gdlm_lock %x,%llx err=%d cur=%d req=%d lkf=%x "
+ log_error("%s: gdlm_lock %x,%llx err=%d cur=%d req=%d lkf=%x "
"flags=%lx", ls->fsname, lp->lockname.ln_type,
(unsigned long long)lp->lockname.ln_number, error,
lp->cur, lp->req, lp->lkf, lp->flags);
error = dlm_unlock(ls->dlm_lockspace, lp->lksb.sb_lkid, lkf, NULL, lp);
if (error) {
- log_debug("%s: gdlm_unlock %x,%llx err=%d cur=%d req=%d lkf=%x "
+ log_error("%s: gdlm_unlock %x,%llx err=%d cur=%d req=%d lkf=%x "
"flags=%lx", ls->fsname, lp->lockname.ln_type,
(unsigned long long)lp->lockname.ln_number, error,
lp->cur, lp->req, lp->lkf, lp->flags);
#define GDLM_STRNAME_BYTES 24
#define GDLM_LVB_SIZE 32
-#define GDLM_DROP_COUNT 200000
+#define GDLM_DROP_COUNT 0
#define GDLM_DROP_PERIOD 60
#define GDLM_NAME_LEN 128
struct gdlm_lock {
struct gdlm_ls *ls;
struct lm_lockname lockname;
+ struct gdlm_strname strname;
char *lvb;
struct dlm_lksb lksb;
tr->tr_touched = 1;
- if (!list_empty(&le->le_list))
- return;
-
gl = container_of(le, struct gfs2_glock, gl_le);
if (gfs2_assert_withdraw(sdp, gfs2_glock_is_held_excl(gl)))
return;
- gfs2_glock_hold(gl);
- set_bit(GLF_DIRTY, &gl->gl_flags);
gfs2_log_lock(sdp);
+ if (!list_empty(&le->le_list)){
+ gfs2_log_unlock(sdp);
+ return;
+ }
+ gfs2_glock_hold(gl);
+ set_bit(GLF_DIRTY, &gl->gl_flags);
sdp->sd_log_num_gl++;
list_add(&le->le_list, &sdp->sd_log_le_gl);
gfs2_log_unlock(sdp);
tr->tr_touched = 1;
- if (!list_empty(&le->le_list))
- return;
-
rgd = container_of(le, struct gfs2_rgrpd, rd_le);
- gfs2_rgrp_bh_hold(rgd);
gfs2_log_lock(sdp);
+ if (!list_empty(&le->le_list)){
+ gfs2_log_unlock(sdp);
+ return;
+ }
+ gfs2_rgrp_bh_hold(rgd);
sdp->sd_log_num_rg++;
list_add(&le->le_list, &sdp->sd_log_le_rg);
gfs2_log_unlock(sdp);
spin_lock_init(&gl->gl_spin);
INIT_LIST_HEAD(&gl->gl_holders);
INIT_LIST_HEAD(&gl->gl_waiters1);
- INIT_LIST_HEAD(&gl->gl_waiters2);
INIT_LIST_HEAD(&gl->gl_waiters3);
gl->gl_lvb = NULL;
atomic_set(&gl->gl_lvb_count, 0);
if (error)
goto fail_unregister;
+ gfs2_register_debugfs();
+
printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__);
return 0;
static void __exit exit_gfs2_fs(void)
{
+ gfs2_unregister_debugfs();
unregister_filesystem(&gfs2_fs_type);
unregister_filesystem(&gfs2meta_fs_type);
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/lm_interface.h>
+#include <linux/parser.h>
#include "gfs2.h"
#include "incore.h"
#include "sys.h"
#include "util.h"
+enum {
+ Opt_lockproto,
+ Opt_locktable,
+ Opt_hostdata,
+ Opt_spectator,
+ Opt_ignore_local_fs,
+ Opt_localflocks,
+ Opt_localcaching,
+ Opt_debug,
+ Opt_nodebug,
+ Opt_upgrade,
+ Opt_num_glockd,
+ Opt_acl,
+ Opt_noacl,
+ Opt_quota_off,
+ Opt_quota_account,
+ Opt_quota_on,
+ Opt_suiddir,
+ Opt_nosuiddir,
+ Opt_data_writeback,
+ Opt_data_ordered,
+};
+
+static match_table_t tokens = {
+ {Opt_lockproto, "lockproto=%s"},
+ {Opt_locktable, "locktable=%s"},
+ {Opt_hostdata, "hostdata=%s"},
+ {Opt_spectator, "spectator"},
+ {Opt_ignore_local_fs, "ignore_local_fs"},
+ {Opt_localflocks, "localflocks"},
+ {Opt_localcaching, "localcaching"},
+ {Opt_debug, "debug"},
+ {Opt_nodebug, "nodebug"},
+ {Opt_upgrade, "upgrade"},
+ {Opt_num_glockd, "num_glockd=%d"},
+ {Opt_acl, "acl"},
+ {Opt_noacl, "noacl"},
+ {Opt_quota_off, "quota=off"},
+ {Opt_quota_account, "quota=account"},
+ {Opt_quota_on, "quota=on"},
+ {Opt_suiddir, "suiddir"},
+ {Opt_nosuiddir, "nosuiddir"},
+ {Opt_data_writeback, "data=writeback"},
+ {Opt_data_ordered, "data=ordered"}
+};
+
/**
* gfs2_mount_args - Parse mount options
* @sdp:
process them */
for (options = data; (o = strsep(&options, ",")); ) {
+ int token, option;
+ substring_t tmp[MAX_OPT_ARGS];
+
if (!*o)
continue;
- v = strchr(o, '=');
- if (v)
- *v++ = 0;
+ token = match_token(o, tokens, tmp);
+ switch (token) {
+ case Opt_lockproto:
+ v = match_strdup(&tmp[0]);
+ if (!v) {
+ fs_info(sdp, "no memory for lockproto\n");
+ error = -ENOMEM;
+ goto out_error;
+ }
- if (!strcmp(o, "lockproto")) {
- if (!v)
- goto need_value;
- if (remount && strcmp(v, args->ar_lockproto))
+ if (remount && strcmp(v, args->ar_lockproto)) {
+ kfree(v);
goto cant_remount;
+ }
+
strncpy(args->ar_lockproto, v, GFS2_LOCKNAME_LEN);
args->ar_lockproto[GFS2_LOCKNAME_LEN - 1] = 0;
- }
+ kfree(v);
+ break;
+ case Opt_locktable:
+ v = match_strdup(&tmp[0]);
+ if (!v) {
+ fs_info(sdp, "no memory for locktable\n");
+ error = -ENOMEM;
+ goto out_error;
+ }
- else if (!strcmp(o, "locktable")) {
- if (!v)
- goto need_value;
- if (remount && strcmp(v, args->ar_locktable))
+ if (remount && strcmp(v, args->ar_locktable)) {
+ kfree(v);
goto cant_remount;
+ }
+
strncpy(args->ar_locktable, v, GFS2_LOCKNAME_LEN);
- args->ar_locktable[GFS2_LOCKNAME_LEN - 1] = 0;
- }
+ args->ar_locktable[GFS2_LOCKNAME_LEN - 1] = 0;
+ kfree(v);
+ break;
+ case Opt_hostdata:
+ v = match_strdup(&tmp[0]);
+ if (!v) {
+ fs_info(sdp, "no memory for hostdata\n");
+ error = -ENOMEM;
+ goto out_error;
+ }
- else if (!strcmp(o, "hostdata")) {
- if (!v)
- goto need_value;
- if (remount && strcmp(v, args->ar_hostdata))
+ if (remount && strcmp(v, args->ar_hostdata)) {
+ kfree(v);
goto cant_remount;
+ }
+
strncpy(args->ar_hostdata, v, GFS2_LOCKNAME_LEN);
args->ar_hostdata[GFS2_LOCKNAME_LEN - 1] = 0;
- }
-
- else if (!strcmp(o, "spectator")) {
+ kfree(v);
+ break;
+ case Opt_spectator:
if (remount && !args->ar_spectator)
goto cant_remount;
args->ar_spectator = 1;
sdp->sd_vfs->s_flags |= MS_RDONLY;
- }
-
- else if (!strcmp(o, "ignore_local_fs")) {
+ break;
+ case Opt_ignore_local_fs:
if (remount && !args->ar_ignore_local_fs)
goto cant_remount;
args->ar_ignore_local_fs = 1;
- }
-
- else if (!strcmp(o, "localflocks")) {
+ break;
+ case Opt_localflocks:
if (remount && !args->ar_localflocks)
goto cant_remount;
args->ar_localflocks = 1;
- }
-
- else if (!strcmp(o, "localcaching")) {
+ break;
+ case Opt_localcaching:
if (remount && !args->ar_localcaching)
goto cant_remount;
args->ar_localcaching = 1;
- }
-
- else if (!strcmp(o, "debug"))
+ break;
+ case Opt_debug:
args->ar_debug = 1;
-
- else if (!strcmp(o, "nodebug"))
+ break;
+ case Opt_nodebug:
args->ar_debug = 0;
-
- else if (!strcmp(o, "upgrade")) {
+ break;
+ case Opt_upgrade:
if (remount && !args->ar_upgrade)
goto cant_remount;
args->ar_upgrade = 1;
- }
+ break;
+ case Opt_num_glockd:
+ if ((error = match_int(&tmp[0], &option))) {
+ fs_info(sdp, "problem getting num_glockd\n");
+ goto out_error;
+ }
- else if (!strcmp(o, "num_glockd")) {
- unsigned int x;
- if (!v)
- goto need_value;
- sscanf(v, "%u", &x);
- if (remount && x != args->ar_num_glockd)
+ if (remount && option != args->ar_num_glockd)
goto cant_remount;
- if (!x || x > GFS2_GLOCKD_MAX) {
+ if (!option || option > GFS2_GLOCKD_MAX) {
fs_info(sdp, "0 < num_glockd <= %u (not %u)\n",
- GFS2_GLOCKD_MAX, x);
+ GFS2_GLOCKD_MAX, option);
error = -EINVAL;
- break;
+ goto out_error;
}
- args->ar_num_glockd = x;
- }
-
- else if (!strcmp(o, "acl")) {
+ args->ar_num_glockd = option;
+ break;
+ case Opt_acl:
args->ar_posix_acl = 1;
sdp->sd_vfs->s_flags |= MS_POSIXACL;
- }
-
- else if (!strcmp(o, "noacl")) {
+ break;
+ case Opt_noacl:
args->ar_posix_acl = 0;
sdp->sd_vfs->s_flags &= ~MS_POSIXACL;
- }
-
- else if (!strcmp(o, "quota")) {
- if (!v)
- goto need_value;
- if (!strcmp(v, "off"))
- args->ar_quota = GFS2_QUOTA_OFF;
- else if (!strcmp(v, "account"))
- args->ar_quota = GFS2_QUOTA_ACCOUNT;
- else if (!strcmp(v, "on"))
- args->ar_quota = GFS2_QUOTA_ON;
- else {
- fs_info(sdp, "invalid value for quota\n");
- error = -EINVAL;
- break;
- }
- }
-
- else if (!strcmp(o, "suiddir"))
+ break;
+ case Opt_quota_off:
+ args->ar_quota = GFS2_QUOTA_OFF;
+ break;
+ case Opt_quota_account:
+ args->ar_quota = GFS2_QUOTA_ACCOUNT;
+ break;
+ case Opt_quota_on:
+ args->ar_quota = GFS2_QUOTA_ON;
+ break;
+ case Opt_suiddir:
args->ar_suiddir = 1;
-
- else if (!strcmp(o, "nosuiddir"))
+ break;
+ case Opt_nosuiddir:
args->ar_suiddir = 0;
-
- else if (!strcmp(o, "data")) {
- if (!v)
- goto need_value;
- if (!strcmp(v, "writeback"))
- args->ar_data = GFS2_DATA_WRITEBACK;
- else if (!strcmp(v, "ordered"))
- args->ar_data = GFS2_DATA_ORDERED;
- else {
- fs_info(sdp, "invalid value for data\n");
- error = -EINVAL;
- break;
- }
- }
-
- else {
+ break;
+ case Opt_data_writeback:
+ args->ar_data = GFS2_DATA_WRITEBACK;
+ break;
+ case Opt_data_ordered:
+ args->ar_data = GFS2_DATA_ORDERED;
+ break;
+ default:
fs_info(sdp, "unknown option: %s\n", o);
error = -EINVAL;
- break;
+ goto out_error;
}
}
+out_error:
if (error)
fs_info(sdp, "invalid mount option(s)\n");
return error;
-need_value:
- fs_info(sdp, "need value for option %s\n", o);
- return -EINVAL;
-
cant_remount:
fs_info(sdp, "can't remount with option %s\n", o);
return -EINVAL;
void *kaddr;
int error;
- BUG_ON(page->index);
+ /*
+ * Due to the order of unstuffing files and ->nopage(), we can be
+ * asked for a zero page in the case of a stuffed file being extended,
+ * so we need to supply one here. It doesn't happen often.
+ */
+ if (unlikely(page->index)) {
+ kaddr = kmap_atomic(page, KM_USER0);
+ memset(kaddr, 0, PAGE_CACHE_SIZE);
+ kunmap_atomic(kaddr, KM_USER0);
+ flush_dcache_page(page);
+ SetPageUptodate(page);
+ return 0;
+ }
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
ip->i_di.di_size);
memset(kaddr + ip->i_di.di_size, 0, PAGE_CACHE_SIZE - ip->i_di.di_size);
kunmap_atomic(kaddr, KM_USER0);
-
+ flush_dcache_page(page);
brelse(dibh);
-
SetPageUptodate(page);
return 0;
gfs2_quota_unlock(ip);
gfs2_alloc_put(ip);
}
+ unlock_page(page);
gfs2_glock_dq_m(1, &ip->i_gh);
+ lock_page(page);
gfs2_holder_uninit(&ip->i_gh);
return 0;
gfs2_quota_unlock(ip);
gfs2_alloc_put(ip);
}
+ unlock_page(page);
gfs2_glock_dq_m(1, &ip->i_gh);
+ lock_page(page);
gfs2_holder_uninit(&ip->i_gh);
fail_nounlock:
ClearPageUptodate(page);
if (error)
goto fail;
+ gfs2_create_debugfs_file(sdp);
+
error = gfs2_sys_fs_add(sdp);
if (error)
goto fail;
fail_sys:
gfs2_sys_fs_del(sdp);
fail:
+ gfs2_delete_debugfs_file(sdp);
kfree(sdp);
sb->s_fs_info = NULL;
return error;
static void gfs2_kill_sb(struct super_block *sb)
{
+ gfs2_delete_debugfs_file(sb->s_fs_info);
kill_block_super(sb);
}
return error;
}
+/**
+ * gfs2_drop_inode - Drop an inode (test for remote unlink)
+ * @inode: The inode to drop
+ *
+ * If we've received a callback on an iopen lock then its because a
+ * remote node tried to deallocate the inode but failed due to this node
+ * still having the inode open. Here we mark the link count zero
+ * since we know that it must have reached zero if the GLF_DEMOTE flag
+ * is set on the iopen glock. If we didn't do a disk read since the
+ * remote node removed the final link then we might otherwise miss
+ * this event. This check ensures that this node will deallocate the
+ * inode's blocks, or alternatively pass the baton on to another
+ * node for later deallocation.
+ */
+static void gfs2_drop_inode(struct inode *inode)
+{
+ if (inode->i_private && inode->i_nlink) {
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_glock *gl = ip->i_iopen_gh.gh_gl;
+ if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
+ clear_nlink(inode);
+ }
+ generic_drop_inode(inode);
+}
+
/**
* gfs2_clear_inode - Deallocate an inode when VFS is done with it
* @inode: The VFS inode
out_uninit:
gfs2_holder_uninit(&ip->i_iopen_gh);
gfs2_glock_dq_uninit(&gh);
- if (error)
+ if (error && error != GLR_TRYFAILED)
fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
out:
truncate_inode_pages(&inode->i_data, 0);
.statfs = gfs2_statfs,
.remount_fs = gfs2_remount_fs,
.clear_inode = gfs2_clear_inode,
+ .drop_inode = gfs2_drop_inode,
.show_options = gfs2_show_options,
};
#include "trans.h"
#include "ops_file.h"
#include "util.h"
+#include "log.h"
#define BFITNOENT ((u32)~0)
* @al: the struct gfs2_alloc structure describing the reservation
*
* If there's room for the requested blocks to be allocated from the RG:
- * Sets the $al_reserved_data field in @al.
- * Sets the $al_reserved_meta field in @al.
* Sets the $al_rgd field in @al.
*
* Returns: 1 on success (it fits), 0 on failure (it doesn't fit)
struct gfs2_sbd *sdp = rgd->rd_sbd;
int ret = 0;
+ if (rgd->rd_rg.rg_flags & GFS2_RGF_NOALLOC)
+ return 0;
+
spin_lock(&sdp->sd_rindex_spin);
if (rgd->rd_free_clone >= al->al_requested) {
al->al_rgd = rgd;
rgd = gfs2_rgrpd_get_first(sdp);
if (rgd == begin) {
- if (++loops >= 2 || !skipped)
+ if (++loops >= 3)
return -ENOSPC;
+ if (!skipped)
+ loops++;
flags = 0;
+ if (loops == 2)
+ gfs2_log_flush(sdp, NULL);
}
}
/* Version of the device interface */
#define DLM_DEVICE_VERSION_MAJOR 5
-#define DLM_DEVICE_VERSION_MINOR 0
+#define DLM_DEVICE_VERSION_MINOR 1
#define DLM_DEVICE_VERSION_PATCH 0
/* struct passed to the lock write */
char name[0];
};
+struct dlm_purge_params {
+ __u32 nodeid;
+ __u32 pid;
+};
+
struct dlm_write_request {
__u32 version[3];
__u8 cmd;
union {
struct dlm_lock_params lock;
struct dlm_lspace_params lspace;
+ struct dlm_purge_params purge;
} i;
};
#define DLM_USER_QUERY 3
#define DLM_USER_CREATE_LOCKSPACE 4
#define DLM_USER_REMOVE_LOCKSPACE 5
+#define DLM_USER_PURGE 6
/* Arbitrary length restriction */
#define MAX_LS_NAME_LEN 64
projects / mirror_ubuntu-zesty-kernel.git / commitdiff