aboutsummaryrefslogtreecommitdiffstats
path: root/fs/dlm
diff options
context:
space:
mode:
Diffstat (limited to 'fs/dlm')
-rw-r--r--fs/dlm/Kconfig10
-rw-r--r--fs/dlm/Makefile2
-rw-r--r--fs/dlm/ast.c31
-rw-r--r--fs/dlm/ast.h1
-rw-r--r--fs/dlm/config.c163
-rw-r--r--fs/dlm/config.h9
-rw-r--r--fs/dlm/debug_fs.c151
-rw-r--r--fs/dlm/dir.c7
-rw-r--r--fs/dlm/dlm_internal.h147
-rw-r--r--fs/dlm/lock.c1069
-rw-r--r--fs/dlm/lock.h23
-rw-r--r--fs/dlm/lockspace.c173
-rw-r--r--fs/dlm/lockspace.h14
-rw-r--r--fs/dlm/lowcomms.c1975
-rw-r--r--fs/dlm/lowcomms.h33
-rw-r--r--fs/dlm/main.c3
-rw-r--r--fs/dlm/member.c59
-rw-r--r--fs/dlm/memory.c68
-rw-r--r--fs/dlm/memory.h6
-rw-r--r--fs/dlm/midcomms.c1514
-rw-r--r--fs/dlm/midcomms.h21
-rw-r--r--fs/dlm/netlink.c9
-rw-r--r--fs/dlm/plock.c213
-rw-r--r--fs/dlm/rcom.c246
-rw-r--r--fs/dlm/recover.c49
-rw-r--r--fs/dlm/recoverd.c40
-rw-r--r--fs/dlm/requestqueue.c37
-rw-r--r--fs/dlm/user.c56
-rw-r--r--fs/dlm/util.c90
-rw-r--r--fs/dlm/util.h6
30 files changed, 4267 insertions, 1958 deletions
diff --git a/fs/dlm/Kconfig b/fs/dlm/Kconfig
index f82a4952769d..1105ce3c80cb 100644
--- a/fs/dlm/Kconfig
+++ b/fs/dlm/Kconfig
@@ -4,10 +4,20 @@ menuconfig DLM
depends on INET
depends on SYSFS && CONFIGFS_FS && (IPV6 || IPV6=n)
select IP_SCTP
+ select SRCU
help
A general purpose distributed lock manager for kernel or userspace
applications.
+config DLM_DEPRECATED_API
+ bool "DLM deprecated API"
+ depends on DLM
+ help
+ Enables deprecated DLM timeout features that will be removed in
+ later Linux kernel releases.
+
+ If you are unsure, say N.
+
config DLM_DEBUG
bool "DLM debugging"
depends on DLM
diff --git a/fs/dlm/Makefile b/fs/dlm/Makefile
index 3545fdafc6fb..71dab733cf9a 100644
--- a/fs/dlm/Makefile
+++ b/fs/dlm/Makefile
@@ -9,7 +9,6 @@ dlm-y := ast.o \
member.o \
memory.o \
midcomms.o \
- netlink.o \
lowcomms.o \
plock.o \
rcom.o \
@@ -18,5 +17,6 @@ dlm-y := ast.o \
requestqueue.o \
user.o \
util.o
+dlm-$(CONFIG_DLM_DEPRECATED_API) += netlink.o
dlm-$(CONFIG_DLM_DEBUG) += debug_fs.o
diff --git a/fs/dlm/ast.c b/fs/dlm/ast.c
index 283c7b94edda..d60a8d8f109d 100644
--- a/fs/dlm/ast.c
+++ b/fs/dlm/ast.c
@@ -9,6 +9,8 @@
*******************************************************************************
******************************************************************************/
+#include <trace/events/dlm.h>
+
#include "dlm_internal.h"
#include "lock.h"
#include "user.h"
@@ -198,13 +200,13 @@ void dlm_add_cb(struct dlm_lkb *lkb, uint32_t flags, int mode, int status,
if (!prev_seq) {
kref_get(&lkb->lkb_ref);
+ mutex_lock(&ls->ls_cb_mutex);
if (test_bit(LSFL_CB_DELAY, &ls->ls_flags)) {
- mutex_lock(&ls->ls_cb_mutex);
list_add(&lkb->lkb_cb_list, &ls->ls_cb_delay);
- mutex_unlock(&ls->ls_cb_mutex);
} else {
queue_work(ls->ls_callback_wq, &lkb->lkb_cb_work);
}
+ mutex_unlock(&ls->ls_cb_mutex);
}
out:
mutex_unlock(&lkb->lkb_cb_mutex);
@@ -253,10 +255,12 @@ void dlm_callback_work(struct work_struct *work)
if (callbacks[i].flags & DLM_CB_SKIP) {
continue;
} else if (callbacks[i].flags & DLM_CB_BAST) {
+ trace_dlm_bast(ls, lkb, callbacks[i].mode);
bastfn(lkb->lkb_astparam, callbacks[i].mode);
} else if (callbacks[i].flags & DLM_CB_CAST) {
lkb->lkb_lksb->sb_status = callbacks[i].sb_status;
lkb->lkb_lksb->sb_flags = callbacks[i].sb_flags;
+ trace_dlm_ast(ls, lkb);
castfn(lkb->lkb_astparam);
}
}
@@ -284,10 +288,13 @@ void dlm_callback_stop(struct dlm_ls *ls)
void dlm_callback_suspend(struct dlm_ls *ls)
{
- set_bit(LSFL_CB_DELAY, &ls->ls_flags);
+ if (ls->ls_callback_wq) {
+ mutex_lock(&ls->ls_cb_mutex);
+ set_bit(LSFL_CB_DELAY, &ls->ls_flags);
+ mutex_unlock(&ls->ls_cb_mutex);
- if (ls->ls_callback_wq)
flush_workqueue(ls->ls_callback_wq);
+ }
}
#define MAX_CB_QUEUE 25
@@ -295,13 +302,14 @@ void dlm_callback_suspend(struct dlm_ls *ls)
void dlm_callback_resume(struct dlm_ls *ls)
{
struct dlm_lkb *lkb, *safe;
- int count = 0;
-
- clear_bit(LSFL_CB_DELAY, &ls->ls_flags);
+ int count = 0, sum = 0;
+ bool empty;
if (!ls->ls_callback_wq)
return;
+ clear_bit(LSFL_CB_DELAY, &ls->ls_flags);
+
more:
mutex_lock(&ls->ls_cb_mutex);
list_for_each_entry_safe(lkb, safe, &ls->ls_cb_delay, lkb_cb_list) {
@@ -311,14 +319,17 @@ more:
if (count == MAX_CB_QUEUE)
break;
}
+ empty = list_empty(&ls->ls_cb_delay);
mutex_unlock(&ls->ls_cb_mutex);
- if (count)
- log_rinfo(ls, "dlm_callback_resume %d", count);
- if (count == MAX_CB_QUEUE) {
+ sum += count;
+ if (!empty) {
count = 0;
cond_resched();
goto more;
}
+
+ if (sum)
+ log_rinfo(ls, "%s %d", __func__, sum);
}
diff --git a/fs/dlm/ast.h b/fs/dlm/ast.h
index 181ad7d20c4d..e5e05fcc5813 100644
--- a/fs/dlm/ast.h
+++ b/fs/dlm/ast.h
@@ -11,7 +11,6 @@
#ifndef __ASTD_DOT_H__
#define __ASTD_DOT_H__
-void dlm_del_ast(struct dlm_lkb *lkb);
int dlm_add_lkb_callback(struct dlm_lkb *lkb, uint32_t flags, int mode,
int status, uint32_t sbflags, uint64_t seq);
int dlm_rem_lkb_callback(struct dlm_ls *ls, struct dlm_lkb *lkb,
diff --git a/fs/dlm/config.c b/fs/dlm/config.c
index 3b21082e1b55..ac8b62106ce0 100644
--- a/fs/dlm/config.c
+++ b/fs/dlm/config.c
@@ -20,6 +20,7 @@
#include <net/sock.h>
#include "config.h"
+#include "midcomms.h"
#include "lowcomms.h"
/*
@@ -73,11 +74,16 @@ struct dlm_cluster {
unsigned int cl_log_debug;
unsigned int cl_log_info;
unsigned int cl_protocol;
+ unsigned int cl_mark;
+#ifdef CONFIG_DLM_DEPRECATED_API
unsigned int cl_timewarn_cs;
- unsigned int cl_waitwarn_us;
+#endif
unsigned int cl_new_rsb_count;
unsigned int cl_recover_callbacks;
char cl_cluster_name[DLM_LOCKSPACE_LEN];
+
+ struct dlm_spaces *sps;
+ struct dlm_comms *cms;
};
static struct dlm_cluster *config_item_to_cluster(struct config_item *i)
@@ -96,8 +102,10 @@ enum {
CLUSTER_ATTR_LOG_DEBUG,
CLUSTER_ATTR_LOG_INFO,
CLUSTER_ATTR_PROTOCOL,
+ CLUSTER_ATTR_MARK,
+#ifdef CONFIG_DLM_DEPRECATED_API
CLUSTER_ATTR_TIMEWARN_CS,
- CLUSTER_ATTR_WAITWARN_US,
+#endif
CLUSTER_ATTR_NEW_RSB_COUNT,
CLUSTER_ATTR_RECOVER_CALLBACKS,
CLUSTER_ATTR_CLUSTER_NAME,
@@ -123,7 +131,7 @@ static ssize_t cluster_cluster_name_store(struct config_item *item,
CONFIGFS_ATTR(cluster_, cluster_name);
static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
- int *info_field, int check_zero,
+ int *info_field, int (*check_cb)(unsigned int x),
const char *buf, size_t len)
{
unsigned int x;
@@ -135,8 +143,11 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
if (rc)
return rc;
- if (check_zero && !x)
- return -EINVAL;
+ if (check_cb) {
+ rc = check_cb(x);
+ if (rc)
+ return rc;
+ }
*cl_field = x;
*info_field = x;
@@ -144,13 +155,13 @@ static ssize_t cluster_set(struct dlm_cluster *cl, unsigned int *cl_field,
return len;
}
-#define CLUSTER_ATTR(name, check_zero) \
+#define CLUSTER_ATTR(name, check_cb) \
static ssize_t cluster_##name##_store(struct config_item *item, \
const char *buf, size_t len) \
{ \
struct dlm_cluster *cl = config_item_to_cluster(item); \
return cluster_set(cl, &cl->cl_##name, &dlm_config.ci_##name, \
- check_zero, buf, len); \
+ check_cb, buf, len); \
} \
static ssize_t cluster_##name##_show(struct config_item *item, char *buf) \
{ \
@@ -159,19 +170,67 @@ static ssize_t cluster_##name##_show(struct config_item *item, char *buf) \
} \
CONFIGFS_ATTR(cluster_, name);
-CLUSTER_ATTR(tcp_port, 1);
-CLUSTER_ATTR(buffer_size, 1);
-CLUSTER_ATTR(rsbtbl_size, 1);
-CLUSTER_ATTR(recover_timer, 1);
-CLUSTER_ATTR(toss_secs, 1);
-CLUSTER_ATTR(scan_secs, 1);
-CLUSTER_ATTR(log_debug, 0);
-CLUSTER_ATTR(log_info, 0);
-CLUSTER_ATTR(protocol, 0);
-CLUSTER_ATTR(timewarn_cs, 1);
-CLUSTER_ATTR(waitwarn_us, 0);
-CLUSTER_ATTR(new_rsb_count, 0);
-CLUSTER_ATTR(recover_callbacks, 0);
+static int dlm_check_protocol_and_dlm_running(unsigned int x)
+{
+ switch (x) {
+ case 0:
+ /* TCP */
+ break;
+ case 1:
+ /* SCTP */
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if (dlm_allow_conn)
+ return -EBUSY;
+
+ return 0;
+}
+
+static int dlm_check_zero_and_dlm_running(unsigned int x)
+{
+ if (!x)
+ return -EINVAL;
+
+ if (dlm_allow_conn)
+ return -EBUSY;
+
+ return 0;
+}
+
+static int dlm_check_zero(unsigned int x)
+{
+ if (!x)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int dlm_check_buffer_size(unsigned int x)
+{
+ if (x < DLM_MAX_SOCKET_BUFSIZE)
+ return -EINVAL;
+
+ return 0;
+}
+
+CLUSTER_ATTR(tcp_port, dlm_check_zero_and_dlm_running);
+CLUSTER_ATTR(buffer_size, dlm_check_buffer_size);
+CLUSTER_ATTR(rsbtbl_size, dlm_check_zero);
+CLUSTER_ATTR(recover_timer, dlm_check_zero);
+CLUSTER_ATTR(toss_secs, dlm_check_zero);
+CLUSTER_ATTR(scan_secs, dlm_check_zero);
+CLUSTER_ATTR(log_debug, NULL);
+CLUSTER_ATTR(log_info, NULL);
+CLUSTER_ATTR(protocol, dlm_check_protocol_and_dlm_running);
+CLUSTER_ATTR(mark, NULL);
+#ifdef CONFIG_DLM_DEPRECATED_API
+CLUSTER_ATTR(timewarn_cs, dlm_check_zero);
+#endif
+CLUSTER_ATTR(new_rsb_count, NULL);
+CLUSTER_ATTR(recover_callbacks, NULL);
static struct configfs_attribute *cluster_attrs[] = {
[CLUSTER_ATTR_TCP_PORT] = &cluster_attr_tcp_port,
@@ -183,8 +242,10 @@ static struct configfs_attribute *cluster_attrs[] = {
[CLUSTER_ATTR_LOG_DEBUG] = &cluster_attr_log_debug,
[CLUSTER_ATTR_LOG_INFO] = &cluster_attr_log_info,
[CLUSTER_ATTR_PROTOCOL] = &cluster_attr_protocol,
+ [CLUSTER_ATTR_MARK] = &cluster_attr_mark,
+#ifdef CONFIG_DLM_DEPRECATED_API
[CLUSTER_ATTR_TIMEWARN_CS] = &cluster_attr_timewarn_cs,
- [CLUSTER_ATTR_WAITWARN_US] = &cluster_attr_waitwarn_us,
+#endif
[CLUSTER_ATTR_NEW_RSB_COUNT] = &cluster_attr_new_rsb_count,
[CLUSTER_ATTR_RECOVER_CALLBACKS] = &cluster_attr_recover_callbacks,
[CLUSTER_ATTR_CLUSTER_NAME] = &cluster_attr_cluster_name,
@@ -196,6 +257,7 @@ enum {
COMM_ATTR_LOCAL,
COMM_ATTR_ADDR,
COMM_ATTR_ADDR_LIST,
+ COMM_ATTR_MARK,
};
enum {
@@ -216,6 +278,7 @@ struct dlm_space {
struct list_head members;
struct mutex members_lock;
int members_count;
+ struct dlm_nodes *nds;
};
struct dlm_comms {
@@ -228,6 +291,7 @@ struct dlm_comm {
int nodeid;
int local;
int addr_count;
+ unsigned int mark;
struct sockaddr_storage *addr[DLM_MAX_ADDR_COUNT];
};
@@ -353,6 +417,9 @@ static struct config_group *make_cluster(struct config_group *g,
if (!cl || !sps || !cms)
goto fail;
+ cl->sps = sps;
+ cl->cms = cms;
+
config_group_init_type_name(&cl->group, name, &cluster_type);
config_group_init_type_name(&sps->ss_group, "spaces", &spaces_type);
config_group_init_type_name(&cms->cs_group, "comms", &comms_type);
@@ -369,8 +436,9 @@ static struct config_group *make_cluster(struct config_group *g,
cl->cl_log_debug = dlm_config.ci_log_debug;
cl->cl_log_info = dlm_config.ci_log_info;
cl->cl_protocol = dlm_config.ci_protocol;
+#ifdef CONFIG_DLM_DEPRECATED_API
cl->cl_timewarn_cs = dlm_config.ci_timewarn_cs;
- cl->cl_waitwarn_us = dlm_config.ci_waitwarn_us;
+#endif
cl->cl_new_rsb_count = dlm_config.ci_new_rsb_count;
cl->cl_recover_callbacks = dlm_config.ci_recover_callbacks;
memcpy(cl->cl_cluster_name, dlm_config.ci_cluster_name,
@@ -402,6 +470,9 @@ static void drop_cluster(struct config_group *g, struct config_item *i)
static void release_cluster(struct config_item *i)
{
struct dlm_cluster *cl = config_item_to_cluster(i);
+
+ kfree(cl->sps);
+ kfree(cl->cms);
kfree(cl);
}
@@ -424,6 +495,7 @@ static struct config_group *make_space(struct config_group *g, const char *name)
INIT_LIST_HEAD(&sp->members);
mutex_init(&sp->members_lock);
sp->members_count = 0;
+ sp->nds = nds;
return &sp->group;
fail:
@@ -445,6 +517,7 @@ static void drop_space(struct config_group *g, struct config_item *i)
static void release_space(struct config_item *i)
{
struct dlm_space *sp = config_item_to_space(i);
+ kfree(sp->nds);
kfree(sp);
}
@@ -465,6 +538,7 @@ static struct config_item *make_comm(struct config_group *g, const char *name)
cm->nodeid = -1;
cm->local = 0;
cm->addr_count = 0;
+ cm->mark = 0;
return &cm->item;
}
@@ -473,7 +547,7 @@ static void drop_comm(struct config_group *g, struct config_item *i)
struct dlm_comm *cm = config_item_to_comm(i);
if (local_comm == cm)
local_comm = NULL;
- dlm_lowcomms_close(cm->nodeid);
+ dlm_midcomms_close(cm->nodeid);
while (cm->addr_count--)
kfree(cm->addr[cm->addr_count]);
config_item_put(i);
@@ -660,8 +734,37 @@ static ssize_t comm_addr_list_show(struct config_item *item, char *buf)
return 4096 - allowance;
}
+static ssize_t comm_mark_show(struct config_item *item, char *buf)
+{
+ return sprintf(buf, "%u\n", config_item_to_comm(item)->mark);
+}
+
+static ssize_t comm_mark_store(struct config_item *item, const char *buf,
+ size_t len)
+{
+ struct dlm_comm *comm;
+ unsigned int mark;
+ int rc;
+
+ rc = kstrtouint(buf, 0, &mark);
+ if (rc)
+ return rc;
+
+ if (mark == 0)
+ mark = dlm_config.ci_mark;
+
+ comm = config_item_to_comm(item);
+ rc = dlm_lowcomms_nodes_set_mark(comm->nodeid, mark);
+ if (rc)
+ return rc;
+
+ comm->mark = mark;
+ return len;
+}
+
CONFIGFS_ATTR(comm_, nodeid);
CONFIGFS_ATTR(comm_, local);
+CONFIGFS_ATTR(comm_, mark);
CONFIGFS_ATTR_WO(comm_, addr);
CONFIGFS_ATTR_RO(comm_, addr_list);
@@ -670,6 +773,7 @@ static struct configfs_attribute *comm_attrs[] = {
[COMM_ATTR_LOCAL] = &comm_attr_local,
[COMM_ATTR_ADDR] = &comm_attr_addr,
[COMM_ATTR_ADDR_LIST] = &comm_attr_addr_list,
+ [COMM_ATTR_MARK] = &comm_attr_mark,
NULL,
};
@@ -847,23 +951,24 @@ int dlm_our_addr(struct sockaddr_storage *addr, int num)
/* Config file defaults */
#define DEFAULT_TCP_PORT 21064
-#define DEFAULT_BUFFER_SIZE 4096
#define DEFAULT_RSBTBL_SIZE 1024
#define DEFAULT_RECOVER_TIMER 5
#define DEFAULT_TOSS_SECS 10
#define DEFAULT_SCAN_SECS 5
#define DEFAULT_LOG_DEBUG 0
#define DEFAULT_LOG_INFO 1
-#define DEFAULT_PROTOCOL 0
+#define DEFAULT_PROTOCOL DLM_PROTO_TCP
+#define DEFAULT_MARK 0
+#ifdef CONFIG_DLM_DEPRECATED_API
#define DEFAULT_TIMEWARN_CS 500 /* 5 sec = 500 centiseconds */
-#define DEFAULT_WAITWARN_US 0
+#endif
#define DEFAULT_NEW_RSB_COUNT 128
#define DEFAULT_RECOVER_CALLBACKS 0
#define DEFAULT_CLUSTER_NAME ""
struct dlm_config_info dlm_config = {
.ci_tcp_port = DEFAULT_TCP_PORT,
- .ci_buffer_size = DEFAULT_BUFFER_SIZE,
+ .ci_buffer_size = DLM_MAX_SOCKET_BUFSIZE,
.ci_rsbtbl_size = DEFAULT_RSBTBL_SIZE,
.ci_recover_timer = DEFAULT_RECOVER_TIMER,
.ci_toss_secs = DEFAULT_TOSS_SECS,
@@ -871,8 +976,10 @@ struct dlm_config_info dlm_config = {
.ci_log_debug = DEFAULT_LOG_DEBUG,
.ci_log_info = DEFAULT_LOG_INFO,
.ci_protocol = DEFAULT_PROTOCOL,
+ .ci_mark = DEFAULT_MARK,
+#ifdef CONFIG_DLM_DEPRECATED_API
.ci_timewarn_cs = DEFAULT_TIMEWARN_CS,
- .ci_waitwarn_us = DEFAULT_WAITWARN_US,
+#endif
.ci_new_rsb_count = DEFAULT_NEW_RSB_COUNT,
.ci_recover_callbacks = DEFAULT_RECOVER_CALLBACKS,
.ci_cluster_name = DEFAULT_CLUSTER_NAME
diff --git a/fs/dlm/config.h b/fs/dlm/config.h
index 2b471aae4e61..55c5f2c13ebd 100644
--- a/fs/dlm/config.h
+++ b/fs/dlm/config.h
@@ -12,6 +12,8 @@
#ifndef __CONFIG_DOT_H__
#define __CONFIG_DOT_H__
+#define DLM_MAX_SOCKET_BUFSIZE 4096
+
struct dlm_config_node {
int nodeid;
int weight;
@@ -21,6 +23,9 @@ struct dlm_config_node {
#define DLM_MAX_ADDR_COUNT 3
+#define DLM_PROTO_TCP 0
+#define DLM_PROTO_SCTP 1
+
struct dlm_config_info {
int ci_tcp_port;
int ci_buffer_size;
@@ -31,8 +36,10 @@ struct dlm_config_info {
int ci_log_debug;
int ci_log_info;
int ci_protocol;
+ int ci_mark;
+#ifdef CONFIG_DLM_DEPRECATED_API
int ci_timewarn_cs;
- int ci_waitwarn_us;
+#endif
int ci_new_rsb_count;
int ci_recover_callbacks;
char ci_cluster_name[DLM_LOCKSPACE_LEN];
diff --git a/fs/dlm/debug_fs.c b/fs/dlm/debug_fs.c
index d6bbccb0ed15..8fb04ebbafb5 100644
--- a/fs/dlm/debug_fs.c
+++ b/fs/dlm/debug_fs.c
@@ -16,6 +16,7 @@
#include <linux/slab.h>
#include "dlm_internal.h"
+#include "midcomms.h"
#include "lock.h"
#define DLM_DEBUG_BUF_LEN 4096
@@ -23,6 +24,7 @@ static char debug_buf[DLM_DEBUG_BUF_LEN];
static struct mutex debug_buf_lock;
static struct dentry *dlm_root;
+static struct dentry *dlm_comms;
static char *print_lockmode(int mode)
{
@@ -542,6 +544,7 @@ static void *table_seq_next(struct seq_file *seq, void *iter_ptr, loff_t *pos)
if (bucket >= ls->ls_rsbtbl_size) {
kfree(ri);
+ ++*pos;
return NULL;
}
tree = toss ? &ls->ls_rsbtbl[bucket].toss : &ls->ls_rsbtbl[bucket].keep;
@@ -632,6 +635,35 @@ static int table_open2(struct inode *inode, struct file *file)
return 0;
}
+static ssize_t table_write2(struct file *file, const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct seq_file *seq = file->private_data;
+ int n, len, lkb_nodeid, lkb_status, error;
+ char name[DLM_RESNAME_MAXLEN + 1] = {};
+ struct dlm_ls *ls = seq->private;
+ unsigned int lkb_flags;
+ char buf[256] = {};
+ uint32_t lkb_id;
+
+ if (copy_from_user(buf, user_buf,
+ min_t(size_t, sizeof(buf) - 1, count)))
+ return -EFAULT;
+
+ n = sscanf(buf, "%x %" __stringify(DLM_RESNAME_MAXLEN) "s %x %d %d",
+ &lkb_id, name, &lkb_flags, &lkb_nodeid, &lkb_status);
+ if (n != 5)
+ return -EINVAL;
+
+ len = strnlen(name, DLM_RESNAME_MAXLEN);
+ error = dlm_debug_add_lkb(ls, lkb_id, name, len, lkb_flags,
+ lkb_nodeid, lkb_status);
+ if (error)
+ return error;
+
+ return count;
+}
+
static int table_open3(struct inode *inode, struct file *file)
{
struct seq_file *seq;
@@ -672,6 +704,7 @@ static const struct file_operations format2_fops = {
.owner = THIS_MODULE,
.open = table_open2,
.read = seq_read,
+ .write = table_write2,
.llseek = seq_lseek,
.release = seq_release
};
@@ -721,10 +754,35 @@ static ssize_t waiters_read(struct file *file, char __user *userbuf,
return rv;
}
+static ssize_t waiters_write(struct file *file, const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ struct dlm_ls *ls = file->private_data;
+ int mstype, to_nodeid;
+ char buf[128] = {};
+ uint32_t lkb_id;
+ int n, error;
+
+ if (copy_from_user(buf, user_buf,
+ min_t(size_t, sizeof(buf) - 1, count)))
+ return -EFAULT;
+
+ n = sscanf(buf, "%x %d %d", &lkb_id, &mstype, &to_nodeid);
+ if (n != 3)
+ return -EINVAL;
+
+ error = dlm_debug_add_lkb_to_waiters(ls, lkb_id, mstype, to_nodeid);
+ if (error)
+ return error;
+
+ return count;
+}
+
static const struct file_operations waiters_fops = {
.owner = THIS_MODULE,
.open = simple_open,
.read = waiters_read,
+ .write = waiters_write,
.llseek = default_llseek,
};
@@ -737,6 +795,94 @@ void dlm_delete_debug_file(struct dlm_ls *ls)
debugfs_remove(ls->ls_debug_toss_dentry);
}
+static int dlm_state_show(struct seq_file *file, void *offset)
+{
+ seq_printf(file, "%s\n", dlm_midcomms_state(file->private));
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(dlm_state);
+
+static int dlm_flags_show(struct seq_file *file, void *offset)
+{
+ seq_printf(file, "%lu\n", dlm_midcomms_flags(file->private));
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(dlm_flags);
+
+static int dlm_send_queue_cnt_show(struct seq_file *file, void *offset)
+{
+ seq_printf(file, "%d\n", dlm_midcomms_send_queue_cnt(file->private));
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(dlm_send_queue_cnt);
+
+static int dlm_version_show(struct seq_file *file, void *offset)
+{
+ seq_printf(file, "0x%08x\n", dlm_midcomms_version(file->private));
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(dlm_version);
+
+static ssize_t dlm_rawmsg_write(struct file *fp, const char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ void *buf;
+ int ret;
+
+ if (count > PAGE_SIZE || count < sizeof(struct dlm_header))
+ return -EINVAL;
+
+ buf = kmalloc(PAGE_SIZE, GFP_NOFS);
+ if (!buf)
+ return -ENOMEM;
+
+ if (copy_from_user(buf, user_buf, count)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ ret = dlm_midcomms_rawmsg_send(fp->private_data, buf, count);
+ if (ret)
+ goto out;
+
+ kfree(buf);
+ return count;
+
+out:
+ kfree(buf);
+ return ret;
+}
+
+static const struct file_operations dlm_rawmsg_fops = {
+ .open = simple_open,
+ .write = dlm_rawmsg_write,
+ .llseek = no_llseek,
+};
+
+void *dlm_create_debug_comms_file(int nodeid, void *data)
+{
+ struct dentry *d_node;
+ char name[256];
+
+ memset(name, 0, sizeof(name));
+ snprintf(name, 256, "%d", nodeid);
+
+ d_node = debugfs_create_dir(name, dlm_comms);
+ debugfs_create_file("state", 0444, d_node, data, &dlm_state_fops);
+ debugfs_create_file("flags", 0444, d_node, data, &dlm_flags_fops);
+ debugfs_create_file("send_queue_count", 0444, d_node, data,
+ &dlm_send_queue_cnt_fops);
+ debugfs_create_file("version", 0444, d_node, data, &dlm_version_fops);
+ debugfs_create_file("rawmsg", 0200, d_node, data, &dlm_rawmsg_fops);
+
+ return d_node;
+}
+
+void dlm_delete_debug_comms_file(void *ctx)
+{
+ debugfs_remove(ctx);
+}
+
void dlm_create_debug_file(struct dlm_ls *ls)
{
char name[DLM_LOCKSPACE_LEN + 8];
@@ -755,7 +901,7 @@ void dlm_create_debug_file(struct dlm_ls *ls)
snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_locks", ls->ls_name);
ls->ls_debug_locks_dentry = debugfs_create_file(name,
- S_IFREG | S_IRUGO,
+ 0644,
dlm_root,
ls,
&format2_fops);
@@ -786,7 +932,7 @@ void dlm_create_debug_file(struct dlm_ls *ls)
snprintf(name, DLM_LOCKSPACE_LEN + 8, "%s_waiters", ls->ls_name);
ls->ls_debug_waiters_dentry = debugfs_create_file(name,
- S_IFREG | S_IRUGO,
+ 0644,
dlm_root,
ls,
&waiters_fops);
@@ -796,6 +942,7 @@ void __init dlm_register_debugfs(void)
{
mutex_init(&debug_buf_lock);
dlm_root = debugfs_create_dir("dlm", NULL);
+ dlm_comms = debugfs_create_dir("comms", dlm_root);
}
void dlm_unregister_debugfs(void)
diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c
index 10c36ae1a8f9..fb1981654bb2 100644
--- a/fs/dlm/dir.c
+++ b/fs/dlm/dir.c
@@ -84,9 +84,10 @@ int dlm_recover_directory(struct dlm_ls *ls)
for (;;) {
int left;
- error = dlm_recovery_stopped(ls);
- if (error)
+ if (dlm_recovery_stopped(ls)) {
+ error = -EINTR;
goto out_free;
+ }
error = dlm_rcom_names(ls, memb->nodeid,
last_name, last_len);
@@ -100,7 +101,7 @@ int dlm_recover_directory(struct dlm_ls *ls)
*/
b = ls->ls_recover_buf->rc_buf;
- left = ls->ls_recover_buf->rc_header.h_length;
+ left = le16_to_cpu(ls->ls_recover_buf->rc_header.h_length);
left -= sizeof(struct dlm_rcom);
for (;;) {
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index 416d9de35679..e34c3d2639a5 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -41,12 +41,6 @@
#include <linux/dlm.h>
#include "config.h"
-/* Size of the temp buffer midcomms allocates on the stack.
- We try to make this large enough so most messages fit.
- FIXME: should sctp make this unnecessary? */
-
-#define DLM_INBUF_LEN 148
-
struct dlm_ls;
struct dlm_lkb;
struct dlm_rsb;
@@ -57,9 +51,12 @@ struct dlm_header;
struct dlm_message;
struct dlm_rcom;
struct dlm_mhandle;
+struct dlm_msg;
#define log_print(fmt, args...) \
printk(KERN_ERR "dlm: "fmt"\n" , ##args)
+#define log_print_ratelimited(fmt, args...) \
+ printk_ratelimited(KERN_ERR "dlm: "fmt"\n", ##args)
#define log_error(ls, fmt, args...) \
printk(KERN_ERR "dlm: %s: " fmt "\n", (ls)->ls_name , ##args)
@@ -97,7 +94,6 @@ do { \
__LINE__, __FILE__, #x, jiffies); \
{do} \
printk("\n"); \
- BUG(); \
panic("DLM: Record message above and reboot.\n"); \
} \
}
@@ -149,7 +145,9 @@ struct dlm_args {
void (*bastfn) (void *astparam, int mode);
int mode;
struct dlm_lksb *lksb;
+#ifdef CONFIG_DLM_DEPRECATED_API
unsigned long timeout;
+#endif
};
@@ -207,10 +205,20 @@ struct dlm_args {
#define DLM_IFL_OVERLAP_UNLOCK 0x00080000
#define DLM_IFL_OVERLAP_CANCEL 0x00100000
#define DLM_IFL_ENDOFLIFE 0x00200000
+#ifdef CONFIG_DLM_DEPRECATED_API
#define DLM_IFL_WATCH_TIMEWARN 0x00400000
#define DLM_IFL_TIMEOUT_CANCEL 0x00800000
+#endif
#define DLM_IFL_DEADLOCK_CANCEL 0x01000000
#define DLM_IFL_STUB_MS 0x02000000 /* magic number for m_flags */
+/* least significant 2 bytes are message changed, they are full transmitted
+ * but at receive side only the 2 bytes LSB will be set.
+ *
+ * Even wireshark dlm dissector does only evaluate the lower bytes and note
+ * that they may not be used on transceiver side, we assume the higher bytes
+ * are for internal use or reserved so long they are not parsed on receiver
+ * side.
+ */
#define DLM_IFL_USER 0x00000001
#define DLM_IFL_ORPHAN 0x00000002
@@ -253,10 +261,12 @@ struct dlm_lkb {
struct list_head lkb_rsb_lookup; /* waiting for rsb lookup */
struct list_head lkb_wait_reply; /* waiting for remote reply */
struct list_head lkb_ownqueue; /* list of locks for a process */
- struct list_head lkb_time_list;
ktime_t lkb_timestamp;
- ktime_t lkb_wait_time;
+
+#ifdef CONFIG_DLM_DEPRECATED_API
+ struct list_head lkb_time_list;
unsigned long lkb_timeout_cs;
+#endif
struct mutex lkb_cb_mutex;
struct work_struct lkb_cb_work;
@@ -369,23 +379,33 @@ static inline int rsb_flag(struct dlm_rsb *r, enum rsb_flags flag)
/* dlm_header is first element of all structs sent between nodes */
#define DLM_HEADER_MAJOR 0x00030000
-#define DLM_HEADER_MINOR 0x00000001
+#define DLM_HEADER_MINOR 0x00000002
+
+#define DLM_VERSION_3_1 0x00030001
+#define DLM_VERSION_3_2 0x00030002
#define DLM_HEADER_SLOTS 0x00000001
#define DLM_MSG 1
#define DLM_RCOM 2
+#define DLM_OPTS 3
+#define DLM_ACK 4
+#define DLM_FIN 5
struct dlm_header {
- uint32_t h_version;
- uint32_t h_lockspace;
- uint32_t h_nodeid; /* nodeid of sender */
- uint16_t h_length;
+ __le32 h_version;
+ union {
+ /* for DLM_MSG and DLM_RCOM */
+ __le32 h_lockspace;
+ /* for DLM_ACK and DLM_OPTS */
+ __le32 h_seq;
+ } u;
+ __le32 h_nodeid; /* nodeid of sender */
+ __le16 h_length;
uint8_t h_cmd; /* DLM_MSG, DLM_RCOM */
uint8_t h_pad;
};
-
#define DLM_MSG_REQUEST 1
#define DLM_MSG_CONVERT 2
#define DLM_MSG_UNLOCK 3
@@ -403,25 +423,25 @@ struct dlm_header {
struct dlm_message {
struct dlm_header m_header;
- uint32_t m_type; /* DLM_MSG_ */
- uint32_t m_nodeid;
- uint32_t m_pid;
- uint32_t m_lkid; /* lkid on sender */
- uint32_t m_remid; /* lkid on receiver */
- uint32_t m_parent_lkid;
- uint32_t m_parent_remid;
- uint32_t m_exflags;
- uint32_t m_sbflags;
- uint32_t m_flags;
- uint32_t m_lvbseq;
- uint32_t m_hash;
- int m_status;
- int m_grmode;
- int m_rqmode;
- int m_bastmode;
- int m_asts;
- int m_result; /* 0 or -EXXX */
- char m_extra[0]; /* name or lvb */
+ __le32 m_type; /* DLM_MSG_ */
+ __le32 m_nodeid;
+ __le32 m_pid;
+ __le32 m_lkid; /* lkid on sender */
+ __le32 m_remid; /* lkid on receiver */
+ __le32 m_parent_lkid;
+ __le32 m_parent_remid;
+ __le32 m_exflags;
+ __le32 m_sbflags;
+ __le32 m_flags;
+ __le32 m_lvbseq;
+ __le32 m_hash;
+ __le32 m_status;
+ __le32 m_grmode;
+ __le32 m_rqmode;
+ __le32 m_bastmode;
+ __le32 m_asts;
+ __le32 m_result; /* 0 or -EXXX */
+ char m_extra[]; /* name or lvb */
};
@@ -445,18 +465,37 @@ struct dlm_message {
struct dlm_rcom {
struct dlm_header rc_header;
- uint32_t rc_type; /* DLM_RCOM_ */
- int rc_result; /* multi-purpose */
- uint64_t rc_id; /* match reply with request */
- uint64_t rc_seq; /* sender's ls_recover_seq */
- uint64_t rc_seq_reply; /* remote ls_recover_seq */
- char rc_buf[0];
+ __le32 rc_type; /* DLM_RCOM_ */
+ __le32 rc_result; /* multi-purpose */
+ __le64 rc_id; /* match reply with request */
+ __le64 rc_seq; /* sender's ls_recover_seq */
+ __le64 rc_seq_reply; /* remote ls_recover_seq */
+ char rc_buf[];
+};
+
+struct dlm_opt_header {
+ __le16 t_type;
+ __le16 t_length;
+ __le32 t_pad;
+ /* need to be 8 byte aligned */
+ char t_value[];
+};
+
+/* encapsulation header */
+struct dlm_opts {
+ struct dlm_header o_header;
+ uint8_t o_nextcmd;
+ uint8_t o_pad;
+ __le16 o_optlen;
+ __le32 o_pad2;
+ char o_opts[];
};
union dlm_packet {
struct dlm_header header; /* common to other two */
struct dlm_message message;
struct dlm_rcom rcom;
+ struct dlm_opts opts;
};
#define DLM_RSF_NEED_SLOTS 0x00000001
@@ -506,7 +545,7 @@ struct rcom_lock {
__le16 rl_wait_type;
__le16 rl_namelen;
char rl_name[DLM_RESNAME_MAXLEN];
- char rl_lvb[0];
+ char rl_lvb[];
};
/*
@@ -523,8 +562,9 @@ struct dlm_ls {
uint32_t ls_generation;
uint32_t ls_exflags;
int ls_lvblen;
- int ls_count; /* refcount of processes in
+ atomic_t ls_count; /* refcount of processes in
the dlm using this ls */
+ wait_queue_head_t ls_count_wait;
int ls_create_count; /* create/release refcount */
unsigned long ls_flags; /* LSFL_ */
unsigned long ls_scan_time;
@@ -542,14 +582,17 @@ struct dlm_ls {
struct mutex ls_orphans_mutex;
struct list_head ls_orphans;
+#ifdef CONFIG_DLM_DEPRECATED_API
struct mutex ls_timeout_mutex;
struct list_head ls_timeout;
+#endif
spinlock_t ls_new_rsb_spin;
int ls_new_rsb_count;
struct list_head ls_new_rsb; /* new rsb structs */
spinlock_t ls_remove_spin;
+ wait_queue_head_t ls_remove_wait;
char ls_remove_name[DLM_RESNAME_MAXLEN+1];
char *ls_remove_names[DLM_REMOVE_NAMES_MAX];
int ls_remove_len;
@@ -579,8 +622,8 @@ struct dlm_ls {
wait_queue_head_t ls_uevent_wait; /* user part of join/leave */
int ls_uevent_result;
- struct completion ls_members_done;
- int ls_members_result;
+ struct completion ls_recovery_done;
+ int ls_recovery_result;
struct miscdevice ls_device;
@@ -601,6 +644,8 @@ struct dlm_ls {
struct rw_semaphore ls_in_recovery; /* block local requests */
struct rw_semaphore ls_recv_active; /* block dlm_recv */
struct list_head ls_requestqueue;/* queue remote requests */
+ atomic_t ls_requestqueue_cnt;
+ wait_queue_head_t ls_requestqueue_wait;
struct mutex ls_requestqueue_mutex;
struct dlm_rcom *ls_recover_buf;
int ls_recover_nodeid; /* for debugging */
@@ -616,7 +661,7 @@ struct dlm_ls {
spinlock_t ls_recover_idr_lock;
wait_queue_head_t ls_wait_general;
wait_queue_head_t ls_recover_lock_wait;
- struct mutex ls_clear_proc_locks;
+ spinlock_t ls_clear_proc_locks;
struct list_head ls_root_list; /* root resources */
struct rw_semaphore ls_root_sem; /* protect root_list */
@@ -659,7 +704,9 @@ struct dlm_ls {
#define LSFL_RCOM_READY 5
#define LSFL_RCOM_WAIT 6
#define LSFL_UEVENT_WAIT 7
+#ifdef CONFIG_DLM_DEPRECATED_API
#define LSFL_TIMEWARN 8
+#endif
#define LSFL_CB_DELAY 9
#define LSFL_NODIR 10
@@ -712,9 +759,15 @@ static inline int dlm_no_directory(struct dlm_ls *ls)
return test_bit(LSFL_NODIR, &ls->ls_flags);
}
+#ifdef CONFIG_DLM_DEPRECATED_API
int dlm_netlink_init(void);
void dlm_netlink_exit(void);
void dlm_timeout_warn(struct dlm_lkb *lkb);
+#else
+static inline int dlm_netlink_init(void) { return 0; }
+static inline void dlm_netlink_exit(void) { };
+static inline void dlm_timeout_warn(struct dlm_lkb *lkb) { };
+#endif
int dlm_plock_init(void);
void dlm_plock_exit(void);
@@ -723,11 +776,15 @@ void dlm_register_debugfs(void);
void dlm_unregister_debugfs(void);
void dlm_create_debug_file(struct dlm_ls *ls);
void dlm_delete_debug_file(struct dlm_ls *ls);
+void *dlm_create_debug_comms_file(int nodeid, void *data);
+void dlm_delete_debug_comms_file(void *ctx);
#else
static inline void dlm_register_debugfs(void) { }
static inline void dlm_unregister_debugfs(void) { }
static inline void dlm_create_debug_file(struct dlm_ls *ls) { }
static inline void dlm_delete_debug_file(struct dlm_ls *ls) { }
+static inline void *dlm_create_debug_comms_file(int nodeid, void *data) { return NULL; }
+static inline void dlm_delete_debug_comms_file(void *ctx) { }
#endif
#endif /* __DLM_INTERNAL_DOT_H__ */
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 18d81599522f..94a72ede5764 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -53,13 +53,15 @@
R: do_xxxx()
L: receive_xxxx_reply() <- R: send_xxxx_reply()
*/
+#include <trace/events/dlm.h>
+
#include <linux/types.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include "dlm_internal.h"
#include <linux/dlm_device.h>
#include "memory.h"
-#include "lowcomms.h"
+#include "midcomms.h"
#include "requestqueue.h"
#include "util.h"
#include "dir.h"
@@ -294,12 +296,14 @@ static void queue_cast(struct dlm_rsb *r, struct dlm_lkb *lkb, int rv)
DLM_ASSERT(lkb->lkb_lksb, dlm_print_lkb(lkb););
+#ifdef CONFIG_DLM_DEPRECATED_API
/* if the operation was a cancel, then return -DLM_ECANCEL, if a
timeout caused the cancel then return -ETIMEDOUT */
if (rv == -DLM_ECANCEL && (lkb->lkb_flags & DLM_IFL_TIMEOUT_CANCEL)) {
lkb->lkb_flags &= ~DLM_IFL_TIMEOUT_CANCEL;
rv = -ETIMEDOUT;
}
+#endif
if (rv == -DLM_ECANCEL && (lkb->lkb_flags & DLM_IFL_DEADLOCK_CANCEL)) {
lkb->lkb_flags &= ~DLM_IFL_DEADLOCK_CANCEL;
@@ -348,10 +352,12 @@ static void put_rsb(struct dlm_rsb *r)
{
struct dlm_ls *ls = r->res_ls;
uint32_t bucket = r->res_bucket;
+ int rv;
- spin_lock(&ls->ls_rsbtbl[bucket].lock);
- kref_put(&r->res_ref, toss_rsb);
- spin_unlock(&ls->ls_rsbtbl[bucket].lock);
+ rv = kref_put_lock(&r->res_ref, toss_rsb,
+ &ls->ls_rsbtbl[bucket].lock);
+ if (rv)
+ spin_unlock(&ls->ls_rsbtbl[bucket].lock);
}
void dlm_put_rsb(struct dlm_rsb *r)
@@ -395,7 +401,7 @@ static int pre_rsb_struct(struct dlm_ls *ls)
unlock any spinlocks, go back and call pre_rsb_struct again.
Otherwise, take an rsb off the list and return it. */
-static int get_rsb_struct(struct dlm_ls *ls, char *name, int len,
+static int get_rsb_struct(struct dlm_ls *ls, const void *name, int len,
struct dlm_rsb **r_ret)
{
struct dlm_rsb *r;
@@ -406,7 +412,8 @@ static int get_rsb_struct(struct dlm_ls *ls, char *name, int len,
count = ls->ls_new_rsb_count;
spin_unlock(&ls->ls_new_rsb_spin);
log_debug(ls, "find_rsb retry %d %d %s",
- count, dlm_config.ci_new_rsb_count, name);
+ count, dlm_config.ci_new_rsb_count,
+ (const char *)name);
return -EAGAIN;
}
@@ -442,7 +449,7 @@ static int rsb_cmp(struct dlm_rsb *r, const char *name, int nlen)
return memcmp(r->res_name, maxname, DLM_RESNAME_MAXLEN);
}
-int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len,
+int dlm_search_rsb_tree(struct rb_root *tree, const void *name, int len,
struct dlm_rsb **r_ret)
{
struct rb_node *node = tree->rb_node;
@@ -540,7 +547,7 @@ static int rsb_insert(struct dlm_rsb *rsb, struct rb_root *tree)
* while that rsb has a potentially stale master.)
*/
-static int find_rsb_dir(struct dlm_ls *ls, char *name, int len,
+static int find_rsb_dir(struct dlm_ls *ls, const void *name, int len,
uint32_t hash, uint32_t b,
int dir_nodeid, int from_nodeid,
unsigned int flags, struct dlm_rsb **r_ret)
@@ -600,7 +607,6 @@ static int find_rsb_dir(struct dlm_ls *ls, char *name, int len,
*/
kref_get(&r->res_ref);
- error = 0;
goto out_unlock;
@@ -719,7 +725,7 @@ static int find_rsb_dir(struct dlm_ls *ls, char *name, int len,
dlm_recover_locks) before we've made ourself master (in
dlm_recover_masters). */
-static int find_rsb_nodir(struct dlm_ls *ls, char *name, int len,
+static int find_rsb_nodir(struct dlm_ls *ls, const void *name, int len,
uint32_t hash, uint32_t b,
int dir_nodeid, int from_nodeid,
unsigned int flags, struct dlm_rsb **r_ret)
@@ -813,8 +819,9 @@ static int find_rsb_nodir(struct dlm_ls *ls, char *name, int len,
return error;
}
-static int find_rsb(struct dlm_ls *ls, char *name, int len, int from_nodeid,
- unsigned int flags, struct dlm_rsb **r_ret)
+static int find_rsb(struct dlm_ls *ls, const void *name, int len,
+ int from_nodeid, unsigned int flags,
+ struct dlm_rsb **r_ret)
{
uint32_t hash, b;
int dir_nodeid;
@@ -878,6 +885,88 @@ static int validate_master_nodeid(struct dlm_ls *ls, struct dlm_rsb *r,
}
}
+static void __dlm_master_lookup(struct dlm_ls *ls, struct dlm_rsb *r, int our_nodeid,
+ int from_nodeid, bool toss_list, unsigned int flags,
+ int *r_nodeid, int *result)
+{
+ int fix_master = (flags & DLM_LU_RECOVER_MASTER);
+ int from_master = (flags & DLM_LU_RECOVER_DIR);
+
+ if (r->res_dir_nodeid != our_nodeid) {
+ /* should not happen, but may as well fix it and carry on */
+ log_error(ls, "%s res_dir %d our %d %s", __func__,
+ r->res_dir_nodeid, our_nodeid, r->res_name);
+ r->res_dir_nodeid = our_nodeid;
+ }
+
+ if (fix_master && dlm_is_removed(ls, r->res_master_nodeid)) {
+ /* Recovery uses this function to set a new master when
+ * the previous master failed. Setting NEW_MASTER will
+ * force dlm_recover_masters to call recover_master on this
+ * rsb even though the res_nodeid is no longer removed.
+ */
+
+ r->res_master_nodeid = from_nodeid;
+ r->res_nodeid = from_nodeid;
+ rsb_set_flag(r, RSB_NEW_MASTER);
+
+ if (toss_list) {
+ /* I don't think we should ever find it on toss list. */
+ log_error(ls, "%s fix_master on toss", __func__);
+ dlm_dump_rsb(r);
+ }
+ }
+
+ if (from_master && (r->res_master_nodeid != from_nodeid)) {
+ /* this will happen if from_nodeid became master during
+ * a previous recovery cycle, and we aborted the previous
+ * cycle before recovering this master value
+ */
+
+ log_limit(ls, "%s from_master %d master_nodeid %d res_nodeid %d first %x %s",
+ __func__, from_nodeid, r->res_master_nodeid,
+ r->res_nodeid, r->res_first_lkid, r->res_name);
+
+ if (r->res_master_nodeid == our_nodeid) {
+ log_error(ls, "from_master %d our_master", from_nodeid);
+ dlm_dump_rsb(r);
+ goto ret_assign;
+ }
+
+ r->res_master_nodeid = from_nodeid;
+ r->res_nodeid = from_nodeid;
+ rsb_set_flag(r, RSB_NEW_MASTER);
+ }
+
+ if (!r->res_master_nodeid) {
+ /* this will happen if recovery happens while we're looking
+ * up the master for this rsb
+ */
+
+ log_debug(ls, "%s master 0 to %d first %x %s", __func__,
+ from_nodeid, r->res_first_lkid, r->res_name);
+ r->res_master_nodeid = from_nodeid;
+ r->res_nodeid = from_nodeid;
+ }
+
+ if (!from_master && !fix_master &&
+ (r->res_master_nodeid == from_nodeid)) {
+ /* this can happen when the master sends remove, the dir node
+ * finds the rsb on the keep list and ignores the remove,
+ * and the former master sends a lookup
+ */
+
+ log_limit(ls, "%s from master %d flags %x first %x %s",
+ __func__, from_nodeid, flags, r->res_first_lkid,
+ r->res_name);
+ }
+
+ ret_assign:
+ *r_nodeid = r->res_master_nodeid;
+ if (result)
+ *result = DLM_LU_MATCH;
+}
+
/*
* We're the dir node for this res and another node wants to know the
* master nodeid. During normal operation (non recovery) this is only
@@ -912,10 +1001,8 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, char *name, int len,
{
struct dlm_rsb *r = NULL;
uint32_t hash, b;
- int from_master = (flags & DLM_LU_RECOVER_DIR);
- int fix_master = (flags & DLM_LU_RECOVER_MASTER);
int our_nodeid = dlm_our_nodeid();
- int dir_nodeid, error, toss_list = 0;
+ int dir_nodeid, error;
if (len > DLM_RESNAME_MAXLEN)
return -EINVAL;
@@ -947,12 +1034,21 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, char *name, int len,
error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].keep, name, len, &r);
if (!error) {
/* because the rsb is active, we need to lock_rsb before
- checking/changing re_master_nodeid */
+ * checking/changing re_master_nodeid
+ */
hold_rsb(r);
spin_unlock(&ls->ls_rsbtbl[b].lock);
lock_rsb(r);
- goto found;
+
+ __dlm_master_lookup(ls, r, our_nodeid, from_nodeid, false,
+ flags, r_nodeid, result);
+
+ /* the rsb was active */
+ unlock_rsb(r);
+ put_rsb(r);
+
+ return 0;
}
error = dlm_search_rsb_tree(&ls->ls_rsbtbl[b].toss, name, len, &r);
@@ -960,90 +1056,16 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, char *name, int len,
goto not_found;
/* because the rsb is inactive (on toss list), it's not refcounted
- and lock_rsb is not used, but is protected by the rsbtbl lock */
-
- toss_list = 1;
- found:
- if (r->res_dir_nodeid != our_nodeid) {
- /* should not happen, but may as well fix it and carry on */
- log_error(ls, "dlm_master_lookup res_dir %d our %d %s",
- r->res_dir_nodeid, our_nodeid, r->res_name);
- r->res_dir_nodeid = our_nodeid;
- }
-
- if (fix_master && dlm_is_removed(ls, r->res_master_nodeid)) {
- /* Recovery uses this function to set a new master when
- the previous master failed. Setting NEW_MASTER will
- force dlm_recover_masters to call recover_master on this
- rsb even though the res_nodeid is no longer removed. */
-
- r->res_master_nodeid = from_nodeid;
- r->res_nodeid = from_nodeid;
- rsb_set_flag(r, RSB_NEW_MASTER);
-
- if (toss_list) {
- /* I don't think we should ever find it on toss list. */
- log_error(ls, "dlm_master_lookup fix_master on toss");
- dlm_dump_rsb(r);
- }
- }
-
- if (from_master && (r->res_master_nodeid != from_nodeid)) {
- /* this will happen if from_nodeid became master during
- a previous recovery cycle, and we aborted the previous
- cycle before recovering this master value */
-
- log_limit(ls, "dlm_master_lookup from_master %d "
- "master_nodeid %d res_nodeid %d first %x %s",
- from_nodeid, r->res_master_nodeid, r->res_nodeid,
- r->res_first_lkid, r->res_name);
-
- if (r->res_master_nodeid == our_nodeid) {
- log_error(ls, "from_master %d our_master", from_nodeid);
- dlm_dump_rsb(r);
- goto out_found;
- }
-
- r->res_master_nodeid = from_nodeid;
- r->res_nodeid = from_nodeid;
- rsb_set_flag(r, RSB_NEW_MASTER);
- }
-
- if (!r->res_master_nodeid) {
- /* this will happen if recovery happens while we're looking
- up the master for this rsb */
-
- log_debug(ls, "dlm_master_lookup master 0 to %d first %x %s",
- from_nodeid, r->res_first_lkid, r->res_name);
- r->res_master_nodeid = from_nodeid;
- r->res_nodeid = from_nodeid;
- }
-
- if (!from_master && !fix_master &&
- (r->res_master_nodeid == from_nodeid)) {
- /* this can happen when the master sends remove, the dir node
- finds the rsb on the keep list and ignores the remove,
- and the former master sends a lookup */
+ * and lock_rsb is not used, but is protected by the rsbtbl lock
+ */
- log_limit(ls, "dlm_master_lookup from master %d flags %x "
- "first %x %s", from_nodeid, flags,
- r->res_first_lkid, r->res_name);
- }
+ __dlm_master_lookup(ls, r, our_nodeid, from_nodeid, true, flags,
+ r_nodeid, result);
- out_found:
- *r_nodeid = r->res_master_nodeid;
- if (result)
- *result = DLM_LU_MATCH;
+ r->res_toss_time = jiffies;
+ /* the rsb was inactive (on toss list) */
+ spin_unlock(&ls->ls_rsbtbl[b].lock);
- if (toss_list) {
- r->res_toss_time = jiffies;
- /* the rsb was inactive (on toss list) */
- spin_unlock(&ls->ls_rsbtbl[b].lock);
- } else {
- /* the rsb was active */
- unlock_rsb(r);
- put_rsb(r);
- }
return 0;
not_found:
@@ -1074,7 +1096,6 @@ int dlm_master_lookup(struct dlm_ls *ls, int from_nodeid, char *name, int len,
if (result)
*result = DLM_LU_ADD;
*r_nodeid = from_nodeid;
- error = 0;
out_unlock:
spin_unlock(&ls->ls_rsbtbl[b].lock);
return error;
@@ -1178,7 +1199,8 @@ static void detach_lkb(struct dlm_lkb *lkb)
}
}
-static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
+static int _create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret,
+ int start, int end)
{
struct dlm_lkb *lkb;
int rv;
@@ -1192,14 +1214,16 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
kref_init(&lkb->lkb_ref);
INIT_LIST_HEAD(&lkb->lkb_ownqueue);
INIT_LIST_HEAD(&lkb->lkb_rsb_lookup);
+#ifdef CONFIG_DLM_DEPRECATED_API
INIT_LIST_HEAD(&lkb->lkb_time_list);
+#endif
INIT_LIST_HEAD(&lkb->lkb_cb_list);
mutex_init(&lkb->lkb_cb_mutex);
INIT_WORK(&lkb->lkb_cb_work, dlm_callback_work);
idr_preload(GFP_NOFS);
spin_lock(&ls->ls_lkbidr_spin);
- rv = idr_alloc(&ls->ls_lkbidr, lkb, 1, 0, GFP_NOWAIT);
+ rv = idr_alloc(&ls->ls_lkbidr, lkb, start, end, GFP_NOWAIT);
if (rv >= 0)
lkb->lkb_id = rv;
spin_unlock(&ls->ls_lkbidr_spin);
@@ -1215,6 +1239,11 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
return 0;
}
+static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
+{
+ return _create_lkb(ls, lkb_ret, 1, 0);
+}
+
static int find_lkb(struct dlm_ls *ls, uint32_t lkid, struct dlm_lkb **lkb_ret)
{
struct dlm_lkb *lkb;
@@ -1245,9 +1274,11 @@ static void kill_lkb(struct kref *kref)
static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb)
{
uint32_t lkid = lkb->lkb_id;
+ int rv;
- spin_lock(&ls->ls_lkbidr_spin);
- if (kref_put(&lkb->lkb_ref, kill_lkb)) {
+ rv = kref_put_lock(&lkb->lkb_ref, kill_lkb,
+ &ls->ls_lkbidr_spin);
+ if (rv) {
idr_remove(&ls->ls_lkbidr, lkid);
spin_unlock(&ls->ls_lkbidr_spin);
@@ -1257,11 +1288,9 @@ static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb)
if (lkb->lkb_lvbptr && is_master_copy(lkb))
dlm_free_lvb(lkb->lkb_lvbptr);
dlm_free_lkb(lkb);
- return 1;
- } else {
- spin_unlock(&ls->ls_lkbidr_spin);
- return 0;
}
+
+ return rv;
}
int dlm_put_lkb(struct dlm_lkb *lkb)
@@ -1283,6 +1312,13 @@ static inline void hold_lkb(struct dlm_lkb *lkb)
kref_get(&lkb->lkb_ref);
}
+static void unhold_lkb_assert(struct kref *kref)
+{
+ struct dlm_lkb *lkb = container_of(kref, struct dlm_lkb, lkb_ref);
+
+ DLM_ASSERT(false, dlm_print_lkb(lkb););
+}
+
/* This is called when we need to remove a reference and are certain
it's not the last ref. e.g. del_lkb is always called between a
find_lkb/put_lkb and is always the inverse of a previous add_lkb.
@@ -1290,21 +1326,23 @@ static inline void hold_lkb(struct dlm_lkb *lkb)
static inline void unhold_lkb(struct dlm_lkb *lkb)
{
- int rv;
- rv = kref_put(&lkb->lkb_ref, kill_lkb);
- DLM_ASSERT(!rv, dlm_print_lkb(lkb););
+ kref_put(&lkb->lkb_ref, unhold_lkb_assert);
}
static void lkb_add_ordered(struct list_head *new, struct list_head *head,
int mode)
{
- struct dlm_lkb *lkb = NULL;
+ struct dlm_lkb *lkb = NULL, *iter;
- list_for_each_entry(lkb, head, lkb_statequeue)
- if (lkb->lkb_rqmode < mode)
+ list_for_each_entry(iter, head, lkb_statequeue)
+ if (iter->lkb_rqmode < mode) {
+ lkb = iter;
+ list_add_tail(new, &iter->lkb_statequeue);
break;
+ }
- __list_add(new, lkb->lkb_statequeue.prev, &lkb->lkb_statequeue);
+ if (!lkb)
+ list_add_tail(new, head);
}
/* add/remove lkb to rsb's grant/convert/wait queue */
@@ -1375,75 +1413,6 @@ static int msg_reply_type(int mstype)
return -1;
}
-static int nodeid_warned(int nodeid, int num_nodes, int *warned)
-{
- int i;
-
- for (i = 0; i < num_nodes; i++) {
- if (!warned[i]) {
- warned[i] = nodeid;
- return 0;
- }
- if (warned[i] == nodeid)
- return 1;
- }
- return 0;
-}
-
-void dlm_scan_waiters(struct dlm_ls *ls)
-{
- struct dlm_lkb *lkb;
- s64 us;
- s64 debug_maxus = 0;
- u32 debug_scanned = 0;
- u32 debug_expired = 0;
- int num_nodes = 0;
- int *warned = NULL;
-
- if (!dlm_config.ci_waitwarn_us)
- return;
-
- mutex_lock(&ls->ls_waiters_mutex);
-
- list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
- if (!lkb->lkb_wait_time)
- continue;
-
- debug_scanned++;
-
- us = ktime_to_us(ktime_sub(ktime_get(), lkb->lkb_wait_time));
-
- if (us < dlm_config.ci_waitwarn_us)
- continue;
-
- lkb->lkb_wait_time = 0;
-
- debug_expired++;
- if (us > debug_maxus)
- debug_maxus = us;
-
- if (!num_nodes) {
- num_nodes = ls->ls_num_nodes;
- warned = kcalloc(num_nodes, sizeof(int), GFP_KERNEL);
- }
- if (!warned)
- continue;
- if (nodeid_warned(lkb->lkb_wait_nodeid, num_nodes, warned))
- continue;
-
- log_error(ls, "waitwarn %x %lld %d us check connection to "
- "node %d", lkb->lkb_id, (long long)us,
- dlm_config.ci_waitwarn_us, lkb->lkb_wait_nodeid);
- }
- mutex_unlock(&ls->ls_waiters_mutex);
- kfree(warned);
-
- if (debug_expired)
- log_debug(ls, "scan_waiters %u warn %u over %d us max %lld us",
- debug_scanned, debug_expired,
- dlm_config.ci_waitwarn_us, (long long)debug_maxus);
-}
-
/* add/remove lkb from global waiters list of lkb's waiting for
a reply from a remote node */
@@ -1487,7 +1456,6 @@ static int add_to_waiters(struct dlm_lkb *lkb, int mstype, int to_nodeid)
lkb->lkb_wait_count++;
lkb->lkb_wait_type = mstype;
- lkb->lkb_wait_time = ktime_get();
lkb->lkb_wait_nodeid = to_nodeid; /* for debugging */
hold_lkb(lkb);
list_add(&lkb->lkb_wait_reply, &ls->ls_waiters);
@@ -1551,6 +1519,7 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype,
lkb->lkb_wait_type = 0;
lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
lkb->lkb_wait_count--;
+ unhold_lkb(lkb);
goto out_del;
}
@@ -1563,8 +1532,8 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype,
}
log_error(ls, "remwait error %x remote %d %x msg %d flags %x no wait",
- lkb->lkb_id, ms ? ms->m_header.h_nodeid : 0, lkb->lkb_remid,
- mstype, lkb->lkb_flags);
+ lkb->lkb_id, ms ? le32_to_cpu(ms->m_header.h_nodeid) : 0,
+ lkb->lkb_remid, mstype, lkb->lkb_flags);
return -1;
out_del:
@@ -1577,6 +1546,7 @@ static int _remove_from_waiters(struct dlm_lkb *lkb, int mstype,
log_error(ls, "remwait error %x reply %d wait_type %d overlap",
lkb->lkb_id, mstype, lkb->lkb_wait_type);
lkb->lkb_wait_count--;
+ unhold_lkb(lkb);
lkb->lkb_wait_type = 0;
}
@@ -1609,30 +1579,33 @@ 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->m_flags != DLM_IFL_STUB_MS)
+ if (ms->m_flags != cpu_to_le32(DLM_IFL_STUB_MS))
mutex_lock(&ls->ls_waiters_mutex);
- error = _remove_from_waiters(lkb, ms->m_type, ms);
- if (ms->m_flags != DLM_IFL_STUB_MS)
+ error = _remove_from_waiters(lkb, le32_to_cpu(ms->m_type), ms);
+ if (ms->m_flags != cpu_to_le32(DLM_IFL_STUB_MS))
mutex_unlock(&ls->ls_waiters_mutex);
return error;
}
/* If there's an rsb for the same resource being removed, ensure
- that the remove message is sent before the new lookup message.
- It should be rare to need a delay here, but if not, then it may
- be worthwhile to add a proper wait mechanism rather than a delay. */
+ * that the remove message is sent before the new lookup message.
+ */
+
+#define DLM_WAIT_PENDING_COND(ls, r) \
+ (ls->ls_remove_len && \
+ !rsb_cmp(r, ls->ls_remove_name, \
+ ls->ls_remove_len))
static void wait_pending_remove(struct dlm_rsb *r)
{
struct dlm_ls *ls = r->res_ls;
restart:
spin_lock(&ls->ls_remove_spin);
- if (ls->ls_remove_len &&
- !rsb_cmp(r, ls->ls_remove_name, ls->ls_remove_len)) {
+ if (DLM_WAIT_PENDING_COND(ls, r)) {
log_debug(ls, "delay lookup for remove dir %d %s",
- r->res_dir_nodeid, r->res_name);
+ r->res_dir_nodeid, r->res_name);
spin_unlock(&ls->ls_remove_spin);
- msleep(1);
+ wait_event(ls->ls_remove_wait, !DLM_WAIT_PENDING_COND(ls, r));
goto restart;
}
spin_unlock(&ls->ls_remove_spin);
@@ -1792,6 +1765,7 @@ static void shrink_bucket(struct dlm_ls *ls, int b)
ls->ls_remove_len = 0;
memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN);
spin_unlock(&ls->ls_remove_spin);
+ wake_up(&ls->ls_remove_wait);
dlm_free_rsb(r);
}
@@ -1809,6 +1783,7 @@ void dlm_scan_rsbs(struct dlm_ls *ls)
}
}
+#ifdef CONFIG_DLM_DEPRECATED_API
static void add_timeout(struct dlm_lkb *lkb)
{
struct dlm_ls *ls = lkb->lkb_resource->res_ls;
@@ -1854,7 +1829,7 @@ static void del_timeout(struct dlm_lkb *lkb)
void dlm_scan_timeout(struct dlm_ls *ls)
{
struct dlm_rsb *r;
- struct dlm_lkb *lkb;
+ struct dlm_lkb *lkb = NULL, *iter;
int do_cancel, do_warn;
s64 wait_us;
@@ -1865,27 +1840,28 @@ void dlm_scan_timeout(struct dlm_ls *ls)
do_cancel = 0;
do_warn = 0;
mutex_lock(&ls->ls_timeout_mutex);
- list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list) {
+ list_for_each_entry(iter, &ls->ls_timeout, lkb_time_list) {
wait_us = ktime_to_us(ktime_sub(ktime_get(),
- lkb->lkb_timestamp));
+ iter->lkb_timestamp));
- if ((lkb->lkb_exflags & DLM_LKF_TIMEOUT) &&
- wait_us >= (lkb->lkb_timeout_cs * 10000))
+ if ((iter->lkb_exflags & DLM_LKF_TIMEOUT) &&
+ wait_us >= (iter->lkb_timeout_cs * 10000))
do_cancel = 1;
- if ((lkb->lkb_flags & DLM_IFL_WATCH_TIMEWARN) &&
+ if ((iter->lkb_flags & DLM_IFL_WATCH_TIMEWARN) &&
wait_us >= dlm_config.ci_timewarn_cs * 10000)
do_warn = 1;
if (!do_cancel && !do_warn)
continue;
- hold_lkb(lkb);
+ hold_lkb(iter);
+ lkb = iter;
break;
}
mutex_unlock(&ls->ls_timeout_mutex);
- if (!do_cancel && !do_warn)
+ if (!lkb)
break;
r = lkb->lkb_resource;
@@ -1928,17 +1904,11 @@ void dlm_adjust_timeouts(struct dlm_ls *ls)
list_for_each_entry(lkb, &ls->ls_timeout, lkb_time_list)
lkb->lkb_timestamp = ktime_add_us(lkb->lkb_timestamp, adj_us);
mutex_unlock(&ls->ls_timeout_mutex);
-
- if (!dlm_config.ci_waitwarn_us)
- return;
-
- mutex_lock(&ls->ls_waiters_mutex);
- list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
- if (ktime_to_us(lkb->lkb_wait_time))
- lkb->lkb_wait_time = ktime_get();
- }
- mutex_unlock(&ls->ls_waiters_mutex);
}
+#else
+static void add_timeout(struct dlm_lkb *lkb) { }
+static void del_timeout(struct dlm_lkb *lkb) { }
+#endif
/* lkb is master or local copy */
@@ -2039,7 +2009,7 @@ static void set_lvb_lock_pc(struct dlm_rsb *r, struct dlm_lkb *lkb,
if (len > r->res_ls->ls_lvblen)
len = r->res_ls->ls_lvblen;
memcpy(lkb->lkb_lvbptr, ms->m_extra, len);
- lkb->lkb_lvbseq = ms->m_lvbseq;
+ lkb->lkb_lvbseq = le32_to_cpu(ms->m_lvbseq);
}
}
@@ -2170,10 +2140,10 @@ static void munge_demoted(struct dlm_lkb *lkb)
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) {
+ if (ms->m_type != cpu_to_le32(DLM_MSG_REQUEST_REPLY) &&
+ ms->m_type != cpu_to_le32(DLM_MSG_GRANT)) {
log_print("munge_altmode %x invalid reply type %d",
- lkb->lkb_id, ms->m_type);
+ lkb->lkb_id, le32_to_cpu(ms->m_type));
return;
}
@@ -2803,12 +2773,20 @@ static void confirm_master(struct dlm_rsb *r, int error)
}
}
+#ifdef CONFIG_DLM_DEPRECATED_API
static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags,
int namelen, unsigned long timeout_cs,
void (*ast) (void *astparam),
void *astparam,
void (*bast) (void *astparam, int mode),
struct dlm_args *args)
+#else
+static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags,
+ int namelen, void (*ast)(void *astparam),
+ void *astparam,
+ void (*bast)(void *astparam, int mode),
+ struct dlm_args *args)
+#endif
{
int rv = -EINVAL;
@@ -2861,7 +2839,9 @@ static int set_lock_args(int mode, struct dlm_lksb *lksb, uint32_t flags,
args->astfn = ast;
args->astparam = astparam;
args->bastfn = bast;
+#ifdef CONFIG_DLM_DEPRECATED_API
args->timeout = timeout_cs;
+#endif
args->mode = mode;
args->lksb = lksb;
rv = 0;
@@ -2886,24 +2866,25 @@ static int set_unlock_args(uint32_t flags, void *astarg, struct dlm_args *args)
static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
struct dlm_args *args)
{
- int rv = -EINVAL;
+ int rv = -EBUSY;
if (args->flags & DLM_LKF_CONVERT) {
- if (lkb->lkb_flags & DLM_IFL_MSTCPY)
+ if (lkb->lkb_status != DLM_LKSTS_GRANTED)
goto out;
- if (args->flags & DLM_LKF_QUECVT &&
- !__quecvt_compat_matrix[lkb->lkb_grmode+1][args->mode+1])
+ /* lock not allowed if there's any op in progress */
+ if (lkb->lkb_wait_type || lkb->lkb_wait_count)
goto out;
- rv = -EBUSY;
- if (lkb->lkb_status != DLM_LKSTS_GRANTED)
+ if (is_overlap(lkb))
goto out;
- if (lkb->lkb_wait_type)
+ rv = -EINVAL;
+ if (lkb->lkb_flags & DLM_IFL_MSTCPY)
goto out;
- if (is_overlap(lkb))
+ if (args->flags & DLM_LKF_QUECVT &&
+ !__quecvt_compat_matrix[lkb->lkb_grmode+1][args->mode+1])
goto out;
}
@@ -2916,14 +2897,30 @@ static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
lkb->lkb_lksb = args->lksb;
lkb->lkb_lvbptr = args->lksb->sb_lvbptr;
lkb->lkb_ownpid = (int) current->pid;
+#ifdef CONFIG_DLM_DEPRECATED_API
lkb->lkb_timeout_cs = args->timeout;
+#endif
rv = 0;
out:
- if (rv)
- log_debug(ls, "validate_lock_args %d %x %x %x %d %d %s",
+ switch (rv) {
+ case 0:
+ break;
+ case -EINVAL:
+ /* annoy the user because dlm usage is wrong */
+ WARN_ON(1);
+ log_error(ls, "%s %d %x %x %x %d %d %s", __func__,
+ rv, lkb->lkb_id, lkb->lkb_flags, args->flags,
+ lkb->lkb_status, lkb->lkb_wait_type,
+ lkb->lkb_resource->res_name);
+ break;
+ default:
+ log_debug(ls, "%s %d %x %x %x %d %d %s", __func__,
rv, lkb->lkb_id, lkb->lkb_flags, args->flags,
lkb->lkb_status, lkb->lkb_wait_type,
lkb->lkb_resource->res_name);
+ break;
+ }
+
return rv;
}
@@ -2937,23 +2934,12 @@ static int validate_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
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;
+ int rv = -EBUSY;
- if (lkb->lkb_flags & DLM_IFL_MSTCPY) {
- log_error(ls, "unlock on MSTCPY %x", lkb->lkb_id);
- dlm_print_lkb(lkb);
- goto out;
- }
-
- /* 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 (lkb->lkb_flags & DLM_IFL_ENDOFLIFE) {
- log_debug(ls, "unlock on ENDOFLIFE %x", lkb->lkb_id);
- rv = -ENOENT;
+ /* normal unlock not allowed if there's any op in progress */
+ if (!(args->flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)) &&
+ (lkb->lkb_wait_type || lkb->lkb_wait_count))
goto out;
- }
/* an lkb may be waiting for an rsb lookup to complete where the
lookup was initiated by another lock */
@@ -2968,7 +2954,24 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
unhold_lkb(lkb); /* undoes create_lkb() */
}
/* caller changes -EBUSY to 0 for CANCEL and FORCEUNLOCK */
- rv = -EBUSY;
+ goto out;
+ }
+
+ rv = -EINVAL;
+ if (lkb->lkb_flags & DLM_IFL_MSTCPY) {
+ log_error(ls, "unlock on MSTCPY %x", lkb->lkb_id);
+ dlm_print_lkb(lkb);
+ goto out;
+ }
+
+ /* 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 (lkb->lkb_flags & DLM_IFL_ENDOFLIFE) {
+ log_debug(ls, "unlock on ENDOFLIFE %x", lkb->lkb_id);
+ rv = -ENOENT;
goto out;
}
@@ -3041,14 +3044,8 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
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 || lkb->lkb_wait_count)
- goto out;
-
out_ok:
/* an overlapping op shouldn't blow away exflags from other op */
lkb->lkb_exflags |= args->flags;
@@ -3056,11 +3053,25 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
lkb->lkb_astparam = args->astparam;
rv = 0;
out:
- if (rv)
- log_debug(ls, "validate_unlock_args %d %x %x %x %x %d %s", rv,
+ switch (rv) {
+ case 0:
+ break;
+ case -EINVAL:
+ /* annoy the user because dlm usage is wrong */
+ WARN_ON(1);
+ log_error(ls, "%s %d %x %x %x %x %d %s", __func__, rv,
+ lkb->lkb_id, lkb->lkb_flags, lkb->lkb_exflags,
+ args->flags, lkb->lkb_wait_type,
+ lkb->lkb_resource->res_name);
+ break;
+ default:
+ log_debug(ls, "%s %d %x %x %x %x %d %s", __func__, rv,
lkb->lkb_id, lkb->lkb_flags, lkb->lkb_exflags,
args->flags, lkb->lkb_wait_type,
lkb->lkb_resource->res_name);
+ break;
+ }
+
return rv;
}
@@ -3311,8 +3322,9 @@ static int _cancel_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
* request_lock(), convert_lock(), unlock_lock(), cancel_lock()
*/
-static int request_lock(struct dlm_ls *ls, struct dlm_lkb *lkb, char *name,
- int len, struct dlm_args *args)
+static int request_lock(struct dlm_ls *ls, struct dlm_lkb *lkb,
+ const void *name, int len,
+ struct dlm_args *args)
{
struct dlm_rsb *r;
int error;
@@ -3411,7 +3423,7 @@ int dlm_lock(dlm_lockspace_t *lockspace,
int mode,
struct dlm_lksb *lksb,
uint32_t flags,
- void *name,
+ const void *name,
unsigned int namelen,
uint32_t parent_lkid,
void (*ast) (void *astarg),
@@ -3437,8 +3449,15 @@ int dlm_lock(dlm_lockspace_t *lockspace,
if (error)
goto out;
+ trace_dlm_lock_start(ls, lkb, name, namelen, mode, flags);
+
+#ifdef CONFIG_DLM_DEPRECATED_API
error = set_lock_args(mode, lksb, flags, namelen, 0, ast,
astarg, bast, &args);
+#else
+ error = set_lock_args(mode, lksb, flags, namelen, ast, astarg, bast,
+ &args);
+#endif
if (error)
goto out_put;
@@ -3450,6 +3469,8 @@ int dlm_lock(dlm_lockspace_t *lockspace,
if (error == -EINPROGRESS)
error = 0;
out_put:
+ trace_dlm_lock_end(ls, lkb, name, namelen, mode, flags, error, true);
+
if (convert || error)
__put_lkb(ls, lkb);
if (error == -EAGAIN || error == -EDEADLK)
@@ -3481,6 +3502,8 @@ int dlm_unlock(dlm_lockspace_t *lockspace,
if (error)
goto out;
+ trace_dlm_unlock_start(ls, lkb, flags);
+
error = set_unlock_args(flags, astarg, &args);
if (error)
goto out_put;
@@ -3495,6 +3518,8 @@ int dlm_unlock(dlm_lockspace_t *lockspace,
if (error == -EBUSY && (flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)))
error = 0;
out_put:
+ trace_dlm_unlock_end(ls, lkb, flags, error);
+
dlm_put_lkb(lkb);
out:
dlm_unlock_recovery(ls);
@@ -3534,24 +3559,22 @@ static int _create_message(struct dlm_ls *ls, int mb_len,
char *mb;
/* get_buffer gives us a message handle (mh) that we need to
- pass into lowcomms_commit and a message buffer (mb) that we
+ pass into midcomms_commit and a message buffer (mb) that we
write our data into */
- mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, GFP_NOFS, &mb);
+ mh = dlm_midcomms_get_mhandle(to_nodeid, mb_len, GFP_NOFS, &mb);
if (!mh)
return -ENOBUFS;
- memset(mb, 0, mb_len);
-
ms = (struct dlm_message *) mb;
- ms->m_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
- 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_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+ ms->m_header.u.h_lockspace = cpu_to_le32(ls->ls_global_id);
+ ms->m_header.h_nodeid = cpu_to_le32(dlm_our_nodeid());
+ ms->m_header.h_length = cpu_to_le16(mb_len);
ms->m_header.h_cmd = DLM_MSG;
- ms->m_type = mstype;
+ ms->m_type = cpu_to_le32(mstype);
*mh_ret = mh;
*ms_ret = ms;
@@ -3590,49 +3613,48 @@ static int create_message(struct dlm_rsb *r, struct dlm_lkb *lkb,
static int send_message(struct dlm_mhandle *mh, struct dlm_message *ms)
{
- dlm_message_out(ms);
- dlm_lowcomms_commit_buffer(mh);
+ dlm_midcomms_commit_mhandle(mh);
return 0;
}
static void send_args(struct dlm_rsb *r, struct dlm_lkb *lkb,
struct dlm_message *ms)
{
- ms->m_nodeid = lkb->lkb_nodeid;
- ms->m_pid = lkb->lkb_ownpid;
- ms->m_lkid = lkb->lkb_id;
- ms->m_remid = lkb->lkb_remid;
- ms->m_exflags = lkb->lkb_exflags;
- ms->m_sbflags = lkb->lkb_sbflags;
- ms->m_flags = lkb->lkb_flags;
- ms->m_lvbseq = lkb->lkb_lvbseq;
- ms->m_status = lkb->lkb_status;
- ms->m_grmode = lkb->lkb_grmode;
- ms->m_rqmode = lkb->lkb_rqmode;
- ms->m_hash = r->res_hash;
+ ms->m_nodeid = cpu_to_le32(lkb->lkb_nodeid);
+ ms->m_pid = cpu_to_le32(lkb->lkb_ownpid);
+ ms->m_lkid = cpu_to_le32(lkb->lkb_id);
+ ms->m_remid = cpu_to_le32(lkb->lkb_remid);
+ ms->m_exflags = cpu_to_le32(lkb->lkb_exflags);
+ ms->m_sbflags = cpu_to_le32(lkb->lkb_sbflags);
+ ms->m_flags = cpu_to_le32(lkb->lkb_flags);
+ ms->m_lvbseq = cpu_to_le32(lkb->lkb_lvbseq);
+ ms->m_status = cpu_to_le32(lkb->lkb_status);
+ ms->m_grmode = cpu_to_le32(lkb->lkb_grmode);
+ ms->m_rqmode = cpu_to_le32(lkb->lkb_rqmode);
+ ms->m_hash = cpu_to_le32(r->res_hash);
/* m_result and m_bastmode are set from function args,
not from lkb fields */
if (lkb->lkb_bastfn)
- ms->m_asts |= DLM_CB_BAST;
+ ms->m_asts |= cpu_to_le32(DLM_CB_BAST);
if (lkb->lkb_astfn)
- ms->m_asts |= DLM_CB_CAST;
+ ms->m_asts |= cpu_to_le32(DLM_CB_CAST);
/* compare with switch in create_message; send_remove() doesn't
use send_args() */
switch (ms->m_type) {
- case DLM_MSG_REQUEST:
- case DLM_MSG_LOOKUP:
+ case cpu_to_le32(DLM_MSG_REQUEST):
+ case cpu_to_le32(DLM_MSG_LOOKUP):
memcpy(ms->m_extra, r->res_name, 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_lvbptr)
+ case cpu_to_le32(DLM_MSG_CONVERT):
+ case cpu_to_le32(DLM_MSG_UNLOCK):
+ case cpu_to_le32(DLM_MSG_REQUEST_REPLY):
+ case cpu_to_le32(DLM_MSG_CONVERT_REPLY):
+ case cpu_to_le32(DLM_MSG_GRANT):
+ if (!lkb->lkb_lvbptr || !(lkb->lkb_exflags & DLM_LKF_VALBLK))
break;
memcpy(ms->m_extra, lkb->lkb_lvbptr, r->res_ls->ls_lvblen);
break;
@@ -3681,8 +3703,8 @@ static int send_convert(struct dlm_rsb *r, struct dlm_lkb *lkb)
/* down conversions go without a reply from the master */
if (!error && down_conversion(lkb)) {
remove_from_waiters(lkb, DLM_MSG_CONVERT_REPLY);
- r->res_ls->ls_stub_ms.m_flags = DLM_IFL_STUB_MS;
- r->res_ls->ls_stub_ms.m_type = DLM_MSG_CONVERT_REPLY;
+ r->res_ls->ls_stub_ms.m_flags = cpu_to_le32(DLM_IFL_STUB_MS);
+ r->res_ls->ls_stub_ms.m_type = cpu_to_le32(DLM_MSG_CONVERT_REPLY);
r->res_ls->ls_stub_ms.m_result = 0;
__receive_convert_reply(r, lkb, &r->res_ls->ls_stub_ms);
}
@@ -3739,7 +3761,7 @@ static int send_bast(struct dlm_rsb *r, struct dlm_lkb *lkb, int mode)
send_args(r, lkb, ms);
- ms->m_bastmode = mode;
+ ms->m_bastmode = cpu_to_le32(mode);
error = send_message(mh, ms);
out:
@@ -3787,7 +3809,7 @@ static int send_remove(struct dlm_rsb *r)
goto out;
memcpy(ms->m_extra, r->res_name, r->res_length);
- ms->m_hash = r->res_hash;
+ ms->m_hash = cpu_to_le32(r->res_hash);
error = send_message(mh, ms);
out:
@@ -3809,7 +3831,7 @@ static int send_common_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
send_args(r, lkb, ms);
- ms->m_result = rv;
+ ms->m_result = cpu_to_le32(to_dlm_errno(rv));
error = send_message(mh, ms);
out:
@@ -3842,15 +3864,15 @@ static int send_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms_in,
struct dlm_rsb *r = &ls->ls_stub_rsb;
struct dlm_message *ms;
struct dlm_mhandle *mh;
- int error, nodeid = ms_in->m_header.h_nodeid;
+ int error, nodeid = le32_to_cpu(ms_in->m_header.h_nodeid);
error = create_message(r, NULL, nodeid, DLM_MSG_LOOKUP_REPLY, &ms, &mh);
if (error)
goto out;
ms->m_lkid = ms_in->m_lkid;
- ms->m_result = rv;
- ms->m_nodeid = ret_nodeid;
+ ms->m_result = cpu_to_le32(to_dlm_errno(rv));
+ ms->m_nodeid = cpu_to_le32(ret_nodeid);
error = send_message(mh, ms);
out:
@@ -3863,25 +3885,26 @@ static int send_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms_in,
static void receive_flags(struct dlm_lkb *lkb, struct dlm_message *ms)
{
- lkb->lkb_exflags = ms->m_exflags;
- lkb->lkb_sbflags = ms->m_sbflags;
+ lkb->lkb_exflags = le32_to_cpu(ms->m_exflags);
+ lkb->lkb_sbflags = le32_to_cpu(ms->m_sbflags);
lkb->lkb_flags = (lkb->lkb_flags & 0xFFFF0000) |
- (ms->m_flags & 0x0000FFFF);
+ (le32_to_cpu(ms->m_flags) & 0x0000FFFF);
}
static void receive_flags_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
{
- if (ms->m_flags == DLM_IFL_STUB_MS)
+ if (ms->m_flags == cpu_to_le32(DLM_IFL_STUB_MS))
return;
- lkb->lkb_sbflags = ms->m_sbflags;
+ lkb->lkb_sbflags = le32_to_cpu(ms->m_sbflags);
lkb->lkb_flags = (lkb->lkb_flags & 0xFFFF0000) |
- (ms->m_flags & 0x0000FFFF);
+ (le32_to_cpu(ms->m_flags) & 0x0000FFFF);
}
static int receive_extralen(struct dlm_message *ms)
{
- return (ms->m_header.h_length - sizeof(struct dlm_message));
+ return (le16_to_cpu(ms->m_header.h_length) -
+ sizeof(struct dlm_message));
}
static int receive_lvb(struct dlm_ls *ls, struct dlm_lkb *lkb,
@@ -3915,14 +3938,14 @@ static void fake_astfn(void *astparam)
static int receive_request_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
struct dlm_message *ms)
{
- lkb->lkb_nodeid = ms->m_header.h_nodeid;
- lkb->lkb_ownpid = ms->m_pid;
- lkb->lkb_remid = ms->m_lkid;
+ lkb->lkb_nodeid = le32_to_cpu(ms->m_header.h_nodeid);
+ lkb->lkb_ownpid = le32_to_cpu(ms->m_pid);
+ lkb->lkb_remid = le32_to_cpu(ms->m_lkid);
lkb->lkb_grmode = DLM_LOCK_IV;
- lkb->lkb_rqmode = ms->m_rqmode;
+ lkb->lkb_rqmode = le32_to_cpu(ms->m_rqmode);
- lkb->lkb_bastfn = (ms->m_asts & DLM_CB_BAST) ? &fake_bastfn : NULL;
- lkb->lkb_astfn = (ms->m_asts & DLM_CB_CAST) ? &fake_astfn : NULL;
+ lkb->lkb_bastfn = (ms->m_asts & cpu_to_le32(DLM_CB_BAST)) ? &fake_bastfn : NULL;
+ lkb->lkb_astfn = (ms->m_asts & cpu_to_le32(DLM_CB_CAST)) ? &fake_astfn : NULL;
if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
/* lkb was just created so there won't be an lvb yet */
@@ -3943,8 +3966,8 @@ static int receive_convert_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
if (receive_lvb(ls, lkb, ms))
return -ENOMEM;
- lkb->lkb_rqmode = ms->m_rqmode;
- lkb->lkb_lvbseq = ms->m_lvbseq;
+ lkb->lkb_rqmode = le32_to_cpu(ms->m_rqmode);
+ lkb->lkb_lvbseq = le32_to_cpu(ms->m_lvbseq);
return 0;
}
@@ -3963,8 +3986,8 @@ static int receive_unlock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
static void setup_stub_lkb(struct dlm_ls *ls, struct dlm_message *ms)
{
struct dlm_lkb *lkb = &ls->ls_stub_lkb;
- lkb->lkb_nodeid = ms->m_header.h_nodeid;
- lkb->lkb_remid = ms->m_lkid;
+ lkb->lkb_nodeid = le32_to_cpu(ms->m_header.h_nodeid);
+ lkb->lkb_remid = le32_to_cpu(ms->m_lkid);
}
/* This is called after the rsb is locked so that we can safely inspect
@@ -3972,27 +3995,36 @@ static void setup_stub_lkb(struct dlm_ls *ls, struct dlm_message *ms)
static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms)
{
- int from = ms->m_header.h_nodeid;
+ int from = le32_to_cpu(ms->m_header.h_nodeid);
int error = 0;
+ /* currently mixing of user/kernel locks are not supported */
+ if (ms->m_flags & cpu_to_le32(DLM_IFL_USER) &&
+ ~lkb->lkb_flags & DLM_IFL_USER) {
+ log_error(lkb->lkb_resource->res_ls,
+ "got user dlm message for a kernel lock");
+ error = -EINVAL;
+ goto out;
+ }
+
switch (ms->m_type) {
- case DLM_MSG_CONVERT:
- case DLM_MSG_UNLOCK:
- case DLM_MSG_CANCEL:
+ case cpu_to_le32(DLM_MSG_CONVERT):
+ case cpu_to_le32(DLM_MSG_UNLOCK):
+ case cpu_to_le32(DLM_MSG_CANCEL):
if (!is_master_copy(lkb) || lkb->lkb_nodeid != from)
error = -EINVAL;
break;
- case DLM_MSG_CONVERT_REPLY:
- case DLM_MSG_UNLOCK_REPLY:
- case DLM_MSG_CANCEL_REPLY:
- case DLM_MSG_GRANT:
- case DLM_MSG_BAST:
+ case cpu_to_le32(DLM_MSG_CONVERT_REPLY):
+ case cpu_to_le32(DLM_MSG_UNLOCK_REPLY):
+ case cpu_to_le32(DLM_MSG_CANCEL_REPLY):
+ case cpu_to_le32(DLM_MSG_GRANT):
+ case cpu_to_le32(DLM_MSG_BAST):
if (!is_process_copy(lkb) || lkb->lkb_nodeid != from)
error = -EINVAL;
break;
- case DLM_MSG_REQUEST_REPLY:
+ case cpu_to_le32(DLM_MSG_REQUEST_REPLY):
if (!is_process_copy(lkb))
error = -EINVAL;
else if (lkb->lkb_nodeid != -1 && lkb->lkb_nodeid != from)
@@ -4003,11 +4035,12 @@ static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms)
error = -EINVAL;
}
+out:
if (error)
log_error(lkb->lkb_resource->res_ls,
"ignore invalid message %d from %d %x %x %x %d",
- ms->m_type, from, lkb->lkb_id, lkb->lkb_remid,
- lkb->lkb_flags, lkb->lkb_nodeid);
+ le32_to_cpu(ms->m_type), from, lkb->lkb_id,
+ lkb->lkb_remid, lkb->lkb_flags, lkb->lkb_nodeid);
return error;
}
@@ -4056,17 +4089,19 @@ static void send_repeat_remove(struct dlm_ls *ls, char *ms_name, int len)
rv = _create_message(ls, sizeof(struct dlm_message) + len,
dir_nodeid, DLM_MSG_REMOVE, &ms, &mh);
if (rv)
- return;
+ goto out;
memcpy(ms->m_extra, name, len);
- ms->m_hash = hash;
+ ms->m_hash = cpu_to_le32(hash);
send_message(mh, ms);
+out:
spin_lock(&ls->ls_remove_spin);
ls->ls_remove_len = 0;
memset(ls->ls_remove_name, 0, DLM_RESNAME_MAXLEN);
spin_unlock(&ls->ls_remove_spin);
+ wake_up(&ls->ls_remove_wait);
}
static int receive_request(struct dlm_ls *ls, struct dlm_message *ms)
@@ -4076,7 +4111,7 @@ static int receive_request(struct dlm_ls *ls, struct dlm_message *ms)
int from_nodeid;
int error, namelen = 0;
- from_nodeid = ms->m_header.h_nodeid;
+ from_nodeid = le32_to_cpu(ms->m_header.h_nodeid);
error = create_lkb(ls, &lkb);
if (error)
@@ -4149,7 +4184,7 @@ static int receive_request(struct dlm_ls *ls, struct dlm_message *ms)
if (error != -ENOTBLK) {
log_limit(ls, "receive_request %x from %d %d",
- ms->m_lkid, from_nodeid, error);
+ le32_to_cpu(ms->m_lkid), from_nodeid, error);
}
if (namelen && error == -EBADR) {
@@ -4168,15 +4203,16 @@ static int receive_convert(struct dlm_ls *ls, struct dlm_message *ms)
struct dlm_rsb *r;
int error, reply = 1;
- error = find_lkb(ls, ms->m_remid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb);
if (error)
goto fail;
- if (lkb->lkb_remid != ms->m_lkid) {
+ if (lkb->lkb_remid != le32_to_cpu(ms->m_lkid)) {
log_error(ls, "receive_convert %x remid %x recover_seq %llu "
"remote %d %x", lkb->lkb_id, lkb->lkb_remid,
(unsigned long long)lkb->lkb_recover_seq,
- ms->m_header.h_nodeid, ms->m_lkid);
+ le32_to_cpu(ms->m_header.h_nodeid),
+ le32_to_cpu(ms->m_lkid));
error = -ENOENT;
dlm_put_lkb(lkb);
goto fail;
@@ -4223,14 +4259,15 @@ static int receive_unlock(struct dlm_ls *ls, struct dlm_message *ms)
struct dlm_rsb *r;
int error;
- error = find_lkb(ls, ms->m_remid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb);
if (error)
goto fail;
- if (lkb->lkb_remid != ms->m_lkid) {
+ if (lkb->lkb_remid != le32_to_cpu(ms->m_lkid)) {
log_error(ls, "receive_unlock %x remid %x remote %d %x",
lkb->lkb_id, lkb->lkb_remid,
- ms->m_header.h_nodeid, ms->m_lkid);
+ le32_to_cpu(ms->m_header.h_nodeid),
+ le32_to_cpu(ms->m_lkid));
error = -ENOENT;
dlm_put_lkb(lkb);
goto fail;
@@ -4274,7 +4311,7 @@ static int receive_cancel(struct dlm_ls *ls, struct dlm_message *ms)
struct dlm_rsb *r;
int error;
- error = find_lkb(ls, ms->m_remid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb);
if (error)
goto fail;
@@ -4310,7 +4347,7 @@ static int receive_grant(struct dlm_ls *ls, struct dlm_message *ms)
struct dlm_rsb *r;
int error;
- error = find_lkb(ls, ms->m_remid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb);
if (error)
return error;
@@ -4341,7 +4378,7 @@ static int receive_bast(struct dlm_ls *ls, struct dlm_message *ms)
struct dlm_rsb *r;
int error;
- error = find_lkb(ls, ms->m_remid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb);
if (error)
return error;
@@ -4354,8 +4391,8 @@ static int receive_bast(struct dlm_ls *ls, struct dlm_message *ms)
if (error)
goto out;
- queue_bast(r, lkb, ms->m_bastmode);
- lkb->lkb_highbast = ms->m_bastmode;
+ queue_bast(r, lkb, le32_to_cpu(ms->m_bastmode));
+ lkb->lkb_highbast = le32_to_cpu(ms->m_bastmode);
out:
unlock_rsb(r);
put_rsb(r);
@@ -4367,7 +4404,7 @@ static void receive_lookup(struct dlm_ls *ls, struct dlm_message *ms)
{
int len, error, ret_nodeid, from_nodeid, our_nodeid;
- from_nodeid = ms->m_header.h_nodeid;
+ from_nodeid = le32_to_cpu(ms->m_header.h_nodeid);
our_nodeid = dlm_our_nodeid();
len = receive_extralen(ms);
@@ -4390,7 +4427,7 @@ static void receive_remove(struct dlm_ls *ls, struct dlm_message *ms)
uint32_t hash, b;
int rv, len, dir_nodeid, from_nodeid;
- from_nodeid = ms->m_header.h_nodeid;
+ from_nodeid = le32_to_cpu(ms->m_header.h_nodeid);
len = receive_extralen(ms);
@@ -4400,7 +4437,7 @@ static void receive_remove(struct dlm_ls *ls, struct dlm_message *ms)
return;
}
- dir_nodeid = dlm_hash2nodeid(ls, ms->m_hash);
+ dir_nodeid = dlm_hash2nodeid(ls, le32_to_cpu(ms->m_hash));
if (dir_nodeid != dlm_our_nodeid()) {
log_error(ls, "receive_remove from %d bad nodeid %d",
from_nodeid, dir_nodeid);
@@ -4473,7 +4510,7 @@ static void receive_remove(struct dlm_ls *ls, struct dlm_message *ms)
static void receive_purge(struct dlm_ls *ls, struct dlm_message *ms)
{
- do_purge(ls, ms->m_nodeid, ms->m_pid);
+ do_purge(ls, le32_to_cpu(ms->m_nodeid), le32_to_cpu(ms->m_pid));
}
static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms)
@@ -4481,9 +4518,9 @@ static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms)
struct dlm_lkb *lkb;
struct dlm_rsb *r;
int error, mstype, result;
- int from_nodeid = ms->m_header.h_nodeid;
+ int from_nodeid = le32_to_cpu(ms->m_header.h_nodeid);
- error = find_lkb(ls, ms->m_remid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb);
if (error)
return error;
@@ -4499,7 +4536,8 @@ static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms)
error = remove_from_waiters(lkb, DLM_MSG_REQUEST_REPLY);
if (error) {
log_error(ls, "receive_request_reply %x remote %d %x result %d",
- lkb->lkb_id, from_nodeid, ms->m_lkid, ms->m_result);
+ lkb->lkb_id, from_nodeid, le32_to_cpu(ms->m_lkid),
+ from_dlm_errno(le32_to_cpu(ms->m_result)));
dlm_dump_rsb(r);
goto out;
}
@@ -4513,7 +4551,7 @@ static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms)
}
/* this is the value returned from do_request() on the master */
- result = ms->m_result;
+ result = from_dlm_errno(le32_to_cpu(ms->m_result));
switch (result) {
case -EAGAIN:
@@ -4527,7 +4565,7 @@ static int receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms)
case 0:
/* request was queued or granted on remote master */
receive_flags_reply(lkb, ms);
- lkb->lkb_remid = ms->m_lkid;
+ lkb->lkb_remid = le32_to_cpu(ms->m_lkid);
if (is_altmode(lkb))
munge_altmode(lkb, ms);
if (result) {
@@ -4600,7 +4638,7 @@ static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
struct dlm_message *ms)
{
/* this is the value returned from do_convert() on the master */
- switch (ms->m_result) {
+ switch (from_dlm_errno(le32_to_cpu(ms->m_result))) {
case -EAGAIN:
/* convert would block (be queued) on remote master */
queue_cast(r, lkb, -EAGAIN);
@@ -4633,8 +4671,9 @@ static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
default:
log_error(r->res_ls, "receive_convert_reply %x remote %d %x %d",
- lkb->lkb_id, ms->m_header.h_nodeid, ms->m_lkid,
- ms->m_result);
+ lkb->lkb_id, le32_to_cpu(ms->m_header.h_nodeid),
+ le32_to_cpu(ms->m_lkid),
+ from_dlm_errno(le32_to_cpu(ms->m_result)));
dlm_print_rsb(r);
dlm_print_lkb(lkb);
}
@@ -4668,7 +4707,7 @@ static int receive_convert_reply(struct dlm_ls *ls, struct dlm_message *ms)
struct dlm_lkb *lkb;
int error;
- error = find_lkb(ls, ms->m_remid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb);
if (error)
return error;
@@ -4696,7 +4735,7 @@ static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
/* this is the value returned from do_unlock() on the master */
- switch (ms->m_result) {
+ switch (from_dlm_errno(le32_to_cpu(ms->m_result))) {
case -DLM_EUNLOCK:
receive_flags_reply(lkb, ms);
remove_lock_pc(r, lkb);
@@ -4706,7 +4745,7 @@ static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
break;
default:
log_error(r->res_ls, "receive_unlock_reply %x error %d",
- lkb->lkb_id, ms->m_result);
+ lkb->lkb_id, from_dlm_errno(le32_to_cpu(ms->m_result)));
}
out:
unlock_rsb(r);
@@ -4718,7 +4757,7 @@ static int receive_unlock_reply(struct dlm_ls *ls, struct dlm_message *ms)
struct dlm_lkb *lkb;
int error;
- error = find_lkb(ls, ms->m_remid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb);
if (error)
return error;
@@ -4746,7 +4785,7 @@ static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
/* this is the value returned from do_cancel() on the master */
- switch (ms->m_result) {
+ switch (from_dlm_errno(le32_to_cpu(ms->m_result))) {
case -DLM_ECANCEL:
receive_flags_reply(lkb, ms);
revert_lock_pc(r, lkb);
@@ -4756,7 +4795,8 @@ static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
break;
default:
log_error(r->res_ls, "receive_cancel_reply %x error %d",
- lkb->lkb_id, ms->m_result);
+ lkb->lkb_id,
+ from_dlm_errno(le32_to_cpu(ms->m_result)));
}
out:
unlock_rsb(r);
@@ -4768,7 +4808,7 @@ static int receive_cancel_reply(struct dlm_ls *ls, struct dlm_message *ms)
struct dlm_lkb *lkb;
int error;
- error = find_lkb(ls, ms->m_remid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_remid), &lkb);
if (error)
return error;
@@ -4784,9 +4824,10 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms)
int error, ret_nodeid;
int do_lookup_list = 0;
- error = find_lkb(ls, ms->m_lkid, &lkb);
+ error = find_lkb(ls, le32_to_cpu(ms->m_lkid), &lkb);
if (error) {
- log_error(ls, "receive_lookup_reply no lkid %x", ms->m_lkid);
+ log_error(ls, "%s no lkid %x", __func__,
+ le32_to_cpu(ms->m_lkid));
return;
}
@@ -4801,7 +4842,7 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms)
if (error)
goto out;
- ret_nodeid = ms->m_nodeid;
+ ret_nodeid = le32_to_cpu(ms->m_nodeid);
/* We sometimes receive a request from the dir node for this
rsb before we've received the dir node's loookup_reply for it.
@@ -4813,8 +4854,8 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms)
/* This should never happen */
log_error(ls, "receive_lookup_reply %x from %d ret %d "
"master %d dir %d our %d first %x %s",
- lkb->lkb_id, ms->m_header.h_nodeid, ret_nodeid,
- r->res_master_nodeid, r->res_dir_nodeid,
+ lkb->lkb_id, le32_to_cpu(ms->m_header.h_nodeid),
+ ret_nodeid, r->res_master_nodeid, r->res_dir_nodeid,
dlm_our_nodeid(), r->res_first_lkid, r->res_name);
}
@@ -4826,7 +4867,7 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms)
} else if (ret_nodeid == -1) {
/* the remote node doesn't believe it's the dir node */
log_error(ls, "receive_lookup_reply %x from %d bad ret_nodeid",
- lkb->lkb_id, ms->m_header.h_nodeid);
+ lkb->lkb_id, le32_to_cpu(ms->m_header.h_nodeid));
r->res_master_nodeid = 0;
r->res_nodeid = -1;
lkb->lkb_nodeid = -1;
@@ -4860,10 +4901,12 @@ static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms,
{
int error = 0, noent = 0;
- if (!dlm_is_member(ls, ms->m_header.h_nodeid)) {
+ if (!dlm_is_member(ls, le32_to_cpu(ms->m_header.h_nodeid))) {
log_limit(ls, "receive %d from non-member %d %x %x %d",
- ms->m_type, ms->m_header.h_nodeid, ms->m_lkid,
- ms->m_remid, ms->m_result);
+ le32_to_cpu(ms->m_type),
+ le32_to_cpu(ms->m_header.h_nodeid),
+ le32_to_cpu(ms->m_lkid), le32_to_cpu(ms->m_remid),
+ from_dlm_errno(le32_to_cpu(ms->m_result)));
return;
}
@@ -4871,77 +4914,78 @@ static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms,
/* messages sent to a master node */
- case DLM_MSG_REQUEST:
+ case cpu_to_le32(DLM_MSG_REQUEST):
error = receive_request(ls, ms);
break;
- case DLM_MSG_CONVERT:
+ case cpu_to_le32(DLM_MSG_CONVERT):
error = receive_convert(ls, ms);
break;
- case DLM_MSG_UNLOCK:
+ case cpu_to_le32(DLM_MSG_UNLOCK):
error = receive_unlock(ls, ms);
break;
- case DLM_MSG_CANCEL:
+ case cpu_to_le32(DLM_MSG_CANCEL):
noent = 1;
error = receive_cancel(ls, ms);
break;
/* messages sent from a master node (replies to above) */
- case DLM_MSG_REQUEST_REPLY:
+ case cpu_to_le32(DLM_MSG_REQUEST_REPLY):
error = receive_request_reply(ls, ms);
break;
- case DLM_MSG_CONVERT_REPLY:
+ case cpu_to_le32(DLM_MSG_CONVERT_REPLY):
error = receive_convert_reply(ls, ms);
break;
- case DLM_MSG_UNLOCK_REPLY:
+ case cpu_to_le32(DLM_MSG_UNLOCK_REPLY):
error = receive_unlock_reply(ls, ms);
break;
- case DLM_MSG_CANCEL_REPLY:
+ case cpu_to_le32(DLM_MSG_CANCEL_REPLY):
error = receive_cancel_reply(ls, ms);
break;
/* messages sent from a master node (only two types of async msg) */
- case DLM_MSG_GRANT:
+ case cpu_to_le32(DLM_MSG_GRANT):
noent = 1;
error = receive_grant(ls, ms);
break;
- case DLM_MSG_BAST:
+ case cpu_to_le32(DLM_MSG_BAST):
noent = 1;
error = receive_bast(ls, ms);
break;
/* messages sent to a dir node */
- case DLM_MSG_LOOKUP:
+ case cpu_to_le32(DLM_MSG_LOOKUP):
receive_lookup(ls, ms);
break;
- case DLM_MSG_REMOVE:
+ case cpu_to_le32(DLM_MSG_REMOVE):
receive_remove(ls, ms);
break;
/* messages sent from a dir node (remove has no reply) */
- case DLM_MSG_LOOKUP_REPLY:
+ case cpu_to_le32(DLM_MSG_LOOKUP_REPLY):
receive_lookup_reply(ls, ms);
break;
/* other messages */
- case DLM_MSG_PURGE:
+ case cpu_to_le32(DLM_MSG_PURGE):
receive_purge(ls, ms);
break;
default:
- log_error(ls, "unknown message type %d", ms->m_type);
+ log_error(ls, "unknown message type %d",
+ le32_to_cpu(ms->m_type));
}
/*
@@ -4957,22 +5001,26 @@ static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms,
if (error == -ENOENT && noent) {
log_debug(ls, "receive %d no %x remote %d %x saved_seq %u",
- ms->m_type, ms->m_remid, ms->m_header.h_nodeid,
- ms->m_lkid, saved_seq);
+ le32_to_cpu(ms->m_type), le32_to_cpu(ms->m_remid),
+ le32_to_cpu(ms->m_header.h_nodeid),
+ le32_to_cpu(ms->m_lkid), saved_seq);
} else if (error == -ENOENT) {
log_error(ls, "receive %d no %x remote %d %x saved_seq %u",
- ms->m_type, ms->m_remid, ms->m_header.h_nodeid,
- ms->m_lkid, saved_seq);
+ le32_to_cpu(ms->m_type), le32_to_cpu(ms->m_remid),
+ le32_to_cpu(ms->m_header.h_nodeid),
+ le32_to_cpu(ms->m_lkid), saved_seq);
- if (ms->m_type == DLM_MSG_CONVERT)
- dlm_dump_rsb_hash(ls, ms->m_hash);
+ if (ms->m_type == cpu_to_le32(DLM_MSG_CONVERT))
+ dlm_dump_rsb_hash(ls, le32_to_cpu(ms->m_hash));
}
if (error == -EINVAL) {
log_error(ls, "receive %d inval from %d lkid %x remid %x "
"saved_seq %u",
- ms->m_type, ms->m_header.h_nodeid,
- ms->m_lkid, ms->m_remid, saved_seq);
+ le32_to_cpu(ms->m_type),
+ le32_to_cpu(ms->m_header.h_nodeid),
+ le32_to_cpu(ms->m_lkid), le32_to_cpu(ms->m_remid),
+ saved_seq);
}
}
@@ -4993,7 +5041,7 @@ static void dlm_receive_message(struct dlm_ls *ls, struct dlm_message *ms,
lockspace generation before we left. */
if (!ls->ls_generation) {
log_limit(ls, "receive %d from %d ignore old gen",
- ms->m_type, nodeid);
+ le32_to_cpu(ms->m_type), nodeid);
return;
}
@@ -5026,30 +5074,30 @@ void dlm_receive_buffer(union dlm_packet *p, int nodeid)
switch (hd->h_cmd) {
case DLM_MSG:
- dlm_message_in(&p->message);
- type = p->message.m_type;
+ type = le32_to_cpu(p->message.m_type);
break;
case DLM_RCOM:
- dlm_rcom_in(&p->rcom);
- type = p->rcom.rc_type;
+ type = le32_to_cpu(p->rcom.rc_type);
break;
default:
log_print("invalid h_cmd %d from %u", hd->h_cmd, nodeid);
return;
}
- if (hd->h_nodeid != nodeid) {
+ if (le32_to_cpu(hd->h_nodeid) != nodeid) {
log_print("invalid h_nodeid %d from %d lockspace %x",
- hd->h_nodeid, nodeid, hd->h_lockspace);
+ le32_to_cpu(hd->h_nodeid), nodeid,
+ le32_to_cpu(hd->u.h_lockspace));
return;
}
- ls = dlm_find_lockspace_global(hd->h_lockspace);
+ ls = dlm_find_lockspace_global(le32_to_cpu(hd->u.h_lockspace));
if (!ls) {
if (dlm_config.ci_log_debug) {
printk_ratelimited(KERN_DEBUG "dlm: invalid lockspace "
"%u from %d cmd %d type %d\n",
- hd->h_lockspace, nodeid, hd->h_cmd, type);
+ le32_to_cpu(hd->u.h_lockspace), nodeid,
+ hd->h_cmd, type);
}
if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS)
@@ -5063,8 +5111,11 @@ void dlm_receive_buffer(union dlm_packet *p, int nodeid)
down_read(&ls->ls_recv_active);
if (hd->h_cmd == DLM_MSG)
dlm_receive_message(ls, &p->message, nodeid);
- else
+ else if (hd->h_cmd == DLM_RCOM)
dlm_receive_rcom(ls, &p->rcom, nodeid);
+ else
+ log_error(ls, "invalid h_cmd %d from %d lockspace %x",
+ hd->h_cmd, nodeid, le32_to_cpu(hd->u.h_lockspace));
up_read(&ls->ls_recv_active);
dlm_put_lockspace(ls);
@@ -5076,10 +5127,10 @@ static void recover_convert_waiter(struct dlm_ls *ls, struct dlm_lkb *lkb,
if (middle_conversion(lkb)) {
hold_lkb(lkb);
memset(ms_stub, 0, sizeof(struct dlm_message));
- ms_stub->m_flags = DLM_IFL_STUB_MS;
- ms_stub->m_type = DLM_MSG_CONVERT_REPLY;
- ms_stub->m_result = -EINPROGRESS;
- ms_stub->m_header.h_nodeid = lkb->lkb_nodeid;
+ ms_stub->m_flags = cpu_to_le32(DLM_IFL_STUB_MS);
+ ms_stub->m_type = cpu_to_le32(DLM_MSG_CONVERT_REPLY);
+ ms_stub->m_result = cpu_to_le32(to_dlm_errno(-EINPROGRESS));
+ ms_stub->m_header.h_nodeid = cpu_to_le32(lkb->lkb_nodeid);
_receive_convert_reply(lkb, ms_stub);
/* Same special case as in receive_rcom_lock_args() */
@@ -5198,10 +5249,10 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
case DLM_MSG_UNLOCK:
hold_lkb(lkb);
memset(ms_stub, 0, sizeof(struct dlm_message));
- ms_stub->m_flags = DLM_IFL_STUB_MS;
- ms_stub->m_type = DLM_MSG_UNLOCK_REPLY;
- ms_stub->m_result = stub_unlock_result;
- ms_stub->m_header.h_nodeid = lkb->lkb_nodeid;
+ ms_stub->m_flags = cpu_to_le32(DLM_IFL_STUB_MS);
+ ms_stub->m_type = cpu_to_le32(DLM_MSG_UNLOCK_REPLY);
+ ms_stub->m_result = cpu_to_le32(to_dlm_errno(stub_unlock_result));
+ ms_stub->m_header.h_nodeid = cpu_to_le32(lkb->lkb_nodeid);
_receive_unlock_reply(lkb, ms_stub);
dlm_put_lkb(lkb);
break;
@@ -5209,10 +5260,10 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
case DLM_MSG_CANCEL:
hold_lkb(lkb);
memset(ms_stub, 0, sizeof(struct dlm_message));
- ms_stub->m_flags = DLM_IFL_STUB_MS;
- ms_stub->m_type = DLM_MSG_CANCEL_REPLY;
- ms_stub->m_result = stub_cancel_result;
- ms_stub->m_header.h_nodeid = lkb->lkb_nodeid;
+ ms_stub->m_flags = cpu_to_le32(DLM_IFL_STUB_MS);
+ ms_stub->m_type = cpu_to_le32(DLM_MSG_CANCEL_REPLY);
+ ms_stub->m_result = cpu_to_le32(to_dlm_errno(stub_cancel_result));
+ ms_stub->m_header.h_nodeid = cpu_to_le32(lkb->lkb_nodeid);
_receive_cancel_reply(lkb, ms_stub);
dlm_put_lkb(lkb);
break;
@@ -5229,21 +5280,18 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
static struct dlm_lkb *find_resend_waiter(struct dlm_ls *ls)
{
- struct dlm_lkb *lkb;
- int found = 0;
+ struct dlm_lkb *lkb = NULL, *iter;
mutex_lock(&ls->ls_waiters_mutex);
- list_for_each_entry(lkb, &ls->ls_waiters, lkb_wait_reply) {
- if (lkb->lkb_flags & DLM_IFL_RESEND) {
- hold_lkb(lkb);
- found = 1;
+ list_for_each_entry(iter, &ls->ls_waiters, lkb_wait_reply) {
+ if (iter->lkb_flags & DLM_IFL_RESEND) {
+ hold_lkb(iter);
+ lkb = iter;
break;
}
}
mutex_unlock(&ls->ls_waiters_mutex);
- if (!found)
- lkb = NULL;
return lkb;
}
@@ -5303,11 +5351,16 @@ int dlm_recover_waiters_post(struct dlm_ls *ls)
lkb->lkb_flags &= ~DLM_IFL_OVERLAP_UNLOCK;
lkb->lkb_flags &= ~DLM_IFL_OVERLAP_CANCEL;
lkb->lkb_wait_type = 0;
- lkb->lkb_wait_count = 0;
+ /* drop all wait_count references we still
+ * hold a reference for this iteration.
+ */
+ while (lkb->lkb_wait_count) {
+ lkb->lkb_wait_count--;
+ unhold_lkb(lkb);
+ }
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 */
@@ -5577,7 +5630,7 @@ static int receive_rcom_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
{
struct rcom_lock *rl = (struct rcom_lock *) rc->rc_buf;
- lkb->lkb_nodeid = rc->rc_header.h_nodeid;
+ lkb->lkb_nodeid = le32_to_cpu(rc->rc_header.h_nodeid);
lkb->lkb_ownpid = le32_to_cpu(rl->rl_ownpid);
lkb->lkb_remid = le32_to_cpu(rl->rl_lkid);
lkb->lkb_exflags = le32_to_cpu(rl->rl_exflags);
@@ -5592,8 +5645,8 @@ static int receive_rcom_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
lkb->lkb_astfn = (rl->rl_asts & DLM_CB_CAST) ? &fake_astfn : NULL;
if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
- int lvblen = rc->rc_header.h_length - sizeof(struct dlm_rcom) -
- sizeof(struct rcom_lock);
+ int lvblen = le16_to_cpu(rc->rc_header.h_length) -
+ sizeof(struct dlm_rcom) - sizeof(struct rcom_lock);
if (lvblen > ls->ls_lvblen)
return -EINVAL;
lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
@@ -5629,7 +5682,7 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
struct dlm_rsb *r;
struct dlm_lkb *lkb;
uint32_t remid = 0;
- int from_nodeid = rc->rc_header.h_nodeid;
+ int from_nodeid = le32_to_cpu(rc->rc_header.h_nodeid);
int error;
if (rl->rl_parent_lkid) {
@@ -5679,7 +5732,6 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
attach_lkb(r, lkb);
add_lkb(r, lkb, rl->rl_status);
- error = 0;
ls->ls_recover_locks_in++;
if (!list_empty(&r->res_waitqueue) || !list_empty(&r->res_convertqueue))
@@ -5719,7 +5771,8 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
error = find_lkb(ls, lkid, &lkb);
if (error) {
log_error(ls, "dlm_recover_process_copy no %x remote %d %x %d",
- lkid, rc->rc_header.h_nodeid, remid, result);
+ lkid, le32_to_cpu(rc->rc_header.h_nodeid), remid,
+ result);
return error;
}
@@ -5729,7 +5782,8 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
if (!is_process_copy(lkb)) {
log_error(ls, "dlm_recover_process_copy bad %x remote %d %x %d",
- lkid, rc->rc_header.h_nodeid, remid, result);
+ lkid, le32_to_cpu(rc->rc_header.h_nodeid), remid,
+ result);
dlm_dump_rsb(r);
unlock_rsb(r);
put_rsb(r);
@@ -5744,7 +5798,8 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
a barrier between recover_masters and recover_locks. */
log_debug(ls, "dlm_recover_process_copy %x remote %d %x %d",
- lkid, rc->rc_header.h_nodeid, remid, result);
+ lkid, le32_to_cpu(rc->rc_header.h_nodeid), remid,
+ result);
dlm_send_rcom_lock(r, lkb);
goto out;
@@ -5754,7 +5809,8 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
break;
default:
log_error(ls, "dlm_recover_process_copy %x remote %d %x %d unk",
- lkid, rc->rc_header.h_nodeid, remid, result);
+ lkid, le32_to_cpu(rc->rc_header.h_nodeid), remid,
+ result);
}
/* an ack for dlm_recover_locks() which waits for replies from
@@ -5768,12 +5824,18 @@ int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
return 0;
}
+#ifdef CONFIG_DLM_DEPRECATED_API
int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
int mode, uint32_t flags, void *name, unsigned int namelen,
unsigned long timeout_cs)
+#else
+int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
+ int mode, uint32_t flags, void *name, unsigned int namelen)
+#endif
{
struct dlm_lkb *lkb;
struct dlm_args args;
+ bool do_put = true;
int error;
dlm_lock_recovery(ls);
@@ -5784,23 +5846,28 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
goto out;
}
+ trace_dlm_lock_start(ls, lkb, name, namelen, mode, flags);
+
if (flags & DLM_LKF_VALBLK) {
ua->lksb.sb_lvbptr = kzalloc(DLM_USER_LVB_LEN, GFP_NOFS);
if (!ua->lksb.sb_lvbptr) {
kfree(ua);
- __put_lkb(ls, lkb);
error = -ENOMEM;
- goto out;
+ goto out_put;
}
}
+#ifdef CONFIG_DLM_DEPRECATED_API
error = set_lock_args(mode, &ua->lksb, flags, namelen, timeout_cs,
fake_astfn, ua, fake_bastfn, &args);
+#else
+ error = set_lock_args(mode, &ua->lksb, flags, namelen, fake_astfn, ua,
+ fake_bastfn, &args);
+#endif
if (error) {
kfree(ua->lksb.sb_lvbptr);
ua->lksb.sb_lvbptr = NULL;
kfree(ua);
- __put_lkb(ls, lkb);
- goto out;
+ goto out_put;
}
/* After ua is attached to lkb it will be freed by dlm_free_lkb().
@@ -5817,10 +5884,9 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
break;
case -EAGAIN:
error = 0;
- /* fall through */
+ fallthrough;
default:
- __put_lkb(ls, lkb);
- goto out;
+ goto out_put;
}
/* add this new lkb to the per-process list of locks */
@@ -5828,14 +5894,24 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
hold_lkb(lkb);
list_add_tail(&lkb->lkb_ownqueue, &ua->proc->locks);
spin_unlock(&ua->proc->locks_spin);
+ do_put = false;
+ out_put:
+ trace_dlm_lock_end(ls, lkb, name, namelen, mode, flags, error, false);
+ if (do_put)
+ __put_lkb(ls, lkb);
out:
dlm_unlock_recovery(ls);
return error;
}
+#ifdef CONFIG_DLM_DEPRECATED_API
int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, uint32_t lkid, char *lvb_in,
unsigned long timeout_cs)
+#else
+int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+ int mode, uint32_t flags, uint32_t lkid, char *lvb_in)
+#endif
{
struct dlm_lkb *lkb;
struct dlm_args args;
@@ -5848,6 +5924,8 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
if (error)
goto out;
+ trace_dlm_lock_start(ls, lkb, NULL, 0, mode, flags);
+
/* user can change the params on its lock when it converts it, or
add an lvb that didn't exist before */
@@ -5870,8 +5948,13 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
ua->bastaddr = ua_tmp->bastaddr;
ua->user_lksb = ua_tmp->user_lksb;
+#ifdef CONFIG_DLM_DEPRECATED_API
error = set_lock_args(mode, &ua->lksb, flags, 0, timeout_cs,
fake_astfn, ua, fake_bastfn, &args);
+#else
+ error = set_lock_args(mode, &ua->lksb, flags, 0, fake_astfn, ua,
+ fake_bastfn, &args);
+#endif
if (error)
goto out_put;
@@ -5880,6 +5963,7 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
if (error == -EINPROGRESS || error == -EAGAIN || error == -EDEADLK)
error = 0;
out_put:
+ trace_dlm_lock_end(ls, lkb, NULL, 0, mode, flags, error, false);
dlm_put_lkb(lkb);
out:
dlm_unlock_recovery(ls);
@@ -5895,39 +5979,38 @@ int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, void *name, unsigned int namelen,
- unsigned long timeout_cs, uint32_t *lkid)
+ uint32_t *lkid)
{
- struct dlm_lkb *lkb;
+ struct dlm_lkb *lkb = NULL, *iter;
struct dlm_user_args *ua;
int found_other_mode = 0;
- int found = 0;
int rv = 0;
mutex_lock(&ls->ls_orphans_mutex);
- list_for_each_entry(lkb, &ls->ls_orphans, lkb_ownqueue) {
- if (lkb->lkb_resource->res_length != namelen)
+ list_for_each_entry(iter, &ls->ls_orphans, lkb_ownqueue) {
+ if (iter->lkb_resource->res_length != namelen)
continue;
- if (memcmp(lkb->lkb_resource->res_name, name, namelen))
+ if (memcmp(iter->lkb_resource->res_name, name, namelen))
continue;
- if (lkb->lkb_grmode != mode) {
+ if (iter->lkb_grmode != mode) {
found_other_mode = 1;
continue;
}
- found = 1;
- list_del_init(&lkb->lkb_ownqueue);
- lkb->lkb_flags &= ~DLM_IFL_ORPHAN;
- *lkid = lkb->lkb_id;
+ lkb = iter;
+ list_del_init(&iter->lkb_ownqueue);
+ iter->lkb_flags &= ~DLM_IFL_ORPHAN;
+ *lkid = iter->lkb_id;
break;
}
mutex_unlock(&ls->ls_orphans_mutex);
- if (!found && found_other_mode) {
+ if (!lkb && found_other_mode) {
rv = -EAGAIN;
goto out;
}
- if (!found) {
+ if (!lkb) {
rv = -ENOENT;
goto out;
}
@@ -5973,6 +6056,8 @@ int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
if (error)
goto out;
+ trace_dlm_unlock_start(ls, lkb, flags);
+
ua = lkb->lkb_ua;
if (lvb_in && ua->lksb.sb_lvbptr)
@@ -6001,6 +6086,7 @@ int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
list_move(&lkb->lkb_ownqueue, &ua->proc->unlocking);
spin_unlock(&ua->proc->locks_spin);
out_put:
+ trace_dlm_unlock_end(ls, lkb, flags, error);
dlm_put_lkb(lkb);
out:
dlm_unlock_recovery(ls);
@@ -6022,6 +6108,8 @@ int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
if (error)
goto out;
+ trace_dlm_unlock_start(ls, lkb, flags);
+
ua = lkb->lkb_ua;
if (ua_tmp->castparam)
ua->castparam = ua_tmp->castparam;
@@ -6039,6 +6127,7 @@ int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
if (error == -EBUSY)
error = 0;
out_put:
+ trace_dlm_unlock_end(ls, lkb, flags, error);
dlm_put_lkb(lkb);
out:
dlm_unlock_recovery(ls);
@@ -6060,6 +6149,8 @@ int dlm_user_deadlock(struct dlm_ls *ls, uint32_t flags, uint32_t lkid)
if (error)
goto out;
+ trace_dlm_unlock_start(ls, lkb, flags);
+
ua = lkb->lkb_ua;
error = set_unlock_args(flags, ua, &args);
@@ -6088,6 +6179,7 @@ int dlm_user_deadlock(struct dlm_ls *ls, uint32_t flags, uint32_t lkid)
if (error == -EBUSY)
error = 0;
out_put:
+ trace_dlm_unlock_end(ls, lkb, flags, error);
dlm_put_lkb(lkb);
out:
dlm_unlock_recovery(ls);
@@ -6143,7 +6235,7 @@ static struct dlm_lkb *del_proc_lock(struct dlm_ls *ls,
{
struct dlm_lkb *lkb = NULL;
- mutex_lock(&ls->ls_clear_proc_locks);
+ spin_lock(&ls->ls_clear_proc_locks);
if (list_empty(&proc->locks))
goto out;
@@ -6155,7 +6247,7 @@ static struct dlm_lkb *del_proc_lock(struct dlm_ls *ls,
else
lkb->lkb_flags |= DLM_IFL_DEAD;
out:
- mutex_unlock(&ls->ls_clear_proc_locks);
+ spin_unlock(&ls->ls_clear_proc_locks);
return lkb;
}
@@ -6192,7 +6284,7 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
dlm_put_lkb(lkb);
}
- mutex_lock(&ls->ls_clear_proc_locks);
+ spin_lock(&ls->ls_clear_proc_locks);
/* in-progress unlocks */
list_for_each_entry_safe(lkb, safe, &proc->unlocking, lkb_ownqueue) {
@@ -6208,7 +6300,7 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
dlm_put_lkb(lkb);
}
- mutex_unlock(&ls->ls_clear_proc_locks);
+ spin_unlock(&ls->ls_clear_proc_locks);
dlm_unlock_recovery(ls);
}
@@ -6279,8 +6371,8 @@ static int send_purge(struct dlm_ls *ls, int nodeid, int pid)
DLM_MSG_PURGE, &ms, &mh);
if (error)
return error;
- ms->m_nodeid = nodeid;
- ms->m_pid = pid;
+ ms->m_nodeid = cpu_to_le32(nodeid);
+ ms->m_pid = cpu_to_le32(pid);
return send_message(mh, ms);
}
@@ -6303,3 +6395,64 @@ int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,
return error;
}
+/* debug functionality */
+int dlm_debug_add_lkb(struct dlm_ls *ls, uint32_t lkb_id, char *name, int len,
+ int lkb_nodeid, unsigned int lkb_flags, int lkb_status)
+{
+ struct dlm_lksb *lksb;
+ struct dlm_lkb *lkb;
+ struct dlm_rsb *r;
+ int error;
+
+ /* we currently can't set a valid user lock */
+ if (lkb_flags & DLM_IFL_USER)
+ return -EOPNOTSUPP;
+
+ lksb = kzalloc(sizeof(*lksb), GFP_NOFS);
+ if (!lksb)
+ return -ENOMEM;
+
+ error = _create_lkb(ls, &lkb, lkb_id, lkb_id + 1);
+ if (error) {
+ kfree(lksb);
+ return error;
+ }
+
+ lkb->lkb_flags = lkb_flags;
+ lkb->lkb_nodeid = lkb_nodeid;
+ lkb->lkb_lksb = lksb;
+ /* user specific pointer, just don't have it NULL for kernel locks */
+ if (~lkb_flags & DLM_IFL_USER)
+ lkb->lkb_astparam = (void *)0xDEADBEEF;
+
+ error = find_rsb(ls, name, len, 0, R_REQUEST, &r);
+ if (error) {
+ kfree(lksb);
+ __put_lkb(ls, lkb);
+ return error;
+ }
+
+ lock_rsb(r);
+ attach_lkb(r, lkb);
+ add_lkb(r, lkb, lkb_status);
+ unlock_rsb(r);
+ put_rsb(r);
+
+ return 0;
+}
+
+int dlm_debug_add_lkb_to_waiters(struct dlm_ls *ls, uint32_t lkb_id,
+ int mstype, int to_nodeid)
+{
+ struct dlm_lkb *lkb;
+ int error;
+
+ error = find_lkb(ls, lkb_id, &lkb);
+ if (error)
+ return error;
+
+ error = add_to_waiters(lkb, mstype, to_nodeid);
+ dlm_put_lkb(lkb);
+ return error;
+}
+
diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h
index 456c6ec3ef6f..40c76b5544da 100644
--- a/fs/dlm/lock.h
+++ b/fs/dlm/lock.h
@@ -24,13 +24,19 @@ int dlm_put_lkb(struct dlm_lkb *lkb);
void dlm_scan_rsbs(struct dlm_ls *ls);
int dlm_lock_recovery_try(struct dlm_ls *ls);
void dlm_unlock_recovery(struct dlm_ls *ls);
-void dlm_scan_waiters(struct dlm_ls *ls);
+
+#ifdef CONFIG_DLM_DEPRECATED_API
void dlm_scan_timeout(struct dlm_ls *ls);
void dlm_adjust_timeouts(struct dlm_ls *ls);
+#else
+static inline void dlm_scan_timeout(struct dlm_ls *ls) { }
+static inline void dlm_adjust_timeouts(struct dlm_ls *ls) { }
+#endif
+
int dlm_master_lookup(struct dlm_ls *ls, int nodeid, char *name, int len,
unsigned int flags, int *r_nodeid, int *result);
-int dlm_search_rsb_tree(struct rb_root *tree, char *name, int len,
+int dlm_search_rsb_tree(struct rb_root *tree, const void *name, int len,
struct dlm_rsb **r_ret);
void dlm_recover_purge(struct dlm_ls *ls);
@@ -41,15 +47,22 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls);
int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
int dlm_recover_process_copy(struct dlm_ls *ls, struct dlm_rcom *rc);
+#ifdef CONFIG_DLM_DEPRECATED_API
int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode,
uint32_t flags, void *name, unsigned int namelen,
unsigned long timeout_cs);
int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, uint32_t lkid, char *lvb_in,
unsigned long timeout_cs);
+#else
+int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua, int mode,
+ uint32_t flags, void *name, unsigned int namelen);
+int dlm_user_convert(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
+ int mode, uint32_t flags, uint32_t lkid, char *lvb_in);
+#endif
int dlm_user_adopt_orphan(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
int mode, uint32_t flags, void *name, unsigned int namelen,
- unsigned long timeout_cs, uint32_t *lkid);
+ uint32_t *lkid);
int dlm_user_unlock(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
uint32_t flags, uint32_t lkid, char *lvb_in);
int dlm_user_cancel(struct dlm_ls *ls, struct dlm_user_args *ua_tmp,
@@ -58,6 +71,10 @@ int dlm_user_purge(struct dlm_ls *ls, struct dlm_user_proc *proc,
int nodeid, int pid);
int dlm_user_deadlock(struct dlm_ls *ls, uint32_t flags, uint32_t lkid);
void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc);
+int dlm_debug_add_lkb(struct dlm_ls *ls, uint32_t lkb_id, char *name, int len,
+ int lkb_nodeid, unsigned int lkb_flags, int lkb_status);
+int dlm_debug_add_lkb_to_waiters(struct dlm_ls *ls, uint32_t lkb_id,
+ int mstype, int to_nodeid);
static inline int is_master(struct dlm_rsb *r)
{
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index afb8340918b8..bae050df7abf 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -16,6 +16,7 @@
#include "member.h"
#include "recoverd.h"
#include "dir.h"
+#include "midcomms.h"
#include "lowcomms.h"
#include "config.h"
#include "memory.h"
@@ -197,8 +198,6 @@ static struct kset *dlm_kset;
static int do_uevent(struct dlm_ls *ls, int in)
{
- int error;
-
if (in)
kobject_uevent(&ls->ls_kobj, KOBJ_ONLINE);
else
@@ -209,24 +208,15 @@ static int do_uevent(struct dlm_ls *ls, int in)
/* dlm_controld will see the uevent, do the necessary group management
and then write to sysfs to wake us */
- error = wait_event_interruptible(ls->ls_uevent_wait,
- test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags));
+ wait_event(ls->ls_uevent_wait,
+ test_and_clear_bit(LSFL_UEVENT_WAIT, &ls->ls_flags));
- log_rinfo(ls, "group event done %d %d", error, ls->ls_uevent_result);
+ log_rinfo(ls, "group event done %d", ls->ls_uevent_result);
- if (error)
- goto out;
-
- error = ls->ls_uevent_result;
- out:
- if (error)
- log_error(ls, "group %s failed %d %d", in ? "join" : "leave",
- error, ls->ls_uevent_result);
- return error;
+ return ls->ls_uevent_result;
}
-static int dlm_uevent(struct kset *kset, struct kobject *kobj,
- struct kobj_uevent_env *env)
+static int dlm_uevent(struct kobject *kobj, struct kobj_uevent_env *env)
{
struct dlm_ls *ls = container_of(kobj, struct dlm_ls, ls_kobj);
@@ -285,7 +275,6 @@ static int dlm_scand(void *data)
ls->ls_scan_time = jiffies;
dlm_scan_rsbs(ls);
dlm_scan_timeout(ls);
- dlm_scan_waiters(ls);
dlm_unlock_recovery(ls);
} else {
ls->ls_scan_time += HZ;
@@ -323,7 +312,7 @@ struct dlm_ls *dlm_find_lockspace_global(uint32_t id)
list_for_each_entry(ls, &lslist, ls_list) {
if (ls->ls_global_id == id) {
- ls->ls_count++;
+ atomic_inc(&ls->ls_count);
goto out;
}
}
@@ -340,7 +329,7 @@ struct dlm_ls *dlm_find_lockspace_local(dlm_lockspace_t *lockspace)
spin_lock(&lslist_lock);
list_for_each_entry(ls, &lslist, ls_list) {
if (ls->ls_local_handle == lockspace) {
- ls->ls_count++;
+ atomic_inc(&ls->ls_count);
goto out;
}
}
@@ -357,7 +346,7 @@ struct dlm_ls *dlm_find_lockspace_device(int minor)
spin_lock(&lslist_lock);
list_for_each_entry(ls, &lslist, ls_list) {
if (ls->ls_device.minor == minor) {
- ls->ls_count++;
+ atomic_inc(&ls->ls_count);
goto out;
}
}
@@ -369,24 +358,24 @@ struct dlm_ls *dlm_find_lockspace_device(int minor)
void dlm_put_lockspace(struct dlm_ls *ls)
{
- spin_lock(&lslist_lock);
- ls->ls_count--;
- spin_unlock(&lslist_lock);
+ if (atomic_dec_and_test(&ls->ls_count))
+ wake_up(&ls->ls_count_wait);
}
static void remove_lockspace(struct dlm_ls *ls)
{
- for (;;) {
- spin_lock(&lslist_lock);
- if (ls->ls_count == 0) {
- WARN_ON(ls->ls_create_count != 0);
- list_del(&ls->ls_list);
- spin_unlock(&lslist_lock);
- return;
- }
+retry:
+ wait_event(ls->ls_count_wait, atomic_read(&ls->ls_count) == 0);
+
+ spin_lock(&lslist_lock);
+ if (atomic_read(&ls->ls_count) != 0) {
spin_unlock(&lslist_lock);
- ssleep(1);
+ goto retry;
}
+
+ WARN_ON(ls->ls_create_count != 0);
+ list_del(&ls->ls_list);
+ spin_unlock(&lslist_lock);
}
static int threads_start(void)
@@ -400,7 +389,7 @@ static int threads_start(void)
}
/* Thread for sending/receiving messages for all lockspace's */
- error = dlm_lowcomms_start();
+ error = dlm_midcomms_start();
if (error) {
log_print("cannot start dlm lowcomms %d", error);
goto scand_fail;
@@ -414,12 +403,6 @@ static int threads_start(void)
return error;
}
-static void threads_stop(void)
-{
- dlm_scand_stop();
- dlm_lowcomms_stop();
-}
-
static int new_lockspace(const char *name, const char *cluster,
uint32_t flags, int lvblen,
const struct dlm_lockspace_ops *ops, void *ops_arg,
@@ -433,7 +416,7 @@ static int new_lockspace(const char *name, const char *cluster,
if (namelen > DLM_LOCKSPACE_LEN || namelen == 0)
return -EINVAL;
- if (!lvblen || (lvblen % 8))
+ if (lvblen % 8)
return -EINVAL;
if (!try_module_get(THIS_MODULE))
@@ -496,7 +479,8 @@ static int new_lockspace(const char *name, const char *cluster,
memcpy(ls->ls_name, name, namelen);
ls->ls_namelen = namelen;
ls->ls_lvblen = lvblen;
- ls->ls_count = 0;
+ atomic_set(&ls->ls_count, 0);
+ init_waitqueue_head(&ls->ls_count_wait);
ls->ls_flags = 0;
ls->ls_scan_time = jiffies;
@@ -505,15 +489,30 @@ static int new_lockspace(const char *name, const char *cluster,
ls->ls_ops_arg = ops_arg;
}
- if (flags & DLM_LSFL_TIMEWARN)
+#ifdef CONFIG_DLM_DEPRECATED_API
+ if (flags & DLM_LSFL_TIMEWARN) {
+ pr_warn_once("===============================================================\n"
+ "WARNING: the dlm DLM_LSFL_TIMEWARN flag is being deprecated and\n"
+ " will be removed in v6.2!\n"
+ " Inclusive DLM_LSFL_TIMEWARN define in UAPI header!\n"
+ "===============================================================\n");
+
set_bit(LSFL_TIMEWARN, &ls->ls_flags);
+ }
/* ls_exflags are forced to match among nodes, and we don't
- need to require all nodes to have some flags set */
+ * need to require all nodes to have some flags set
+ */
ls->ls_exflags = (flags & ~(DLM_LSFL_TIMEWARN | DLM_LSFL_FS |
DLM_LSFL_NEWEXCL));
+#else
+ /* ls_exflags are forced to match among nodes, and we don't
+ * need to require all nodes to have some flags set
+ */
+ ls->ls_exflags = (flags & ~(DLM_LSFL_FS | DLM_LSFL_NEWEXCL));
+#endif
- size = dlm_config.ci_rsbtbl_size;
+ size = READ_ONCE(dlm_config.ci_rsbtbl_size);
ls->ls_rsbtbl_size = size;
ls->ls_rsbtbl = vmalloc(array_size(size, sizeof(struct dlm_rsbtable)));
@@ -526,6 +525,7 @@ static int new_lockspace(const char *name, const char *cluster,
}
spin_lock_init(&ls->ls_remove_spin);
+ init_waitqueue_head(&ls->ls_remove_wait);
for (i = 0; i < DLM_REMOVE_NAMES_MAX; i++) {
ls->ls_remove_names[i] = kzalloc(DLM_RESNAME_MAXLEN+1,
@@ -541,8 +541,10 @@ static int new_lockspace(const char *name, const char *cluster,
mutex_init(&ls->ls_waiters_mutex);
INIT_LIST_HEAD(&ls->ls_orphans);
mutex_init(&ls->ls_orphans_mutex);
+#ifdef CONFIG_DLM_DEPRECATED_API
INIT_LIST_HEAD(&ls->ls_timeout);
mutex_init(&ls->ls_timeout_mutex);
+#endif
INIT_LIST_HEAD(&ls->ls_new_rsb);
spin_lock_init(&ls->ls_new_rsb_spin);
@@ -562,8 +564,8 @@ static int new_lockspace(const char *name, const char *cluster,
init_waitqueue_head(&ls->ls_uevent_wait);
ls->ls_uevent_result = 0;
- init_completion(&ls->ls_members_done);
- ls->ls_members_result = -1;
+ init_completion(&ls->ls_recovery_done);
+ ls->ls_recovery_result = -1;
mutex_init(&ls->ls_cb_mutex);
INIT_LIST_HEAD(&ls->ls_cb_delay);
@@ -579,10 +581,17 @@ static int new_lockspace(const char *name, const char *cluster,
init_rwsem(&ls->ls_in_recovery);
init_rwsem(&ls->ls_recv_active);
INIT_LIST_HEAD(&ls->ls_requestqueue);
+ atomic_set(&ls->ls_requestqueue_cnt, 0);
+ init_waitqueue_head(&ls->ls_requestqueue_wait);
mutex_init(&ls->ls_requestqueue_mutex);
- mutex_init(&ls->ls_clear_proc_locks);
+ spin_lock_init(&ls->ls_clear_proc_locks);
- ls->ls_recover_buf = kmalloc(dlm_config.ci_buffer_size, GFP_NOFS);
+ /* Due backwards compatibility with 3.1 we need to use maximum
+ * possible dlm message size to be sure the message will fit and
+ * not having out of bounds issues. However on sending side 3.2
+ * might send less.
+ */
+ ls->ls_recover_buf = kmalloc(DLM_MAX_SOCKET_BUFSIZE, GFP_NOFS);
if (!ls->ls_recover_buf)
goto out_lkbidr;
@@ -632,6 +641,9 @@ static int new_lockspace(const char *name, const char *cluster,
wait_event(ls->ls_recover_lock_wait,
test_bit(LSFL_RECOVER_LOCK, &ls->ls_flags));
+ /* let kobject handle freeing of ls if there's an error */
+ do_unreg = 1;
+
ls->ls_kobj.kset = dlm_kset;
error = kobject_init_and_add(&ls->ls_kobj, &dlm_ktype, NULL,
"%s", ls->ls_name);
@@ -639,9 +651,6 @@ static int new_lockspace(const char *name, const char *cluster,
goto out_recoverd;
kobject_uevent(&ls->ls_kobj, KOBJ_ADD);
- /* let kobject handle freeing of ls if there's an error */
- do_unreg = 1;
-
/* This uevent triggers dlm_controld in userspace to add us to the
group of nodes that are members of this lockspace (managed by the
cluster infrastructure.) Once it's done that, it tells us who the
@@ -652,8 +661,9 @@ static int new_lockspace(const char *name, const char *cluster,
if (error)
goto out_recoverd;
- wait_for_completion(&ls->ls_members_done);
- error = ls->ls_members_result;
+ /* wait until recovery is successful or failed */
+ wait_for_completion(&ls->ls_recovery_done);
+ error = ls->ls_recovery_result;
if (error)
goto out_members;
@@ -693,10 +703,11 @@ static int new_lockspace(const char *name, const char *cluster,
return error;
}
-int dlm_new_lockspace(const char *name, const char *cluster,
- uint32_t flags, int lvblen,
- const struct dlm_lockspace_ops *ops, void *ops_arg,
- int *ops_result, dlm_lockspace_t **lockspace)
+static int __dlm_new_lockspace(const char *name, const char *cluster,
+ uint32_t flags, int lvblen,
+ const struct dlm_lockspace_ops *ops,
+ void *ops_arg, int *ops_result,
+ dlm_lockspace_t **lockspace)
{
int error = 0;
@@ -712,13 +723,35 @@ int dlm_new_lockspace(const char *name, const char *cluster,
ls_count++;
if (error > 0)
error = 0;
- if (!ls_count)
- threads_stop();
+ if (!ls_count) {
+ dlm_scand_stop();
+ dlm_midcomms_shutdown();
+ dlm_lowcomms_stop();
+ }
out:
mutex_unlock(&ls_lock);
return error;
}
+int dlm_new_lockspace(const char *name, const char *cluster, uint32_t flags,
+ int lvblen, const struct dlm_lockspace_ops *ops,
+ void *ops_arg, int *ops_result,
+ dlm_lockspace_t **lockspace)
+{
+ return __dlm_new_lockspace(name, cluster, flags | DLM_LSFL_FS, lvblen,
+ ops, ops_arg, ops_result, lockspace);
+}
+
+int dlm_new_user_lockspace(const char *name, const char *cluster,
+ uint32_t flags, int lvblen,
+ const struct dlm_lockspace_ops *ops,
+ void *ops_arg, int *ops_result,
+ dlm_lockspace_t **lockspace)
+{
+ return __dlm_new_lockspace(name, cluster, flags, lvblen, ops,
+ ops_arg, ops_result, lockspace);
+}
+
static int lkb_idr_is_local(int id, void *p, void *data)
{
struct dlm_lkb *lkb = p;
@@ -798,6 +831,12 @@ static int release_lockspace(struct dlm_ls *ls, int force)
dlm_recoverd_stop(ls);
+ if (ls_count == 1) {
+ dlm_scand_stop();
+ dlm_clear_members(ls);
+ dlm_midcomms_shutdown();
+ }
+
dlm_callback_stop(ls);
remove_lockspace(ls);
@@ -869,7 +908,7 @@ static int release_lockspace(struct dlm_ls *ls, int force)
* until this returns.
*
* Force has 4 possible values:
- * 0 - don't destroy locksapce if it has any LKBs
+ * 0 - don't destroy lockspace if it has any LKBs
* 1 - destroy lockspace if it has remote LKBs but not if it has local LKBs
* 2 - destroy lockspace regardless of LKBs
* 3 - destroy lockspace as part of a forced shutdown
@@ -890,7 +929,7 @@ int dlm_release_lockspace(void *lockspace, int force)
if (!error)
ls_count--;
if (!ls_count)
- threads_stop();
+ dlm_lowcomms_stop();
mutex_unlock(&ls_lock);
return error;
@@ -920,3 +959,15 @@ void dlm_stop_lockspaces(void)
log_print("dlm user daemon left %d lockspaces", count);
}
+void dlm_stop_lockspaces_check(void)
+{
+ struct dlm_ls *ls;
+
+ spin_lock(&lslist_lock);
+ list_for_each_entry(ls, &lslist, ls_list) {
+ if (WARN_ON(!rwsem_is_locked(&ls->ls_in_recovery) ||
+ !dlm_locking_stopped(ls)))
+ break;
+ }
+ spin_unlock(&lslist_lock);
+}
diff --git a/fs/dlm/lockspace.h b/fs/dlm/lockspace.h
index a78d853b9342..03f4a4a3a871 100644
--- a/fs/dlm/lockspace.h
+++ b/fs/dlm/lockspace.h
@@ -12,6 +12,14 @@
#ifndef __LOCKSPACE_DOT_H__
#define __LOCKSPACE_DOT_H__
+/* DLM_LSFL_FS
+ * The lockspace user is in the kernel (i.e. filesystem). Enables
+ * direct bast/cast callbacks.
+ *
+ * internal lockspace flag - will be removed in future
+ */
+#define DLM_LSFL_FS 0x00000004
+
int dlm_lockspace_init(void);
void dlm_lockspace_exit(void);
struct dlm_ls *dlm_find_lockspace_global(uint32_t id);
@@ -19,6 +27,12 @@ struct dlm_ls *dlm_find_lockspace_local(void *id);
struct dlm_ls *dlm_find_lockspace_device(int minor);
void dlm_put_lockspace(struct dlm_ls *ls);
void dlm_stop_lockspaces(void);
+void dlm_stop_lockspaces_check(void);
+int dlm_new_user_lockspace(const char *name, const char *cluster,
+ uint32_t flags, int lvblen,
+ const struct dlm_lockspace_ops *ops,
+ void *ops_arg, int *ops_result,
+ dlm_lockspace_t **lockspace);
#endif /* __LOCKSPACE_DOT_H__ */
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index cdfaf4f0e11a..59f64c596233 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -53,50 +53,19 @@
#include <net/sctp/sctp.h>
#include <net/ipv6.h>
+#include <trace/events/dlm.h>
+
#include "dlm_internal.h"
#include "lowcomms.h"
#include "midcomms.h"
+#include "memory.h"
#include "config.h"
#define NEEDED_RMEM (4*1024*1024)
-#define CONN_HASH_SIZE 32
/* Number of messages to send before rescheduling */
#define MAX_SEND_MSG_COUNT 25
-
-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;
-}
+#define DLM_SHUTDOWN_WAIT_TIMEOUT msecs_to_jiffies(10000)
struct connection {
struct socket *sock; /* NULL if not connected */
@@ -110,21 +79,37 @@ struct connection {
#define CF_CLOSE 6
#define CF_APP_LIMITED 7
#define CF_CLOSING 8
+#define CF_SHUTDOWN 9
+#define CF_CONNECTED 10
+#define CF_RECONNECT 11
+#define CF_DELAY_CONNECT 12
+#define CF_EOF 13
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;
+ atomic_t writequeue_cnt;
int retries;
#define MAX_CONNECT_RETRIES 3
struct hlist_node list;
struct connection *othercon;
+ struct connection *sendcon;
struct work_struct rwork; /* Receive workqueue */
struct work_struct swork; /* Send workqueue */
+ wait_queue_head_t shutdown_wait; /* wait for graceful shutdown */
+ unsigned char *rx_buf;
+ int rx_buflen;
+ int rx_leftover;
+ struct rcu_head rcu;
};
#define sock2con(x) ((struct connection *)(x)->sk_user_data)
+struct listen_connection {
+ struct socket *sock;
+ struct work_struct rwork;
+};
+
+#define DLM_WQ_REMAIN_BYTES(e) (PAGE_SIZE - e->end)
+#define DLM_WQ_LENGTH_BYTES(e) (e->end - e->offset)
+
/* An entry waiting to be sent */
struct writequeue_entry {
struct list_head list;
@@ -133,17 +118,51 @@ struct writequeue_entry {
int len;
int end;
int users;
+ bool dirty;
struct connection *con;
+ struct list_head msgs;
+ struct kref ref;
+};
+
+struct dlm_msg {
+ struct writequeue_entry *entry;
+ struct dlm_msg *orig_msg;
+ bool retransmit;
+ void *ppc;
+ int len;
+ int idx; /* new()/commit() idx exchange */
+
+ struct list_head list;
+ struct kref ref;
};
struct dlm_node_addr {
struct list_head list;
int nodeid;
+ int mark;
int addr_count;
int curr_addr_index;
struct sockaddr_storage *addr[DLM_MAX_ADDR_COUNT];
};
+struct dlm_proto_ops {
+ bool try_new_addr;
+ const char *name;
+ int proto;
+
+ int (*connect)(struct connection *con, struct socket *sock,
+ struct sockaddr *addr, int addr_len);
+ void (*sockopts)(struct socket *sock);
+ int (*bind)(struct socket *sock);
+ int (*listen_validate)(void);
+ void (*listen_sockopts)(struct socket *sock);
+ int (*listen_bind)(struct socket *sock);
+ /* What to do to shutdown */
+ void (*shutdown_action)(struct connection *con);
+ /* What to do to eof check */
+ bool (*eof_condition)(struct connection *con);
+};
+
static struct listen_sock_callbacks {
void (*sk_error_report)(struct sock *);
void (*sk_data_ready)(struct sock *);
@@ -154,80 +173,139 @@ static struct listen_sock_callbacks {
static LIST_HEAD(dlm_node_addrs);
static DEFINE_SPINLOCK(dlm_node_addrs_spin);
+static struct listen_connection listen_con;
static struct sockaddr_storage *dlm_local_addr[DLM_MAX_ADDR_COUNT];
static int dlm_local_count;
-static int dlm_allow_conn;
+int dlm_allow_conn;
/* Work queues */
static struct workqueue_struct *recv_workqueue;
static struct workqueue_struct *send_workqueue;
static struct hlist_head connection_hash[CONN_HASH_SIZE];
-static DEFINE_MUTEX(connections_lock);
-static struct kmem_cache *con_cache;
+static DEFINE_SPINLOCK(connections_lock);
+DEFINE_STATIC_SRCU(connections_srcu);
+
+static const struct dlm_proto_ops *dlm_proto_ops;
static void process_recv_sockets(struct work_struct *work);
static void process_send_sockets(struct work_struct *work);
+static void writequeue_entry_ctor(void *data)
+{
+ struct writequeue_entry *entry = data;
+
+ INIT_LIST_HEAD(&entry->msgs);
+}
-/* This is deliberately very simple because most clusters have simple
- sequential nodeids, so we should be able to go straight to a connection
- struct in the array */
-static inline int nodeid_hash(int nodeid)
+struct kmem_cache *dlm_lowcomms_writequeue_cache_create(void)
{
- return nodeid & (CONN_HASH_SIZE-1);
+ return kmem_cache_create("dlm_writequeue", sizeof(struct writequeue_entry),
+ 0, 0, writequeue_entry_ctor);
}
-static struct connection *__find_con(int nodeid)
+struct kmem_cache *dlm_lowcomms_msg_cache_create(void)
{
- int r;
- struct connection *con;
+ return kmem_cache_create("dlm_msg", sizeof(struct dlm_msg), 0, 0, NULL);
+}
- r = nodeid_hash(nodeid);
+/* need to held writequeue_lock */
+static struct writequeue_entry *con_next_wq(struct connection *con)
+{
+ struct writequeue_entry *e;
+
+ if (list_empty(&con->writequeue))
+ return NULL;
+
+ e = list_first_entry(&con->writequeue, struct writequeue_entry,
+ list);
+ /* if len is zero nothing is to send, if there are users filling
+ * buffers we wait until the users are done so we can send more.
+ */
+ if (e->users || e->len == 0)
+ return NULL;
- hlist_for_each_entry(con, &connection_hash[r], list) {
+ return e;
+}
+
+static struct connection *__find_con(int nodeid, int r)
+{
+ struct connection *con;
+
+ hlist_for_each_entry_rcu(con, &connection_hash[r], list) {
if (con->nodeid == nodeid)
return con;
}
+
return NULL;
}
+static bool tcp_eof_condition(struct connection *con)
+{
+ return atomic_read(&con->writequeue_cnt);
+}
+
+static int dlm_con_init(struct connection *con, int nodeid)
+{
+ con->rx_buflen = dlm_config.ci_buffer_size;
+ con->rx_buf = kmalloc(con->rx_buflen, GFP_NOFS);
+ if (!con->rx_buf)
+ return -ENOMEM;
+
+ con->nodeid = nodeid;
+ mutex_init(&con->sock_mutex);
+ INIT_LIST_HEAD(&con->writequeue);
+ spin_lock_init(&con->writequeue_lock);
+ atomic_set(&con->writequeue_cnt, 0);
+ INIT_WORK(&con->swork, process_send_sockets);
+ INIT_WORK(&con->rwork, process_recv_sockets);
+ init_waitqueue_head(&con->shutdown_wait);
+
+ return 0;
+}
+
/*
* 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)
+static struct connection *nodeid2con(int nodeid, gfp_t alloc)
{
- struct connection *con = NULL;
- int r;
+ struct connection *con, *tmp;
+ int r, ret;
- con = __find_con(nodeid);
+ r = nodeid_hash(nodeid);
+ con = __find_con(nodeid, r);
if (con || !alloc)
return con;
- con = kmem_cache_zalloc(con_cache, alloc);
+ con = kzalloc(sizeof(*con), alloc);
if (!con)
return NULL;
- r = nodeid_hash(nodeid);
- hlist_add_head(&con->list, &connection_hash[r]);
-
- 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 = __find_con(0);
+ ret = dlm_con_init(con, nodeid);
+ if (ret) {
+ kfree(con);
+ return NULL;
+ }
- con->connect_action = zerocon->connect_action;
- if (!con->rx_action)
- con->rx_action = zerocon->rx_action;
+ spin_lock(&connections_lock);
+ /* Because multiple workqueues/threads calls this function it can
+ * race on multiple cpu's. Instead of locking hot path __find_con()
+ * we just check in rare cases of recently added nodes again
+ * under protection of connections_lock. If this is the case we
+ * abort our connection creation and return the existing connection.
+ */
+ tmp = __find_con(nodeid, r);
+ if (tmp) {
+ spin_unlock(&connections_lock);
+ kfree(con->rx_buf);
+ kfree(con);
+ return tmp;
}
+ hlist_add_head_rcu(&con->list, &connection_hash[r]);
+ spin_unlock(&connections_lock);
+
return con;
}
@@ -235,26 +313,14 @@ static struct connection *__nodeid2con(int nodeid, gfp_t alloc)
static void foreach_conn(void (*conn_func)(struct connection *c))
{
int i;
- struct hlist_node *n;
struct connection *con;
for (i = 0; i < CONN_HASH_SIZE; i++) {
- hlist_for_each_entry_safe(con, n, &connection_hash[i], list)
+ hlist_for_each_entry_rcu(con, &connection_hash[i], list)
conn_func(con);
}
}
-static struct connection *nodeid2con(int nodeid, gfp_t allocation)
-{
- struct connection *con;
-
- mutex_lock(&connections_lock);
- con = __nodeid2con(nodeid, allocation);
- mutex_unlock(&connections_lock);
-
- return con;
-}
-
static struct dlm_node_addr *find_node_addr(int nodeid)
{
struct dlm_node_addr *na;
@@ -266,7 +332,8 @@ static struct dlm_node_addr *find_node_addr(int nodeid)
return NULL;
}
-static int addr_compare(struct sockaddr_storage *x, struct sockaddr_storage *y)
+static int addr_compare(const struct sockaddr_storage *x,
+ const struct sockaddr_storage *y)
{
switch (x->ss_family) {
case AF_INET: {
@@ -294,7 +361,8 @@ static int addr_compare(struct sockaddr_storage *x, struct sockaddr_storage *y)
}
static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out,
- struct sockaddr *sa_out, bool try_new_addr)
+ struct sockaddr *sa_out, bool try_new_addr,
+ unsigned int *mark)
{
struct sockaddr_storage sas;
struct dlm_node_addr *na;
@@ -322,6 +390,8 @@ static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out,
if (!na->addr_count)
return -ENOENT;
+ *mark = na->mark;
+
if (sas_out)
memcpy(sas_out, &sas, sizeof(struct sockaddr_storage));
@@ -341,7 +411,8 @@ static int nodeid_to_addr(int nodeid, struct sockaddr_storage *sas_out,
return 0;
}
-static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
+static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid,
+ unsigned int *mark)
{
struct dlm_node_addr *na;
int rv = -EEXIST;
@@ -355,6 +426,7 @@ static int addr_to_nodeid(struct sockaddr_storage *addr, int *nodeid)
for (addr_i = 0; addr_i < na->addr_count; addr_i++) {
if (addr_compare(na->addr[addr_i], addr)) {
*nodeid = na->nodeid;
+ *mark = na->mark;
rv = 0;
goto unlock;
}
@@ -365,10 +437,25 @@ unlock:
return rv;
}
+/* caller need to held dlm_node_addrs_spin lock */
+static bool dlm_lowcomms_na_has_addr(const struct dlm_node_addr *na,
+ const struct sockaddr_storage *addr)
+{
+ int i;
+
+ for (i = 0; i < na->addr_count; i++) {
+ if (addr_compare(na->addr[i], addr))
+ return true;
+ }
+
+ return false;
+}
+
int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len)
{
struct sockaddr_storage *new_addr;
struct dlm_node_addr *new_node, *na;
+ bool ret;
new_node = kzalloc(sizeof(struct dlm_node_addr), GFP_NOFS);
if (!new_node)
@@ -388,11 +475,20 @@ int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len)
new_node->nodeid = nodeid;
new_node->addr[0] = new_addr;
new_node->addr_count = 1;
+ new_node->mark = dlm_config.ci_mark;
list_add(&new_node->list, &dlm_node_addrs);
spin_unlock(&dlm_node_addrs_spin);
return 0;
}
+ ret = dlm_lowcomms_na_has_addr(na, addr);
+ if (ret) {
+ spin_unlock(&dlm_node_addrs_spin);
+ kfree(new_addr);
+ kfree(new_node);
+ return -EEXIST;
+ }
+
if (na->addr_count >= DLM_MAX_ADDR_COUNT) {
spin_unlock(&dlm_node_addrs_spin);
kfree(new_addr);
@@ -411,21 +507,32 @@ static void lowcomms_data_ready(struct sock *sk)
{
struct connection *con;
- read_lock_bh(&sk->sk_callback_lock);
con = sock2con(sk);
if (con && !test_and_set_bit(CF_READ_PENDING, &con->flags))
queue_work(recv_workqueue, &con->rwork);
- read_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void lowcomms_listen_data_ready(struct sock *sk)
+{
+ if (!dlm_allow_conn)
+ return;
+
+ queue_work(recv_workqueue, &listen_con.rwork);
}
static void lowcomms_write_space(struct sock *sk)
{
struct connection *con;
- read_lock_bh(&sk->sk_callback_lock);
con = sock2con(sk);
if (!con)
- goto out;
+ return;
+
+ if (!test_and_set_bit(CF_CONNECTED, &con->flags)) {
+ log_print("connected to node %d", con->nodeid);
+ queue_work(send_workqueue, &con->swork);
+ return;
+ }
clear_bit(SOCK_NOSPACE, &con->sock->flags);
@@ -435,8 +542,6 @@ static void lowcomms_write_space(struct sock *sk)
}
queue_work(send_workqueue, &con->swork);
-out:
- read_unlock_bh(&sk->sk_callback_lock);
}
static inline void lowcomms_connect_sock(struct connection *con)
@@ -465,60 +570,97 @@ static void lowcomms_state_change(struct sock *sk)
int dlm_lowcomms_connect_node(int nodeid)
{
struct connection *con;
+ int idx;
if (nodeid == dlm_our_nodeid())
return 0;
+ idx = srcu_read_lock(&connections_srcu);
con = nodeid2con(nodeid, GFP_NOFS);
- if (!con)
+ if (!con) {
+ srcu_read_unlock(&connections_srcu, idx);
return -ENOMEM;
+ }
+
lowcomms_connect_sock(con);
+ srcu_read_unlock(&connections_srcu, idx);
+
+ return 0;
+}
+
+int dlm_lowcomms_nodes_set_mark(int nodeid, unsigned int mark)
+{
+ struct dlm_node_addr *na;
+
+ spin_lock(&dlm_node_addrs_spin);
+ na = find_node_addr(nodeid);
+ if (!na) {
+ spin_unlock(&dlm_node_addrs_spin);
+ return -ENOENT;
+ }
+
+ na->mark = mark;
+ spin_unlock(&dlm_node_addrs_spin);
+
return 0;
}
static void lowcomms_error_report(struct sock *sk)
{
struct connection *con;
- struct sockaddr_storage saddr;
void (*orig_report)(struct sock *) = NULL;
+ struct inet_sock *inet;
- read_lock_bh(&sk->sk_callback_lock);
con = sock2con(sk);
if (con == NULL)
goto out;
orig_report = listen_sock.sk_error_report;
- if (con->sock == NULL ||
- kernel_getpeername(con->sock, (struct sockaddr *)&saddr) < 0) {
- printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
- "sending to node %d, port %d, "
- "sk_err=%d/%d\n", dlm_our_nodeid(),
- con->nodeid, dlm_config.ci_tcp_port,
- sk->sk_err, sk->sk_err_soft);
- } else if (saddr.ss_family == AF_INET) {
- struct sockaddr_in *sin4 = (struct sockaddr_in *)&saddr;
+ inet = inet_sk(sk);
+ switch (sk->sk_family) {
+ case AF_INET:
printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
- "sending to node %d at %pI4, port %d, "
+ "sending to node %d at %pI4, dport %d, "
"sk_err=%d/%d\n", dlm_our_nodeid(),
- con->nodeid, &sin4->sin_addr.s_addr,
- dlm_config.ci_tcp_port, sk->sk_err,
+ con->nodeid, &inet->inet_daddr,
+ ntohs(inet->inet_dport), sk->sk_err,
sk->sk_err_soft);
- } else {
- struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&saddr;
-
+ break;
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6:
printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
- "sending to node %d at %u.%u.%u.%u, "
- "port %d, sk_err=%d/%d\n", dlm_our_nodeid(),
- con->nodeid, sin6->sin6_addr.s6_addr32[0],
- sin6->sin6_addr.s6_addr32[1],
- sin6->sin6_addr.s6_addr32[2],
- sin6->sin6_addr.s6_addr32[3],
- dlm_config.ci_tcp_port, sk->sk_err,
+ "sending to node %d at %pI6c, "
+ "dport %d, sk_err=%d/%d\n", dlm_our_nodeid(),
+ con->nodeid, &sk->sk_v6_daddr,
+ ntohs(inet->inet_dport), sk->sk_err,
sk->sk_err_soft);
+ break;
+#endif
+ default:
+ printk_ratelimited(KERN_ERR "dlm: node %d: socket error "
+ "invalid socket family %d set, "
+ "sk_err=%d/%d\n", dlm_our_nodeid(),
+ sk->sk_family, sk->sk_err, sk->sk_err_soft);
+ goto out;
+ }
+
+ /* below sendcon only handling */
+ if (test_bit(CF_IS_OTHERCON, &con->flags))
+ con = con->sendcon;
+
+ switch (sk->sk_err) {
+ case ECONNREFUSED:
+ set_bit(CF_DELAY_CONNECT, &con->flags);
+ break;
+ default:
+ break;
}
+
+ if (!test_and_set_bit(CF_RECONNECT, &con->flags))
+ queue_work(send_workqueue, &con->swork);
+
out:
- read_unlock_bh(&sk->sk_callback_lock);
if (orig_report)
orig_report(sk);
}
@@ -538,13 +680,28 @@ static void restore_callbacks(struct socket *sock)
{
struct sock *sk = sock->sk;
- write_lock_bh(&sk->sk_callback_lock);
+ lock_sock(sk);
sk->sk_user_data = NULL;
sk->sk_data_ready = listen_sock.sk_data_ready;
sk->sk_state_change = listen_sock.sk_state_change;
sk->sk_write_space = listen_sock.sk_write_space;
sk->sk_error_report = listen_sock.sk_error_report;
- write_unlock_bh(&sk->sk_callback_lock);
+ release_sock(sk);
+}
+
+static void add_listen_sock(struct socket *sock, struct listen_connection *con)
+{
+ struct sock *sk = sock->sk;
+
+ lock_sock(sk);
+ save_listen_callbacks(sock);
+ con->sock = sock;
+
+ sk->sk_user_data = con;
+ sk->sk_allocation = GFP_NOFS;
+ /* Install a data_ready callback */
+ sk->sk_data_ready = lowcomms_listen_data_ready;
+ release_sock(sk);
}
/* Make a socket active */
@@ -552,7 +709,7 @@ static void add_sock(struct socket *sock, struct connection *con)
{
struct sock *sk = sock->sk;
- write_lock_bh(&sk->sk_callback_lock);
+ lock_sock(sk);
con->sock = sock;
sk->sk_user_data = con;
@@ -562,7 +719,7 @@ static void add_sock(struct socket *sock, struct connection *con)
sk->sk_state_change = lowcomms_state_change;
sk->sk_allocation = GFP_NOFS;
sk->sk_error_report = lowcomms_error_report;
- write_unlock_bh(&sk->sk_callback_lock);
+ release_sock(sk);
}
/* Add the port number to an IPv6 or 4 sockaddr and return the address
@@ -584,11 +741,57 @@ static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port,
memset((char *)saddr + *addr_len, 0, sizeof(struct sockaddr_storage) - *addr_len);
}
+static void dlm_page_release(struct kref *kref)
+{
+ struct writequeue_entry *e = container_of(kref, struct writequeue_entry,
+ ref);
+
+ __free_page(e->page);
+ dlm_free_writequeue(e);
+}
+
+static void dlm_msg_release(struct kref *kref)
+{
+ struct dlm_msg *msg = container_of(kref, struct dlm_msg, ref);
+
+ kref_put(&msg->entry->ref, dlm_page_release);
+ dlm_free_msg(msg);
+}
+
+static void free_entry(struct writequeue_entry *e)
+{
+ struct dlm_msg *msg, *tmp;
+
+ list_for_each_entry_safe(msg, tmp, &e->msgs, list) {
+ if (msg->orig_msg) {
+ msg->orig_msg->retransmit = false;
+ kref_put(&msg->orig_msg->ref, dlm_msg_release);
+ }
+
+ list_del(&msg->list);
+ kref_put(&msg->ref, dlm_msg_release);
+ }
+
+ list_del(&e->list);
+ atomic_dec(&e->con->writequeue_cnt);
+ kref_put(&e->ref, dlm_page_release);
+}
+
+static void dlm_close_sock(struct socket **sock)
+{
+ if (*sock) {
+ restore_callbacks(*sock);
+ sock_release(*sock);
+ *sock = NULL;
+ }
+}
+
/* Close a remote connection and tidy up */
static void close_connection(struct connection *con, bool and_other,
bool tx, bool rx)
{
bool closing = test_and_set_bit(CF_CLOSING, &con->flags);
+ struct writequeue_entry *e;
if (tx && !closing && cancel_work_sync(&con->swork)) {
log_print("canceled swork for node %d", con->nodeid);
@@ -600,35 +803,115 @@ static void close_connection(struct connection *con, bool and_other,
}
mutex_lock(&con->sock_mutex);
- if (con->sock) {
- restore_callbacks(con->sock);
- sock_release(con->sock);
- con->sock = NULL;
- }
+ dlm_close_sock(&con->sock);
+
if (con->othercon && and_other) {
/* Will only re-enter once. */
- close_connection(con->othercon, false, true, true);
- }
- if (con->rx_page) {
- __free_page(con->rx_page);
- con->rx_page = NULL;
+ close_connection(con->othercon, false, tx, rx);
+ }
+
+ /* if we send a writequeue entry only a half way, we drop the
+ * whole entry because reconnection and that we not start of the
+ * middle of a msg which will confuse the other end.
+ *
+ * we can always drop messages because retransmits, but what we
+ * cannot allow is to transmit half messages which may be processed
+ * at the other side.
+ *
+ * our policy is to start on a clean state when disconnects, we don't
+ * know what's send/received on transport layer in this case.
+ */
+ spin_lock(&con->writequeue_lock);
+ if (!list_empty(&con->writequeue)) {
+ e = list_first_entry(&con->writequeue, struct writequeue_entry,
+ list);
+ if (e->dirty)
+ free_entry(e);
}
+ spin_unlock(&con->writequeue_lock);
+ con->rx_leftover = 0;
con->retries = 0;
+ clear_bit(CF_APP_LIMITED, &con->flags);
+ clear_bit(CF_CONNECTED, &con->flags);
+ clear_bit(CF_DELAY_CONNECT, &con->flags);
+ clear_bit(CF_RECONNECT, &con->flags);
+ clear_bit(CF_EOF, &con->flags);
mutex_unlock(&con->sock_mutex);
clear_bit(CF_CLOSING, &con->flags);
}
+static void shutdown_connection(struct connection *con)
+{
+ int ret;
+
+ flush_work(&con->swork);
+
+ mutex_lock(&con->sock_mutex);
+ /* nothing to shutdown */
+ if (!con->sock) {
+ mutex_unlock(&con->sock_mutex);
+ return;
+ }
+
+ set_bit(CF_SHUTDOWN, &con->flags);
+ ret = kernel_sock_shutdown(con->sock, SHUT_WR);
+ mutex_unlock(&con->sock_mutex);
+ if (ret) {
+ log_print("Connection %p failed to shutdown: %d will force close",
+ con, ret);
+ goto force_close;
+ } else {
+ ret = wait_event_timeout(con->shutdown_wait,
+ !test_bit(CF_SHUTDOWN, &con->flags),
+ DLM_SHUTDOWN_WAIT_TIMEOUT);
+ if (ret == 0) {
+ log_print("Connection %p shutdown timed out, will force close",
+ con);
+ goto force_close;
+ }
+ }
+
+ return;
+
+force_close:
+ clear_bit(CF_SHUTDOWN, &con->flags);
+ close_connection(con, false, true, true);
+}
+
+static void dlm_tcp_shutdown(struct connection *con)
+{
+ if (con->othercon)
+ shutdown_connection(con->othercon);
+ shutdown_connection(con);
+}
+
+static int con_realloc_receive_buf(struct connection *con, int newlen)
+{
+ unsigned char *newbuf;
+
+ newbuf = kmalloc(newlen, GFP_NOFS);
+ if (!newbuf)
+ return -ENOMEM;
+
+ /* copy any leftover from last receive */
+ if (con->rx_leftover)
+ memmove(newbuf, con->rx_buf, con->rx_leftover);
+
+ /* swap to new buffer space */
+ kfree(con->rx_buf);
+ con->rx_buflen = newlen;
+ con->rx_buf = newbuf;
+
+ return 0;
+}
+
/* 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;
+ struct msghdr msg;
+ struct kvec iov;
+ int ret, buflen;
mutex_lock(&con->sock_mutex);
@@ -636,71 +919,50 @@ static int receive_from_sock(struct connection *con)
ret = -EAGAIN;
goto out_close;
}
- if (con->nodeid == 0) {
- ret = -EINVAL;
- 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)
+ /* realloc if we get new buffer size to read out */
+ buflen = dlm_config.ci_buffer_size;
+ if (con->rx_buflen != buflen && con->rx_leftover <= buflen) {
+ ret = con_realloc_receive_buf(con, buflen);
+ if (ret < 0)
goto out_resched;
- cbuf_init(&con->cb, PAGE_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);
- 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_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;
- iov_iter_kvec(&msg.msg_iter, READ, iov, nvec, len);
-
- r = ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT | MSG_NOSIGNAL);
- if (ret <= 0)
- goto out_close;
- else 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_SIZE);
- if (ret == -EBADMSG) {
- log_print("lowcomms: addr=%p, base=%u, len=%u, read=%d",
- page_address(con->rx_page), con->cb.base,
- con->cb.len, 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;
+ for (;;) {
+ /* calculate new buffer parameter regarding last receive and
+ * possible leftover bytes
+ */
+ iov.iov_base = con->rx_buf + con->rx_leftover;
+ iov.iov_len = con->rx_buflen - con->rx_leftover;
+
+ memset(&msg, 0, sizeof(msg));
+ msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
+ ret = kernel_recvmsg(con->sock, &msg, &iov, 1, iov.iov_len,
+ msg.msg_flags);
+ trace_dlm_recv(con->nodeid, ret);
+ if (ret == -EAGAIN)
+ break;
+ else if (ret <= 0)
+ goto out_close;
+
+ /* new buflen according readed bytes and leftover from last receive */
+ buflen = ret + con->rx_leftover;
+ ret = dlm_process_incoming_buffer(con->nodeid, con->rx_buf, buflen);
+ if (ret < 0)
+ goto out_close;
+
+ /* calculate leftover bytes from process and put it into begin of
+ * the receive buffer, so next receive we have the full message
+ * at the start address of the receive buffer.
+ */
+ con->rx_leftover = buflen - ret;
+ if (con->rx_leftover) {
+ memmove(con->rx_buf, con->rx_buf + ret,
+ con->rx_leftover);
+ }
}
- if (call_again_soon)
- goto out_resched;
+ dlm_midcomms_receive_done(con->nodeid);
mutex_unlock(&con->sock_mutex);
return 0;
@@ -711,42 +973,45 @@ out_resched:
return -EAGAIN;
out_close:
- mutex_unlock(&con->sock_mutex);
- if (ret != -EAGAIN) {
- close_connection(con, true, true, false);
- /* Reconnect when there is something to send */
- }
- /* Don't return success if we really got EOF */
- if (ret == 0)
- ret = -EAGAIN;
+ if (ret == 0) {
+ log_print("connection %p got EOF from %d",
+ con, con->nodeid);
+
+ if (dlm_proto_ops->eof_condition &&
+ dlm_proto_ops->eof_condition(con)) {
+ set_bit(CF_EOF, &con->flags);
+ mutex_unlock(&con->sock_mutex);
+ } else {
+ mutex_unlock(&con->sock_mutex);
+ close_connection(con, false, true, false);
+ /* handling for tcp shutdown */
+ clear_bit(CF_SHUTDOWN, &con->flags);
+ wake_up(&con->shutdown_wait);
+ }
+
+ /* signal to breaking receive worker */
+ ret = -1;
+ } else {
+ mutex_unlock(&con->sock_mutex);
+ }
return ret;
}
/* Listening socket is busy, accept a connection */
-static int tcp_accept_from_sock(struct connection *con)
+static int accept_from_sock(struct listen_connection *con)
{
int result;
struct sockaddr_storage peeraddr;
struct socket *newsock;
- int len;
+ int len, idx;
int nodeid;
struct connection *newcon;
struct connection *addcon;
+ unsigned int mark;
- mutex_lock(&connections_lock);
- if (!dlm_allow_conn) {
- mutex_unlock(&connections_lock);
- return -1;
- }
- mutex_unlock(&connections_lock);
-
- mutex_lock_nested(&con->sock_mutex, 0);
-
- if (!con->sock) {
- mutex_unlock(&con->sock_mutex);
+ if (!con->sock)
return -ENOTCONN;
- }
result = kernel_accept(con->sock, &newsock, O_NONBLOCK);
if (result < 0)
@@ -762,13 +1027,30 @@ static int tcp_accept_from_sock(struct connection *con)
/* Get the new node's NODEID */
make_sockaddr(&peeraddr, 0, &len);
- if (addr_to_nodeid(&peeraddr, &nodeid)) {
- unsigned char *b=(unsigned char *)&peeraddr;
- log_print("connect from non cluster node");
- print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE,
- b, sizeof(struct sockaddr_storage));
+ if (addr_to_nodeid(&peeraddr, &nodeid, &mark)) {
+ switch (peeraddr.ss_family) {
+ case AF_INET: {
+ struct sockaddr_in *sin = (struct sockaddr_in *)&peeraddr;
+
+ log_print("connect from non cluster IPv4 node %pI4",
+ &sin->sin_addr);
+ break;
+ }
+#if IS_ENABLED(CONFIG_IPV6)
+ case AF_INET6: {
+ struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)&peeraddr;
+
+ log_print("connect from non cluster IPv6 node %pI6c",
+ &sin6->sin6_addr);
+ break;
+ }
+#endif
+ default:
+ log_print("invalid family from non cluster node");
+ break;
+ }
+
sock_release(newsock);
- mutex_unlock(&con->sock_mutex);
return -1;
}
@@ -779,49 +1061,53 @@ static int tcp_accept_from_sock(struct connection *con)
* the same time and the connections cross on the wire.
* In this case we store the incoming one in "othercon"
*/
+ idx = srcu_read_lock(&connections_srcu);
newcon = nodeid2con(nodeid, GFP_NOFS);
if (!newcon) {
+ srcu_read_unlock(&connections_srcu, idx);
result = -ENOMEM;
goto accept_err;
}
- mutex_lock_nested(&newcon->sock_mutex, 1);
+
+ sock_set_mark(newsock->sk, mark);
+
+ mutex_lock(&newcon->sock_mutex);
if (newcon->sock) {
struct connection *othercon = newcon->othercon;
if (!othercon) {
- othercon = kmem_cache_zalloc(con_cache, GFP_NOFS);
+ othercon = kzalloc(sizeof(*othercon), GFP_NOFS);
if (!othercon) {
log_print("failed to allocate incoming socket");
mutex_unlock(&newcon->sock_mutex);
+ srcu_read_unlock(&connections_srcu, idx);
result = -ENOMEM;
goto accept_err;
}
- othercon->nodeid = nodeid;
- othercon->rx_action = receive_from_sock;
- mutex_init(&othercon->sock_mutex);
- INIT_LIST_HEAD(&othercon->writequeue);
- spin_lock_init(&othercon->writequeue_lock);
- INIT_WORK(&othercon->swork, process_send_sockets);
- INIT_WORK(&othercon->rwork, process_recv_sockets);
+
+ result = dlm_con_init(othercon, nodeid);
+ if (result < 0) {
+ kfree(othercon);
+ mutex_unlock(&newcon->sock_mutex);
+ srcu_read_unlock(&connections_srcu, idx);
+ goto accept_err;
+ }
+
+ lockdep_set_subclass(&othercon->sock_mutex, 1);
set_bit(CF_IS_OTHERCON, &othercon->flags);
- }
- mutex_lock_nested(&othercon->sock_mutex, 2);
- if (!othercon->sock) {
newcon->othercon = othercon;
- add_sock(newsock, othercon);
- addcon = othercon;
- mutex_unlock(&othercon->sock_mutex);
- }
- else {
- printk("Extra connection from node %d attempted\n", nodeid);
- result = -EAGAIN;
- mutex_unlock(&othercon->sock_mutex);
- mutex_unlock(&newcon->sock_mutex);
- goto accept_err;
+ othercon->sendcon = newcon;
+ } else {
+ /* close other sock con if we have something new */
+ close_connection(othercon, false, true, false);
}
+
+ mutex_lock(&othercon->sock_mutex);
+ add_sock(newsock, othercon);
+ addcon = othercon;
+ mutex_unlock(&othercon->sock_mutex);
}
else {
- newcon->rx_action = receive_from_sock;
/* accept copies the sk after we've saved the callbacks, so we
don't want to save them a second time or comm errors will
result in calling sk_error_report recursively. */
@@ -829,6 +1115,7 @@ static int tcp_accept_from_sock(struct connection *con)
addcon = newcon;
}
+ set_bit(CF_CONNECTED, &addcon->flags);
mutex_unlock(&newcon->sock_mutex);
/*
@@ -838,12 +1125,12 @@ static int tcp_accept_from_sock(struct connection *con)
*/
if (!test_and_set_bit(CF_READ_PENDING, &addcon->flags))
queue_work(recv_workqueue, &addcon->rwork);
- mutex_unlock(&con->sock_mutex);
+
+ srcu_read_unlock(&connections_srcu, idx);
return 0;
accept_err:
- mutex_unlock(&con->sock_mutex);
if (newsock)
sock_release(newsock);
@@ -852,129 +1139,6 @@ accept_err:
return result;
}
-static int sctp_accept_from_sock(struct connection *con)
-{
- /* Check that the new node is in the lockspace */
- struct sctp_prim prim;
- int nodeid;
- int prim_len, ret;
- int addr_len;
- struct connection *newcon;
- struct connection *addcon;
- struct socket *newsock;
-
- mutex_lock(&connections_lock);
- if (!dlm_allow_conn) {
- mutex_unlock(&connections_lock);
- return -1;
- }
- mutex_unlock(&connections_lock);
-
- mutex_lock_nested(&con->sock_mutex, 0);
-
- ret = kernel_accept(con->sock, &newsock, O_NONBLOCK);
- if (ret < 0)
- goto accept_err;
-
- memset(&prim, 0, sizeof(struct sctp_prim));
- prim_len = sizeof(struct sctp_prim);
-
- ret = kernel_getsockopt(newsock, IPPROTO_SCTP, SCTP_PRIMARY_ADDR,
- (char *)&prim, &prim_len);
- if (ret < 0) {
- log_print("getsockopt/sctp_primary_addr failed: %d", ret);
- goto accept_err;
- }
-
- make_sockaddr(&prim.ssp_addr, 0, &addr_len);
- ret = addr_to_nodeid(&prim.ssp_addr, &nodeid);
- if (ret) {
- unsigned char *b = (unsigned char *)&prim.ssp_addr;
-
- log_print("reject connect from unknown addr");
- print_hex_dump_bytes("ss: ", DUMP_PREFIX_NONE,
- b, sizeof(struct sockaddr_storage));
- goto accept_err;
- }
-
- newcon = nodeid2con(nodeid, GFP_NOFS);
- if (!newcon) {
- ret = -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_NOFS);
- if (!othercon) {
- log_print("failed to allocate incoming socket");
- mutex_unlock(&newcon->sock_mutex);
- ret = -ENOMEM;
- goto accept_err;
- }
- othercon->nodeid = nodeid;
- othercon->rx_action = receive_from_sock;
- mutex_init(&othercon->sock_mutex);
- INIT_LIST_HEAD(&othercon->writequeue);
- spin_lock_init(&othercon->writequeue_lock);
- INIT_WORK(&othercon->swork, process_send_sockets);
- INIT_WORK(&othercon->rwork, process_recv_sockets);
- set_bit(CF_IS_OTHERCON, &othercon->flags);
- }
- mutex_lock_nested(&othercon->sock_mutex, 2);
- if (!othercon->sock) {
- newcon->othercon = othercon;
- add_sock(newsock, othercon);
- addcon = othercon;
- mutex_unlock(&othercon->sock_mutex);
- } else {
- printk("Extra connection from node %d attempted\n", nodeid);
- ret = -EAGAIN;
- mutex_unlock(&othercon->sock_mutex);
- mutex_unlock(&newcon->sock_mutex);
- goto accept_err;
- }
- } else {
- newcon->rx_action = receive_from_sock;
- add_sock(newsock, newcon);
- addcon = newcon;
- }
-
- log_print("connected to %d", nodeid);
-
- mutex_unlock(&newcon->sock_mutex);
-
- /*
- * Add it to the active queue in case we got data
- * between 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);
- if (newsock)
- sock_release(newsock);
- if (ret != -EAGAIN)
- log_print("error accepting connection from node: %d", ret);
-
- return ret;
-}
-
-static void free_entry(struct writequeue_entry *e)
-{
- __free_page(e->page);
- kfree(e);
-}
-
/*
* writequeue_entry_complete - try to delete and free write queue entry
* @e: write queue entry to try to delete
@@ -986,19 +1150,20 @@ static void writequeue_entry_complete(struct writequeue_entry *e, int completed)
{
e->offset += completed;
e->len -= completed;
+ /* signal that page was half way transmitted */
+ e->dirty = true;
- if (e->len == 0 && e->users == 0) {
- list_del(&e->list);
+ if (e->len == 0 && e->users == 0)
free_entry(e);
- }
}
/*
* sctp_bind_addrs - bind a SCTP socket to all our addresses
*/
-static int sctp_bind_addrs(struct connection *con, uint16_t port)
+static int sctp_bind_addrs(struct socket *sock, uint16_t port)
{
struct sockaddr_storage localaddr;
+ struct sockaddr *addr = (struct sockaddr *)&localaddr;
int i, addr_len, result = 0;
for (i = 0; i < dlm_local_count; i++) {
@@ -1006,13 +1171,9 @@ static int sctp_bind_addrs(struct connection *con, uint16_t port)
make_sockaddr(&localaddr, port, &addr_len);
if (!i)
- result = kernel_bind(con->sock,
- (struct sockaddr *)&localaddr,
- addr_len);
+ result = kernel_bind(sock, addr, addr_len);
else
- result = kernel_setsockopt(con->sock, SOL_SCTP,
- SCTP_SOCKOPT_BINDX_ADD,
- (char *)&localaddr, addr_len);
+ result = sock_bind_add(sock->sk, addr, addr_len);
if (result < 0) {
log_print("Can't bind to %d addr number %d, %d.\n",
@@ -1023,268 +1184,6 @@ static int sctp_bind_addrs(struct connection *con, uint16_t port)
return result;
}
-/* 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_connect_to_sock(struct connection *con)
-{
- struct sockaddr_storage daddr;
- int one = 1;
- int result;
- int addr_len;
- struct socket *sock;
- struct __kernel_sock_timeval tv = { .tv_sec = 5, .tv_usec = 0 };
-
- if (con->nodeid == 0) {
- log_print("attempt to connect sock 0 foiled");
- return;
- }
-
- mutex_lock(&con->sock_mutex);
-
- /* Some odd races can cause double-connects, ignore them */
- if (con->retries++ > MAX_CONNECT_RETRIES)
- goto out;
-
- if (con->sock) {
- log_print("node %d already connected.", con->nodeid);
- goto out;
- }
-
- memset(&daddr, 0, sizeof(daddr));
- result = nodeid_to_addr(con->nodeid, &daddr, NULL, true);
- if (result < 0) {
- log_print("no address for nodeid %d", con->nodeid);
- goto out;
- }
-
- /* Create a socket to communicate with */
- result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
- SOCK_STREAM, IPPROTO_SCTP, &sock);
- if (result < 0)
- goto socket_err;
-
- con->rx_action = receive_from_sock;
- con->connect_action = sctp_connect_to_sock;
- add_sock(sock, con);
-
- /* Bind to all addresses. */
- if (sctp_bind_addrs(con, 0))
- goto bind_err;
-
- make_sockaddr(&daddr, dlm_config.ci_tcp_port, &addr_len);
-
- log_print("connecting to %d", con->nodeid);
-
- /* Turn off Nagle's algorithm */
- kernel_setsockopt(sock, SOL_SCTP, SCTP_NODELAY, (char *)&one,
- sizeof(one));
-
- /*
- * Make sock->ops->connect() function return in specified time,
- * since O_NONBLOCK argument in connect() function does not work here,
- * then, we should restore the default value of this attribute.
- */
- kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_NEW, (char *)&tv,
- sizeof(tv));
- result = sock->ops->connect(sock, (struct sockaddr *)&daddr, addr_len,
- 0);
- memset(&tv, 0, sizeof(tv));
- kernel_setsockopt(sock, SOL_SOCKET, SO_SNDTIMEO_NEW, (char *)&tv,
- sizeof(tv));
-
- if (result == -EINPROGRESS)
- result = 0;
- if (result == 0)
- goto out;
-
-bind_err:
- con->sock = NULL;
- sock_release(sock);
-
-socket_err:
- /*
- * 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) {
- log_print("connect %d try %d error %d", con->nodeid,
- con->retries, result);
- mutex_unlock(&con->sock_mutex);
- msleep(1000);
- lowcomms_connect_sock(con);
- return;
- }
-
-out:
- mutex_unlock(&con->sock_mutex);
-}
-
-/* Connect a new socket to its peer */
-static void tcp_connect_to_sock(struct connection *con)
-{
- struct sockaddr_storage saddr, src_addr;
- int addr_len;
- struct socket *sock = NULL;
- int one = 1;
- int result;
-
- 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)
- goto out;
-
- /* Create a socket to communicate with */
- result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
- SOCK_STREAM, IPPROTO_TCP, &sock);
- if (result < 0)
- goto out_err;
-
- memset(&saddr, 0, sizeof(saddr));
- result = nodeid_to_addr(con->nodeid, &saddr, NULL, false);
- if (result < 0) {
- log_print("no address for nodeid %d", con->nodeid);
- goto out_err;
- }
-
- con->rx_action = receive_from_sock;
- con->connect_action = tcp_connect_to_sock;
- add_sock(sock, con);
-
- /* Bind to our cluster-known address connecting to avoid
- routing problems */
- memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr));
- make_sockaddr(&src_addr, 0, &addr_len);
- result = sock->ops->bind(sock, (struct sockaddr *) &src_addr,
- addr_len);
- if (result < 0) {
- log_print("could not bind for connect: %d", result);
- /* This *may* not indicate a critical error */
- }
-
- make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len);
-
- log_print("connecting to %d", con->nodeid);
-
- /* Turn off Nagle's algorithm */
- kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
- sizeof(one));
-
- 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;
- } else if (sock) {
- sock_release(sock);
- }
- /*
- * 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) {
- log_print("connect %d try %d error %d", con->nodeid,
- con->retries, result);
- mutex_unlock(&con->sock_mutex);
- msleep(1000);
- lowcomms_connect_sock(con);
- return;
- }
-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(&init_net, 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;
- }
-
- /* Turn off Nagle's algorithm */
- kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY, (char *)&one,
- sizeof(one));
-
- 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);
- }
- write_lock_bh(&sock->sk->sk_callback_lock);
- sock->sk->sk_user_data = con;
- save_listen_callbacks(sock);
- con->rx_action = tcp_accept_from_sock;
- con->connect_action = tcp_connect_to_sock;
- write_unlock_bh(&sock->sk->sk_callback_lock);
-
- /* 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)
{
@@ -1303,175 +1202,163 @@ static void init_local(void)
}
}
-/* Initialise SCTP socket and bind to all interfaces */
-static int sctp_listen_for_all(void)
+static void deinit_local(void)
{
- struct socket *sock = NULL;
- int result = -EINVAL;
- struct connection *con = nodeid2con(0, GFP_NOFS);
- int bufsize = NEEDED_RMEM;
- int one = 1;
-
- if (!con)
- return -ENOMEM;
-
- log_print("Using SCTP for communications");
-
- result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
- SOCK_STREAM, IPPROTO_SCTP, &sock);
- if (result < 0) {
- log_print("Can't create comms socket, check SCTP is loaded");
- goto out;
- }
-
- result = kernel_setsockopt(sock, SOL_SOCKET, SO_RCVBUFFORCE,
- (char *)&bufsize, sizeof(bufsize));
- if (result)
- log_print("Error increasing buffer space on socket %d", result);
-
- result = kernel_setsockopt(sock, SOL_SCTP, SCTP_NODELAY, (char *)&one,
- sizeof(one));
- if (result < 0)
- log_print("Could not set SCTP NODELAY error %d\n", result);
+ int i;
- write_lock_bh(&sock->sk->sk_callback_lock);
- /* Init con struct */
- sock->sk->sk_user_data = con;
- save_listen_callbacks(sock);
- con->sock = sock;
- con->sock->sk->sk_data_ready = lowcomms_data_ready;
- con->rx_action = sctp_accept_from_sock;
- con->connect_action = sctp_connect_to_sock;
+ for (i = 0; i < dlm_local_count; i++)
+ kfree(dlm_local_addr[i]);
+}
- write_unlock_bh(&sock->sk->sk_callback_lock);
+static struct writequeue_entry *new_writequeue_entry(struct connection *con)
+{
+ struct writequeue_entry *entry;
- /* Bind to all addresses. */
- if (sctp_bind_addrs(con, dlm_config.ci_tcp_port))
- goto create_delsock;
+ entry = dlm_allocate_writequeue();
+ if (!entry)
+ return NULL;
- result = sock->ops->listen(sock, 5);
- if (result < 0) {
- log_print("Can't set socket listening");
- goto create_delsock;
+ entry->page = alloc_page(GFP_ATOMIC | __GFP_ZERO);
+ if (!entry->page) {
+ dlm_free_writequeue(entry);
+ return NULL;
}
- return 0;
-
-create_delsock:
- sock_release(sock);
- con->sock = NULL;
-out:
- return result;
+ entry->offset = 0;
+ entry->len = 0;
+ entry->end = 0;
+ entry->dirty = false;
+ entry->con = con;
+ entry->users = 1;
+ kref_init(&entry->ref);
+ return entry;
}
-static int tcp_listen_for_all(void)
+static struct writequeue_entry *new_wq_entry(struct connection *con, int len,
+ char **ppc, void (*cb)(void *data),
+ void *data)
{
- struct socket *sock = NULL;
- struct connection *con = nodeid2con(0, GFP_NOFS);
- int result = -EINVAL;
-
- if (!con)
- return -ENOMEM;
+ struct writequeue_entry *e;
- /* 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;
+ spin_lock(&con->writequeue_lock);
+ if (!list_empty(&con->writequeue)) {
+ e = list_last_entry(&con->writequeue, struct writequeue_entry, list);
+ if (DLM_WQ_REMAIN_BYTES(e) >= len) {
+ kref_get(&e->ref);
+
+ *ppc = page_address(e->page) + e->end;
+ if (cb)
+ cb(data);
+
+ e->end += len;
+ e->users++;
+ goto out;
+ }
}
- log_print("Using TCP for communications");
-
- sock = tcp_create_listen_sock(con, dlm_local_addr[0]);
- if (sock) {
- add_sock(sock, con);
- result = 0;
- }
- else {
- result = -EADDRINUSE;
- }
+ e = new_writequeue_entry(con);
+ if (!e)
+ goto out;
- return result;
-}
+ kref_get(&e->ref);
+ *ppc = page_address(e->page);
+ e->end += len;
+ atomic_inc(&con->writequeue_cnt);
+ if (cb)
+ cb(data);
+ list_add_tail(&e->list, &con->writequeue);
+out:
+ spin_unlock(&con->writequeue_lock);
+ return e;
+};
-static struct writequeue_entry *new_writequeue_entry(struct connection *con,
- gfp_t allocation)
+static struct dlm_msg *dlm_lowcomms_new_msg_con(struct connection *con, int len,
+ gfp_t allocation, char **ppc,
+ void (*cb)(void *data),
+ void *data)
{
- struct writequeue_entry *entry;
+ struct writequeue_entry *e;
+ struct dlm_msg *msg;
- entry = kmalloc(sizeof(struct writequeue_entry), allocation);
- if (!entry)
+ msg = dlm_allocate_msg(allocation);
+ if (!msg)
return NULL;
- entry->page = alloc_page(allocation);
- if (!entry->page) {
- kfree(entry);
+ kref_init(&msg->ref);
+
+ e = new_wq_entry(con, len, ppc, cb, data);
+ if (!e) {
+ dlm_free_msg(msg);
return NULL;
}
- entry->offset = 0;
- entry->len = 0;
- entry->end = 0;
- entry->users = 0;
- entry->con = con;
+ msg->retransmit = false;
+ msg->orig_msg = NULL;
+ msg->ppc = *ppc;
+ msg->len = len;
+ msg->entry = e;
- return entry;
+ return msg;
}
-void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc)
+/* avoid false positive for nodes_srcu, unlock happens in
+ * dlm_lowcomms_commit_msg which is a must call if success
+ */
+#ifndef __CHECKER__
+struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation,
+ char **ppc, void (*cb)(void *data),
+ void *data)
{
struct connection *con;
- struct writequeue_entry *e;
- int offset = 0;
+ struct dlm_msg *msg;
+ int idx;
+
+ if (len > DLM_MAX_SOCKET_BUFSIZE ||
+ len < sizeof(struct dlm_header)) {
+ BUILD_BUG_ON(PAGE_SIZE < DLM_MAX_SOCKET_BUFSIZE);
+ log_print("failed to allocate a buffer of size %d", len);
+ WARN_ON(1);
+ return NULL;
+ }
+ idx = srcu_read_lock(&connections_srcu);
con = nodeid2con(nodeid, allocation);
- if (!con)
+ if (!con) {
+ srcu_read_unlock(&connections_srcu, idx);
return NULL;
-
- spin_lock(&con->writequeue_lock);
- e = list_entry(con->writequeue.prev, struct writequeue_entry, list);
- if ((&e->list == &con->writequeue) ||
- (PAGE_SIZE - e->end < len)) {
- e = NULL;
- } else {
- offset = e->end;
- e->end += len;
- e->users++;
}
- spin_unlock(&con->writequeue_lock);
- if (e) {
- got_one:
- *ppc = page_address(e->page) + offset;
- return e;
+ msg = dlm_lowcomms_new_msg_con(con, len, allocation, ppc, cb, data);
+ if (!msg) {
+ srcu_read_unlock(&connections_srcu, idx);
+ return NULL;
}
- e = new_writequeue_entry(con, allocation);
- if (e) {
- spin_lock(&con->writequeue_lock);
- offset = e->end;
- e->end += len;
- e->users++;
- list_add_tail(&e->list, &con->writequeue);
- spin_unlock(&con->writequeue_lock);
- goto got_one;
- }
- return NULL;
+ /* for dlm_lowcomms_commit_msg() */
+ kref_get(&msg->ref);
+ /* we assume if successful commit must called */
+ msg->idx = idx;
+ return msg;
}
+#endif
-void dlm_lowcomms_commit_buffer(void *mh)
+static void _dlm_lowcomms_commit_msg(struct dlm_msg *msg)
{
- struct writequeue_entry *e = (struct writequeue_entry *)mh;
+ struct writequeue_entry *e = msg->entry;
struct connection *con = e->con;
int users;
spin_lock(&con->writequeue_lock);
+ kref_get(&msg->ref);
+ list_add(&msg->list, &e->msgs);
+
users = --e->users;
if (users)
goto out;
- e->len = e->end - e->offset;
+
+ e->len = DLM_WQ_LENGTH_BYTES(e);
spin_unlock(&con->writequeue_lock);
queue_work(send_workqueue, &con->swork);
@@ -1482,13 +1369,55 @@ out:
return;
}
+/* avoid false positive for nodes_srcu, lock was happen in
+ * dlm_lowcomms_new_msg
+ */
+#ifndef __CHECKER__
+void dlm_lowcomms_commit_msg(struct dlm_msg *msg)
+{
+ _dlm_lowcomms_commit_msg(msg);
+ srcu_read_unlock(&connections_srcu, msg->idx);
+ /* because dlm_lowcomms_new_msg() */
+ kref_put(&msg->ref, dlm_msg_release);
+}
+#endif
+
+void dlm_lowcomms_put_msg(struct dlm_msg *msg)
+{
+ kref_put(&msg->ref, dlm_msg_release);
+}
+
+/* does not held connections_srcu, usage workqueue only */
+int dlm_lowcomms_resend_msg(struct dlm_msg *msg)
+{
+ struct dlm_msg *msg_resend;
+ char *ppc;
+
+ if (msg->retransmit)
+ return 1;
+
+ msg_resend = dlm_lowcomms_new_msg_con(msg->entry->con, msg->len,
+ GFP_ATOMIC, &ppc, NULL, NULL);
+ if (!msg_resend)
+ return -ENOMEM;
+
+ msg->retransmit = true;
+ kref_get(&msg->ref);
+ msg_resend->orig_msg = msg;
+
+ memcpy(ppc, msg->ppc, msg->len);
+ _dlm_lowcomms_commit_msg(msg_resend);
+ dlm_lowcomms_put_msg(msg_resend);
+
+ return 0;
+}
+
/* Send a message */
static void send_to_sock(struct connection *con)
{
- int ret = 0;
const int msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
struct writequeue_entry *e;
- int len, offset;
+ int len, offset, ret;
int count = 0;
mutex_lock(&con->sock_mutex);
@@ -1497,9 +1426,8 @@ static void send_to_sock(struct connection *con)
spin_lock(&con->writequeue_lock);
for (;;) {
- e = list_entry(con->writequeue.next, struct writequeue_entry,
- list);
- if ((struct list_head *) e == &con->writequeue)
+ e = con_next_wq(con);
+ if (!e)
break;
len = e->len;
@@ -1507,25 +1435,23 @@ static void send_to_sock(struct connection *con)
BUG_ON(len == 0 && e->users == 0);
spin_unlock(&con->writequeue_lock);
- ret = 0;
- if (len) {
- ret = kernel_sendpage(con->sock, e->page, offset, len,
- msg_flags);
- if (ret == -EAGAIN || ret == 0) {
- if (ret == -EAGAIN &&
- test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) &&
- !test_and_set_bit(CF_APP_LIMITED, &con->flags)) {
- /* Notify TCP that we're limited by the
- * application window size.
- */
- set_bit(SOCK_NOSPACE, &con->sock->flags);
- con->sock->sk->sk_write_pending++;
- }
- cond_resched();
- goto out;
- } else if (ret < 0)
- goto send_error;
- }
+ ret = kernel_sendpage(con->sock, e->page, offset, len,
+ msg_flags);
+ trace_dlm_send(con->nodeid, ret);
+ if (ret == -EAGAIN || ret == 0) {
+ if (ret == -EAGAIN &&
+ test_bit(SOCKWQ_ASYNC_NOSPACE, &con->sock->flags) &&
+ !test_and_set_bit(CF_APP_LIMITED, &con->flags)) {
+ /* Notify TCP that we're limited by the
+ * application window size.
+ */
+ set_bit(SOCK_NOSPACE, &con->sock->flags);
+ con->sock->sk->sk_write_pending++;
+ }
+ cond_resched();
+ goto out;
+ } else if (ret < 0)
+ goto out;
/* Don't starve people filling buffers */
if (++count >= MAX_SEND_MSG_COUNT) {
@@ -1537,16 +1463,23 @@ static void send_to_sock(struct connection *con)
writequeue_entry_complete(e, ret);
}
spin_unlock(&con->writequeue_lock);
-out:
- mutex_unlock(&con->sock_mutex);
+
+ /* close if we got EOF */
+ if (test_and_clear_bit(CF_EOF, &con->flags)) {
+ mutex_unlock(&con->sock_mutex);
+ close_connection(con, false, false, true);
+
+ /* handling for tcp shutdown */
+ clear_bit(CF_SHUTDOWN, &con->flags);
+ wake_up(&con->shutdown_wait);
+ } else {
+ mutex_unlock(&con->sock_mutex);
+ }
+
return;
-send_error:
+out:
mutex_unlock(&con->sock_mutex);
- close_connection(con, true, false, true);
- /* Requeue the send work. When the work daemon runs again, it will try
- a new connection, then call this function again. */
- queue_work(send_workqueue, &con->swork);
return;
out_connect:
@@ -1561,7 +1494,6 @@ static void clean_one_writequeue(struct connection *con)
spin_lock(&con->writequeue_lock);
list_for_each_entry_safe(e, safe, &con->writequeue, list) {
- list_del(&e->list);
free_entry(e);
}
spin_unlock(&con->writequeue_lock);
@@ -1573,14 +1505,19 @@ int dlm_lowcomms_close(int nodeid)
{
struct connection *con;
struct dlm_node_addr *na;
+ int idx;
log_print("closing connection to node %d", nodeid);
+ idx = srcu_read_lock(&connections_srcu);
con = nodeid2con(nodeid, 0);
if (con) {
set_bit(CF_CLOSE, &con->flags);
close_connection(con, true, true, true);
clean_one_writequeue(con);
+ if (con->othercon)
+ clean_one_writequeue(con->othercon);
}
+ srcu_read_unlock(&connections_srcu, idx);
spin_lock(&dlm_node_addrs_spin);
na = find_node_addr(nodeid);
@@ -1599,12 +1536,82 @@ int dlm_lowcomms_close(int nodeid)
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);
+ receive_from_sock(con);
+}
+
+static void process_listen_recv_socket(struct work_struct *work)
+{
+ accept_from_sock(&listen_con);
+}
+
+static void dlm_connect(struct connection *con)
+{
+ struct sockaddr_storage addr;
+ int result, addr_len;
+ struct socket *sock;
+ unsigned int mark;
+
+ /* Some odd races can cause double-connects, ignore them */
+ if (con->retries++ > MAX_CONNECT_RETRIES)
+ return;
+
+ if (con->sock) {
+ log_print("node %d already connected.", con->nodeid);
+ return;
+ }
+
+ memset(&addr, 0, sizeof(addr));
+ result = nodeid_to_addr(con->nodeid, &addr, NULL,
+ dlm_proto_ops->try_new_addr, &mark);
+ if (result < 0) {
+ log_print("no address for nodeid %d", con->nodeid);
+ return;
+ }
+
+ /* Create a socket to communicate with */
+ result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
+ SOCK_STREAM, dlm_proto_ops->proto, &sock);
+ if (result < 0)
+ goto socket_err;
+
+ sock_set_mark(sock->sk, mark);
+ dlm_proto_ops->sockopts(sock);
+
+ add_sock(sock, con);
+
+ result = dlm_proto_ops->bind(sock);
+ if (result < 0)
+ goto add_sock_err;
+
+ log_print_ratelimited("connecting to %d", con->nodeid);
+ make_sockaddr(&addr, dlm_config.ci_tcp_port, &addr_len);
+ result = dlm_proto_ops->connect(con, sock, (struct sockaddr *)&addr,
+ addr_len);
+ if (result < 0)
+ goto add_sock_err;
+
+ return;
+
+add_sock_err:
+ dlm_close_sock(&con->sock);
+
+socket_err:
+ /*
+ * 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) {
+ log_print("connect %d try %d error %d", con->nodeid,
+ con->retries, result);
+ msleep(1000);
+ lowcomms_connect_sock(con);
+ }
}
/* Send workqueue function */
@@ -1612,48 +1619,87 @@ static void process_send_sockets(struct work_struct *work)
{
struct connection *con = container_of(work, struct connection, swork);
+ WARN_ON(test_bit(CF_IS_OTHERCON, &con->flags));
+
clear_bit(CF_WRITE_PENDING, &con->flags);
- if (con->sock == NULL) /* not mutex protected so check it inside too */
- con->connect_action(con);
- if (!list_empty(&con->writequeue))
- send_to_sock(con);
-}
+ if (test_and_clear_bit(CF_RECONNECT, &con->flags)) {
+ close_connection(con, false, false, true);
+ dlm_midcomms_unack_msg_resend(con->nodeid);
+ }
-/* Discard all entries on the write queues */
-static void clean_writequeues(void)
-{
- foreach_conn(clean_one_writequeue);
+ if (con->sock == NULL) {
+ if (test_and_clear_bit(CF_DELAY_CONNECT, &con->flags))
+ msleep(1000);
+
+ mutex_lock(&con->sock_mutex);
+ dlm_connect(con);
+ mutex_unlock(&con->sock_mutex);
+ }
+
+ if (!list_empty(&con->writequeue))
+ send_to_sock(con);
}
static void work_stop(void)
{
- if (recv_workqueue)
+ if (recv_workqueue) {
destroy_workqueue(recv_workqueue);
- if (send_workqueue)
+ recv_workqueue = NULL;
+ }
+
+ if (send_workqueue) {
destroy_workqueue(send_workqueue);
+ send_workqueue = NULL;
+ }
}
static int work_start(void)
{
- recv_workqueue = alloc_workqueue("dlm_recv",
- WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
+ recv_workqueue = alloc_ordered_workqueue("dlm_recv", WQ_MEM_RECLAIM);
if (!recv_workqueue) {
log_print("can't start dlm_recv");
return -ENOMEM;
}
- send_workqueue = alloc_workqueue("dlm_send",
- WQ_UNBOUND | WQ_MEM_RECLAIM, 1);
+ send_workqueue = alloc_ordered_workqueue("dlm_send", WQ_MEM_RECLAIM);
if (!send_workqueue) {
log_print("can't start dlm_send");
destroy_workqueue(recv_workqueue);
+ recv_workqueue = NULL;
return -ENOMEM;
}
return 0;
}
+static void shutdown_conn(struct connection *con)
+{
+ if (dlm_proto_ops->shutdown_action)
+ dlm_proto_ops->shutdown_action(con);
+}
+
+void dlm_lowcomms_shutdown(void)
+{
+ int idx;
+
+ /* Set all the flags to prevent any
+ * socket activity.
+ */
+ dlm_allow_conn = 0;
+
+ if (recv_workqueue)
+ flush_workqueue(recv_workqueue);
+ if (send_workqueue)
+ flush_workqueue(send_workqueue);
+
+ dlm_close_sock(&listen_con.sock);
+
+ idx = srcu_read_lock(&connections_srcu);
+ foreach_conn(shutdown_conn);
+ srcu_read_unlock(&connections_srcu, idx);
+}
+
static void _stop_conn(struct connection *con, bool and_other)
{
mutex_lock(&con->sock_mutex);
@@ -1661,9 +1707,9 @@ static void _stop_conn(struct connection *con, bool and_other)
set_bit(CF_READ_PENDING, &con->flags);
set_bit(CF_WRITE_PENDING, &con->flags);
if (con->sock && con->sock->sk) {
- write_lock_bh(&con->sock->sk->sk_callback_lock);
+ lock_sock(con->sock->sk);
con->sock->sk->sk_user_data = NULL;
- write_unlock_bh(&con->sock->sk->sk_callback_lock);
+ release_sock(con->sock->sk);
}
if (con->othercon && and_other)
_stop_conn(con->othercon, false);
@@ -1675,26 +1721,35 @@ static void stop_conn(struct connection *con)
_stop_conn(con, true);
}
+static void connection_release(struct rcu_head *rcu)
+{
+ struct connection *con = container_of(rcu, struct connection, rcu);
+
+ kfree(con->rx_buf);
+ kfree(con);
+}
+
static void free_conn(struct connection *con)
{
close_connection(con, true, true, true);
- if (con->othercon)
- kmem_cache_free(con_cache, con->othercon);
- hlist_del(&con->list);
- kmem_cache_free(con_cache, con);
+ spin_lock(&connections_lock);
+ hlist_del_rcu(&con->list);
+ spin_unlock(&connections_lock);
+ if (con->othercon) {
+ clean_one_writequeue(con->othercon);
+ call_srcu(&connections_srcu, &con->othercon->rcu,
+ connection_release);
+ }
+ clean_one_writequeue(con);
+ call_srcu(&connections_srcu, &con->rcu, connection_release);
}
static void work_flush(void)
{
int ok;
int i;
- struct hlist_node *n;
struct connection *con;
- if (recv_workqueue)
- flush_workqueue(recv_workqueue);
- if (send_workqueue)
- flush_workqueue(send_workqueue);
do {
ok = 1;
foreach_conn(stop_conn);
@@ -1703,8 +1758,8 @@ static void work_flush(void)
if (send_workqueue)
flush_workqueue(send_workqueue);
for (i = 0; i < CONN_HASH_SIZE && ok; i++) {
- hlist_for_each_entry_safe(con, n,
- &connection_hash[i], list) {
+ hlist_for_each_entry_rcu(con, &connection_hash[i],
+ list) {
ok &= test_bit(CF_READ_PENDING, &con->flags);
ok &= test_bit(CF_WRITE_PENDING, &con->flags);
if (con->othercon) {
@@ -1720,24 +1775,209 @@ static void work_flush(void)
void dlm_lowcomms_stop(void)
{
- /* Set all the flags to prevent any
- socket activity.
- */
- mutex_lock(&connections_lock);
- dlm_allow_conn = 0;
- mutex_unlock(&connections_lock);
+ int idx;
+
+ idx = srcu_read_lock(&connections_srcu);
work_flush();
- clean_writequeues();
foreach_conn(free_conn);
+ srcu_read_unlock(&connections_srcu, idx);
work_stop();
+ deinit_local();
+
+ dlm_proto_ops = NULL;
+}
+
+static int dlm_listen_for_all(void)
+{
+ struct socket *sock;
+ int result;
+
+ log_print("Using %s for communications",
+ dlm_proto_ops->name);
+
+ result = dlm_proto_ops->listen_validate();
+ if (result < 0)
+ return result;
+
+ result = sock_create_kern(&init_net, dlm_local_addr[0]->ss_family,
+ SOCK_STREAM, dlm_proto_ops->proto, &sock);
+ if (result < 0) {
+ log_print("Can't create comms socket: %d", result);
+ return result;
+ }
+
+ sock_set_mark(sock->sk, dlm_config.ci_mark);
+ dlm_proto_ops->listen_sockopts(sock);
+
+ result = dlm_proto_ops->listen_bind(sock);
+ if (result < 0)
+ goto out;
+
+ save_listen_callbacks(sock);
+ add_listen_sock(sock, &listen_con);
+
+ INIT_WORK(&listen_con.rwork, process_listen_recv_socket);
+ result = sock->ops->listen(sock, 5);
+ if (result < 0) {
+ dlm_close_sock(&listen_con.sock);
+ goto out;
+ }
+
+ return 0;
- kmem_cache_destroy(con_cache);
+out:
+ sock_release(sock);
+ return result;
+}
+
+static int dlm_tcp_bind(struct socket *sock)
+{
+ struct sockaddr_storage src_addr;
+ int result, addr_len;
+
+ /* Bind to our cluster-known address connecting to avoid
+ * routing problems.
+ */
+ memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr));
+ make_sockaddr(&src_addr, 0, &addr_len);
+
+ result = sock->ops->bind(sock, (struct sockaddr *)&src_addr,
+ addr_len);
+ if (result < 0) {
+ /* This *may* not indicate a critical error */
+ log_print("could not bind for connect: %d", result);
+ }
+
+ return 0;
+}
+
+static int dlm_tcp_connect(struct connection *con, struct socket *sock,
+ struct sockaddr *addr, int addr_len)
+{
+ int ret;
+
+ ret = sock->ops->connect(sock, addr, addr_len, O_NONBLOCK);
+ switch (ret) {
+ case -EINPROGRESS:
+ fallthrough;
+ case 0:
+ return 0;
+ }
+
+ return ret;
+}
+
+static int dlm_tcp_listen_validate(void)
+{
+ /* We don't support multi-homed hosts */
+ if (dlm_local_count > 1) {
+ log_print("TCP protocol can't handle multi-homed hosts, try SCTP");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static void dlm_tcp_sockopts(struct socket *sock)
+{
+ /* Turn off Nagle's algorithm */
+ tcp_sock_set_nodelay(sock->sk);
}
+static void dlm_tcp_listen_sockopts(struct socket *sock)
+{
+ dlm_tcp_sockopts(sock);
+ sock_set_reuseaddr(sock->sk);
+}
+
+static int dlm_tcp_listen_bind(struct socket *sock)
+{
+ int addr_len;
+
+ /* Bind to our port */
+ make_sockaddr(dlm_local_addr[0], dlm_config.ci_tcp_port, &addr_len);
+ return sock->ops->bind(sock, (struct sockaddr *)dlm_local_addr[0],
+ addr_len);
+}
+
+static const struct dlm_proto_ops dlm_tcp_ops = {
+ .name = "TCP",
+ .proto = IPPROTO_TCP,
+ .connect = dlm_tcp_connect,
+ .sockopts = dlm_tcp_sockopts,
+ .bind = dlm_tcp_bind,
+ .listen_validate = dlm_tcp_listen_validate,
+ .listen_sockopts = dlm_tcp_listen_sockopts,
+ .listen_bind = dlm_tcp_listen_bind,
+ .shutdown_action = dlm_tcp_shutdown,
+ .eof_condition = tcp_eof_condition,
+};
+
+static int dlm_sctp_bind(struct socket *sock)
+{
+ return sctp_bind_addrs(sock, 0);
+}
+
+static int dlm_sctp_connect(struct connection *con, struct socket *sock,
+ struct sockaddr *addr, int addr_len)
+{
+ int ret;
+
+ /*
+ * Make sock->ops->connect() function return in specified time,
+ * since O_NONBLOCK argument in connect() function does not work here,
+ * then, we should restore the default value of this attribute.
+ */
+ sock_set_sndtimeo(sock->sk, 5);
+ ret = sock->ops->connect(sock, addr, addr_len, 0);
+ sock_set_sndtimeo(sock->sk, 0);
+ if (ret < 0)
+ return ret;
+
+ if (!test_and_set_bit(CF_CONNECTED, &con->flags))
+ log_print("connected to node %d", con->nodeid);
+
+ return 0;
+}
+
+static int dlm_sctp_listen_validate(void)
+{
+ if (!IS_ENABLED(CONFIG_IP_SCTP)) {
+ log_print("SCTP is not enabled by this kernel");
+ return -EOPNOTSUPP;
+ }
+
+ request_module("sctp");
+ return 0;
+}
+
+static int dlm_sctp_bind_listen(struct socket *sock)
+{
+ return sctp_bind_addrs(sock, dlm_config.ci_tcp_port);
+}
+
+static void dlm_sctp_sockopts(struct socket *sock)
+{
+ /* Turn off Nagle's algorithm */
+ sctp_sock_set_nodelay(sock->sk);
+ sock_set_rcvbuf(sock->sk, NEEDED_RMEM);
+}
+
+static const struct dlm_proto_ops dlm_sctp_ops = {
+ .name = "SCTP",
+ .proto = IPPROTO_SCTP,
+ .try_new_addr = true,
+ .connect = dlm_sctp_connect,
+ .sockopts = dlm_sctp_sockopts,
+ .bind = dlm_sctp_bind,
+ .listen_validate = dlm_sctp_listen_validate,
+ .listen_sockopts = dlm_sctp_sockopts,
+ .listen_bind = dlm_sctp_bind_listen,
+};
+
int dlm_lowcomms_start(void)
{
int error = -EINVAL;
- struct connection *con;
int i;
for (i = 0; i < CONN_HASH_SIZE; i++)
@@ -1750,38 +1990,43 @@ int dlm_lowcomms_start(void)
goto fail;
}
- error = -ENOMEM;
- con_cache = kmem_cache_create("dlm_conn", sizeof(struct connection),
- __alignof__(struct connection), 0,
- NULL);
- if (!con_cache)
- goto fail;
+ INIT_WORK(&listen_con.rwork, process_listen_recv_socket);
error = work_start();
if (error)
- goto fail_destroy;
+ goto fail_local;
dlm_allow_conn = 1;
/* Start listening */
- if (dlm_config.ci_protocol == 0)
- error = tcp_listen_for_all();
- else
- error = sctp_listen_for_all();
+ switch (dlm_config.ci_protocol) {
+ case DLM_PROTO_TCP:
+ dlm_proto_ops = &dlm_tcp_ops;
+ break;
+ case DLM_PROTO_SCTP:
+ dlm_proto_ops = &dlm_sctp_ops;
+ break;
+ default:
+ log_print("Invalid protocol identifier %d set",
+ dlm_config.ci_protocol);
+ error = -EINVAL;
+ goto fail_proto_ops;
+ }
+
+ error = dlm_listen_for_all();
if (error)
- goto fail_unlisten;
+ goto fail_listen;
return 0;
-fail_unlisten:
+fail_listen:
+ dlm_proto_ops = NULL;
+fail_proto_ops:
dlm_allow_conn = 0;
- con = nodeid2con(0,0);
- if (con) {
- close_connection(con, false, true, true);
- kmem_cache_free(con_cache, con);
- }
-fail_destroy:
- kmem_cache_destroy(con_cache);
+ dlm_close_sock(&listen_con.sock);
+ work_stop();
+fail_local:
+ deinit_local();
fail:
return error;
}
diff --git a/fs/dlm/lowcomms.h b/fs/dlm/lowcomms.h
index 687b2894e469..29369feea991 100644
--- a/fs/dlm/lowcomms.h
+++ b/fs/dlm/lowcomms.h
@@ -12,14 +12,43 @@
#ifndef __LOWCOMMS_DOT_H__
#define __LOWCOMMS_DOT_H__
+#include "dlm_internal.h"
+
+#define DLM_MIDCOMMS_OPT_LEN sizeof(struct dlm_opts)
+#define DLM_MAX_APP_BUFSIZE (DLM_MAX_SOCKET_BUFSIZE - \
+ DLM_MIDCOMMS_OPT_LEN)
+
+#define CONN_HASH_SIZE 32
+
+/* This is deliberately very simple because most clusters have simple
+ * sequential nodeids, so we should be able to go straight to a connection
+ * struct in the array
+ */
+static inline int nodeid_hash(int nodeid)
+{
+ return nodeid & (CONN_HASH_SIZE-1);
+}
+
+/* switch to check if dlm is running */
+extern int dlm_allow_conn;
+
int dlm_lowcomms_start(void);
+void dlm_lowcomms_shutdown(void);
void dlm_lowcomms_stop(void);
void dlm_lowcomms_exit(void);
int dlm_lowcomms_close(int nodeid);
-void *dlm_lowcomms_get_buffer(int nodeid, int len, gfp_t allocation, char **ppc);
-void dlm_lowcomms_commit_buffer(void *mh);
+struct dlm_msg *dlm_lowcomms_new_msg(int nodeid, int len, gfp_t allocation,
+ char **ppc, void (*cb)(void *data),
+ void *data);
+void dlm_lowcomms_commit_msg(struct dlm_msg *msg);
+void dlm_lowcomms_put_msg(struct dlm_msg *msg);
+int dlm_lowcomms_resend_msg(struct dlm_msg *msg);
int dlm_lowcomms_connect_node(int nodeid);
+int dlm_lowcomms_nodes_set_mark(int nodeid, unsigned int mark);
int dlm_lowcomms_addr(int nodeid, struct sockaddr_storage *addr, int len);
+void dlm_midcomms_receive_done(int nodeid);
+struct kmem_cache *dlm_lowcomms_writequeue_cache_create(void);
+struct kmem_cache *dlm_lowcomms_msg_cache_create(void);
#endif /* __LOWCOMMS_DOT_H__ */
diff --git a/fs/dlm/main.c b/fs/dlm/main.c
index afc66a1346d3..1c5be4b70ac1 100644
--- a/fs/dlm/main.c
+++ b/fs/dlm/main.c
@@ -19,6 +19,9 @@
#include "config.h"
#include "lowcomms.h"
+#define CREATE_TRACE_POINTS
+#include <trace/events/dlm.h>
+
static int __init init_dlm(void)
{
int error;
diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index 7ad83deb4505..2af2ccfe43a9 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -15,11 +15,12 @@
#include "recover.h"
#include "rcom.h"
#include "config.h"
+#include "midcomms.h"
#include "lowcomms.h"
int dlm_slots_version(struct dlm_header *h)
{
- if ((h->h_version & 0x0000FFFF) < DLM_HEADER_SLOTS)
+ if ((le32_to_cpu(h->h_version) & 0x0000FFFF) < DLM_HEADER_SLOTS)
return 0;
return 1;
}
@@ -119,18 +120,13 @@ int dlm_slots_copy_in(struct dlm_ls *ls)
ro0 = (struct rcom_slot *)(rc->rc_buf + sizeof(struct rcom_config));
- for (i = 0, ro = ro0; i < num_slots; i++, ro++) {
- ro->ro_nodeid = le32_to_cpu(ro->ro_nodeid);
- ro->ro_slot = le16_to_cpu(ro->ro_slot);
- }
-
log_slots(ls, gen, num_slots, ro0, NULL, 0);
list_for_each_entry(memb, &ls->ls_nodes, list) {
for (i = 0, ro = ro0; i < num_slots; i++, ro++) {
- if (ro->ro_nodeid != memb->nodeid)
+ if (le32_to_cpu(ro->ro_nodeid) != memb->nodeid)
continue;
- memb->slot = ro->ro_slot;
+ memb->slot = le16_to_cpu(ro->ro_slot);
memb->slot_prev = memb->slot;
break;
}
@@ -270,7 +266,7 @@ int dlm_slots_assign(struct dlm_ls *ls, int *num_slots, int *slots_size,
log_slots(ls, gen, num, NULL, array, array_size);
- max_slots = (dlm_config.ci_buffer_size - sizeof(struct dlm_rcom) -
+ max_slots = (DLM_MAX_APP_BUFSIZE - sizeof(struct dlm_rcom) -
sizeof(struct rcom_config)) / sizeof(struct rcom_slot);
if (num > max_slots) {
@@ -329,6 +325,7 @@ static int dlm_add_member(struct dlm_ls *ls, struct dlm_config_node *node)
memb->nodeid = node->nodeid;
memb->weight = node->weight;
memb->comm_seq = node->comm_seq;
+ dlm_midcomms_add_member(node->nodeid);
add_ordered_member(ls, memb);
ls->ls_num_nodes++;
return 0;
@@ -359,26 +356,34 @@ int dlm_is_removed(struct dlm_ls *ls, int nodeid)
return 0;
}
-static void clear_memb_list(struct list_head *head)
+static void clear_memb_list(struct list_head *head,
+ void (*after_del)(int nodeid))
{
struct dlm_member *memb;
while (!list_empty(head)) {
memb = list_entry(head->next, struct dlm_member, list);
list_del(&memb->list);
+ if (after_del)
+ after_del(memb->nodeid);
kfree(memb);
}
}
+static void clear_members_cb(int nodeid)
+{
+ dlm_midcomms_remove_member(nodeid);
+}
+
void dlm_clear_members(struct dlm_ls *ls)
{
- clear_memb_list(&ls->ls_nodes);
+ clear_memb_list(&ls->ls_nodes, clear_members_cb);
ls->ls_num_nodes = 0;
}
void dlm_clear_members_gone(struct dlm_ls *ls)
{
- clear_memb_list(&ls->ls_nodes_gone);
+ clear_memb_list(&ls->ls_nodes_gone, NULL);
}
static void make_member_array(struct dlm_ls *ls)
@@ -432,9 +437,10 @@ static int ping_members(struct dlm_ls *ls)
int error = 0;
list_for_each_entry(memb, &ls->ls_nodes, list) {
- error = dlm_recovery_stopped(ls);
- if (error)
+ if (dlm_recovery_stopped(ls)) {
+ error = -EINTR;
break;
+ }
error = dlm_rcom_status(ls, memb->nodeid, 0);
if (error)
break;
@@ -528,7 +534,11 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
int i, error, neg = 0, low = -1;
/* previously removed members that we've not finished removing need to
- count as a negative change so the "neg" recovery steps will happen */
+ * count as a negative change so the "neg" recovery steps will happen
+ *
+ * This functionality must report all member changes to lsops or
+ * midcomms layer and must never return before.
+ */
list_for_each_entry(memb, &ls->ls_nodes_gone, list) {
log_rinfo(ls, "prev removed member %d", memb->nodeid);
@@ -552,6 +562,7 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
neg++;
list_move(&memb->list, &ls->ls_nodes_gone);
+ dlm_midcomms_remove_member(memb->nodeid);
ls->ls_num_nodes--;
dlm_lsop_recover_slot(ls, memb);
}
@@ -576,13 +587,6 @@ int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv, int *neg_out)
*neg_out = neg;
error = ping_members(ls);
- if (!error || error == -EPROTO) {
- /* new_lockspace() may be waiting to know if the config
- is good or bad */
- ls->ls_members_result = error;
- complete(&ls->ls_members_done);
- }
-
log_rinfo(ls, "dlm_recover_members %d nodes", ls->ls_num_nodes);
return error;
}
@@ -662,7 +666,16 @@ int dlm_ls_stop(struct dlm_ls *ls)
if (!ls->ls_recover_begin)
ls->ls_recover_begin = jiffies;
- dlm_lsop_recover_prep(ls);
+ /* call recover_prep ops only once and not multiple times
+ * for each possible dlm_ls_stop() when recovery is already
+ * stopped.
+ *
+ * If we successful was able to clear LSFL_RUNNING bit and
+ * it was set we know it is the first dlm_ls_stop() call.
+ */
+ if (new)
+ dlm_lsop_recover_prep(ls);
+
return 0;
}
diff --git a/fs/dlm/memory.c b/fs/dlm/memory.c
index 5918f4d39586..ce35c3c19aeb 100644
--- a/fs/dlm/memory.c
+++ b/fs/dlm/memory.c
@@ -10,32 +10,61 @@
******************************************************************************/
#include "dlm_internal.h"
+#include "midcomms.h"
+#include "lowcomms.h"
#include "config.h"
#include "memory.h"
+static struct kmem_cache *writequeue_cache;
+static struct kmem_cache *mhandle_cache;
+static struct kmem_cache *msg_cache;
static struct kmem_cache *lkb_cache;
static struct kmem_cache *rsb_cache;
int __init dlm_memory_init(void)
{
+ writequeue_cache = dlm_lowcomms_writequeue_cache_create();
+ if (!writequeue_cache)
+ goto out;
+
+ mhandle_cache = dlm_midcomms_cache_create();
+ if (!mhandle_cache)
+ goto mhandle;
+
lkb_cache = kmem_cache_create("dlm_lkb", sizeof(struct dlm_lkb),
__alignof__(struct dlm_lkb), 0, NULL);
if (!lkb_cache)
- return -ENOMEM;
+ goto lkb;
+
+ msg_cache = dlm_lowcomms_msg_cache_create();
+ if (!msg_cache)
+ goto msg;
rsb_cache = kmem_cache_create("dlm_rsb", sizeof(struct dlm_rsb),
__alignof__(struct dlm_rsb), 0, NULL);
- if (!rsb_cache) {
- kmem_cache_destroy(lkb_cache);
- return -ENOMEM;
- }
+ if (!rsb_cache)
+ goto rsb;
return 0;
+
+rsb:
+ kmem_cache_destroy(msg_cache);
+msg:
+ kmem_cache_destroy(lkb_cache);
+lkb:
+ kmem_cache_destroy(mhandle_cache);
+mhandle:
+ kmem_cache_destroy(writequeue_cache);
+out:
+ return -ENOMEM;
}
void dlm_memory_exit(void)
{
+ kmem_cache_destroy(writequeue_cache);
+ kmem_cache_destroy(mhandle_cache);
+ kmem_cache_destroy(msg_cache);
kmem_cache_destroy(lkb_cache);
kmem_cache_destroy(rsb_cache);
}
@@ -89,3 +118,32 @@ void dlm_free_lkb(struct dlm_lkb *lkb)
kmem_cache_free(lkb_cache, lkb);
}
+struct dlm_mhandle *dlm_allocate_mhandle(void)
+{
+ return kmem_cache_alloc(mhandle_cache, GFP_NOFS);
+}
+
+void dlm_free_mhandle(struct dlm_mhandle *mhandle)
+{
+ kmem_cache_free(mhandle_cache, mhandle);
+}
+
+struct writequeue_entry *dlm_allocate_writequeue(void)
+{
+ return kmem_cache_alloc(writequeue_cache, GFP_ATOMIC);
+}
+
+void dlm_free_writequeue(struct writequeue_entry *writequeue)
+{
+ kmem_cache_free(writequeue_cache, writequeue);
+}
+
+struct dlm_msg *dlm_allocate_msg(gfp_t allocation)
+{
+ return kmem_cache_alloc(msg_cache, allocation);
+}
+
+void dlm_free_msg(struct dlm_msg *msg)
+{
+ kmem_cache_free(msg_cache, msg);
+}
diff --git a/fs/dlm/memory.h b/fs/dlm/memory.h
index 4f218ea4b187..7bd3f1a391ca 100644
--- a/fs/dlm/memory.h
+++ b/fs/dlm/memory.h
@@ -20,6 +20,12 @@ struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls);
void dlm_free_lkb(struct dlm_lkb *l);
char *dlm_allocate_lvb(struct dlm_ls *ls);
void dlm_free_lvb(char *l);
+struct dlm_mhandle *dlm_allocate_mhandle(void);
+void dlm_free_mhandle(struct dlm_mhandle *mhandle);
+struct writequeue_entry *dlm_allocate_writequeue(void);
+void dlm_free_writequeue(struct writequeue_entry *writequeue);
+struct dlm_msg *dlm_allocate_msg(gfp_t allocation);
+void dlm_free_msg(struct dlm_msg *msg);
#endif /* __MEMORY_DOT_H__ */
diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c
index 921322d133e3..6489bc22ad61 100644
--- a/fs/dlm/midcomms.c
+++ b/fs/dlm/midcomms.c
@@ -3,7 +3,7 @@
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2004-2021 Red Hat, Inc. All rights reserved.
**
**
*******************************************************************************
@@ -12,124 +12,1484 @@
/*
* midcomms.c
*
- * This is the appallingly named "mid-level" comms layer.
+ * This is the appallingly named "mid-level" comms layer. It takes care about
+ * deliver an on application layer "reliable" communication above the used
+ * lowcomms transport layer.
*
- * Its purpose is to take packets from the "real" comms layer,
- * split them up into packets and pass them to the interested
- * part of the locking mechanism.
+ * How it works:
*
- * It also takes messages from the locking layer, formats them
- * into packets and sends them to the comms layer.
+ * Each nodes keeps track of all send DLM messages in send_queue with a sequence
+ * number. The receive will send an DLM_ACK message back for every DLM message
+ * received at the other side. If a reconnect happens in lowcomms we will send
+ * all unacknowledged dlm messages again. The receiving side might drop any already
+ * received message by comparing sequence numbers.
+ *
+ * How version detection works:
+ *
+ * Due the fact that dlm has pre-configured node addresses on every side
+ * it is in it's nature that every side connects at starts to transmit
+ * dlm messages which ends in a race. However DLM_RCOM_NAMES, DLM_RCOM_STATUS
+ * and their replies are the first messages which are exchanges. Due backwards
+ * compatibility these messages are not covered by the midcomms re-transmission
+ * layer. These messages have their own re-transmission handling in the dlm
+ * application layer. The version field of every node will be set on these RCOM
+ * messages as soon as they arrived and the node isn't yet part of the nodes
+ * hash. There exists also logic to detect version mismatched if something weird
+ * going on or the first messages isn't an expected one.
+ *
+ * Termination:
+ *
+ * The midcomms layer does a 4 way handshake for termination on DLM protocol
+ * like TCP supports it with half-closed socket support. SCTP doesn't support
+ * half-closed socket, so we do it on DLM layer. Also socket shutdown() can be
+ * interrupted by .e.g. tcp reset itself. Additional there exists the othercon
+ * paradigm in lowcomms which cannot be easily without breaking backwards
+ * compatibility. A node cannot send anything to another node when a DLM_FIN
+ * message was send. There exists additional logic to print a warning if
+ * DLM wants to do it. There exists a state handling like RFC 793 but reduced
+ * to termination only. The event "member removal event" describes the cluster
+ * manager removed the node from internal lists, at this point DLM does not
+ * send any message to the other node. There exists two cases:
+ *
+ * 1. The cluster member was removed and we received a FIN
+ * OR
+ * 2. We received a FIN but the member was not removed yet
+ *
+ * One of these cases will do the CLOSE_WAIT to LAST_ACK change.
+ *
+ *
+ * +---------+
+ * | CLOSED |
+ * +---------+
+ * | add member/receive RCOM version
+ * | detection msg
+ * V
+ * +---------+
+ * | ESTAB |
+ * +---------+
+ * CLOSE | | rcv FIN
+ * ------- | | -------
+ * +---------+ snd FIN / \ snd ACK +---------+
+ * | FIN |<----------------- ------------------>| CLOSE |
+ * | WAIT-1 |------------------ | WAIT |
+ * +---------+ rcv FIN \ +---------+
+ * | rcv ACK of FIN ------- | CLOSE | member
+ * | -------------- snd ACK | ------- | removal
+ * V x V snd FIN V event
+ * +---------+ +---------+ +---------+
+ * |FINWAIT-2| | CLOSING | | LAST-ACK|
+ * +---------+ +---------+ +---------+
+ * | rcv ACK of FIN | rcv ACK of FIN |
+ * | rcv FIN -------------- | -------------- |
+ * | ------- x V x V
+ * \ snd ACK +---------+ +---------+
+ * ------------------------>| CLOSED | | CLOSED |
+ * +---------+ +---------+
+ *
+ * NOTE: any state can interrupted by midcomms_close() and state will be
+ * switched to CLOSED in case of fencing. There exists also some timeout
+ * handling when we receive the version detection RCOM messages which is
+ * made by observation.
+ *
+ * Future improvements:
+ *
+ * There exists some known issues/improvements of the dlm handling. Some
+ * of them should be done in a next major dlm version bump which makes
+ * it incompatible with previous versions.
+ *
+ * Unaligned memory access:
+ *
+ * There exists cases when the dlm message buffer length is not aligned
+ * to 8 byte. However seems nobody detected any problem with it. This
+ * can be fixed in the next major version bump of dlm.
+ *
+ * Version detection:
+ *
+ * The version detection and how it's done is related to backwards
+ * compatibility. There exists better ways to make a better handling.
+ * However this should be changed in the next major version bump of dlm.
+ *
+ * Tail Size checking:
+ *
+ * There exists a message tail payload in e.g. DLM_MSG however we don't
+ * check it against the message length yet regarding to the receive buffer
+ * length. That need to be validated.
+ *
+ * Fencing bad nodes:
+ *
+ * At timeout places or weird sequence number behaviours we should send
+ * a fencing request to the cluster manager.
*/
+/* Debug switch to enable a 5 seconds sleep waiting of a termination.
+ * This can be useful to test fencing while termination is running.
+ * This requires a setup with only gfs2 as dlm user, so that the
+ * last umount will terminate the connection.
+ *
+ * However it became useful to test, while the 5 seconds block in umount
+ * just press the reset button. In a lot of dropping the termination
+ * process can could take several seconds.
+ */
+#define DLM_DEBUG_FENCE_TERMINATION 0
+
+#include <net/tcp.h>
+
#include "dlm_internal.h"
+#include "lockspace.h"
#include "lowcomms.h"
#include "config.h"
+#include "memory.h"
#include "lock.h"
+#include "util.h"
#include "midcomms.h"
+/* init value for sequence numbers for testing purpose only e.g. overflows */
+#define DLM_SEQ_INIT 0
+/* 3 minutes wait to sync ending of dlm */
+#define DLM_SHUTDOWN_TIMEOUT msecs_to_jiffies(3 * 60 * 1000)
+#define DLM_VERSION_NOT_SET 0
+
+struct midcomms_node {
+ int nodeid;
+ uint32_t version;
+ uint32_t seq_send;
+ uint32_t seq_next;
+ /* These queues are unbound because we cannot drop any message in dlm.
+ * We could send a fence signal for a specific node to the cluster
+ * manager if queues hits some maximum value, however this handling
+ * not supported yet.
+ */
+ struct list_head send_queue;
+ spinlock_t send_queue_lock;
+ atomic_t send_queue_cnt;
+#define DLM_NODE_FLAG_CLOSE 1
+#define DLM_NODE_FLAG_STOP_TX 2
+#define DLM_NODE_FLAG_STOP_RX 3
+#define DLM_NODE_ULP_DELIVERED 4
+ unsigned long flags;
+ wait_queue_head_t shutdown_wait;
+
+ /* dlm tcp termination state */
+#define DLM_CLOSED 1
+#define DLM_ESTABLISHED 2
+#define DLM_FIN_WAIT1 3
+#define DLM_FIN_WAIT2 4
+#define DLM_CLOSE_WAIT 5
+#define DLM_LAST_ACK 6
+#define DLM_CLOSING 7
+ int state;
+ spinlock_t state_lock;
-static void copy_from_cb(void *dst, const void *base, unsigned offset,
- unsigned len, unsigned limit)
+ /* counts how many lockspaces are using this node
+ * this refcount is necessary to determine if the
+ * node wants to disconnect.
+ */
+ int users;
+
+ /* not protected by srcu, node_hash lifetime */
+ void *debugfs;
+
+ struct hlist_node hlist;
+ struct rcu_head rcu;
+};
+
+struct dlm_mhandle {
+ const struct dlm_header *inner_hd;
+ struct midcomms_node *node;
+ struct dlm_opts *opts;
+ struct dlm_msg *msg;
+ bool committed;
+ uint32_t seq;
+
+ void (*ack_rcv)(struct midcomms_node *node);
+
+ /* get_mhandle/commit srcu idx exchange */
+ int idx;
+
+ struct list_head list;
+ struct rcu_head rcu;
+};
+
+static struct hlist_head node_hash[CONN_HASH_SIZE];
+static DEFINE_SPINLOCK(nodes_lock);
+DEFINE_STATIC_SRCU(nodes_srcu);
+
+/* This mutex prevents that midcomms_close() is running while
+ * stop() or remove(). As I experienced invalid memory access
+ * behaviours when DLM_DEBUG_FENCE_TERMINATION is enabled and
+ * resetting machines. I will end in some double deletion in nodes
+ * datastructure.
+ */
+static DEFINE_MUTEX(close_lock);
+
+struct kmem_cache *dlm_midcomms_cache_create(void)
{
- unsigned copy = len;
+ return kmem_cache_create("dlm_mhandle", sizeof(struct dlm_mhandle),
+ 0, 0, NULL);
+}
- if ((copy + offset) > limit)
- copy = limit - offset;
- memcpy(dst, base + offset, copy);
- len -= copy;
- if (len)
- memcpy(dst + copy, base, len);
+static inline const char *dlm_state_str(int state)
+{
+ switch (state) {
+ case DLM_CLOSED:
+ return "CLOSED";
+ case DLM_ESTABLISHED:
+ return "ESTABLISHED";
+ case DLM_FIN_WAIT1:
+ return "FIN_WAIT1";
+ case DLM_FIN_WAIT2:
+ return "FIN_WAIT2";
+ case DLM_CLOSE_WAIT:
+ return "CLOSE_WAIT";
+ case DLM_LAST_ACK:
+ return "LAST_ACK";
+ case DLM_CLOSING:
+ return "CLOSING";
+ default:
+ return "UNKNOWN";
+ }
}
-/*
- * Called from the low-level comms layer to process a buffer of
- * commands.
- *
- * Only complete messages are processed here, any "spare" bytes from
- * the end of a buffer are saved and tacked onto the front of the next
- * message that comes in. I doubt this will happen very often but we
- * need to be able to cope with it and I don't want the task to be waiting
- * for packets to come in when there is useful work to be done.
- */
+const char *dlm_midcomms_state(struct midcomms_node *node)
+{
+ return dlm_state_str(node->state);
+}
-int dlm_process_incoming_buffer(int nodeid, const void *base,
- unsigned offset, unsigned len, unsigned limit)
+unsigned long dlm_midcomms_flags(struct midcomms_node *node)
{
- union {
- unsigned char __buf[DLM_INBUF_LEN];
- /* this is to force proper alignment on some arches */
- union dlm_packet p;
- } __tmp;
- union dlm_packet *p = &__tmp.p;
- int ret = 0;
- int err = 0;
- uint16_t msglen;
- uint32_t lockspace;
+ return node->flags;
+}
- while (len > sizeof(struct dlm_header)) {
+int dlm_midcomms_send_queue_cnt(struct midcomms_node *node)
+{
+ return atomic_read(&node->send_queue_cnt);
+}
- /* Copy just the header to check the total length. The
- message may wrap around the end of the buffer back to the
- start, so we need to use a temp buffer and copy_from_cb. */
+uint32_t dlm_midcomms_version(struct midcomms_node *node)
+{
+ return node->version;
+}
- copy_from_cb(p, base, offset, sizeof(struct dlm_header),
- limit);
+static struct midcomms_node *__find_node(int nodeid, int r)
+{
+ struct midcomms_node *node;
- msglen = le16_to_cpu(p->header.h_length);
- lockspace = p->header.h_lockspace;
+ hlist_for_each_entry_rcu(node, &node_hash[r], hlist) {
+ if (node->nodeid == nodeid)
+ return node;
+ }
+
+ return NULL;
+}
+
+static void dlm_mhandle_release(struct rcu_head *rcu)
+{
+ struct dlm_mhandle *mh = container_of(rcu, struct dlm_mhandle, rcu);
+
+ dlm_lowcomms_put_msg(mh->msg);
+ dlm_free_mhandle(mh);
+}
+
+static void dlm_mhandle_delete(struct midcomms_node *node,
+ struct dlm_mhandle *mh)
+{
+ list_del_rcu(&mh->list);
+ atomic_dec(&node->send_queue_cnt);
+ call_rcu(&mh->rcu, dlm_mhandle_release);
+}
+
+static void dlm_send_queue_flush(struct midcomms_node *node)
+{
+ struct dlm_mhandle *mh;
+
+ pr_debug("flush midcomms send queue of node %d\n", node->nodeid);
+
+ rcu_read_lock();
+ spin_lock(&node->send_queue_lock);
+ list_for_each_entry_rcu(mh, &node->send_queue, list) {
+ dlm_mhandle_delete(node, mh);
+ }
+ spin_unlock(&node->send_queue_lock);
+ rcu_read_unlock();
+}
+
+static void midcomms_node_reset(struct midcomms_node *node)
+{
+ pr_debug("reset node %d\n", node->nodeid);
+
+ node->seq_next = DLM_SEQ_INIT;
+ node->seq_send = DLM_SEQ_INIT;
+ node->version = DLM_VERSION_NOT_SET;
+ node->flags = 0;
+
+ dlm_send_queue_flush(node);
+ node->state = DLM_CLOSED;
+ wake_up(&node->shutdown_wait);
+}
+
+static struct midcomms_node *nodeid2node(int nodeid, gfp_t alloc)
+{
+ struct midcomms_node *node, *tmp;
+ int r = nodeid_hash(nodeid);
+
+ node = __find_node(nodeid, r);
+ if (node || !alloc)
+ return node;
+
+ node = kmalloc(sizeof(*node), alloc);
+ if (!node)
+ return NULL;
+
+ node->nodeid = nodeid;
+ spin_lock_init(&node->state_lock);
+ spin_lock_init(&node->send_queue_lock);
+ atomic_set(&node->send_queue_cnt, 0);
+ INIT_LIST_HEAD(&node->send_queue);
+ init_waitqueue_head(&node->shutdown_wait);
+ node->users = 0;
+ midcomms_node_reset(node);
+
+ spin_lock(&nodes_lock);
+ /* check again if there was somebody else
+ * earlier here to add the node
+ */
+ tmp = __find_node(nodeid, r);
+ if (tmp) {
+ spin_unlock(&nodes_lock);
+ kfree(node);
+ return tmp;
+ }
+
+ hlist_add_head_rcu(&node->hlist, &node_hash[r]);
+ spin_unlock(&nodes_lock);
+
+ node->debugfs = dlm_create_debug_comms_file(nodeid, node);
+ return node;
+}
+
+static int dlm_send_ack(int nodeid, uint32_t seq)
+{
+ int mb_len = sizeof(struct dlm_header);
+ struct dlm_header *m_header;
+ struct dlm_msg *msg;
+ char *ppc;
+
+ msg = dlm_lowcomms_new_msg(nodeid, mb_len, GFP_NOFS, &ppc,
+ NULL, NULL);
+ if (!msg)
+ return -ENOMEM;
+
+ m_header = (struct dlm_header *)ppc;
+
+ m_header->h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+ m_header->h_nodeid = cpu_to_le32(dlm_our_nodeid());
+ m_header->h_length = cpu_to_le16(mb_len);
+ m_header->h_cmd = DLM_ACK;
+ m_header->u.h_seq = cpu_to_le32(seq);
+
+ dlm_lowcomms_commit_msg(msg);
+ dlm_lowcomms_put_msg(msg);
+
+ return 0;
+}
+
+static int dlm_send_fin(struct midcomms_node *node,
+ void (*ack_rcv)(struct midcomms_node *node))
+{
+ int mb_len = sizeof(struct dlm_header);
+ struct dlm_header *m_header;
+ struct dlm_mhandle *mh;
+ char *ppc;
+
+ mh = dlm_midcomms_get_mhandle(node->nodeid, mb_len, GFP_NOFS, &ppc);
+ if (!mh)
+ return -ENOMEM;
+
+ mh->ack_rcv = ack_rcv;
- err = -EINVAL;
- if (msglen < sizeof(struct dlm_header))
+ m_header = (struct dlm_header *)ppc;
+
+ m_header->h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+ m_header->h_nodeid = cpu_to_le32(dlm_our_nodeid());
+ m_header->h_length = cpu_to_le16(mb_len);
+ m_header->h_cmd = DLM_FIN;
+
+ pr_debug("sending fin msg to node %d\n", node->nodeid);
+ dlm_midcomms_commit_mhandle(mh);
+ set_bit(DLM_NODE_FLAG_STOP_TX, &node->flags);
+
+ return 0;
+}
+
+static void dlm_receive_ack(struct midcomms_node *node, uint32_t seq)
+{
+ struct dlm_mhandle *mh;
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(mh, &node->send_queue, list) {
+ if (before(mh->seq, seq)) {
+ if (mh->ack_rcv)
+ mh->ack_rcv(node);
+ } else {
+ /* send queue should be ordered */
break;
- if (p->header.h_cmd == DLM_MSG) {
- if (msglen < sizeof(struct dlm_message))
- break;
+ }
+ }
+
+ spin_lock(&node->send_queue_lock);
+ list_for_each_entry_rcu(mh, &node->send_queue, list) {
+ if (before(mh->seq, seq)) {
+ dlm_mhandle_delete(node, mh);
} else {
- if (msglen < sizeof(struct dlm_rcom))
+ /* send queue should be ordered */
+ break;
+ }
+ }
+ spin_unlock(&node->send_queue_lock);
+ rcu_read_unlock();
+}
+
+static void dlm_pas_fin_ack_rcv(struct midcomms_node *node)
+{
+ spin_lock(&node->state_lock);
+ pr_debug("receive passive fin ack from node %d with state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+
+ switch (node->state) {
+ case DLM_LAST_ACK:
+ /* DLM_CLOSED */
+ midcomms_node_reset(node);
+ break;
+ case DLM_CLOSED:
+ /* not valid but somehow we got what we want */
+ wake_up(&node->shutdown_wait);
+ break;
+ default:
+ spin_unlock(&node->state_lock);
+ log_print("%s: unexpected state: %d\n",
+ __func__, node->state);
+ WARN_ON(1);
+ return;
+ }
+ spin_unlock(&node->state_lock);
+}
+
+static void dlm_midcomms_receive_buffer(union dlm_packet *p,
+ struct midcomms_node *node,
+ uint32_t seq)
+{
+ if (seq == node->seq_next) {
+ node->seq_next++;
+
+ switch (p->header.h_cmd) {
+ case DLM_FIN:
+ /* send ack before fin */
+ dlm_send_ack(node->nodeid, node->seq_next);
+
+ spin_lock(&node->state_lock);
+ pr_debug("receive fin msg from node %d with state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+
+ switch (node->state) {
+ case DLM_ESTABLISHED:
+ node->state = DLM_CLOSE_WAIT;
+ pr_debug("switch node %d to state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ /* passive shutdown DLM_LAST_ACK case 1
+ * additional we check if the node is used by
+ * cluster manager events at all.
+ */
+ if (node->users == 0) {
+ node->state = DLM_LAST_ACK;
+ pr_debug("switch node %d to state %s case 1\n",
+ node->nodeid, dlm_state_str(node->state));
+ spin_unlock(&node->state_lock);
+ goto send_fin;
+ }
+ break;
+ case DLM_FIN_WAIT1:
+ node->state = DLM_CLOSING;
+ pr_debug("switch node %d to state %s\n",
+ node->nodeid, dlm_state_str(node->state));
break;
+ case DLM_FIN_WAIT2:
+ midcomms_node_reset(node);
+ pr_debug("switch node %d to state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ wake_up(&node->shutdown_wait);
+ break;
+ case DLM_LAST_ACK:
+ /* probably remove_member caught it, do nothing */
+ break;
+ default:
+ spin_unlock(&node->state_lock);
+ log_print("%s: unexpected state: %d\n",
+ __func__, node->state);
+ WARN_ON(1);
+ return;
+ }
+ spin_unlock(&node->state_lock);
+
+ set_bit(DLM_NODE_FLAG_STOP_RX, &node->flags);
+ break;
+ default:
+ WARN_ON(test_bit(DLM_NODE_FLAG_STOP_RX, &node->flags));
+ dlm_receive_buffer(p, node->nodeid);
+ set_bit(DLM_NODE_ULP_DELIVERED, &node->flags);
+ break;
+ }
+ } else {
+ /* retry to ack message which we already have by sending back
+ * current node->seq_next number as ack.
+ */
+ if (seq < node->seq_next)
+ dlm_send_ack(node->nodeid, node->seq_next);
+
+ log_print_ratelimited("ignore dlm msg because seq mismatch, seq: %u, expected: %u, nodeid: %d",
+ seq, node->seq_next, node->nodeid);
+ }
+
+ return;
+
+send_fin:
+ set_bit(DLM_NODE_FLAG_STOP_RX, &node->flags);
+ dlm_send_fin(node, dlm_pas_fin_ack_rcv);
+}
+
+static struct midcomms_node *
+dlm_midcomms_recv_node_lookup(int nodeid, const union dlm_packet *p,
+ uint16_t msglen, int (*cb)(struct midcomms_node *node))
+{
+ struct midcomms_node *node = NULL;
+ gfp_t allocation = 0;
+ int ret;
+
+ switch (p->header.h_cmd) {
+ case DLM_RCOM:
+ if (msglen < sizeof(struct dlm_rcom)) {
+ log_print("rcom msg too small: %u, will skip this message from node %d",
+ msglen, nodeid);
+ return NULL;
}
- err = -E2BIG;
- if (msglen > dlm_config.ci_buffer_size) {
- log_print("message size %d from %d too big, buf len %d",
- msglen, nodeid, len);
+
+ switch (p->rcom.rc_type) {
+ case cpu_to_le32(DLM_RCOM_NAMES):
+ fallthrough;
+ case cpu_to_le32(DLM_RCOM_NAMES_REPLY):
+ fallthrough;
+ case cpu_to_le32(DLM_RCOM_STATUS):
+ fallthrough;
+ case cpu_to_le32(DLM_RCOM_STATUS_REPLY):
+ node = nodeid2node(nodeid, 0);
+ if (node) {
+ spin_lock(&node->state_lock);
+ if (node->state != DLM_ESTABLISHED)
+ pr_debug("receive begin RCOM msg from node %d with state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+
+ switch (node->state) {
+ case DLM_CLOSED:
+ node->state = DLM_ESTABLISHED;
+ pr_debug("switch node %d to state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ break;
+ case DLM_ESTABLISHED:
+ break;
+ default:
+ /* some invalid state passive shutdown
+ * was failed, we try to reset and
+ * hope it will go on.
+ */
+ log_print("reset node %d because shutdown stuck",
+ node->nodeid);
+
+ midcomms_node_reset(node);
+ node->state = DLM_ESTABLISHED;
+ break;
+ }
+ spin_unlock(&node->state_lock);
+ }
+
+ allocation = GFP_NOFS;
+ break;
+ default:
break;
}
- err = 0;
- /* If only part of the full message is contained in this
- buffer, then do nothing and wait for lowcomms to call
- us again later with more data. We return 0 meaning
- we've consumed none of the input buffer. */
+ break;
+ default:
+ break;
+ }
+
+ node = nodeid2node(nodeid, allocation);
+ if (!node) {
+ switch (p->header.h_cmd) {
+ case DLM_OPTS:
+ if (msglen < sizeof(struct dlm_opts)) {
+ log_print("opts msg too small: %u, will skip this message from node %d",
+ msglen, nodeid);
+ return NULL;
+ }
+
+ log_print_ratelimited("received dlm opts message nextcmd %d from node %d in an invalid sequence",
+ p->opts.o_nextcmd, nodeid);
+ break;
+ default:
+ log_print_ratelimited("received dlm message cmd %d from node %d in an invalid sequence",
+ p->header.h_cmd, nodeid);
+ break;
+ }
+
+ return NULL;
+ }
+
+ ret = cb(node);
+ if (ret < 0)
+ return NULL;
+
+ return node;
+}
+
+static int dlm_midcomms_version_check_3_2(struct midcomms_node *node)
+{
+ switch (node->version) {
+ case DLM_VERSION_NOT_SET:
+ node->version = DLM_VERSION_3_2;
+ log_print("version 0x%08x for node %d detected", DLM_VERSION_3_2,
+ node->nodeid);
+ break;
+ case DLM_VERSION_3_2:
+ break;
+ default:
+ log_print_ratelimited("version mismatch detected, assumed 0x%08x but node %d has 0x%08x",
+ DLM_VERSION_3_2, node->nodeid, node->version);
+ return -1;
+ }
+
+ return 0;
+}
+
+static int dlm_opts_check_msglen(union dlm_packet *p, uint16_t msglen, int nodeid)
+{
+ int len = msglen;
+
+ /* we only trust outer header msglen because
+ * it's checked against receive buffer length.
+ */
+ if (len < sizeof(struct dlm_opts))
+ return -1;
+ len -= sizeof(struct dlm_opts);
+
+ if (len < le16_to_cpu(p->opts.o_optlen))
+ return -1;
+ len -= le16_to_cpu(p->opts.o_optlen);
+
+ switch (p->opts.o_nextcmd) {
+ case DLM_FIN:
+ if (len < sizeof(struct dlm_header)) {
+ log_print("fin too small: %d, will skip this message from node %d",
+ len, nodeid);
+ return -1;
+ }
+
+ break;
+ case DLM_MSG:
+ if (len < sizeof(struct dlm_message)) {
+ log_print("msg too small: %d, will skip this message from node %d",
+ msglen, nodeid);
+ return -1;
+ }
+
+ break;
+ case DLM_RCOM:
+ if (len < sizeof(struct dlm_rcom)) {
+ log_print("rcom msg too small: %d, will skip this message from node %d",
+ len, nodeid);
+ return -1;
+ }
+
+ break;
+ default:
+ log_print("unsupported o_nextcmd received: %u, will skip this message from node %d",
+ p->opts.o_nextcmd, nodeid);
+ return -1;
+ }
+
+ return 0;
+}
+
+static void dlm_midcomms_receive_buffer_3_2(union dlm_packet *p, int nodeid)
+{
+ uint16_t msglen = le16_to_cpu(p->header.h_length);
+ struct midcomms_node *node;
+ uint32_t seq;
+ int ret, idx;
+
+ idx = srcu_read_lock(&nodes_srcu);
+ node = dlm_midcomms_recv_node_lookup(nodeid, p, msglen,
+ dlm_midcomms_version_check_3_2);
+ if (!node)
+ goto out;
+
+ switch (p->header.h_cmd) {
+ case DLM_RCOM:
+ /* these rcom message we use to determine version.
+ * they have their own retransmission handling and
+ * are the first messages of dlm.
+ *
+ * length already checked.
+ */
+ switch (p->rcom.rc_type) {
+ case cpu_to_le32(DLM_RCOM_NAMES):
+ fallthrough;
+ case cpu_to_le32(DLM_RCOM_NAMES_REPLY):
+ fallthrough;
+ case cpu_to_le32(DLM_RCOM_STATUS):
+ fallthrough;
+ case cpu_to_le32(DLM_RCOM_STATUS_REPLY):
+ break;
+ default:
+ log_print("unsupported rcom type received: %u, will skip this message from node %d",
+ le32_to_cpu(p->rcom.rc_type), nodeid);
+ goto out;
+ }
+
+ WARN_ON(test_bit(DLM_NODE_FLAG_STOP_RX, &node->flags));
+ dlm_receive_buffer(p, nodeid);
+ break;
+ case DLM_OPTS:
+ seq = le32_to_cpu(p->header.u.h_seq);
+
+ ret = dlm_opts_check_msglen(p, msglen, nodeid);
+ if (ret < 0) {
+ log_print("opts msg too small: %u, will skip this message from node %d",
+ msglen, nodeid);
+ goto out;
+ }
+
+ p = (union dlm_packet *)((unsigned char *)p->opts.o_opts +
+ le16_to_cpu(p->opts.o_optlen));
+
+ /* recheck inner msglen just if it's not garbage */
+ msglen = le16_to_cpu(p->header.h_length);
+ switch (p->header.h_cmd) {
+ case DLM_RCOM:
+ if (msglen < sizeof(struct dlm_rcom)) {
+ log_print("inner rcom msg too small: %u, will skip this message from node %d",
+ msglen, nodeid);
+ goto out;
+ }
- if (msglen > len)
break;
+ case DLM_MSG:
+ if (msglen < sizeof(struct dlm_message)) {
+ log_print("inner msg too small: %u, will skip this message from node %d",
+ msglen, nodeid);
+ goto out;
+ }
- /* Allocate a larger temp buffer if the full message won't fit
- in the buffer on the stack (which should work for most
- ordinary messages). */
+ break;
+ case DLM_FIN:
+ if (msglen < sizeof(struct dlm_header)) {
+ log_print("inner fin too small: %u, will skip this message from node %d",
+ msglen, nodeid);
+ goto out;
+ }
- if (msglen > sizeof(__tmp) && p == &__tmp.p) {
- p = kmalloc(dlm_config.ci_buffer_size, GFP_NOFS);
- if (p == NULL)
- return ret;
+ break;
+ default:
+ log_print("unsupported inner h_cmd received: %u, will skip this message from node %d",
+ msglen, nodeid);
+ goto out;
}
- copy_from_cb(p, base, offset, msglen, limit);
+ dlm_midcomms_receive_buffer(p, node, seq);
+ break;
+ case DLM_ACK:
+ seq = le32_to_cpu(p->header.u.h_seq);
+ dlm_receive_ack(node, seq);
+ break;
+ default:
+ log_print("unsupported h_cmd received: %u, will skip this message from node %d",
+ p->header.h_cmd, nodeid);
+ break;
+ }
- BUG_ON(lockspace != p->header.h_lockspace);
+out:
+ srcu_read_unlock(&nodes_srcu, idx);
+}
+
+static int dlm_midcomms_version_check_3_1(struct midcomms_node *node)
+{
+ switch (node->version) {
+ case DLM_VERSION_NOT_SET:
+ node->version = DLM_VERSION_3_1;
+ log_print("version 0x%08x for node %d detected", DLM_VERSION_3_1,
+ node->nodeid);
+ break;
+ case DLM_VERSION_3_1:
+ break;
+ default:
+ log_print_ratelimited("version mismatch detected, assumed 0x%08x but node %d has 0x%08x",
+ DLM_VERSION_3_1, node->nodeid, node->version);
+ return -1;
+ }
+
+ return 0;
+}
+
+static void dlm_midcomms_receive_buffer_3_1(union dlm_packet *p, int nodeid)
+{
+ uint16_t msglen = le16_to_cpu(p->header.h_length);
+ struct midcomms_node *node;
+ int idx;
+
+ idx = srcu_read_lock(&nodes_srcu);
+ node = dlm_midcomms_recv_node_lookup(nodeid, p, msglen,
+ dlm_midcomms_version_check_3_1);
+ if (!node) {
+ srcu_read_unlock(&nodes_srcu, idx);
+ return;
+ }
+ srcu_read_unlock(&nodes_srcu, idx);
+
+ switch (p->header.h_cmd) {
+ case DLM_RCOM:
+ /* length already checked */
+ break;
+ case DLM_MSG:
+ if (msglen < sizeof(struct dlm_message)) {
+ log_print("msg too small: %u, will skip this message from node %d",
+ msglen, nodeid);
+ return;
+ }
+
+ break;
+ default:
+ log_print("unsupported h_cmd received: %u, will skip this message from node %d",
+ p->header.h_cmd, nodeid);
+ return;
+ }
+
+ dlm_receive_buffer(p, nodeid);
+}
+
+/*
+ * Called from the low-level comms layer to process a buffer of
+ * commands.
+ */
+
+int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int len)
+{
+ const unsigned char *ptr = buf;
+ const struct dlm_header *hd;
+ uint16_t msglen;
+ int ret = 0;
+
+ while (len >= sizeof(struct dlm_header)) {
+ hd = (struct dlm_header *)ptr;
+
+ /* no message should be more than DLM_MAX_SOCKET_BUFSIZE or
+ * less than dlm_header size.
+ *
+ * Some messages does not have a 8 byte length boundary yet
+ * which can occur in a unaligned memory access of some dlm
+ * messages. However this problem need to be fixed at the
+ * sending side, for now it seems nobody run into architecture
+ * related issues yet but it slows down some processing.
+ * Fixing this issue should be scheduled in future by doing
+ * the next major version bump.
+ */
+ msglen = le16_to_cpu(hd->h_length);
+ if (msglen > DLM_MAX_SOCKET_BUFSIZE ||
+ msglen < sizeof(struct dlm_header)) {
+ log_print("received invalid length header: %u from node %d, will abort message parsing",
+ msglen, nodeid);
+ return -EBADMSG;
+ }
+
+ /* caller will take care that leftover
+ * will be parsed next call with more data
+ */
+ if (msglen > len)
+ break;
+
+ switch (hd->h_version) {
+ case cpu_to_le32(DLM_VERSION_3_1):
+ dlm_midcomms_receive_buffer_3_1((union dlm_packet *)ptr, nodeid);
+ break;
+ case cpu_to_le32(DLM_VERSION_3_2):
+ dlm_midcomms_receive_buffer_3_2((union dlm_packet *)ptr, nodeid);
+ break;
+ default:
+ log_print("received invalid version header: %u from node %d, will skip this message",
+ le32_to_cpu(hd->h_version), nodeid);
+ break;
+ }
ret += msglen;
- offset += msglen;
- offset &= (limit - 1);
len -= msglen;
+ ptr += msglen;
+ }
- dlm_receive_buffer(p, nodeid);
+ return ret;
+}
+
+void dlm_midcomms_receive_done(int nodeid)
+{
+ struct midcomms_node *node;
+ int idx;
+
+ idx = srcu_read_lock(&nodes_srcu);
+ node = nodeid2node(nodeid, 0);
+ if (!node) {
+ srcu_read_unlock(&nodes_srcu, idx);
+ return;
+ }
+
+ /* old protocol, we do nothing */
+ switch (node->version) {
+ case DLM_VERSION_3_2:
+ break;
+ default:
+ srcu_read_unlock(&nodes_srcu, idx);
+ return;
+ }
+
+ /* do nothing if we didn't delivered stateful to ulp */
+ if (!test_and_clear_bit(DLM_NODE_ULP_DELIVERED,
+ &node->flags)) {
+ srcu_read_unlock(&nodes_srcu, idx);
+ return;
+ }
+
+ spin_lock(&node->state_lock);
+ /* we only ack if state is ESTABLISHED */
+ switch (node->state) {
+ case DLM_ESTABLISHED:
+ spin_unlock(&node->state_lock);
+ dlm_send_ack(node->nodeid, node->seq_next);
+ break;
+ default:
+ spin_unlock(&node->state_lock);
+ /* do nothing FIN has it's own ack send */
+ break;
+ }
+ srcu_read_unlock(&nodes_srcu, idx);
+}
+
+void dlm_midcomms_unack_msg_resend(int nodeid)
+{
+ struct midcomms_node *node;
+ struct dlm_mhandle *mh;
+ int idx, ret;
+
+ idx = srcu_read_lock(&nodes_srcu);
+ node = nodeid2node(nodeid, 0);
+ if (!node) {
+ srcu_read_unlock(&nodes_srcu, idx);
+ return;
+ }
+
+ /* old protocol, we don't support to retransmit on failure */
+ switch (node->version) {
+ case DLM_VERSION_3_2:
+ break;
+ default:
+ srcu_read_unlock(&nodes_srcu, idx);
+ return;
+ }
+
+ rcu_read_lock();
+ list_for_each_entry_rcu(mh, &node->send_queue, list) {
+ if (!mh->committed)
+ continue;
+
+ ret = dlm_lowcomms_resend_msg(mh->msg);
+ if (!ret)
+ log_print_ratelimited("retransmit dlm msg, seq %u, nodeid %d",
+ mh->seq, node->nodeid);
+ }
+ rcu_read_unlock();
+ srcu_read_unlock(&nodes_srcu, idx);
+}
+
+static void dlm_fill_opts_header(struct dlm_opts *opts, uint16_t inner_len,
+ uint32_t seq)
+{
+ opts->o_header.h_cmd = DLM_OPTS;
+ opts->o_header.h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+ opts->o_header.h_nodeid = cpu_to_le32(dlm_our_nodeid());
+ opts->o_header.h_length = cpu_to_le16(DLM_MIDCOMMS_OPT_LEN + inner_len);
+ opts->o_header.u.h_seq = cpu_to_le32(seq);
+}
+
+static void midcomms_new_msg_cb(void *data)
+{
+ struct dlm_mhandle *mh = data;
+
+ atomic_inc(&mh->node->send_queue_cnt);
+
+ spin_lock(&mh->node->send_queue_lock);
+ list_add_tail_rcu(&mh->list, &mh->node->send_queue);
+ spin_unlock(&mh->node->send_queue_lock);
+
+ mh->seq = mh->node->seq_send++;
+}
+
+static struct dlm_msg *dlm_midcomms_get_msg_3_2(struct dlm_mhandle *mh, int nodeid,
+ int len, gfp_t allocation, char **ppc)
+{
+ struct dlm_opts *opts;
+ struct dlm_msg *msg;
+
+ msg = dlm_lowcomms_new_msg(nodeid, len + DLM_MIDCOMMS_OPT_LEN,
+ allocation, ppc, midcomms_new_msg_cb, mh);
+ if (!msg)
+ return NULL;
+
+ opts = (struct dlm_opts *)*ppc;
+ mh->opts = opts;
+
+ /* add possible options here */
+ dlm_fill_opts_header(opts, len, mh->seq);
+
+ *ppc += sizeof(*opts);
+ mh->inner_hd = (const struct dlm_header *)*ppc;
+ return msg;
+}
+
+/* avoid false positive for nodes_srcu, unlock happens in
+ * dlm_midcomms_commit_mhandle which is a must call if success
+ */
+#ifndef __CHECKER__
+struct dlm_mhandle *dlm_midcomms_get_mhandle(int nodeid, int len,
+ gfp_t allocation, char **ppc)
+{
+ struct midcomms_node *node;
+ struct dlm_mhandle *mh;
+ struct dlm_msg *msg;
+ int idx;
+
+ idx = srcu_read_lock(&nodes_srcu);
+ node = nodeid2node(nodeid, 0);
+ if (!node) {
+ WARN_ON_ONCE(1);
+ goto err;
+ }
+
+ /* this is a bug, however we going on and hope it will be resolved */
+ WARN_ON(test_bit(DLM_NODE_FLAG_STOP_TX, &node->flags));
+
+ mh = dlm_allocate_mhandle();
+ if (!mh)
+ goto err;
+
+ mh->committed = false;
+ mh->ack_rcv = NULL;
+ mh->idx = idx;
+ mh->node = node;
+
+ switch (node->version) {
+ case DLM_VERSION_3_1:
+ msg = dlm_lowcomms_new_msg(nodeid, len, allocation, ppc,
+ NULL, NULL);
+ if (!msg) {
+ dlm_free_mhandle(mh);
+ goto err;
+ }
+
+ break;
+ case DLM_VERSION_3_2:
+ msg = dlm_midcomms_get_msg_3_2(mh, nodeid, len, allocation,
+ ppc);
+ if (!msg) {
+ dlm_free_mhandle(mh);
+ goto err;
+ }
+
+ break;
+ default:
+ dlm_free_mhandle(mh);
+ WARN_ON(1);
+ goto err;
+ }
+
+ mh->msg = msg;
+
+ /* keep in mind that is a must to call
+ * dlm_midcomms_commit_msg() which releases
+ * nodes_srcu using mh->idx which is assumed
+ * here that the application will call it.
+ */
+ return mh;
+
+err:
+ srcu_read_unlock(&nodes_srcu, idx);
+ return NULL;
+}
+#endif
+
+static void dlm_midcomms_commit_msg_3_2(struct dlm_mhandle *mh)
+{
+ /* nexthdr chain for fast lookup */
+ mh->opts->o_nextcmd = mh->inner_hd->h_cmd;
+ mh->committed = true;
+ dlm_lowcomms_commit_msg(mh->msg);
+}
+
+/* avoid false positive for nodes_srcu, lock was happen in
+ * dlm_midcomms_get_mhandle
+ */
+#ifndef __CHECKER__
+void dlm_midcomms_commit_mhandle(struct dlm_mhandle *mh)
+{
+ switch (mh->node->version) {
+ case DLM_VERSION_3_1:
+ srcu_read_unlock(&nodes_srcu, mh->idx);
+
+ dlm_lowcomms_commit_msg(mh->msg);
+ dlm_lowcomms_put_msg(mh->msg);
+ /* mh is not part of rcu list in this case */
+ dlm_free_mhandle(mh);
+ break;
+ case DLM_VERSION_3_2:
+ dlm_midcomms_commit_msg_3_2(mh);
+ srcu_read_unlock(&nodes_srcu, mh->idx);
+ break;
+ default:
+ srcu_read_unlock(&nodes_srcu, mh->idx);
+ WARN_ON(1);
+ break;
+ }
+}
+#endif
+
+int dlm_midcomms_start(void)
+{
+ int i;
+
+ for (i = 0; i < CONN_HASH_SIZE; i++)
+ INIT_HLIST_HEAD(&node_hash[i]);
+
+ return dlm_lowcomms_start();
+}
+
+static void dlm_act_fin_ack_rcv(struct midcomms_node *node)
+{
+ spin_lock(&node->state_lock);
+ pr_debug("receive active fin ack from node %d with state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+
+ switch (node->state) {
+ case DLM_FIN_WAIT1:
+ node->state = DLM_FIN_WAIT2;
+ pr_debug("switch node %d to state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ break;
+ case DLM_CLOSING:
+ midcomms_node_reset(node);
+ pr_debug("switch node %d to state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ wake_up(&node->shutdown_wait);
+ break;
+ case DLM_CLOSED:
+ /* not valid but somehow we got what we want */
+ wake_up(&node->shutdown_wait);
+ break;
+ default:
+ spin_unlock(&node->state_lock);
+ log_print("%s: unexpected state: %d\n",
+ __func__, node->state);
+ WARN_ON(1);
+ return;
+ }
+ spin_unlock(&node->state_lock);
+}
+
+void dlm_midcomms_add_member(int nodeid)
+{
+ struct midcomms_node *node;
+ int idx;
+
+ if (nodeid == dlm_our_nodeid())
+ return;
+
+ idx = srcu_read_lock(&nodes_srcu);
+ node = nodeid2node(nodeid, GFP_NOFS);
+ if (!node) {
+ srcu_read_unlock(&nodes_srcu, idx);
+ return;
+ }
+
+ spin_lock(&node->state_lock);
+ if (!node->users) {
+ pr_debug("receive add member from node %d with state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ switch (node->state) {
+ case DLM_ESTABLISHED:
+ break;
+ case DLM_CLOSED:
+ node->state = DLM_ESTABLISHED;
+ pr_debug("switch node %d to state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ break;
+ default:
+ /* some invalid state passive shutdown
+ * was failed, we try to reset and
+ * hope it will go on.
+ */
+ log_print("reset node %d because shutdown stuck",
+ node->nodeid);
+
+ midcomms_node_reset(node);
+ node->state = DLM_ESTABLISHED;
+ break;
+ }
+ }
+
+ node->users++;
+ pr_debug("node %d users inc count %d\n", nodeid, node->users);
+ spin_unlock(&node->state_lock);
+
+ srcu_read_unlock(&nodes_srcu, idx);
+}
+
+void dlm_midcomms_remove_member(int nodeid)
+{
+ struct midcomms_node *node;
+ int idx;
+
+ if (nodeid == dlm_our_nodeid())
+ return;
+
+ idx = srcu_read_lock(&nodes_srcu);
+ node = nodeid2node(nodeid, 0);
+ if (!node) {
+ srcu_read_unlock(&nodes_srcu, idx);
+ return;
+ }
+
+ spin_lock(&node->state_lock);
+ node->users--;
+ pr_debug("node %d users dec count %d\n", nodeid, node->users);
+
+ /* hitting users count to zero means the
+ * other side is running dlm_midcomms_stop()
+ * we meet us to have a clean disconnect.
+ */
+ if (node->users == 0) {
+ pr_debug("receive remove member from node %d with state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ switch (node->state) {
+ case DLM_ESTABLISHED:
+ break;
+ case DLM_CLOSE_WAIT:
+ /* passive shutdown DLM_LAST_ACK case 2 */
+ node->state = DLM_LAST_ACK;
+ spin_unlock(&node->state_lock);
+
+ pr_debug("switch node %d to state %s case 2\n",
+ node->nodeid, dlm_state_str(node->state));
+ goto send_fin;
+ case DLM_LAST_ACK:
+ /* probably receive fin caught it, do nothing */
+ break;
+ case DLM_CLOSED:
+ /* already gone, do nothing */
+ break;
+ default:
+ log_print("%s: unexpected state: %d\n",
+ __func__, node->state);
+ break;
+ }
+ }
+ spin_unlock(&node->state_lock);
+
+ srcu_read_unlock(&nodes_srcu, idx);
+ return;
+
+send_fin:
+ set_bit(DLM_NODE_FLAG_STOP_RX, &node->flags);
+ dlm_send_fin(node, dlm_pas_fin_ack_rcv);
+ srcu_read_unlock(&nodes_srcu, idx);
+}
+
+static void midcomms_node_release(struct rcu_head *rcu)
+{
+ struct midcomms_node *node = container_of(rcu, struct midcomms_node, rcu);
+
+ WARN_ON(atomic_read(&node->send_queue_cnt));
+ kfree(node);
+}
+
+static void midcomms_shutdown(struct midcomms_node *node)
+{
+ int ret;
+
+ /* old protocol, we don't wait for pending operations */
+ switch (node->version) {
+ case DLM_VERSION_3_2:
+ break;
+ default:
+ return;
+ }
+
+ spin_lock(&node->state_lock);
+ pr_debug("receive active shutdown for node %d with state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ switch (node->state) {
+ case DLM_ESTABLISHED:
+ node->state = DLM_FIN_WAIT1;
+ pr_debug("switch node %d to state %s case 2\n",
+ node->nodeid, dlm_state_str(node->state));
+ break;
+ case DLM_CLOSED:
+ /* we have what we want */
+ spin_unlock(&node->state_lock);
+ return;
+ default:
+ /* busy to enter DLM_FIN_WAIT1, wait until passive
+ * done in shutdown_wait to enter DLM_CLOSED.
+ */
+ break;
+ }
+ spin_unlock(&node->state_lock);
+
+ if (node->state == DLM_FIN_WAIT1) {
+ dlm_send_fin(node, dlm_act_fin_ack_rcv);
+
+ if (DLM_DEBUG_FENCE_TERMINATION)
+ msleep(5000);
+ }
+
+ /* wait for other side dlm + fin */
+ ret = wait_event_timeout(node->shutdown_wait,
+ node->state == DLM_CLOSED ||
+ test_bit(DLM_NODE_FLAG_CLOSE, &node->flags),
+ DLM_SHUTDOWN_TIMEOUT);
+ if (!ret || test_bit(DLM_NODE_FLAG_CLOSE, &node->flags)) {
+ pr_debug("active shutdown timed out for node %d with state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+ midcomms_node_reset(node);
+ return;
+ }
+
+ pr_debug("active shutdown done for node %d with state %s\n",
+ node->nodeid, dlm_state_str(node->state));
+}
+
+void dlm_midcomms_shutdown(void)
+{
+ struct midcomms_node *node;
+ int i, idx;
+
+ mutex_lock(&close_lock);
+ idx = srcu_read_lock(&nodes_srcu);
+ for (i = 0; i < CONN_HASH_SIZE; i++) {
+ hlist_for_each_entry_rcu(node, &node_hash[i], hlist) {
+ midcomms_shutdown(node);
+
+ dlm_delete_debug_comms_file(node->debugfs);
+
+ spin_lock(&nodes_lock);
+ hlist_del_rcu(&node->hlist);
+ spin_unlock(&nodes_lock);
+
+ call_srcu(&nodes_srcu, &node->rcu, midcomms_node_release);
+ }
+ }
+ srcu_read_unlock(&nodes_srcu, idx);
+ mutex_unlock(&close_lock);
+
+ dlm_lowcomms_shutdown();
+}
+
+int dlm_midcomms_close(int nodeid)
+{
+ struct midcomms_node *node;
+ int idx, ret;
+
+ if (nodeid == dlm_our_nodeid())
+ return 0;
+
+ dlm_stop_lockspaces_check();
+
+ idx = srcu_read_lock(&nodes_srcu);
+ /* Abort pending close/remove operation */
+ node = nodeid2node(nodeid, 0);
+ if (node) {
+ /* let shutdown waiters leave */
+ set_bit(DLM_NODE_FLAG_CLOSE, &node->flags);
+ wake_up(&node->shutdown_wait);
+ }
+ srcu_read_unlock(&nodes_srcu, idx);
+
+ synchronize_srcu(&nodes_srcu);
+
+ idx = srcu_read_lock(&nodes_srcu);
+ mutex_lock(&close_lock);
+ node = nodeid2node(nodeid, 0);
+ if (!node) {
+ mutex_unlock(&close_lock);
+ srcu_read_unlock(&nodes_srcu, idx);
+ return dlm_lowcomms_close(nodeid);
+ }
+
+ ret = dlm_lowcomms_close(nodeid);
+ spin_lock(&node->state_lock);
+ midcomms_node_reset(node);
+ spin_unlock(&node->state_lock);
+ srcu_read_unlock(&nodes_srcu, idx);
+ mutex_unlock(&close_lock);
+
+ return ret;
+}
+
+/* debug functionality to send raw dlm msg from user space */
+struct dlm_rawmsg_data {
+ struct midcomms_node *node;
+ void *buf;
+};
+
+static void midcomms_new_rawmsg_cb(void *data)
+{
+ struct dlm_rawmsg_data *rd = data;
+ struct dlm_header *h = rd->buf;
+
+ switch (h->h_version) {
+ case cpu_to_le32(DLM_VERSION_3_1):
+ break;
+ default:
+ switch (h->h_cmd) {
+ case DLM_OPTS:
+ if (!h->u.h_seq)
+ h->u.h_seq = cpu_to_le32(rd->node->seq_send++);
+ break;
+ default:
+ break;
+ }
+ break;
}
+}
+
+int dlm_midcomms_rawmsg_send(struct midcomms_node *node, void *buf,
+ int buflen)
+{
+ struct dlm_rawmsg_data rd;
+ struct dlm_msg *msg;
+ char *msgbuf;
+
+ rd.node = node;
+ rd.buf = buf;
- if (p != &__tmp.p)
- kfree(p);
+ msg = dlm_lowcomms_new_msg(node->nodeid, buflen, GFP_NOFS,
+ &msgbuf, midcomms_new_rawmsg_cb, &rd);
+ if (!msg)
+ return -ENOMEM;
- return err ? err : ret;
+ memcpy(msgbuf, buf, buflen);
+ dlm_lowcomms_commit_msg(msg);
+ return 0;
}
diff --git a/fs/dlm/midcomms.h b/fs/dlm/midcomms.h
index 2e122e81c8d0..82bcd9661922 100644
--- a/fs/dlm/midcomms.h
+++ b/fs/dlm/midcomms.h
@@ -12,8 +12,25 @@
#ifndef __MIDCOMMS_DOT_H__
#define __MIDCOMMS_DOT_H__
-int dlm_process_incoming_buffer(int nodeid, const void *base, unsigned offset,
- unsigned len, unsigned limit);
+struct midcomms_node;
+
+int dlm_process_incoming_buffer(int nodeid, unsigned char *buf, int buflen);
+struct dlm_mhandle *dlm_midcomms_get_mhandle(int nodeid, int len,
+ gfp_t allocation, char **ppc);
+void dlm_midcomms_commit_mhandle(struct dlm_mhandle *mh);
+int dlm_midcomms_close(int nodeid);
+int dlm_midcomms_start(void);
+void dlm_midcomms_shutdown(void);
+void dlm_midcomms_add_member(int nodeid);
+void dlm_midcomms_remove_member(int nodeid);
+void dlm_midcomms_unack_msg_resend(int nodeid);
+const char *dlm_midcomms_state(struct midcomms_node *node);
+unsigned long dlm_midcomms_flags(struct midcomms_node *node);
+int dlm_midcomms_send_queue_cnt(struct midcomms_node *node);
+uint32_t dlm_midcomms_version(struct midcomms_node *node);
+int dlm_midcomms_rawmsg_send(struct midcomms_node *node, void *buf,
+ int buflen);
+struct kmem_cache *dlm_midcomms_cache_create(void);
#endif /* __MIDCOMMS_DOT_H__ */
diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c
index e7f550327d5d..4de4b8651c6c 100644
--- a/fs/dlm/netlink.c
+++ b/fs/dlm/netlink.c
@@ -62,7 +62,7 @@ static int user_cmd(struct sk_buff *skb, struct genl_info *info)
return 0;
}
-static const struct genl_ops dlm_nl_ops[] = {
+static const struct genl_small_ops dlm_nl_ops[] = {
{
.cmd = DLM_CMD_HELLO,
.validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP,
@@ -73,8 +73,9 @@ static const struct genl_ops dlm_nl_ops[] = {
static struct genl_family family __ro_after_init = {
.name = DLM_GENL_NAME,
.version = DLM_GENL_VERSION,
- .ops = dlm_nl_ops,
- .n_ops = ARRAY_SIZE(dlm_nl_ops),
+ .small_ops = dlm_nl_ops,
+ .n_small_ops = ARRAY_SIZE(dlm_nl_ops),
+ .resv_start_op = DLM_CMD_HELLO + 1,
.module = THIS_MODULE,
};
@@ -113,7 +114,7 @@ static void fill_data(struct dlm_lock_data *data, struct dlm_lkb *lkb)
void dlm_timeout_warn(struct dlm_lkb *lkb)
{
- struct sk_buff *uninitialized_var(send_skb);
+ struct sk_buff *send_skb;
struct dlm_lock_data *data;
size_t size;
int rv;
diff --git a/fs/dlm/plock.c b/fs/dlm/plock.c
index c38b2b8ffd1d..737f185aad8d 100644
--- a/fs/dlm/plock.c
+++ b/fs/dlm/plock.c
@@ -13,26 +13,28 @@
#include "dlm_internal.h"
#include "lockspace.h"
-static spinlock_t ops_lock;
-static struct list_head send_list;
-static struct list_head recv_list;
-static wait_queue_head_t send_wq;
-static wait_queue_head_t recv_wq;
+static DEFINE_SPINLOCK(ops_lock);
+static LIST_HEAD(send_list);
+static LIST_HEAD(recv_list);
+static DECLARE_WAIT_QUEUE_HEAD(send_wq);
+static DECLARE_WAIT_QUEUE_HEAD(recv_wq);
-struct plock_op {
- struct list_head list;
- int done;
- struct dlm_plock_info info;
-};
-
-struct plock_xop {
- struct plock_op xop;
- int (*callback)(struct file_lock *fl, int result);
+struct plock_async_data {
void *fl;
void *file;
struct file_lock flc;
+ int (*callback)(struct file_lock *fl, int result);
};
+struct plock_op {
+ struct list_head list;
+ int done;
+ /* if lock op got interrupted while waiting dlm_controld reply */
+ bool sigint;
+ struct dlm_plock_info info;
+ /* if set indicates async handling */
+ struct plock_async_data *data;
+};
static inline void set_version(struct dlm_plock_info *info)
{
@@ -58,10 +60,15 @@ static int check_version(struct dlm_plock_info *info)
return 0;
}
+static void dlm_release_plock_op(struct plock_op *op)
+{
+ kfree(op->data);
+ kfree(op);
+}
+
static void send_op(struct plock_op *op)
{
set_version(&op->info);
- INIT_LIST_HEAD(&op->list);
spin_lock(&ops_lock);
list_add_tail(&op->list, &send_list);
spin_unlock(&ops_lock);
@@ -74,8 +81,7 @@ static void send_op(struct plock_op *op)
abandoned waiter. So, we have to insert the unlock-close when the
lock call is interrupted. */
-static void do_unlock_close(struct dlm_ls *ls, u64 number,
- struct file *file, struct file_lock *fl)
+static void do_unlock_close(const struct dlm_plock_info *info)
{
struct plock_op *op;
@@ -84,15 +90,12 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number,
return;
op->info.optype = DLM_PLOCK_OP_UNLOCK;
- op->info.pid = fl->fl_pid;
- op->info.fsid = ls->ls_global_id;
- op->info.number = number;
+ op->info.pid = info->pid;
+ op->info.fsid = info->fsid;
+ op->info.number = info->number;
op->info.start = 0;
op->info.end = OFFSET_MAX;
- if (fl->fl_lmops && fl->fl_lmops->lm_grant)
- op->info.owner = (__u64) fl->fl_pid;
- else
- op->info.owner = (__u64)(long) fl->fl_owner;
+ op->info.owner = info->owner;
op->info.flags |= DLM_PLOCK_FL_CLOSE;
send_op(op);
@@ -101,22 +104,21 @@ static void do_unlock_close(struct dlm_ls *ls, u64 number,
int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
int cmd, struct file_lock *fl)
{
+ struct plock_async_data *op_data;
struct dlm_ls *ls;
struct plock_op *op;
- struct plock_xop *xop;
int rv;
ls = dlm_find_lockspace_local(lockspace);
if (!ls)
return -EINVAL;
- xop = kzalloc(sizeof(*xop), GFP_NOFS);
- if (!xop) {
+ op = kzalloc(sizeof(*op), GFP_NOFS);
+ if (!op) {
rv = -ENOMEM;
goto out;
}
- op = &xop->xop;
op->info.optype = DLM_PLOCK_OP_LOCK;
op->info.pid = fl->fl_pid;
op->info.ex = (fl->fl_type == F_WRLCK);
@@ -125,46 +127,57 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
op->info.number = number;
op->info.start = fl->fl_start;
op->info.end = fl->fl_end;
+ /* async handling */
if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
+ op_data = kzalloc(sizeof(*op_data), GFP_NOFS);
+ if (!op_data) {
+ dlm_release_plock_op(op);
+ rv = -ENOMEM;
+ goto out;
+ }
+
/* fl_owner is lockd which doesn't distinguish
processes on the nfs client */
op->info.owner = (__u64) fl->fl_pid;
- xop->callback = fl->fl_lmops->lm_grant;
- locks_init_lock(&xop->flc);
- locks_copy_lock(&xop->flc, fl);
- xop->fl = fl;
- xop->file = file;
+ op_data->callback = fl->fl_lmops->lm_grant;
+ locks_init_lock(&op_data->flc);
+ locks_copy_lock(&op_data->flc, fl);
+ op_data->fl = fl;
+ op_data->file = file;
+
+ op->data = op_data;
+
+ send_op(op);
+ rv = FILE_LOCK_DEFERRED;
+ goto out;
} else {
op->info.owner = (__u64)(long) fl->fl_owner;
- xop->callback = NULL;
}
send_op(op);
- if (xop->callback == NULL) {
- rv = wait_event_interruptible(recv_wq, (op->done != 0));
- if (rv == -ERESTARTSYS) {
- log_debug(ls, "dlm_posix_lock: wait killed %llx",
- (unsigned long long)number);
- spin_lock(&ops_lock);
- list_del(&op->list);
+ rv = wait_event_interruptible(recv_wq, (op->done != 0));
+ if (rv == -ERESTARTSYS) {
+ spin_lock(&ops_lock);
+ /* recheck under ops_lock if we got a done != 0,
+ * if so this interrupt case should be ignored
+ */
+ if (op->done != 0) {
spin_unlock(&ops_lock);
- kfree(xop);
- do_unlock_close(ls, number, file, fl);
- goto out;
+ goto do_lock_wait;
}
- } else {
- rv = FILE_LOCK_DEFERRED;
+
+ op->sigint = true;
+ spin_unlock(&ops_lock);
+ log_debug(ls, "%s: wait interrupted %x %llx pid %d",
+ __func__, ls->ls_global_id,
+ (unsigned long long)number, op->info.pid);
goto out;
}
- spin_lock(&ops_lock);
- if (!list_empty(&op->list)) {
- log_error(ls, "dlm_posix_lock: op on list %llx",
- (unsigned long long)number);
- list_del(&op->list);
- }
- spin_unlock(&ops_lock);
+do_lock_wait:
+
+ WARN_ON(!list_empty(&op->list));
rv = op->info.rv;
@@ -174,7 +187,7 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
(unsigned long long)number);
}
- kfree(xop);
+ dlm_release_plock_op(op);
out:
dlm_put_lockspace(ls);
return rv;
@@ -184,26 +197,20 @@ EXPORT_SYMBOL_GPL(dlm_posix_lock);
/* Returns failure iff a successful lock operation should be canceled */
static int dlm_plock_callback(struct plock_op *op)
{
+ struct plock_async_data *op_data = op->data;
struct file *file;
struct file_lock *fl;
struct file_lock *flc;
int (*notify)(struct file_lock *fl, int result) = NULL;
- struct plock_xop *xop = (struct plock_xop *)op;
int rv = 0;
- spin_lock(&ops_lock);
- if (!list_empty(&op->list)) {
- log_print("dlm_plock_callback: op on list %llx",
- (unsigned long long)op->info.number);
- list_del(&op->list);
- }
- spin_unlock(&ops_lock);
+ WARN_ON(!list_empty(&op->list));
/* check if the following 2 are still valid or make a copy */
- file = xop->file;
- flc = &xop->flc;
- fl = xop->fl;
- notify = xop->callback;
+ file = op_data->file;
+ flc = &op_data->flc;
+ fl = op_data->fl;
+ notify = op_data->callback;
if (op->info.rv) {
notify(fl, op->info.rv);
@@ -234,7 +241,7 @@ static int dlm_plock_callback(struct plock_op *op)
}
out:
- kfree(xop);
+ dlm_release_plock_op(op);
return rv;
}
@@ -290,13 +297,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
send_op(op);
wait_event(recv_wq, (op->done != 0));
- spin_lock(&ops_lock);
- if (!list_empty(&op->list)) {
- log_error(ls, "dlm_posix_unlock: op on list %llx",
- (unsigned long long)number);
- list_del(&op->list);
- }
- spin_unlock(&ops_lock);
+ WARN_ON(!list_empty(&op->list));
rv = op->info.rv;
@@ -304,7 +305,7 @@ int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
rv = 0;
out_free:
- kfree(op);
+ dlm_release_plock_op(op);
out:
dlm_put_lockspace(ls);
fl->fl_flags = fl_flags;
@@ -344,13 +345,7 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
send_op(op);
wait_event(recv_wq, (op->done != 0));
- spin_lock(&ops_lock);
- if (!list_empty(&op->list)) {
- log_error(ls, "dlm_posix_get: op on list %llx",
- (unsigned long long)number);
- list_del(&op->list);
- }
- spin_unlock(&ops_lock);
+ WARN_ON(!list_empty(&op->list));
/* info.rv from userspace is 1 for conflict, 0 for no-conflict,
-ENOENT if there are no locks on the file */
@@ -370,7 +365,7 @@ int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
rv = 0;
}
- kfree(op);
+ dlm_release_plock_op(op);
out:
dlm_put_lockspace(ls);
return rv;
@@ -389,7 +384,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
spin_lock(&ops_lock);
if (!list_empty(&send_list)) {
- op = list_entry(send_list.next, struct plock_op, list);
+ op = list_first_entry(&send_list, struct plock_op, list);
if (op->info.flags & DLM_PLOCK_FL_CLOSE)
list_del(&op->list);
else
@@ -406,7 +401,7 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
(the process did not make an unlock call). */
if (op->info.flags & DLM_PLOCK_FL_CLOSE)
- kfree(op);
+ dlm_release_plock_op(op);
if (copy_to_user(u, &info, sizeof(info)))
return -EFAULT;
@@ -418,9 +413,9 @@ static ssize_t dev_read(struct file *file, char __user *u, size_t count,
static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
loff_t *ppos)
{
+ struct plock_op *op = NULL, *iter;
struct dlm_plock_info info;
- struct plock_op *op;
- int found = 0, do_callback = 0;
+ int do_callback = 0;
if (count != sizeof(info))
return -EINVAL;
@@ -432,31 +427,43 @@ static ssize_t dev_write(struct file *file, const char __user *u, size_t count,
return -EINVAL;
spin_lock(&ops_lock);
- list_for_each_entry(op, &recv_list, list) {
- if (op->info.fsid == info.fsid &&
- op->info.number == info.number &&
- op->info.owner == info.owner) {
- struct plock_xop *xop = (struct plock_xop *)op;
- list_del_init(&op->list);
- memcpy(&op->info, &info, sizeof(info));
- if (xop->callback)
+ list_for_each_entry(iter, &recv_list, list) {
+ if (iter->info.fsid == info.fsid &&
+ iter->info.number == info.number &&
+ iter->info.owner == info.owner) {
+ if (iter->sigint) {
+ list_del(&iter->list);
+ spin_unlock(&ops_lock);
+
+ pr_debug("%s: sigint cleanup %x %llx pid %d",
+ __func__, iter->info.fsid,
+ (unsigned long long)iter->info.number,
+ iter->info.pid);
+ do_unlock_close(&iter->info);
+ memcpy(&iter->info, &info, sizeof(info));
+ dlm_release_plock_op(iter);
+ return count;
+ }
+ list_del_init(&iter->list);
+ memcpy(&iter->info, &info, sizeof(info));
+ if (iter->data)
do_callback = 1;
else
- op->done = 1;
- found = 1;
+ iter->done = 1;
+ op = iter;
break;
}
}
spin_unlock(&ops_lock);
- if (found) {
+ if (op) {
if (do_callback)
dlm_plock_callback(op);
else
wake_up(&recv_wq);
} else
- log_print("dev_write no op %x %llx", info.fsid,
- (unsigned long long)info.number);
+ log_print("%s: no op %x %llx", __func__,
+ info.fsid, (unsigned long long)info.number);
return count;
}
@@ -492,12 +499,6 @@ int dlm_plock_init(void)
{
int rv;
- spin_lock_init(&ops_lock);
- INIT_LIST_HEAD(&send_list);
- INIT_LIST_HEAD(&recv_list);
- init_waitqueue_head(&send_wq);
- init_waitqueue_head(&recv_wq);
-
rv = misc_register(&plock_dev_misc);
if (rv)
log_print("dlm_plock_init: misc_register failed %d", rv);
diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c
index e3d9f72c640d..f19860315043 100644
--- a/fs/dlm/rcom.c
+++ b/fs/dlm/rcom.c
@@ -27,46 +27,77 @@ static int rcom_response(struct dlm_ls *ls)
return test_bit(LSFL_RCOM_READY, &ls->ls_flags);
}
+static void _create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len,
+ struct dlm_rcom **rc_ret, char *mb, int mb_len)
+{
+ struct dlm_rcom *rc;
+
+ rc = (struct dlm_rcom *) mb;
+
+ rc->rc_header.h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+ rc->rc_header.u.h_lockspace = cpu_to_le32(ls->ls_global_id);
+ rc->rc_header.h_nodeid = cpu_to_le32(dlm_our_nodeid());
+ rc->rc_header.h_length = cpu_to_le16(mb_len);
+ rc->rc_header.h_cmd = DLM_RCOM;
+
+ rc->rc_type = cpu_to_le32(type);
+
+ spin_lock(&ls->ls_recover_lock);
+ rc->rc_seq = cpu_to_le64(ls->ls_recover_seq);
+ spin_unlock(&ls->ls_recover_lock);
+
+ *rc_ret = rc;
+}
+
static int create_rcom(struct dlm_ls *ls, int to_nodeid, int type, int len,
struct dlm_rcom **rc_ret, struct dlm_mhandle **mh_ret)
{
- struct dlm_rcom *rc;
+ int mb_len = sizeof(struct dlm_rcom) + len;
struct dlm_mhandle *mh;
char *mb;
- int mb_len = sizeof(struct dlm_rcom) + len;
- mh = dlm_lowcomms_get_buffer(to_nodeid, mb_len, GFP_NOFS, &mb);
+ mh = dlm_midcomms_get_mhandle(to_nodeid, mb_len, GFP_NOFS, &mb);
if (!mh) {
- log_print("create_rcom to %d type %d len %d ENOBUFS",
- to_nodeid, type, len);
+ log_print("%s to %d type %d len %d ENOBUFS",
+ __func__, to_nodeid, type, len);
return -ENOBUFS;
}
- memset(mb, 0, mb_len);
- rc = (struct dlm_rcom *) mb;
-
- rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
- rc->rc_header.h_lockspace = ls->ls_global_id;
- rc->rc_header.h_nodeid = dlm_our_nodeid();
- rc->rc_header.h_length = mb_len;
- rc->rc_header.h_cmd = DLM_RCOM;
+ _create_rcom(ls, to_nodeid, type, len, rc_ret, mb, mb_len);
+ *mh_ret = mh;
+ return 0;
+}
- rc->rc_type = type;
+static int create_rcom_stateless(struct dlm_ls *ls, int to_nodeid, int type,
+ int len, struct dlm_rcom **rc_ret,
+ struct dlm_msg **msg_ret)
+{
+ int mb_len = sizeof(struct dlm_rcom) + len;
+ struct dlm_msg *msg;
+ char *mb;
- spin_lock(&ls->ls_recover_lock);
- rc->rc_seq = ls->ls_recover_seq;
- spin_unlock(&ls->ls_recover_lock);
+ msg = dlm_lowcomms_new_msg(to_nodeid, mb_len, GFP_NOFS, &mb,
+ NULL, NULL);
+ if (!msg) {
+ log_print("create_rcom to %d type %d len %d ENOBUFS",
+ to_nodeid, type, len);
+ return -ENOBUFS;
+ }
- *mh_ret = mh;
- *rc_ret = rc;
+ _create_rcom(ls, to_nodeid, type, len, rc_ret, mb, mb_len);
+ *msg_ret = msg;
return 0;
}
-static void send_rcom(struct dlm_ls *ls, struct dlm_mhandle *mh,
- struct dlm_rcom *rc)
+static void send_rcom(struct dlm_mhandle *mh, struct dlm_rcom *rc)
+{
+ dlm_midcomms_commit_mhandle(mh);
+}
+
+static void send_rcom_stateless(struct dlm_msg *msg, struct dlm_rcom *rc)
{
- dlm_rcom_out(rc);
- dlm_lowcomms_commit_buffer(mh);
+ dlm_lowcomms_commit_msg(msg);
+ dlm_lowcomms_put_msg(msg);
}
static void set_rcom_status(struct dlm_ls *ls, struct rcom_status *rs,
@@ -94,10 +125,10 @@ static int check_rcom_config(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
{
struct rcom_config *rf = (struct rcom_config *) rc->rc_buf;
- if ((rc->rc_header.h_version & 0xFFFF0000) != DLM_HEADER_MAJOR) {
+ if ((le32_to_cpu(rc->rc_header.h_version) & 0xFFFF0000) != DLM_HEADER_MAJOR) {
log_error(ls, "version mismatch: %x nodeid %d: %x",
DLM_HEADER_MAJOR | DLM_HEADER_MINOR, nodeid,
- rc->rc_header.h_version);
+ le32_to_cpu(rc->rc_header.h_version));
return -EPROTO;
}
@@ -112,10 +143,10 @@ static int check_rcom_config(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
return 0;
}
-static void allow_sync_reply(struct dlm_ls *ls, uint64_t *new_seq)
+static void allow_sync_reply(struct dlm_ls *ls, __le64 *new_seq)
{
spin_lock(&ls->ls_rcom_spin);
- *new_seq = ++ls->ls_rcom_seq;
+ *new_seq = cpu_to_le64(++ls->ls_rcom_seq);
set_bit(LSFL_RCOM_WAIT, &ls->ls_flags);
spin_unlock(&ls->ls_rcom_spin);
}
@@ -142,29 +173,29 @@ static void disallow_sync_reply(struct dlm_ls *ls)
int dlm_rcom_status(struct dlm_ls *ls, int nodeid, uint32_t status_flags)
{
struct dlm_rcom *rc;
- struct dlm_mhandle *mh;
+ struct dlm_msg *msg;
int error = 0;
ls->ls_recover_nodeid = nodeid;
if (nodeid == dlm_our_nodeid()) {
rc = ls->ls_recover_buf;
- rc->rc_result = dlm_recover_status(ls);
+ rc->rc_result = cpu_to_le32(dlm_recover_status(ls));
goto out;
}
retry:
- error = create_rcom(ls, nodeid, DLM_RCOM_STATUS,
- sizeof(struct rcom_status), &rc, &mh);
+ error = create_rcom_stateless(ls, nodeid, DLM_RCOM_STATUS,
+ sizeof(struct rcom_status), &rc, &msg);
if (error)
goto out;
set_rcom_status(ls, (struct rcom_status *)rc->rc_buf, status_flags);
allow_sync_reply(ls, &rc->rc_id);
- memset(ls->ls_recover_buf, 0, dlm_config.ci_buffer_size);
+ memset(ls->ls_recover_buf, 0, DLM_MAX_SOCKET_BUFSIZE);
- send_rcom(ls, mh, rc);
+ send_rcom_stateless(msg, rc);
error = dlm_wait_function(ls, &rcom_response);
disallow_sync_reply(ls);
@@ -175,7 +206,7 @@ retry:
rc = ls->ls_recover_buf;
- if (rc->rc_result == -ESRCH) {
+ if (rc->rc_result == cpu_to_le32(-ESRCH)) {
/* we pretend the remote lockspace exists with 0 status */
log_debug(ls, "remote node %d not ready", nodeid);
rc->rc_result = 0;
@@ -192,11 +223,11 @@ retry:
static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in)
{
struct dlm_rcom *rc;
- struct dlm_mhandle *mh;
struct rcom_status *rs;
uint32_t status;
- int nodeid = rc_in->rc_header.h_nodeid;
+ int nodeid = le32_to_cpu(rc_in->rc_header.h_nodeid);
int len = sizeof(struct rcom_config);
+ struct dlm_msg *msg;
int num_slots = 0;
int error;
@@ -219,14 +250,14 @@ static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in)
len += num_slots * sizeof(struct rcom_slot);
do_create:
- error = create_rcom(ls, nodeid, DLM_RCOM_STATUS_REPLY,
- len, &rc, &mh);
+ error = create_rcom_stateless(ls, nodeid, DLM_RCOM_STATUS_REPLY,
+ len, &rc, &msg);
if (error)
return;
rc->rc_id = rc_in->rc_id;
rc->rc_seq_reply = rc_in->rc_seq;
- rc->rc_result = status;
+ rc->rc_result = cpu_to_le32(status);
set_rcom_config(ls, (struct rcom_config *)rc->rc_buf, num_slots);
@@ -247,21 +278,23 @@ static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in)
spin_unlock(&ls->ls_recover_lock);
do_send:
- send_rcom(ls, mh, rc);
+ send_rcom_stateless(msg, rc);
}
static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
{
spin_lock(&ls->ls_rcom_spin);
if (!test_bit(LSFL_RCOM_WAIT, &ls->ls_flags) ||
- rc_in->rc_id != ls->ls_rcom_seq) {
+ le64_to_cpu(rc_in->rc_id) != ls->ls_rcom_seq) {
log_debug(ls, "reject reply %d from %d seq %llx expect %llx",
- rc_in->rc_type, rc_in->rc_header.h_nodeid,
- (unsigned long long)rc_in->rc_id,
+ le32_to_cpu(rc_in->rc_type),
+ le32_to_cpu(rc_in->rc_header.h_nodeid),
+ (unsigned long long)le64_to_cpu(rc_in->rc_id),
(unsigned long long)ls->ls_rcom_seq);
goto out;
}
- memcpy(ls->ls_recover_buf, rc_in, rc_in->rc_header.h_length);
+ memcpy(ls->ls_recover_buf, rc_in,
+ le16_to_cpu(rc_in->rc_header.h_length));
set_bit(LSFL_RCOM_READY, &ls->ls_flags);
clear_bit(LSFL_RCOM_WAIT, &ls->ls_flags);
wake_up(&ls->ls_wait_general);
@@ -272,21 +305,22 @@ static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len)
{
struct dlm_rcom *rc;
- struct dlm_mhandle *mh;
+ struct dlm_msg *msg;
int error = 0;
ls->ls_recover_nodeid = nodeid;
retry:
- error = create_rcom(ls, nodeid, DLM_RCOM_NAMES, last_len, &rc, &mh);
+ error = create_rcom_stateless(ls, nodeid, DLM_RCOM_NAMES, last_len,
+ &rc, &msg);
if (error)
goto out;
memcpy(rc->rc_buf, last_name, last_len);
allow_sync_reply(ls, &rc->rc_id);
- memset(ls->ls_recover_buf, 0, dlm_config.ci_buffer_size);
+ memset(ls->ls_recover_buf, 0, DLM_MAX_SOCKET_BUFSIZE);
- send_rcom(ls, mh, rc);
+ send_rcom_stateless(msg, rc);
error = dlm_wait_function(ls, &rcom_response);
disallow_sync_reply(ls);
@@ -299,14 +333,16 @@ retry:
static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in)
{
struct dlm_rcom *rc;
- struct dlm_mhandle *mh;
int error, inlen, outlen, nodeid;
+ struct dlm_msg *msg;
- nodeid = rc_in->rc_header.h_nodeid;
- inlen = rc_in->rc_header.h_length - sizeof(struct dlm_rcom);
- outlen = dlm_config.ci_buffer_size - sizeof(struct dlm_rcom);
+ nodeid = le32_to_cpu(rc_in->rc_header.h_nodeid);
+ inlen = le16_to_cpu(rc_in->rc_header.h_length) -
+ sizeof(struct dlm_rcom);
+ outlen = DLM_MAX_APP_BUFSIZE - sizeof(struct dlm_rcom);
- error = create_rcom(ls, nodeid, DLM_RCOM_NAMES_REPLY, outlen, &rc, &mh);
+ error = create_rcom_stateless(ls, nodeid, DLM_RCOM_NAMES_REPLY, outlen,
+ &rc, &msg);
if (error)
return;
rc->rc_id = rc_in->rc_id;
@@ -314,7 +350,7 @@ static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in)
dlm_copy_master_names(ls, rc_in->rc_buf, inlen, rc->rc_buf, outlen,
nodeid);
- send_rcom(ls, mh, rc);
+ send_rcom_stateless(msg, rc);
}
int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid)
@@ -329,9 +365,9 @@ int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid)
if (error)
goto out;
memcpy(rc->rc_buf, r->res_name, r->res_length);
- rc->rc_id = (unsigned long) r->res_id;
+ rc->rc_id = cpu_to_le64(r->res_id);
- send_rcom(ls, mh, rc);
+ send_rcom(mh, rc);
out:
return error;
}
@@ -340,29 +376,30 @@ static void receive_rcom_lookup(struct dlm_ls *ls, struct dlm_rcom *rc_in)
{
struct dlm_rcom *rc;
struct dlm_mhandle *mh;
- int error, ret_nodeid, nodeid = rc_in->rc_header.h_nodeid;
- int len = rc_in->rc_header.h_length - sizeof(struct dlm_rcom);
-
- error = create_rcom(ls, nodeid, DLM_RCOM_LOOKUP_REPLY, 0, &rc, &mh);
- if (error)
- return;
+ int error, ret_nodeid, nodeid = le32_to_cpu(rc_in->rc_header.h_nodeid);
+ int len = le16_to_cpu(rc_in->rc_header.h_length) -
+ sizeof(struct dlm_rcom);
/* Old code would send this special id to trigger a debug dump. */
- if (rc_in->rc_id == 0xFFFFFFFF) {
+ if (rc_in->rc_id == cpu_to_le64(0xFFFFFFFF)) {
log_error(ls, "receive_rcom_lookup dump from %d", nodeid);
dlm_dump_rsb_name(ls, rc_in->rc_buf, len);
return;
}
+ error = create_rcom(ls, nodeid, DLM_RCOM_LOOKUP_REPLY, 0, &rc, &mh);
+ if (error)
+ return;
+
error = dlm_master_lookup(ls, nodeid, rc_in->rc_buf, len,
DLM_LU_RECOVER_MASTER, &ret_nodeid, NULL);
if (error)
ret_nodeid = error;
- rc->rc_result = ret_nodeid;
+ rc->rc_result = cpu_to_le32(ret_nodeid);
rc->rc_id = rc_in->rc_id;
rc->rc_seq_reply = rc_in->rc_seq;
- send_rcom(ls, mh, rc);
+ send_rcom(mh, rc);
}
static void receive_rcom_lookup_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
@@ -417,9 +454,9 @@ int dlm_send_rcom_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
rl = (struct rcom_lock *) rc->rc_buf;
pack_rcom_lock(r, lkb, rl);
- rc->rc_id = (unsigned long) r;
+ rc->rc_id = cpu_to_le64((uintptr_t)r);
- send_rcom(ls, mh, rc);
+ send_rcom(mh, rc);
out:
return error;
}
@@ -429,7 +466,7 @@ static void receive_rcom_lock(struct dlm_ls *ls, struct dlm_rcom *rc_in)
{
struct dlm_rcom *rc;
struct dlm_mhandle *mh;
- int error, nodeid = rc_in->rc_header.h_nodeid;
+ int error, nodeid = le32_to_cpu(rc_in->rc_header.h_nodeid);
dlm_recover_master_copy(ls, rc_in);
@@ -445,7 +482,7 @@ static void receive_rcom_lock(struct dlm_ls *ls, struct dlm_rcom *rc_in)
rc->rc_id = rc_in->rc_id;
rc->rc_seq_reply = rc_in->rc_seq;
- send_rcom(ls, mh, rc);
+ send_rcom(mh, rc);
}
/* If the lockspace doesn't exist then still send a status message
@@ -459,29 +496,27 @@ int dlm_send_ls_not_ready(int nodeid, struct dlm_rcom *rc_in)
char *mb;
int mb_len = sizeof(struct dlm_rcom) + sizeof(struct rcom_config);
- mh = dlm_lowcomms_get_buffer(nodeid, mb_len, GFP_NOFS, &mb);
+ mh = dlm_midcomms_get_mhandle(nodeid, mb_len, GFP_NOFS, &mb);
if (!mh)
return -ENOBUFS;
- memset(mb, 0, mb_len);
rc = (struct dlm_rcom *) mb;
- rc->rc_header.h_version = (DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
- rc->rc_header.h_lockspace = rc_in->rc_header.h_lockspace;
- rc->rc_header.h_nodeid = dlm_our_nodeid();
- rc->rc_header.h_length = mb_len;
+ rc->rc_header.h_version = cpu_to_le32(DLM_HEADER_MAJOR | DLM_HEADER_MINOR);
+ rc->rc_header.u.h_lockspace = rc_in->rc_header.u.h_lockspace;
+ rc->rc_header.h_nodeid = cpu_to_le32(dlm_our_nodeid());
+ rc->rc_header.h_length = cpu_to_le16(mb_len);
rc->rc_header.h_cmd = DLM_RCOM;
- rc->rc_type = DLM_RCOM_STATUS_REPLY;
+ rc->rc_type = cpu_to_le32(DLM_RCOM_STATUS_REPLY);
rc->rc_id = rc_in->rc_id;
rc->rc_seq_reply = rc_in->rc_seq;
- rc->rc_result = -ESRCH;
+ rc->rc_result = cpu_to_le32(-ESRCH);
rf = (struct rcom_config *) rc->rc_buf;
rf->rf_lvblen = cpu_to_le32(~0U);
- dlm_rcom_out(rc);
- dlm_lowcomms_commit_buffer(mh);
+ dlm_midcomms_commit_mhandle(mh);
return 0;
}
@@ -539,42 +574,42 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
uint64_t seq;
switch (rc->rc_type) {
- case DLM_RCOM_STATUS_REPLY:
+ case cpu_to_le32(DLM_RCOM_STATUS_REPLY):
reply = 1;
break;
- case DLM_RCOM_NAMES:
+ case cpu_to_le32(DLM_RCOM_NAMES):
names = 1;
break;
- case DLM_RCOM_NAMES_REPLY:
+ case cpu_to_le32(DLM_RCOM_NAMES_REPLY):
names = 1;
reply = 1;
break;
- case DLM_RCOM_LOOKUP:
+ case cpu_to_le32(DLM_RCOM_LOOKUP):
lookup = 1;
break;
- case DLM_RCOM_LOOKUP_REPLY:
+ case cpu_to_le32(DLM_RCOM_LOOKUP_REPLY):
lookup = 1;
reply = 1;
break;
- case DLM_RCOM_LOCK:
+ case cpu_to_le32(DLM_RCOM_LOCK):
lock = 1;
break;
- case DLM_RCOM_LOCK_REPLY:
+ case cpu_to_le32(DLM_RCOM_LOCK_REPLY):
lock = 1;
reply = 1;
break;
- };
+ }
spin_lock(&ls->ls_recover_lock);
status = ls->ls_recover_status;
- stop = test_bit(LSFL_RECOVER_STOP, &ls->ls_flags);
+ stop = dlm_recovery_stopped(ls);
seq = ls->ls_recover_seq;
spin_unlock(&ls->ls_recover_lock);
- if (stop && (rc->rc_type != DLM_RCOM_STATUS))
+ if (stop && (rc->rc_type != cpu_to_le32(DLM_RCOM_STATUS)))
goto ignore;
- if (reply && (rc->rc_seq_reply != seq))
+ if (reply && (le64_to_cpu(rc->rc_seq_reply) != seq))
goto ignore;
if (!(status & DLM_RS_NODES) && (names || lookup || lock))
@@ -584,59 +619,60 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
goto ignore;
switch (rc->rc_type) {
- case DLM_RCOM_STATUS:
+ case cpu_to_le32(DLM_RCOM_STATUS):
receive_rcom_status(ls, rc);
break;
- case DLM_RCOM_NAMES:
+ case cpu_to_le32(DLM_RCOM_NAMES):
receive_rcom_names(ls, rc);
break;
- case DLM_RCOM_LOOKUP:
+ case cpu_to_le32(DLM_RCOM_LOOKUP):
receive_rcom_lookup(ls, rc);
break;
- case DLM_RCOM_LOCK:
- if (rc->rc_header.h_length < lock_size)
+ case cpu_to_le32(DLM_RCOM_LOCK):
+ if (le16_to_cpu(rc->rc_header.h_length) < lock_size)
goto Eshort;
receive_rcom_lock(ls, rc);
break;
- case DLM_RCOM_STATUS_REPLY:
+ case cpu_to_le32(DLM_RCOM_STATUS_REPLY):
receive_sync_reply(ls, rc);
break;
- case DLM_RCOM_NAMES_REPLY:
+ case cpu_to_le32(DLM_RCOM_NAMES_REPLY):
receive_sync_reply(ls, rc);
break;
- case DLM_RCOM_LOOKUP_REPLY:
+ case cpu_to_le32(DLM_RCOM_LOOKUP_REPLY):
receive_rcom_lookup_reply(ls, rc);
break;
- case DLM_RCOM_LOCK_REPLY:
- if (rc->rc_header.h_length < lock_size)
+ case cpu_to_le32(DLM_RCOM_LOCK_REPLY):
+ if (le16_to_cpu(rc->rc_header.h_length) < lock_size)
goto Eshort;
dlm_recover_process_copy(ls, rc);
break;
default:
- log_error(ls, "receive_rcom bad type %d", rc->rc_type);
+ log_error(ls, "receive_rcom bad type %d",
+ le32_to_cpu(rc->rc_type));
}
return;
ignore:
log_limit(ls, "dlm_receive_rcom ignore msg %d "
"from %d %llu %llu recover seq %llu sts %x gen %u",
- rc->rc_type,
+ le32_to_cpu(rc->rc_type),
nodeid,
- (unsigned long long)rc->rc_seq,
- (unsigned long long)rc->rc_seq_reply,
+ (unsigned long long)le64_to_cpu(rc->rc_seq),
+ (unsigned long long)le64_to_cpu(rc->rc_seq_reply),
(unsigned long long)seq,
status, ls->ls_generation);
return;
Eshort:
log_error(ls, "recovery message %d from %d is too short",
- rc->rc_type, nodeid);
+ le32_to_cpu(rc->rc_type), nodeid);
}
diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c
index 8928e99dfd47..ccff1791803f 100644
--- a/fs/dlm/recover.c
+++ b/fs/dlm/recover.c
@@ -114,7 +114,7 @@ static int wait_status_all(struct dlm_ls *ls, uint32_t wait_status,
if (save_slots)
dlm_slot_save(ls, rc, memb);
- if (rc->rc_result & wait_status)
+ if (le32_to_cpu(rc->rc_result) & wait_status)
break;
if (delay < 1000)
delay += 20;
@@ -141,7 +141,7 @@ static int wait_status_low(struct dlm_ls *ls, uint32_t wait_status,
if (error)
break;
- if (rc->rc_result & wait_status)
+ if (le32_to_cpu(rc->rc_result) & wait_status)
break;
if (delay < 1000)
delay += 20;
@@ -568,14 +568,14 @@ int dlm_recover_master_reply(struct dlm_ls *ls, struct dlm_rcom *rc)
struct dlm_rsb *r;
int ret_nodeid, new_master;
- r = recover_idr_find(ls, rc->rc_id);
+ r = recover_idr_find(ls, le64_to_cpu(rc->rc_id));
if (!r) {
log_error(ls, "dlm_recover_master_reply no id %llx",
- (unsigned long long)rc->rc_id);
+ (unsigned long long)le64_to_cpu(rc->rc_id));
goto out;
}
- ret_nodeid = rc->rc_result;
+ ret_nodeid = le32_to_cpu(rc->rc_result);
if (ret_nodeid == dlm_our_nodeid())
new_master = 0;
@@ -732,10 +732,9 @@ void dlm_recovered_lock(struct dlm_rsb *r)
static void recover_lvb(struct dlm_rsb *r)
{
- struct dlm_lkb *lkb, *high_lkb = NULL;
+ struct dlm_lkb *big_lkb = NULL, *iter, *high_lkb = NULL;
uint32_t high_seq = 0;
int lock_lvb_exists = 0;
- int big_lock_exists = 0;
int lvblen = r->res_ls->ls_lvblen;
if (!rsb_flag(r, RSB_NEW_MASTER2) &&
@@ -751,37 +750,37 @@ static void recover_lvb(struct dlm_rsb *r)
/* we are the new master, so figure out if VALNOTVALID should
be set, and set the rsb lvb from the best lkb available. */
- list_for_each_entry(lkb, &r->res_grantqueue, lkb_statequeue) {
- if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+ list_for_each_entry(iter, &r->res_grantqueue, lkb_statequeue) {
+ if (!(iter->lkb_exflags & DLM_LKF_VALBLK))
continue;
lock_lvb_exists = 1;
- if (lkb->lkb_grmode > DLM_LOCK_CR) {
- big_lock_exists = 1;
+ if (iter->lkb_grmode > DLM_LOCK_CR) {
+ big_lkb = iter;
goto setflag;
}
- if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
- high_lkb = lkb;
- high_seq = lkb->lkb_lvbseq;
+ if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) {
+ high_lkb = iter;
+ high_seq = iter->lkb_lvbseq;
}
}
- list_for_each_entry(lkb, &r->res_convertqueue, lkb_statequeue) {
- if (!(lkb->lkb_exflags & DLM_LKF_VALBLK))
+ list_for_each_entry(iter, &r->res_convertqueue, lkb_statequeue) {
+ if (!(iter->lkb_exflags & DLM_LKF_VALBLK))
continue;
lock_lvb_exists = 1;
- if (lkb->lkb_grmode > DLM_LOCK_CR) {
- big_lock_exists = 1;
+ if (iter->lkb_grmode > DLM_LOCK_CR) {
+ big_lkb = iter;
goto setflag;
}
- if (((int)lkb->lkb_lvbseq - (int)high_seq) >= 0) {
- high_lkb = lkb;
- high_seq = lkb->lkb_lvbseq;
+ if (((int)iter->lkb_lvbseq - (int)high_seq) >= 0) {
+ high_lkb = iter;
+ high_seq = iter->lkb_lvbseq;
}
}
@@ -790,7 +789,7 @@ static void recover_lvb(struct dlm_rsb *r)
goto out;
/* lvb is invalidated if only NL/CR locks remain */
- if (!big_lock_exists)
+ if (!big_lkb)
rsb_set_flag(r, RSB_VALNOTVALID);
if (!r->res_lvbptr) {
@@ -799,9 +798,9 @@ static void recover_lvb(struct dlm_rsb *r)
goto out;
}
- if (big_lock_exists) {
- r->res_lvbseq = lkb->lkb_lvbseq;
- memcpy(r->res_lvbptr, lkb->lkb_lvbptr, lvblen);
+ if (big_lkb) {
+ r->res_lvbseq = big_lkb->lkb_lvbseq;
+ memcpy(r->res_lvbptr, big_lkb->lkb_lvbptr, lvblen);
} else if (high_lkb) {
r->res_lvbseq = high_lkb->lkb_lvbseq;
memcpy(r->res_lvbptr, high_lkb->lkb_lvbptr, lvblen);
diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c
index 85e245392715..e15eb511b04b 100644
--- a/fs/dlm/recoverd.c
+++ b/fs/dlm/recoverd.c
@@ -70,6 +70,10 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
/*
* Add or remove nodes from the lockspace's ls_nodes list.
+ *
+ * Due to the fact that we must report all membership changes to lsops
+ * or midcomms layer, it is not permitted to abort ls_recover() until
+ * this is done.
*/
error = dlm_recover_members(ls, rv, &neg);
@@ -124,9 +128,10 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
dlm_recover_waiters_pre(ls);
- error = dlm_recovery_stopped(ls);
- if (error)
+ if (dlm_recovery_stopped(ls)) {
+ error = -EINTR;
goto fail;
+ }
if (neg || dlm_no_directory(ls)) {
/*
@@ -238,14 +243,12 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
jiffies_to_msecs(jiffies - start));
mutex_unlock(&ls->ls_recoverd_active);
- dlm_lsop_recover_done(ls);
return 0;
fail:
dlm_release_root_list(ls);
- log_rinfo(ls, "dlm_recover %llu error %d",
- (unsigned long long)rv->seq, error);
mutex_unlock(&ls->ls_recoverd_active);
+
return error;
}
@@ -256,6 +259,7 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
static void do_ls_recovery(struct dlm_ls *ls)
{
struct dlm_recover *rv = NULL;
+ int error;
spin_lock(&ls->ls_recover_lock);
rv = ls->ls_recover_args;
@@ -265,7 +269,31 @@ static void do_ls_recovery(struct dlm_ls *ls)
spin_unlock(&ls->ls_recover_lock);
if (rv) {
- ls_recover(ls, rv);
+ error = ls_recover(ls, rv);
+ switch (error) {
+ case 0:
+ ls->ls_recovery_result = 0;
+ complete(&ls->ls_recovery_done);
+
+ dlm_lsop_recover_done(ls);
+ break;
+ case -EINTR:
+ /* if recovery was interrupted -EINTR we wait for the next
+ * ls_recover() iteration until it hopefully succeeds.
+ */
+ log_rinfo(ls, "%s %llu interrupted and should be queued to run again",
+ __func__, (unsigned long long)rv->seq);
+ break;
+ default:
+ log_rinfo(ls, "%s %llu error %d", __func__,
+ (unsigned long long)rv->seq, error);
+
+ /* let new_lockspace() get aware of critical error */
+ ls->ls_recovery_result = error;
+ complete(&ls->ls_recovery_done);
+ break;
+ }
+
kfree(rv->nodes);
kfree(rv);
}
diff --git a/fs/dlm/requestqueue.c b/fs/dlm/requestqueue.c
index e89e0ff8bfa3..036a9a0078f6 100644
--- a/fs/dlm/requestqueue.c
+++ b/fs/dlm/requestqueue.c
@@ -14,6 +14,7 @@
#include "dir.h"
#include "config.h"
#include "requestqueue.h"
+#include "util.h"
struct rq_entry {
struct list_head list;
@@ -32,7 +33,8 @@ struct rq_entry {
void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms)
{
struct rq_entry *e;
- int length = ms->m_header.h_length - sizeof(struct dlm_message);
+ int length = le16_to_cpu(ms->m_header.h_length) -
+ sizeof(struct dlm_message);
e = kmalloc(sizeof(struct rq_entry) + length, GFP_NOFS);
if (!e) {
@@ -42,8 +44,9 @@ void dlm_add_requestqueue(struct dlm_ls *ls, int nodeid, struct dlm_message *ms)
e->recover_seq = ls->ls_recover_seq & 0xFFFFFFFF;
e->nodeid = nodeid;
- memcpy(&e->request, ms, ms->m_header.h_length);
+ memcpy(&e->request, ms, le16_to_cpu(ms->m_header.h_length));
+ atomic_inc(&ls->ls_requestqueue_cnt);
mutex_lock(&ls->ls_requestqueue_mutex);
list_add_tail(&e->list, &ls->ls_requestqueue);
mutex_unlock(&ls->ls_requestqueue_mutex);
@@ -81,14 +84,18 @@ int dlm_process_requestqueue(struct dlm_ls *ls)
log_limit(ls, "dlm_process_requestqueue msg %d from %d "
"lkid %x remid %x result %d seq %u",
- ms->m_type, ms->m_header.h_nodeid,
- ms->m_lkid, ms->m_remid, ms->m_result,
+ le32_to_cpu(ms->m_type),
+ le32_to_cpu(ms->m_header.h_nodeid),
+ le32_to_cpu(ms->m_lkid), le32_to_cpu(ms->m_remid),
+ from_dlm_errno(le32_to_cpu(ms->m_result)),
e->recover_seq);
dlm_receive_message_saved(ls, &e->request, e->recover_seq);
mutex_lock(&ls->ls_requestqueue_mutex);
list_del(&e->list);
+ if (atomic_dec_and_test(&ls->ls_requestqueue_cnt))
+ wake_up(&ls->ls_requestqueue_wait);
kfree(e);
if (dlm_locking_stopped(ls)) {
@@ -115,22 +122,16 @@ int dlm_process_requestqueue(struct dlm_ls *ls)
void dlm_wait_requestqueue(struct dlm_ls *ls)
{
- for (;;) {
- mutex_lock(&ls->ls_requestqueue_mutex);
- if (list_empty(&ls->ls_requestqueue))
- break;
- mutex_unlock(&ls->ls_requestqueue_mutex);
- schedule();
- }
- mutex_unlock(&ls->ls_requestqueue_mutex);
+ wait_event(ls->ls_requestqueue_wait,
+ atomic_read(&ls->ls_requestqueue_cnt) == 0);
}
static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid)
{
- uint32_t type = ms->m_type;
+ __le32 type = ms->m_type;
/* the ls is being cleaned up and freed by release_lockspace */
- if (!ls->ls_count)
+ if (!atomic_read(&ls->ls_count))
return 1;
if (dlm_is_removed(ls, nodeid))
@@ -139,9 +140,9 @@ static int purge_request(struct dlm_ls *ls, struct dlm_message *ms, int nodeid)
/* directory operations are always purged because the directory is
always rebuilt during recovery and the lookups resent */
- if (type == DLM_MSG_REMOVE ||
- type == DLM_MSG_LOOKUP ||
- type == DLM_MSG_LOOKUP_REPLY)
+ if (type == cpu_to_le32(DLM_MSG_REMOVE) ||
+ type == cpu_to_le32(DLM_MSG_LOOKUP) ||
+ type == cpu_to_le32(DLM_MSG_LOOKUP_REPLY))
return 1;
if (!dlm_no_directory(ls))
@@ -161,6 +162,8 @@ void dlm_purge_requestqueue(struct dlm_ls *ls)
if (purge_request(ls, ms, e->nodeid)) {
list_del(&e->list);
+ if (atomic_dec_and_test(&ls->ls_requestqueue_cnt))
+ wake_up(&ls->ls_requestqueue_wait);
kfree(e);
}
}
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 5264bac75115..c5d27bccc3dc 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -16,6 +16,8 @@
#include <linux/slab.h>
#include <linux/sched/signal.h>
+#include <trace/events/dlm.h>
+
#include "dlm_internal.h"
#include "lockspace.h"
#include "lock.h"
@@ -46,7 +48,7 @@ struct dlm_lock_params32 {
__u32 bastaddr;
__u32 lksb;
char lvb[DLM_USER_LVB_LEN];
- char name[0];
+ char name[];
};
struct dlm_write_request32 {
@@ -108,11 +110,11 @@ static void compat_input(struct dlm_write_request *kb,
kb->i.lock.parent = kb32->i.lock.parent;
kb->i.lock.xid = kb32->i.lock.xid;
kb->i.lock.timeout = kb32->i.lock.timeout;
- kb->i.lock.castparam = (void *)(long)kb32->i.lock.castparam;
- kb->i.lock.castaddr = (void *)(long)kb32->i.lock.castaddr;
- kb->i.lock.bastparam = (void *)(long)kb32->i.lock.bastparam;
- kb->i.lock.bastaddr = (void *)(long)kb32->i.lock.bastaddr;
- kb->i.lock.lksb = (void *)(long)kb32->i.lock.lksb;
+ kb->i.lock.castparam = (__user void *)(long)kb32->i.lock.castparam;
+ kb->i.lock.castaddr = (__user void *)(long)kb32->i.lock.castaddr;
+ kb->i.lock.bastparam = (__user void *)(long)kb32->i.lock.bastparam;
+ kb->i.lock.bastaddr = (__user void *)(long)kb32->i.lock.bastaddr;
+ kb->i.lock.lksb = (__user void *)(long)kb32->i.lock.lksb;
memcpy(kb->i.lock.lvb, kb32->i.lock.lvb, DLM_USER_LVB_LEN);
memcpy(kb->i.lock.name, kb32->i.lock.name, namelen);
}
@@ -127,9 +129,9 @@ static void compat_output(struct dlm_lock_result *res,
res32->version[1] = res->version[1];
res32->version[2] = res->version[2];
- res32->user_astaddr = (__u32)(long)res->user_astaddr;
- res32->user_astparam = (__u32)(long)res->user_astparam;
- res32->user_lksb = (__u32)(long)res->user_lksb;
+ res32->user_astaddr = (__u32)(__force long)res->user_astaddr;
+ res32->user_astparam = (__u32)(__force long)res->user_astparam;
+ res32->user_lksb = (__u32)(__force long)res->user_lksb;
res32->bast_mode = res->bast_mode;
res32->lvb_offset = res->lvb_offset;
@@ -184,7 +186,7 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
return;
ls = lkb->lkb_resource->res_ls;
- mutex_lock(&ls->ls_clear_proc_locks);
+ spin_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
@@ -230,7 +232,7 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, uint32_t flags, int mode,
spin_unlock(&proc->locks_spin);
}
out:
- mutex_unlock(&ls->ls_clear_proc_locks);
+ spin_unlock(&ls->ls_clear_proc_locks);
}
static int device_user_lock(struct dlm_user_proc *proc,
@@ -250,6 +252,14 @@ static int device_user_lock(struct dlm_user_proc *proc,
goto out;
}
+#ifdef CONFIG_DLM_DEPRECATED_API
+ if (params->timeout)
+ pr_warn_once("========================================================\n"
+ "WARNING: the lkb timeout feature is being deprecated and\n"
+ " will be removed in v6.2!\n"
+ "========================================================\n");
+#endif
+
ua = kzalloc(sizeof(struct dlm_user_args), GFP_NOFS);
if (!ua)
goto out;
@@ -262,23 +272,34 @@ static int device_user_lock(struct dlm_user_proc *proc,
ua->xid = params->xid;
if (params->flags & DLM_LKF_CONVERT) {
+#ifdef CONFIG_DLM_DEPRECATED_API
error = dlm_user_convert(ls, ua,
params->mode, params->flags,
params->lkid, params->lvb,
(unsigned long) params->timeout);
+#else
+ error = dlm_user_convert(ls, ua,
+ params->mode, params->flags,
+ params->lkid, params->lvb);
+#endif
} else if (params->flags & DLM_LKF_ORPHAN) {
error = dlm_user_adopt_orphan(ls, ua,
params->mode, params->flags,
params->name, params->namelen,
- (unsigned long) params->timeout,
&lkid);
if (!error)
error = lkid;
} else {
+#ifdef CONFIG_DLM_DEPRECATED_API
error = dlm_user_request(ls, ua,
params->mode, params->flags,
params->name, params->namelen,
(unsigned long) params->timeout);
+#else
+ error = dlm_user_request(ls, ua,
+ params->mode, params->flags,
+ params->name, params->namelen);
+#endif
if (!error)
error = ua->lksb.sb_lkid;
}
@@ -402,9 +423,9 @@ static int device_create_lockspace(struct dlm_lspace_params *params)
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- error = dlm_new_lockspace(params->name, dlm_config.ci_cluster_name, params->flags,
- DLM_USER_LVB_LEN, NULL, NULL, NULL,
- &lockspace);
+ error = dlm_new_user_lockspace(params->name, dlm_config.ci_cluster_name,
+ params->flags, DLM_USER_LVB_LEN, NULL,
+ NULL, NULL, &lockspace);
if (error)
return error;
@@ -863,7 +884,9 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
goto try_another;
}
- if (cb.flags & DLM_CB_CAST) {
+ if (cb.flags & DLM_CB_BAST) {
+ trace_dlm_bast(lkb->lkb_resource->res_ls, lkb, cb.mode);
+ } else if (cb.flags & DLM_CB_CAST) {
new_mode = cb.mode;
if (!cb.sb_status && lkb->lkb_lksb->sb_lvbptr &&
@@ -872,6 +895,7 @@ static ssize_t device_read(struct file *file, char __user *buf, size_t count,
lkb->lkb_lksb->sb_status = cb.sb_status;
lkb->lkb_lksb->sb_flags = cb.sb_flags;
+ trace_dlm_ast(lkb->lkb_resource->res_ls, lkb);
}
rv = copy_result_to_user(lkb->lkb_ua,
diff --git a/fs/dlm/util.c b/fs/dlm/util.c
index cfd0d00b19ae..f2bc401f312f 100644
--- a/fs/dlm/util.c
+++ b/fs/dlm/util.c
@@ -20,26 +20,10 @@
#define DLM_ERRNO_ETIMEDOUT 110
#define DLM_ERRNO_EINPROGRESS 115
-static void header_out(struct dlm_header *hd)
-{
- hd->h_version = cpu_to_le32(hd->h_version);
- hd->h_lockspace = cpu_to_le32(hd->h_lockspace);
- hd->h_nodeid = cpu_to_le32(hd->h_nodeid);
- hd->h_length = cpu_to_le16(hd->h_length);
-}
-
-static void header_in(struct dlm_header *hd)
-{
- hd->h_version = le32_to_cpu(hd->h_version);
- hd->h_lockspace = le32_to_cpu(hd->h_lockspace);
- hd->h_nodeid = le32_to_cpu(hd->h_nodeid);
- hd->h_length = le16_to_cpu(hd->h_length);
-}
-
/* higher errno values are inconsistent across architectures, so select
one set of values for on the wire */
-static int to_dlm_errno(int err)
+int to_dlm_errno(int err)
{
switch (err) {
case -EDEADLK:
@@ -60,7 +44,7 @@ static int to_dlm_errno(int err)
return err;
}
-static int from_dlm_errno(int err)
+int from_dlm_errno(int err)
{
switch (err) {
case -DLM_ERRNO_EDEADLK:
@@ -80,73 +64,3 @@ static int from_dlm_errno(int err)
}
return err;
}
-
-void dlm_message_out(struct dlm_message *ms)
-{
- header_out(&ms->m_header);
-
- ms->m_type = cpu_to_le32(ms->m_type);
- ms->m_nodeid = cpu_to_le32(ms->m_nodeid);
- ms->m_pid = cpu_to_le32(ms->m_pid);
- ms->m_lkid = cpu_to_le32(ms->m_lkid);
- ms->m_remid = cpu_to_le32(ms->m_remid);
- ms->m_parent_lkid = cpu_to_le32(ms->m_parent_lkid);
- ms->m_parent_remid = cpu_to_le32(ms->m_parent_remid);
- ms->m_exflags = cpu_to_le32(ms->m_exflags);
- ms->m_sbflags = cpu_to_le32(ms->m_sbflags);
- ms->m_flags = cpu_to_le32(ms->m_flags);
- ms->m_lvbseq = cpu_to_le32(ms->m_lvbseq);
- ms->m_hash = cpu_to_le32(ms->m_hash);
- ms->m_status = cpu_to_le32(ms->m_status);
- ms->m_grmode = cpu_to_le32(ms->m_grmode);
- ms->m_rqmode = cpu_to_le32(ms->m_rqmode);
- ms->m_bastmode = cpu_to_le32(ms->m_bastmode);
- ms->m_asts = cpu_to_le32(ms->m_asts);
- ms->m_result = cpu_to_le32(to_dlm_errno(ms->m_result));
-}
-
-void dlm_message_in(struct dlm_message *ms)
-{
- header_in(&ms->m_header);
-
- ms->m_type = le32_to_cpu(ms->m_type);
- ms->m_nodeid = le32_to_cpu(ms->m_nodeid);
- ms->m_pid = le32_to_cpu(ms->m_pid);
- ms->m_lkid = le32_to_cpu(ms->m_lkid);
- ms->m_remid = le32_to_cpu(ms->m_remid);
- ms->m_parent_lkid = le32_to_cpu(ms->m_parent_lkid);
- ms->m_parent_remid = le32_to_cpu(ms->m_parent_remid);
- ms->m_exflags = le32_to_cpu(ms->m_exflags);
- ms->m_sbflags = le32_to_cpu(ms->m_sbflags);
- ms->m_flags = le32_to_cpu(ms->m_flags);
- ms->m_lvbseq = le32_to_cpu(ms->m_lvbseq);
- ms->m_hash = le32_to_cpu(ms->m_hash);
- ms->m_status = le32_to_cpu(ms->m_status);
- ms->m_grmode = le32_to_cpu(ms->m_grmode);
- ms->m_rqmode = le32_to_cpu(ms->m_rqmode);
- ms->m_bastmode = le32_to_cpu(ms->m_bastmode);
- ms->m_asts = le32_to_cpu(ms->m_asts);
- ms->m_result = from_dlm_errno(le32_to_cpu(ms->m_result));
-}
-
-void dlm_rcom_out(struct dlm_rcom *rc)
-{
- header_out(&rc->rc_header);
-
- rc->rc_type = cpu_to_le32(rc->rc_type);
- rc->rc_result = cpu_to_le32(rc->rc_result);
- rc->rc_id = cpu_to_le64(rc->rc_id);
- rc->rc_seq = cpu_to_le64(rc->rc_seq);
- rc->rc_seq_reply = cpu_to_le64(rc->rc_seq_reply);
-}
-
-void dlm_rcom_in(struct dlm_rcom *rc)
-{
- header_in(&rc->rc_header);
-
- rc->rc_type = le32_to_cpu(rc->rc_type);
- rc->rc_result = le32_to_cpu(rc->rc_result);
- rc->rc_id = le64_to_cpu(rc->rc_id);
- rc->rc_seq = le64_to_cpu(rc->rc_seq);
- rc->rc_seq_reply = le64_to_cpu(rc->rc_seq_reply);
-}
diff --git a/fs/dlm/util.h b/fs/dlm/util.h
index cc719ca9397e..b6a4b8adca8d 100644
--- a/fs/dlm/util.h
+++ b/fs/dlm/util.h
@@ -11,10 +11,8 @@
#ifndef __UTIL_DOT_H__
#define __UTIL_DOT_H__
-void dlm_message_out(struct dlm_message *ms);
-void dlm_message_in(struct dlm_message *ms);
-void dlm_rcom_out(struct dlm_rcom *rc);
-void dlm_rcom_in(struct dlm_rcom *rc);
+int to_dlm_errno(int err);
+int from_dlm_errno(int err);
#endif
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.